CN118335091A

CN118335091A - Speech recognition in digital assistant systems

Info

Publication number: CN118335091A
Application number: CN202410549025.0A
Authority: CN
Inventors: S·H·沈; C·J·彼得森; S·S·卡贾雷卡; B·S·菲普斯; E·玛奇; J·配克; A·比斯瓦斯; H·西蒙兹; C·曼纳马拉
Original assignee: Apple Inc
Current assignee: Apple Inc
Priority date: 2019-05-31
Filing date: 2020-05-15
Publication date: 2024-07-12
Also published as: WO2020242595A1

Abstract

The present disclosure relates to voice recognition in digital assistant systems. The present disclosure provides systems and processes for operating intelligent automated assistants. An example method includes receiving a plurality of speaker profiles for a plurality of users from one or more external electronic devices; receiving natural language voice input; based on comparing the natural language speech input to the plurality of speaker profiles: the natural language speech input corresponds to a first likelihood of a first user of the plurality of users; and a second likelihood that the natural language speech input corresponds to a second user of the plurality of users; determining whether the first likelihood and the second likelihood are within a first threshold; and in accordance with a determination that the first likelihood and the second likelihood are not within the first threshold: a response to the natural language voice input is provided, the response being personalized to the first user.

Description

Speech recognition in digital assistant systems

The application is a divisional application of an application patent application with the application date of 2020, the application number of 202010418092.0 and the application of 'voice recognition in digital assistant system'.

Technical Field

The present disclosure relates generally to intelligent automated assistants, and more particularly, to identifying users of intelligent automated assistants in a multi-user or shared environment.

Background

An intelligent automated assistant (or digital assistant) may provide an advantageous interface between a human user and an electronic device. Such assistants may allow a user to interact with a device or system in voice form and/or text form using natural language. For example, a user may provide a voice input containing a user request to a digital assistant running on an electronic device. The digital assistant may interpret the user intent from the voice input and operate the user intent into a task. These tasks may then be performed by executing one or more services of the electronic device, and the relevant output in response to the user request may be returned to the user.

The digital assistant may operate on a device shared by many users. Accordingly, it may be desirable for a digital assistant to identify a current user of a device in a multi-user or shared environment.

Disclosure of Invention

Example methods are disclosed herein. An example method includes, at an electronic device having a memory and one or more processors: receiving a plurality of speaker profiles for a plurality of users from one or more external electronic devices; receiving natural language voice input; based on comparing the natural language speech input to the plurality of speaker profiles: the natural language speech input corresponds to a first likelihood of a first user of the plurality of users; and a second likelihood that the natural language speech input corresponds to a second user of the plurality of users, the second likelihood being less than the first likelihood; determining whether the first likelihood and the second likelihood are within a first threshold; and in accordance with a determination that the first likelihood and the second likelihood are not within the first threshold: a response to the natural language voice input is provided, the response being personalized to the first user.

Example non-transitory computer-readable media are disclosed herein. An example non-transitory computer readable storage medium stores one or more programs. The one or more programs include instructions, which when executed by one or more processors of the electronic device, cause the electronic device to: receiving a plurality of speaker profiles for a plurality of users from one or more external electronic devices; receiving natural language voice input; based on comparing the natural language speech input to the plurality of speaker profiles: the natural language speech input corresponds to a first likelihood of a first user of the plurality of users; and a second likelihood that the natural language speech input corresponds to a second user of the plurality of users, the second likelihood being less than the first likelihood; determining whether the first likelihood and the second likelihood are within a first threshold; and in accordance with a determination that the first likelihood and the second likelihood are not within the first threshold: a response to the natural language voice input is provided, the response being personalized to the first user.

Example electronic devices are disclosed herein. An example electronic device includes one or more processors; a memory; and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising instructions for: receiving a plurality of speaker profiles for a plurality of users from one or more external electronic devices; receiving natural language voice input; based on comparing the natural language speech input to the plurality of speaker profiles: the natural language speech input corresponds to a first likelihood of a first user of the plurality of users; and a second likelihood that the natural language speech input corresponds to a second user of the plurality of users, the second likelihood being less than the first likelihood; determining whether the first likelihood and the second likelihood are within a first threshold; and in accordance with a determination that the first likelihood and the second likelihood are not within the first threshold: a response to the natural language voice input is provided, the response being personalized to the first user.

An example electronic device includes means for: receiving a plurality of speaker profiles for a plurality of users from one or more external electronic devices; receiving natural language voice input; based on comparing the natural language speech input to the plurality of speaker profiles: the natural language speech input corresponds to a first likelihood of a first user of the plurality of users; and a second likelihood that the natural language speech input corresponds to a second user of the plurality of users, the second likelihood being less than the first likelihood; determining whether the first likelihood and the second likelihood are within a first threshold; and in accordance with a determination that the first likelihood and the second likelihood are not within the first threshold: a response to the natural language voice input is provided, the response being personalized to the first user.

Example methods are disclosed herein. An example method includes, at an electronic device having a memory and one or more processors: receiving a voice media request; determining whether a user of a plurality of registered users corresponds to the voice media request; in accordance with a determination that a first user of the plurality of registered users corresponds to a voice media request: providing a first response to the voice media request, the first response being personalized for the first user; and in accordance with a determination that none of the plurality of registered users corresponds to a voice media request: determining whether the voice media request includes a personal media request; in accordance with a determination that the voice media request includes a personal media request: acquiring an identification of a user providing a voice media request; according to the acquisition identification: a second response to the voice media request is provided, the second response being personalized for the user providing the voice media request.

Example non-transitory computer-readable media are disclosed herein. An example non-transitory computer readable storage medium stores one or more programs. The one or more programs include instructions, which when executed by one or more processors of the electronic device, cause the electronic device to: receiving a voice media request; determining whether a user of a plurality of registered users corresponds to the voice media request; in accordance with a determination that a first user of the plurality of registered users corresponds to a voice media request: providing a first response to the voice media request, the first response being personalized for the first user; and in accordance with a determination that none of the plurality of registered users corresponds to a voice media request: determining whether the voice media request includes a personal media request; in accordance with a determination that the voice media request includes a personal media request: acquiring an identification of a user providing a voice media request; according to the acquisition identification: a second response to the voice media request is provided, the second response being personalized for the user providing the voice media request.

Example electronic devices are disclosed herein. An example electronic device includes one or more processors; a memory; and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising instructions for: receiving a voice media request; determining whether a user of a plurality of registered users corresponds to the voice media request; in accordance with a determination that a first user of the plurality of registered users corresponds to a voice media request: providing a first response to the voice media request, the first response being personalized for the first user; and in accordance with a determination that none of the plurality of registered users corresponds to a voice media request: determining whether the voice media request includes a personal media request; in accordance with a determination that the voice media request includes a personal media request: acquiring an identification of a user providing a voice media request; according to the acquisition identification: a second response to the voice media request is provided, the second response being personalized for the user providing the voice media request.

An example electronic device includes means for: receiving a voice media request; determining whether a user of a plurality of registered users corresponds to the voice media request; in accordance with a determination that a first user of the plurality of registered users corresponds to a voice media request: providing a first response to the voice media request, the first response being personalized for the first user; and in accordance with a determination that none of the plurality of registered users corresponds to a voice media request: determining whether the voice media request includes a personal media request; in accordance with a determination that the voice media request includes a personal media request: acquiring an identification of a user providing a voice media request; according to the acquisition identification: a second response to the voice media request is provided, the second response being personalized for the user providing the voice media request.

Based on comparing the natural language speech input to the plurality of speaker profiles: the natural language speech input corresponds to a first likelihood of a first user of the plurality of users; and a second likelihood that the natural language voice input corresponds to a second user of the plurality of users, the second likelihood being less than the first likelihood allowing the digital assistant to identify the current user. For example, if the digital assistant is operating on a device shared by many users, the digital assistant may identify the current user of the device (e.g., based on its voice input) and provide a response (and/or perform a task) that is personalized to the identified user (e.g., read a text message of the user, add an event to a calendar of the user, call one of the user contacts, etc.). Thus, electronic devices shared by many users can accurately identify the current user and provide personal content to the identified user. In this way, the user device interface may be made more efficient (e.g., by efficiently providing a response associated with the identified user, by increasing the amount of information available to the shared electronic device, by preventing disclosure of personal information to unidentified users), which in turn reduces power usage and extends battery life of the device by enabling the user to use the device more quickly and efficiently.

In accordance with a determination that the first likelihood and the second likelihood are not within the first threshold: providing a response to the natural language voice input that is personalized to the first user allows the digital assistant to determine whether the current user is distinguishable from other users before providing the response personalized to the current user. This may enhance the security of the user's personal information by preventing other users from accessing such information. In addition, determining whether the current user is distinguishable from other users of the electronic device may improve the accuracy of user identification (e.g., particularly when the electronic device is shared by many users). As discussed, accurately identifying the current user and providing personal content to the identified user makes the user device interface more efficient (e.g., by efficiently providing a response related to the identified user, by increasing the amount of information available to the shared electronic device, by preventing disclosure of personal information to unidentified users), which in turn reduces power usage and extends battery life of the device by enabling the user to use the device more quickly and efficiently.

In accordance with a determination that a first user of the plurality of registered users corresponds to a voice media request: a first response to the voice media request is provided that is personalized for the first user, thus allowing electronic devices shared by many users to provide or modify media content for the identified user. Thus, the response to the voice media request may be advantageously personalized for the identified user (e.g., playing music from the identified user's account, adding media content to the identified user's account, providing news from the identified user's preferred content provider, etc.). Further, unauthorized modification or provision of the user's media content may be prevented (e.g., by preventing one user of the shared device from modifying the media content of another user of the device). In this way, the user device interface may be made more efficient (e.g., by providing media content related to the identified user, by preventing other users from modifying the user's media content, by allowing the sharing device to efficiently and securely manage the media content of multiple users), which in turn reduces power usage and extends battery life of the device by enabling the user to more quickly and efficiently use the device.

In accordance with a determination that the voice media request includes a personal media request: acquiring an identification of a user providing a voice media request; according to the acquisition identification: providing a second response to the voice media request that is personalized to the user providing the voice media request, thus allowing the electronic device shared by the plurality of users to securely provide or modify the media content of the identified user. For example, if the device is not sufficiently confident that the voice request corresponds to the user, the device may use other techniques (e.g., in addition to using the voice request) to identify the user before providing the personalized response. This may increase the security of the user's media content by preventing other users from accessing and/or modifying the user's media content. Further, obtaining an identification of a user providing a voice media request in accordance with a determination that the voice media request includes a personal media request may allow other techniques to be performed only when appropriate (e.g., when the voice media request includes a personal request) to identify the user. For example, for voice media requests that do not require user recognition (e.g., "play music"), the device does not undesirably perform other techniques to identify the user (e.g., initiate a conversation with the user). As another example, when user identification is desired (e.g., for a request such as "add this to my playlist", "play my personal music"), the device may perform other techniques to identify the user. Thus, the device may efficiently and securely provide or modify media content without extending user device interactions. In this way, the user device interface may be made more efficient (e.g., by providing media content related to the identified user, by preventing other users from modifying the user's media content, by allowing the sharing device to efficiently and securely manage the media content of multiple users), which in turn reduces power usage and extends battery life of the device by enabling the user to more quickly and efficiently use the device.

Drawings

Fig. 1 is a block diagram illustrating a system and environment for implementing a digital assistant according to various examples.

Fig. 2A is a block diagram illustrating a portable multifunction device implementing a client-side portion of a digital assistant in accordance with various examples.

FIG. 2B is a block diagram illustrating exemplary components for event processing according to various examples.

Fig. 3 illustrates a portable multifunction device implementing a client-side portion of a digital assistant in accordance with various examples.

FIG. 4 is a block diagram of an exemplary multifunction device with a display and a touch-sensitive surface in accordance with various examples.

FIG. 5A illustrates an exemplary user interface of a menu of applications on a portable multifunction device in accordance with various examples.

FIG. 5B illustrates an exemplary user interface of a multi-function device having a touch-sensitive surface separate from a display according to various examples.

Fig. 6A illustrates a personal electronic device according to various examples.

Fig. 6B is a block diagram illustrating a personal electronic device in accordance with various examples.

Fig. 7A is a block diagram illustrating a digital assistant system or server portion thereof according to various examples.

Fig. 7B illustrates the functionality of the digital assistant shown in fig. 7A according to various examples.

Fig. 7C illustrates a portion of a ontology according to various examples.

FIG. 8 illustrates user interactions with an electronic device according to some examples.

9A-9F illustrate a flow chart of a process for responding to speech input according to some examples.

Fig. 10A-10H illustrate exemplary interactions of a user with an electronic device.

11A-11B illustrate a flow chart of a process for providing media content according to some examples.

Fig. 12 illustrates an exemplary system for acquiring personal information.

Fig. 13A-13G illustrate a process for responding to speech input according to some examples.

Fig. 14A-14E illustrate a process for providing media content according to some examples.

Detailed Description

In the following description of the examples, reference is made to the accompanying drawings in which, by way of illustration, specific examples in which the embodiments may be practiced are shown. It is to be understood that other examples may be utilized and structural changes may be made without departing from the scope of the various examples.

This typically involves identifying the user of the digital assistant based on the user's corresponding voice. Once the user is identified, the digital assistant may provide a response that is personalized to the user.

Although the following description uses the terms "first," "second," etc. to describe various elements, these elements should not be limited by the terms. These terms are only used to distinguish one element from another element. For example, a first input may be referred to as a second input, and similarly, a second input may be referred to as a first input, without departing from the scope of the various described examples. The first input and the second input are both inputs, and in some cases are independent and different inputs.

The terminology used in the description of the various illustrated examples herein is for the purpose of describing particular examples only and is not intended to be limiting. As used in the description of the various described examples and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

Depending on the context, the term "if" may be interpreted to mean "when … …" or "at … …" or "in response to a determination" or "in response to detection". Similarly, the phrase "if a determination …" or "if a [ stated condition or event ] is detected" may be interpreted to mean "upon a determination …" or "in response to a determination …" or "upon a detection of a [ stated condition or event ]" or "in response to a detection of a [ stated condition or event ], depending on the context.

1. System and environment

Fig. 1 illustrates a block diagram of a system 100 in accordance with various examples. In some examples, system 100 implements a digital assistant. The terms "digital assistant," "virtual assistant," "intelligent automated assistant," or "automated digital assistant" refer to any information processing system that interprets natural language input in spoken and/or textual form to infer user intent and performs an action based on the inferred user intent. For example, to act on inferred user intent, the system performs one or more of the following steps: identifying a task flow having steps and parameters designed to achieve the inferred user intent, inputting specific requirements into the task flow based on the inferred user intent; executing task flows through calling programs, methods, services, APIs and the like; and generating an output response to the user in audible (e.g., speech) and/or visual form.

In particular, the digital assistant is capable of accepting user requests in the form of, at least in part, natural language commands, requests, statements, lectures, and/or inquiries. Typically, users request that the digital assistant be asked to make informational answers or perform tasks. Satisfactory responses to user requests include providing the requested informational answer, performing the requested task, or a combination of both. For example, the user presents questions to the digital assistant such as "where is i now? ". Based on the user's current location, the digital assistant answers "you are near the central park siemens. "the user also requests to perform a task, such as" please invite my friends to take part in my girl's birthday party next week. In response, the digital assistant may acknowledge the request by speaking "good, immediate" and then send an appropriate calendar invitation on behalf of the user to each of the user's friends listed in the user's electronic address book. During execution of the requested task, the digital assistant sometimes interacts with the user in a continuous conversation involving multiple exchanges of information over a long period of time. There are many other ways to interact with a digital assistant to request information or perform various tasks. In addition to providing verbal responses and taking programmed actions, the digital assistant also provides responses in other video or audio forms, for example as text, alerts, music, video, animation, and the like.

As shown in fig. 1, in some examples, the digital assistant is implemented according to a client-server model. The digital assistant includes a client-side portion 102 (hereinafter "DA client 102") that executes on a user device 104 and a server-side portion 106 (hereinafter "DA server 106") that executes on a server system 108. DA client 102 communicates with DA server 106 through one or more networks 110. The DA client 102 provides client-side functionality such as user-oriented input and output processing, and communication with the DA server 106. The DA server 106 provides server-side functionality for any number of DA clients 102 each located on a respective user device 104.

In some examples, the DA server 106 includes a client-oriented I/O interface 112, one or more processing modules 114, a data and model 116, and an I/O interface 118 to external services. The client-oriented I/O interface 112 facilitates client-oriented input and output processing of the DA server 106. The one or more processing modules 114 process the speech input using the data and models 116 and determine user intent based on the natural language input. Further, the one or more processing modules 114 perform task execution based on the inferred user intent. In some examples, DA server 106 communicates with external services 120 over one or more networks 110 to accomplish tasks or collect information. The I/O interface 118 to external services facilitates such communication.

The user device 104 may be any suitable electronic device. In some examples, the user device 104 is a portable multifunction device (e.g., device 200 described below with reference to fig. 2A), a multifunction device (e.g., device 400 described below with reference to fig. 4), or a personal electronic device (e.g., device 600 described below with reference to fig. 6A-6B). The portable multifunction device is, for example, a mobile phone that also contains other functions, such as PDA and/or music player functions. Specific examples of portable multifunction devices include Apple from Apple inc (Cupertino, california)iPod AndAn apparatus. Other examples of portable multifunction devices include, but are not limited to, earbud/headphones, speakers, and laptop or tablet computers. Further, in some examples, the user device 104 is a non-portable multifunction device. In particular, the user device 104 is a desktop computer, a gaming machine, speakers, a television, or a television set-top box. In some examples, the user device 104 includes a touch-sensitive surface (e.g., a touch screen display and/or a touch pad). In addition, the user device 104 optionally includes one or more other physical user interface devices, such as a physical keyboard, mouse, and/or joystick. Various examples of electronic devices, such as multifunction devices, are described in more detail below.

Examples of one or more communication networks 110 include a Local Area Network (LAN) and a Wide Area Network (WAN), such as the Internet. One or more of the communication networks 110 are implemented using any known network protocol, including various wired or wireless protocols, such as Ethernet, universal Serial Bus (USB), FIREWIRE, global System for Mobile communications (GSM), enhanced Data GSM Environment (EDGE), code Division Multiple Access (CDMA), time Division Multiple Access (TDMA), bluetooth, wi-Fi, voice over Internet protocol (VoIP), wi-MAX, or any other suitable communication protocol.

The server system 108 is implemented on one or more standalone data processing devices or distributed computer networks. In some examples, the server system 108 also employs various virtual devices and/or services of a third party service provider (e.g., a third party cloud service provider) to provide potential computing resources and/or infrastructure resources of the server system 108.

In some examples, the user device 104 communicates with the DA server 106 via a second user device 122. The second user device 122 is similar or identical to the user device 104. For example, the second user device 122 is similar to the device 200, 400, or 600 described below with reference to fig. 2A, 4, and 6A-6B. The user device 104 is configured to be communicatively coupled to the second user device 122 via a direct communication connection (such as bluetooth, NFC, BTLE, etc.) or via a wired or wireless network (such as a local Wi-Fi network). In some examples, the second user device 122 is configured to act as a proxy between the user device 104 and the DA server 106. For example, the DA client 102 of the user device 104 is configured to transmit information (e.g., user requests received at the user device 104) to the DA server 106 via the second user device 122. The DA server 106 processes this information and returns relevant data (e.g., data content in response to a user request) to the user device 104 via the second user device 122.

In some examples, the user device 104 is configured to send a thumbnail request for data to the second user device 122 to reduce the amount of information transmitted from the user device 104. The second user device 122 is configured to determine supplemental information to be added to the thumbnail request to generate a complete request for transmission to the DA server 106. The system architecture may advantageously allow user devices 104 (e.g., watches or similar compact electronic devices) with limited communication capabilities and/or limited battery power to access services provided by the DA server 106 by using a second user device 122 (e.g., mobile phone, laptop, tablet, etc.) with greater communication capabilities and/or battery power as a proxy to the DA server 106. Although only two user devices 104 and 122 are shown in fig. 1, it should be understood that in some examples, system 100 may include any number and type of user devices configured to communicate with DA server system 106 in this proxy configuration.

Although the digital assistant shown in fig. 1 includes both a client-side portion (e.g., DA client 102) and a server-side portion (e.g., DA server 106), in some examples, the functionality of the digital assistant is implemented as a standalone application installed on a user device. Furthermore, the division of functionality between the client portion and the server portion of the digital assistant may vary in different implementations. For example, in some examples, the DA client is a thin client that provides only user-oriented input and output processing functions and delegates all other functions of the digital assistant to the back-end server.

2. Electronic equipment

Attention is now directed to an implementation of an electronic device for implementing a client-side portion of a digital assistant. Fig. 2A is a block diagram illustrating a portable multifunction device 200 with a touch-sensitive display system 212 in accordance with some embodiments. Touch-sensitive display 212 is sometimes referred to as a "touch screen" for convenience and is sometimes referred to or referred to as a "touch-sensitive display system". Device 200 includes memory 202 (which optionally includes one or more computer-readable storage media), memory controller 222, one or more processing units (CPUs) 220, peripheral interface 218, RF circuitry 208, audio circuitry 210, speaker 211, microphone 213, input/output (I/O) subsystem 206, other input control devices 216, and external ports 224. The device 200 optionally includes one or more optical sensors 264. The device 200 optionally includes one or more contact intensity sensors 265 for detecting the intensity of contacts on the device 200 (e.g., a touch-sensitive surface of the device 200 such as the touch-sensitive display system 212). The device 200 optionally includes one or more tactile output generators 267 for generating tactile outputs on the device 200 (e.g., generating tactile outputs on a touch-sensitive surface such as the touch-sensitive display system 212 of the device 200 or the touch pad 455 of the device 400). These components optionally communicate via one or more communication buses or signal lines 203.

As used in this specification and the claims, the term "intensity" of a contact on a touch-sensitive surface refers to the force or pressure (force per unit area) of the contact on the touch-sensitive surface (e.g., finger contact), or to an alternative to the force or pressure of the contact on the touch-sensitive surface (surrogate). The intensity of the contact has a range of values that includes at least four different values and more typically includes hundreds of different values (e.g., at least 256). The intensity of the contact is optionally determined (or measured) using various methods and various sensors or combinations of sensors. For example, one or more force sensors below or adjacent to the touch-sensitive surface are optionally used to measure forces at different points on the touch-sensitive surface. In some implementations, force measurements from multiple force sensors are combined (e.g., weighted average) to determine an estimated contact force. Similarly, the pressure-sensitive tip of the stylus is optionally used to determine the pressure of the stylus on the touch-sensitive surface. Alternatively, the size of the contact area and/or its variation detected on the touch-sensitive surface, the capacitance of the touch-sensitive surface in the vicinity of the contact and/or its variation and/or the resistance of the touch-sensitive surface in the vicinity of the contact and/or its variation are optionally used as a substitute for the force or pressure of the contact on the touch-sensitive surface. In some implementations, surrogate measurements of contact force or pressure are directly used to determine whether an intensity threshold has been exceeded (e.g., the intensity threshold is described in units corresponding to surrogate measurements). In some implementations, surrogate measurements of contact force or pressure are converted to an estimated force or pressure, and the estimated force or pressure is used to determine whether an intensity threshold has been exceeded (e.g., the intensity threshold is a pressure threshold measured in units of pressure). The intensity of the contact is used as an attribute of the user input, allowing the user to access additional device functions that are not otherwise accessible to the user on a smaller sized device of limited real estate for displaying affordances and/or receiving user input (e.g., via a touch-sensitive display, touch-sensitive surface, or physical/mechanical control, such as a knob or button).

As used in this specification and in the claims, the term "haptic output" refers to a physical displacement of a device relative to a previous position of the device, a physical displacement of a component of the device (e.g., a touch sensitive surface) relative to another component of the device (e.g., a housing), or a displacement of a component relative to a centroid of the device, to be detected by a user with a user's feel. For example, in the case where the device or component of the device is in contact with a touch-sensitive surface of the user (e.g., a finger, palm, or other portion of the user's hand), the haptic output generated by the physical displacement will be interpreted by the user as a haptic sensation corresponding to a perceived change in a physical characteristic of the device or component of the device. For example, movement of a touch-sensitive surface (e.g., a touch-sensitive display or touch pad) is optionally interpreted by a user as a "press click" or "click-down" of a physically actuated button. In some cases, the user will feel a tactile sensation, such as "press click" or "click down", even when the physical actuation button associated with the touch-sensitive surface that is physically pressed (e.g., displaced) by the user's movement is not moved. As another example, movement of the touch-sensitive surface may optionally be interpreted or sensed by a user as "roughness" of the touch-sensitive surface, even when the smoothness of the touch-sensitive surface is unchanged. While such interpretation of touches by a user will be limited by the user's individualized sensory perception, many sensory perceptions of touches are common to most users. Thus, when a haptic output is described as corresponding to a particular sensory perception of a user (e.g., "click down," "click up," "roughness"), unless stated otherwise, the haptic output generated corresponds to a physical displacement of the device or component thereof that would generate that sensory perception of a typical (or ordinary) user.

It should be understood that the device 200 is only one example of a portable multifunction device, and that the device 200 optionally has more or fewer components than shown, optionally combines two or more components, or optionally has a different configuration or arrangement of the components. The various components shown in fig. 2A are implemented in hardware, software, or a combination of both hardware and software, including one or more signal processing and/or application specific integrated circuits.

Memory 202 includes one or more computer-readable storage media. These computer readable storage media are, for example, tangible and non-transitory. Memory 202 includes high-speed random access memory, and also includes non-volatile memory, such as one or more magnetic disk storage devices, flash memory devices, or other non-volatile solid-state memory devices. The memory controller 222 controls other components of the device 200 to access the memory 202.

In some examples, the non-transitory computer-readable storage medium of memory 202 is used to store instructions (e.g., for performing aspects of the processes described below) for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. In other examples, the instructions (e.g., for performing aspects of the processes described below) are stored on a non-transitory computer-readable storage medium (not shown) of the server system 108 or divided between a non-transitory computer-readable storage medium of the memory 202 and a non-transitory computer-readable storage medium of the server system 108.

Peripheral interface 218 is used to couple the input and output peripherals of the device to CPU 220 and memory 202. The one or more processors 220 run or execute various software programs and/or sets of instructions stored in the memory 202 to perform various functions of the device 200 and process data. In some embodiments, peripheral interface 218, CPU 220, and memory controller 222 are implemented on a single chip, such as chip 204. In some other embodiments, they are implemented on separate chips.

The RF (radio frequency) circuit 208 receives and transmits RF signals, also referred to as electromagnetic signals. RF circuitry 208 converts/converts electrical signals to/from electromagnetic signals and communicates with communication networks and other communication devices via electromagnetic signals. RF circuitry 208 optionally includes well known circuitry for performing these functions including, but not limited to, an antenna system, an RF transceiver, one or more amplifiers, a tuner, one or more oscillators, a digital signal processor, a codec chipset, a Subscriber Identity Module (SIM) card, memory, and the like. RF circuitry 208 optionally communicates via wireless communication with networks such as the internet (also known as the World Wide Web (WWW)), intranets, and/or wireless networks such as cellular telephone networks, wireless Local Area Networks (LANs), and/or Metropolitan Area Networks (MANs), and other devices. The RF circuitry 208 optionally includes well-known circuitry for detecting a Near Field Communication (NFC) field, such as by a short-range communication radio. Wireless communications optionally use any of a variety of communication standards, protocols, and technologies including, but not limited to, global system for mobile communications (GSM), enhanced Data GSM Environment (EDGE), high Speed Downlink Packet Access (HSDPA), high Speed Uplink Packet Access (HSUPA), evolution, pure data (EV-DO), HSPA, hspa+, dual cell HSPA (DC-HSPDA), long Term Evolution (LTE), near Field Communications (NFC), wideband code division multiple access (W-CDMA), code Division Multiple Access (CDMA), time Division Multiple Access (TDMA), bluetooth low energy (BTLE), wireless fidelity (Wi-Fi) (e.g., IEEE 802.11a, IEEE 802.11b, IEEE 802.11g, IEEE 802.11n, and/or IEEE 802.11 ac), voice over internet protocol (VoIP), wi-MAX, email protocols (e.g., internet Message Access Protocol (IMAP) and/or Post Office Protocol (POP)), messages (e.g., extensible messaging and presence protocol (XMPP), protocols for instant messaging and presence initiation with extended session initiation (sime), messages and presence (pls), or other fashionable communications protocols, or any other suitable fashion-oriented protocols, or non-compliant communications including, such as may be developed on the date of any other suitable date.

Audio circuitry 210, speaker 211, and microphone 213 provide an audio interface between the user and device 200. Audio circuit 210 receives audio data from peripheral interface 218, converts the audio data into an electrical signal, and transmits the electrical signal to speaker 211. The speaker 211 converts electrical signals into sound waves that are audible to humans. The audio circuit 210 also receives electrical signals converted from sound waves by the microphone 213. Audio circuitry 210 converts the electrical signals to audio data and transmits the audio data to peripheral interface 218 for processing. The audio data is retrieved from and/or transmitted to the memory 202 and/or the RF circuitry 208 via the peripheral interface 218. In some embodiments, the audio circuit 210 also includes a headset jack (e.g., 312 in fig. 3). The headset jack provides an interface between the audio circuit 210 and a removable audio input/output peripheral, such as an output-only earphone or a headset having both an output (e.g., a monaural earphone or a binaural earphone) and an input (e.g., a microphone).

I/O subsystem 206 couples input/output peripheral devices on device 200, such as touch screen 212 and other input control devices 216 to peripheral interface 218. The I/O subsystem 206 optionally includes a display controller 256, an optical sensor controller 258, an intensity sensor controller 259, a haptic feedback controller 261, and one or more input controllers 260 for other input or control devices. One or more input controllers 260 receive electrical signals from other input control devices 216/send electrical signals to other input control devices 216. Other input control devices 216 optionally include physical buttons (e.g., push buttons, rocker buttons, etc.), dials, slider switches, joysticks, click wheels, and the like. In some alternative implementations, the input controller 260 is optionally coupled to (or not coupled to) any of the following: a keyboard, an infrared port, a USB port, and a pointing device such as a mouse. One or more buttons (e.g., 308 in fig. 3) optionally include an up/down button for volume control of speaker 211 and/or microphone 213. The one or more buttons optionally include a push button (e.g., 306 in fig. 3).

A quick press of the push button may disengage the lock of the touch screen 212 or begin the process of unlocking the device using gestures on the touch screen, as described in U.S. patent application 11/322,549 to U.S. patent 7,657,849, entitled "Unlocking a Device by Performing Gestures on an Unlock Image," filed on even 23, 12/2005, which is hereby incorporated by reference in its entirety. Longer presses of the push button (e.g., 306) cause the device 200 to power on or off. The user is able to customize the functionality of one or more buttons. Touch screen 212 is used to implement virtual buttons or soft buttons and one or more soft keyboards.

The touch sensitive display 212 provides an input interface and an output interface between the device and the user. Display controller 256 receives electrical signals from touch screen 212 and/or transmits electrical signals to touch screen 212. Touch screen 212 displays visual output to a user. Visual output includes graphics, text, icons, video, and any combination thereof (collectively, "graphics"). In some implementations, some or all of the visual output corresponds to a user interface object.

Touch screen 212 has a touch-sensitive surface, sensor or set of sensors that receives input from a user based on haptic and/or tactile contact. Touch screen 212 and display controller 256 (along with any associated modules and/or sets of instructions in memory 202) detect contact (and any movement or interruption of the contact) on touch screen 212 and translate the detected contact into interactions with user interface objects (e.g., one or more soft keys, icons, web pages, or images) displayed on touch screen 212. In an exemplary embodiment, the point of contact between touch screen 212 and the user corresponds to a user's finger.

Touch screen 212 uses LCD (liquid crystal display) technology, LPD (light emitting polymer display) technology, or LED (light emitting diode) technology, but other display technologies may be used in other embodiments. Touch screen 212 and display controller 256 detect contact and any movement or interruption thereof using any of a variety of touch sensing technologies now known or later developed, including but not limited to capacitive, resistive, infrared, and surface acoustic wave technologies, as well as other proximity sensor arrays or other elements for determining one or more points of contact with touch screen 212. In an exemplary embodiment, a projected mutual capacitance sensing technique is used, such as that described in the text from Apple inc (Cupertino, california)And iPodTechniques used in the above.

In some implementations, the touch sensitive display of touch screen 212 is similar to the following U.S. patents: 6,323,846 (Westerman et al), 6,570,557 (Westerman et al) and/or 6,677,932 (Westerman) and/or a multi-touch-sensitive touch pad as described in U.S. patent publication 2002/0015024A1, which are incorporated herein by reference in their entirety. However, touch screen 212 displays visual output from device 200, while the touch sensitive touchpad does not provide visual output.

In some implementations, the touch sensitive display of touch screen 212 is as described in the following applications: (1) U.S. patent application Ser. No. 11/381,313, entitled "Multipoint Touch Surface Controller," filed on 5/2/2006; (2) U.S. patent application Ser. No.10/840,862 entitled "Multipoint Touchscreen" filed on 5/6/2004; (3) U.S. patent application Ser. No. 10/903,964 entitled "Gestures For Touch Sensitive Input Devices" filed on 7/30/2004; (4) U.S. patent application Ser. No.11/048,264 entitled "Gestures For Touch Sensitive Input Devices" filed on 1/31/2005; (5) U.S. patent application Ser. No.11/038,590, entitled "Mode-Based Graphical User Interfaces For Touch Sensitive Input Devices," filed 1/18/2005; (6) U.S. patent application Ser. No.11/228,758, entitled "Virtual Input DEVICE PLACEMENT On A Touch Screen User Interface," filed 9/16/2005; (7) U.S. patent application Ser. No.11/228,700, entitled "Operation Of A Computer With A Touch SCREEN INTERFACE," filed 9/16/2005; (8) U.S. patent application Ser. No.11/228,737, entitled "ACTIVATING VIRTUAL KEYS OF A TOUCH-Screen Virtual Keyboard," filed 9/16/2005; and (9) U.S. patent application Ser. No.11/367,749, entitled "Multi-Functional Hand-HELD DEVICE," filed 3/2006. All of these applications are incorporated by reference herein in their entirety.

Touch screen 212 has, for example, a video resolution in excess of 100 dpi. In some implementations, the touch screen has a video resolution of about 160 dpi. The user makes contact with touch screen 212 using any suitable object or appendage, such as a stylus, finger, or the like. In some embodiments, the user interface is designed to work primarily with finger-based contacts and gestures, which may not be as accurate as stylus-based input due to the large contact area of the finger on the touch screen. In some embodiments, the device translates the finger-based coarse input into a precise pointer/cursor position or command for performing the action desired by the user.

In some embodiments, the device 200 includes a touch pad (not shown) for activating or deactivating a specific function in addition to the touch screen. In some embodiments, the touch pad is a touch sensitive area of the device that, unlike a touch screen, does not display visual output. The touch pad is a touch sensitive surface separate from the touch screen 212 or an extension of the touch sensitive surface formed by the touch screen.

The device 200 also includes a power system 262 for powering the various components. The power system 262 includes a power management system, one or more power sources (e.g., batteries, alternating Current (AC)), a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator (e.g., light Emitting Diode (LED)), and any other components associated with the generation, management, and distribution of power in the portable device.

The device 200 also includes one or more optical sensors 264. Fig. 2A shows an optical sensor coupled to an optical sensor controller 258 in the I/O subsystem 206. The optical sensor 264 includes a Charge Coupled Device (CCD) or a Complementary Metal Oxide Semiconductor (CMOS) phototransistor. The optical sensor 264 receives light projected through one or more lenses from the environment and converts the light into data representing an image. In conjunction with an imaging module 243 (also called a camera module), the optical sensor 264 captures still images or video. In some embodiments, the optical sensor is located at the back of the device 200, opposite the touch screen display 212 at the front of the device, such that the touch screen display is used as a viewfinder for still image and/or video image acquisition. In some embodiments, the optical sensor is located at the front of the device such that the user's image is acquired for the video conference while the user views other video conference participants on the touch screen display. In some implementations, the position of the optical sensor 264 can be changed by the user (e.g., by rotating a lens and sensor in the device housing) such that a single optical sensor 264 is used with the touch screen display for both video conferencing and still image and/or video image acquisition.

The device 200 optionally further includes one or more contact strength sensors 265. Fig. 2A shows a contact intensity sensor coupled to an intensity sensor controller 259 in the I/O subsystem 206. The contact strength sensor 265 optionally includes one or more piezoresistive strain gauges, capacitive force sensors, electrical force sensors, piezoelectric force sensors, optical force sensors, capacitive touch-sensitive surfaces, or other strength sensors (e.g., sensors for measuring force (or pressure) of a contact on a touch-sensitive surface). The contact strength sensor 265 receives contact strength information (e.g., pressure information or a surrogate for pressure information) from the environment. In some implementations, at least one contact intensity sensor is juxtaposed or adjacent to a touch-sensitive surface (e.g., touch-sensitive display system 212). In some embodiments, at least one contact intensity sensor is located on the rear of the device 200, opposite the touch screen display 212 located on the front of the device 200.

The device 200 also includes one or more proximity sensors 266. Fig. 2A shows a proximity sensor 266 coupled to the peripheral interface 218. Alternatively, the proximity sensor 266 is coupled to the input controller 260 in the I/O subsystem 206. The proximity sensor 266 performs as described in the following U.S. patent applications: 11/241,839, entitled "Proximity Detector IN HANDHELD DEVICE"; no.11/240,788, entitled "Proximity Detector IN HANDHELD DEVICE"; no.11/620,702, entitled "Using Ambient Light Sensor To Augment Proximity Sensor Output"; no.11/586,862, entitled "Automated Response To AND SENSING OfUser ACTIVITY IN Portable Devices"; and No.11/638,251, entitled Methods AND SYSTEMS For Automatic Configuration Of Peripherals, which are hereby incorporated by reference in their entirety. In some implementations, the proximity sensor turns off and disables the touch screen 212 when the multifunction device is placed near the user's ear (e.g., when the user is making a telephone call).

The device 200 optionally further comprises one or more tactile output generators 267. Fig. 2A illustrates a haptic output generator coupled to a haptic feedback controller 261 in I/O subsystem 206. The tactile output generator 267 optionally includes one or more electroacoustic devices such as speakers or other audio components; and/or electromechanical devices for converting energy into linear motion such as motors, solenoids, electroactive polymers, piezoelectric actuators, electrostatic actuators, or other tactile output generating means (e.g., means for converting an electrical signal into a tactile output on a device). The contact strength sensor 265 receives haptic feedback generation instructions from the haptic feedback module 233 and generates a haptic output on the device 200 that can be perceived by a user of the device 200. In some embodiments, at least one tactile output generator is juxtaposed or adjacent to a touch-sensitive surface (e.g., touch-sensitive display system 212), and optionally generates tactile output by moving the touch-sensitive surface vertically (e.g., inward/outward of the surface of device 200) or laterally (e.g., backward and forward in the same plane as the surface of device 200). In some embodiments, at least one tactile output generator sensor is located on the rear of the device 200, opposite the touch screen display 212 located on the front of the device 200.

The device 200 also includes one or more accelerometers 268. Fig. 2A shows accelerometer 268 coupled to peripheral interface 218. Alternatively, accelerometer 268 is coupled to input controller 260 in I/O subsystem 206. Accelerometer 268 performs as described in the following U.S. patent publications: U.S. patent publication 20050190059, "acceletion-based Theft Detection System for Portable Electronic Devices" and U.S. patent publication 20060017692, "Methods And Apparatuses For Operating A Portable Device Based On An Accelerometer," which are incorporated herein by reference in their entirety. In some implementations, information is displayed in a portrait view or a landscape view on a touch screen display based on analysis of data received from one or more accelerometers. The device 200 optionally includes a magnetometer (not shown) and a GPS (or GLONASS or other global navigation system) receiver (not shown) in addition to the accelerometer 268 for obtaining information about the position and orientation (e.g., longitudinal or lateral) of the device 200.

In some embodiments, the software components stored in memory 202 include an operating system 226, a communication module (or set of instructions) 228, a contact/motion module (or set of instructions) 230, a graphics module (or set of instructions) 232, a text input module (or set of instructions) 234, a Global Positioning System (GPS) module (or set of instructions) 235, a digital assistant client module 229, and an application program (or set of instructions) 236. In addition, the memory 202 stores data and models, such as user data and models 231. Further, in some embodiments, memory 202 (fig. 2A) or 470 (fig. 4) stores device/global internal state 257, as shown in fig. 2A and 4. The device/global internal state 257 includes one or more of the following: an active application state indicating which applications (if any) are currently active; a display state indicating what applications, views, or other information occupy various areas of the touch screen display 212; sensor status, including information obtained from the various sensors of the device and the input control device 216; and location information regarding the location and/or pose of the device.

Operating system 226 (e.g., darwin, RTXC, LINUX, UNIX, OS X, iOS, WINDOWS, or embedded operating systems such as VxWorks) includes various software components and/or drivers for controlling and managing general system tasks (e.g., memory management, storage device control, power management, etc.), and facilitates communication between the various hardware components and software components.

The communication module 228 facilitates communication with other devices through one or more external ports 224 and also includes various software components for processing data received by the RF circuitry 208 and/or the external ports 224. External port 224 (e.g., universal Serial Bus (USB), firewire, etc.) is adapted to be coupled directly to other devices or indirectly via a network (e.g., the internet, wireless LAN, etc.). In some embodiments, the external port is in communication withThe 30-pin connector used on the (Apple inc. Trademark) device is the same or similar and/or compatible with a multi-pin (e.g., 30-pin) connector.

The contact/motion module 230 optionally detects contact with the touch screen 212 (in conjunction with the display controller 256) and other touch sensitive devices (e.g., a touch pad or physical click wheel). The contact/motion module 230 includes various software components for performing various operations related to contact detection, such as determining whether contact has occurred (e.g., detecting a finger press event), determining the strength of the contact (e.g., the force or pressure of the contact, or a substitute for the force or pressure of the contact), determining whether there is movement of the contact and tracking movement across the touch-sensitive surface (e.g., detecting one or more finger drag events), and determining whether the contact has stopped (e.g., detecting a finger lift event or a contact break). The contact/motion module 230 receives contact data from the touch-sensitive surface. Determining movement of the point of contact optionally includes determining a velocity (magnitude), a speed (magnitude and direction), and/or an acceleration (change in magnitude and/or direction) of the point of contact, the movement of the point of contact being represented by a series of contact data. These operations are optionally applied to single point contacts (e.g., single finger contacts) or simultaneous multi-point contacts (e.g., "multi-touch"/multiple finger contacts). In some embodiments, the contact/motion module 230 and the display controller 256 detect contact on the touch pad.

In some implementations, the contact/motion module 230 uses a set of one or more intensity thresholds to determine whether an operation has been performed by a user (e.g., to determine whether the user has "clicked" on an icon). In some embodiments, at least a subset of the intensity thresholds are determined according to software parameters (e.g., the intensity thresholds are not determined by activation thresholds of specific physical actuators and may be adjusted without changing the physical hardware of the device 200). For example, without changing the touchpad or touch screen display hardware, the mouse "click" threshold of the touchpad or touch screen may be set to any of a wide range of predefined thresholds. Additionally, in some implementations, a user of the device is provided with software settings for adjusting one or more intensity thresholds in a set of intensity thresholds (e.g., by adjusting individual intensity thresholds and/or by adjusting multiple intensity thresholds at once with a system-level click on an "intensity" parameter).

The contact/motion module 230 optionally detects gesture input by the user. Different gestures on the touch-sensitive surface have different contact patterns (e.g., different movements, timings, and/or intensities of the detected contacts). Thus, gestures are optionally detected by detecting a particular contact pattern. For example, detecting a finger tap gesture includes detecting a finger press event, and then detecting a finger lift (lift off) event at the same location (or substantially the same location) as the finger press event (e.g., at the location of an icon). As another example, detecting a finger swipe gesture on the touch-sensitive surface includes detecting a finger-down event, then detecting one or more finger-dragging events, and then detecting a finger-up (lift-off) event.

Graphics module 232 includes various known software components for rendering and displaying graphics on touch screen 212 or other display, including components for changing the visual impact (e.g., brightness, transparency, saturation, contrast, or other visual characteristics) of the displayed graphics. As used herein, the term "graphic" includes any object that may be displayed to a user, including without limitation text, web pages, icons (such as user interface objects including soft keys), digital images, video, animation, and the like.

In some embodiments, graphics module 232 stores data representing graphics to be used. Each graphic is optionally assigned a corresponding code. The graphic module 232 receives one or more codes designating graphics to be displayed from an application program or the like, and also receives coordinate data and other graphic attribute data together if necessary, and then generates screen image data to output to the display controller 256.

Haptic feedback module 233 includes various software components for generating instructions for use by haptic output generator 267 to generate haptic output at one or more locations on device 200 in response to user interaction with device 200.

The text input module 234, which in some examples is a component of the graphics module 232, provides a soft keyboard for entering text in various applications (e.g., contacts 237, email 240, IM 241, browser 247, and any other application requiring text input).

The GPS module 235 determines the location of the device and provides this information for use in various applications (e.g., to the phone 238 for use in location-based dialing, to the camera 243 as picture/video metadata, and to applications that provide location-based services, such as weather desktops, local page desktops, and map/navigation desktops).

The digital assistant client module 229 includes various client-side digital assistant instructions to provide client-side functionality of the digital assistant. For example, the digital assistant client module 229 is capable of accepting acoustic input (e.g., voice input), text input, touch input, and/or gesture input through various user interfaces of the portable multifunction device 200 (e.g., microphone 213, one or more accelerometers 268, touch-sensitive display system 212, one or more optical sensors 264, other input control devices 216, etc.). The digital assistant client module 229 is also capable of providing output in audio form (e.g., voice output), visual form, and/or tactile form through various output interfaces of the portable multifunction device 200 (e.g., speaker 211, touch-sensitive display system 212, one or more tactile output generators 267, etc.). For example, the output is provided as voice, sound, an alert, a text message, a menu, graphics, video, animation, vibration, and/or a combination of two or more of the foregoing. During operation, the digital assistant client module 229 communicates with the DA server 106 using the RF circuitry 208.

The user data and model 231 includes various data associated with the user (e.g., user-specific vocabulary data, user preference data, user-specified name pronunciations, data from a user electronic address book, backlog, shopping list, etc.) to provide client-side functionality of the digital assistant. Further, the user data and models 231 include various models (e.g., speech recognition models, statistical language models, natural language processing models, ontologies, task flow models, service models, etc.) for processing user inputs and determining user intent.

In some examples, the digital assistant client module 229 utilizes the various sensors, subsystems, and peripherals of the portable multifunction device 200 to gather additional information from the surrounding environment of the portable multifunction device 200 to establish a context associated with a user, current user interaction, and/or current user input. In some examples, the digital assistant client module 229 provides contextual information, or a subset thereof, along with user input to the DA server 106 to help infer user intent. In some examples, the digital assistant also uses the context information to determine how to prepare the output and communicate it to the user. The context information is referred to as context data.

In some examples, the contextual information accompanying the user input includes sensor information such as lighting, ambient noise, ambient temperature, images or videos of the surrounding environment, and the like. In some examples, the contextual information may also include a physical state of the device, such as device orientation, device location, device temperature, power level, speed, acceleration, movement pattern, cellular signal strength, and the like. In some examples, information related to the software state of the DA server 106, such as the running process of the portable multifunction device 200, installed programs, past and current network activities, background services, error logs, resource usage, etc., is provided to the DA server 106 as contextual information associated with user input.

In some examples, the digital assistant client module 229 selectively provides information (e.g., user data 231) stored on the portable multifunction device 200 in response to a request from the DA server 106. In some examples, the digital assistant client module 229 also brings up additional input from the user via a natural language dialog or other user interface upon request by the DA server 106. The digital assistant client module 229 communicates this additional input to the DA server 106 to assist the DA server 106 in intent inference and/or to implement user intent expressed in the user request.

The digital assistant is described in more detail below with reference to fig. 7A-7C. It should be appreciated that the digital assistant client module 229 may include any number of sub-modules of the digital assistant module 726 described below.

The application 236 includes the following modules (or instruction sets) or a subset or superset thereof:

Contact module 237 (sometimes referred to as an address book or contact list);

A telephone module 238;

Video conferencing module 239;

Email client module 240;

an Instant Messaging (IM) module 241;

A fitness support module 242;

A camera module 243 for still and/or video images;

an image management module 244;

A video player module;

A music player module;

Browser module 247;

calendar module 248;

A desktop applet module 249 that in some examples includes one or more of the following: weather desktop applet 249-1, stock desktop applet 249-2, calculator desktop applet 249-3, alarm desktop applet 249-4, dictionary desktop applet 249-5 and other desktop applet obtained by user and user created desktop applet 249-6;

A desktop applet creator module 250 for forming the user-created desktop applet 249-6;

Search module 251;

A video and music player module 252 that incorporates the video player module and the music player module;

Notepad module 253;

map module 254; and/or

An online video module 255.

Examples of other applications 236 stored in the memory 202 include other word processing applications, other image editing applications, drawing applications, presentation applications, JAVA-enabled applications, encryption, digital rights management, voice recognition, and voice replication.

In conjunction with touch screen 212, display controller 256, contact/motion module 230, graphics module 232, and text input module 234, contacts module 237 is used to manage an address book or contact list (e.g., in application internal state 292 of contacts module 237 stored in memory 202 or memory 470), including: adding one or more names to the address book; deleting the name from the address book; associating a telephone number, email address, physical address, or other information with the name; associating the image with a name; classifying and classifying names; providing a telephone number or email address to initiate and/or facilitate communications through telephone 238, video conferencing module 239, email 240 or IM 241; etc.

In conjunction with RF circuitry 208, audio circuitry 210, speaker 211, microphone 213, touch screen 212, display controller 256, contact/motion module 230, graphics module 232, and text input module 234, telephone module 238 is used to input a sequence of characters corresponding to a telephone number, access one or more telephone numbers in contact module 237, modify telephone numbers that have been entered, dial a corresponding telephone number, conduct a conversation, and disconnect or hang-up when the conversation is completed. As described above, wireless communication uses any of a variety of communication standards, protocols, and technologies.

In conjunction with RF circuitry 208, audio circuitry 210, speaker 211, microphone 213, touch screen 212, display controller 256, optical sensor 264, optical sensor controller 258, contact/motion module 230, graphics module 232, text input module 234, contacts module 237, and telephony module 238, videoconferencing module 239 includes executable instructions to initiate, conduct, and terminate a videoconference between a user and one or more other parties according to user instructions.

In conjunction with RF circuitry 208, touch screen 212, display controller 256, contact/motion module 230, graphics module 232, and text input module 234, email client module 240 includes executable instructions for creating, sending, receiving, and managing emails in response to user instructions. In conjunction with the image management module 244, the email client module 240 makes it very easy to create and send emails with still or video images captured by the camera module 243.

In conjunction with RF circuitry 208, touch screen 212, display controller 256, contact/motion module 230, graphics module 232, and text input module 234, instant message module 241 includes executable instructions for: inputting a character sequence corresponding to an instant message, modifying previously inputted characters, transmitting a corresponding instant message (e.g., using a Short Message Service (SMS) or Multimedia Message Service (MMS) protocol for a phone-based instant message or using XMPP, SIMPLE or IMPS for an internet-based instant message), receiving an instant message, and viewing the received instant message. In some embodiments, the transmitted and/or received instant messages include graphics, photographs, audio files, video files, and/or other attachments as supported in MMS and/or Enhanced Messaging Services (EMS). As used herein, "instant message" refers to both telephony-based messages (e.g., messages sent using SMS or MMS) and internet-based messages (e.g., messages sent using XMPP, SIMPLE, or IMPS).

In conjunction with RF circuitry 208, touch screen 212, display controller 256, contact/motion module 230, graphics module 232, text input module 234, GPS module 235, map module 254, and music player module, workout support module 242 includes executable instructions for: creating workouts (e.g., with time, distance, and/or calorie burn targets); communicate with a fitness sensor (exercise device); receiving fitness sensor data; calibrating a sensor for monitoring fitness; selecting and playing music for exercise; and displaying, storing and transmitting the fitness data.

In conjunction with touch screen 212, display controller 256, optical sensor 264, optical sensor controller 258, contact/motion module 230, graphics module 232, and image management module 244, camera module 243 includes executable instructions for: capturing still images or videos (including video streams) and storing them in the memory 202, modifying features of still images or videos, or deleting still images or videos from the memory 202.

In conjunction with touch screen 212, display controller 256, contact/motion module 230, graphics module 232, text input module 234, and camera module 243, image management module 244 includes executable instructions for arranging, modifying (e.g., editing), or otherwise manipulating, tagging, deleting, presenting (e.g., in a digital slide or album), and storing still and/or video images.

In conjunction with RF circuitry 208, touch screen 212, display controller 256, contact/motion module 230, graphics module 232, and text input module 234, browser module 247 includes executable instructions for browsing the internet according to user instructions, including searching, linking to, receiving, and displaying web pages or portions thereof, as well as attachments and other files linked to web pages.

In conjunction with RF circuitry 208, touch screen 212, display controller 256, contact/motion module 230, graphics module 232, text input module 234, email client module 240, and browser module 247, calendar module 248 includes executable instructions to create, display, modify, and store calendars and data associated with calendars (e.g., calendar entries, to-do items, etc.) according to user instructions.

In conjunction with the RF circuitry 208, touch screen 212, display controller 256, contact/motion module 230, graphics module 232, text input module 234, and browser module 247, the desktop applet module 249 is a mini-application (e.g., weather desktop applet 249-1, stock market desktop applet 249-2, calculator desktop applet 249-3, alarm clock desktop applet 249-4, and dictionary desktop applet 249-5) or a mini-application created by a user (e.g., user created desktop applet 249-6) that can be downloaded and used by a user. In some embodiments, the desktop applet includes an HTML (hypertext markup language) file, a CSS (cascading style sheet) file, and a JavaScript file. In some embodiments, the desktop applet includes an XML (extensible markup language) file and a JavaScript file (e.g., yahoo.

In conjunction with RF circuitry 208, touch screen 212, display controller 256, contact/motion module 230, graphics module 232, text input module 234, and browser module 247, a desktop applet creator module 250 is used by a user to create a desktop applet (e.g., to cause a user-specified portion of a web page to become a desktop applet).

In conjunction with touch screen 212, display controller 256, contact/motion module 230, graphics module 232, and text input module 234, search module 251 includes executable instructions for searching memory 202 for text, music, sound, images, video, and/or other files matching one or more search criteria (e.g., one or more user-specified search terms) according to user instructions.

In conjunction with the touch screen 212, display controller 256, contact/motion module 230, graphics module 232, audio circuit 210, speaker 211, RF circuit 208, and browser module 247, the video and music player module 252 includes executable instructions that allow a user to download and playback recorded music and other sound files stored in one or more file formats (such as MP3 or AAC files), as well as executable instructions for displaying, rendering, or otherwise playing back video (e.g., on the touch screen 212 or on an external display connected via the external port 224). In some embodiments, the device 200 optionally includes the functionality of an MP3 player such as an iPod (trademark of Apple inc.).

In conjunction with touch screen 212, display controller 256, contact/motion module 230, graphics module 232, and text input module 234, notepad module 253 includes executable instructions for creating and managing notepads, backlog, etc. in accordance with user instructions.

In conjunction with the RF circuitry 208, touch screen 212, display controller 256, contact/motion module 230, graphics module 232, text input module 234, GPS module 235, and browser module 247, map module 254 is configured to receive, display, modify, and store maps and data associated with maps (e.g., driving directions, data related to shops and other points of interest at or near a particular location, and other location-based data) according to user instructions.

In conjunction with touch screen 212, display controller 256, contact/motion module 230, graphics module 232, audio circuit 210, speaker 211, RF circuit 208, text input module 234, email client module 240, and browser module 247, online video module 255 includes instructions that allow a user to access, browse, receive (e.g., by streaming and/or downloading), play back (e.g., on a touch screen or on a connected external display via external port 224), send emails with links to particular online videos, and otherwise manage online videos in one or more file formats (such as h.264). In some embodiments, the instant messaging module 241 is used instead of the email client module 240 to send links to particular online videos. Additional description of online video applications can be found in U.S. provisional patent application Ser. No.60/936,562, entitled "Portable Multifunction Device, method, AND GRAPHICAL User Interface for Playing Online Videos," filed on even 20, 6, 2007, and U.S. patent application Ser. No.11/968,067, entitled "Portable Multifunction Device, method, AND GRAPHICAL User Interface for Playing Online Videos," filed on even 31, 12, 2007, the contents of both of which are hereby incorporated by reference in their entirety.

Each of the modules and applications described above corresponds to a set of executable instructions for performing one or more of the functions described above, as well as the methods described in this patent application (e.g., the computer-implemented methods and other information processing methods described herein). These modules (e.g., sets of instructions) need not be implemented as separate software programs, procedures or modules, and thus various subsets of these modules may be combined or otherwise rearranged in various embodiments. For example, the video player module may be combined with the music player module into a single module (e.g., video and music player module 252 in fig. 2A). In some embodiments, memory 202 stores a subset of the modules and data structures described above. Further, the memory 202 stores additional modules and data structures not described above.

In some embodiments, device 200 is a device on which the operation of a predefined set of functions is performed exclusively by a touch screen and/or touch pad. By using a touch screen and/or a touch pad as the primary input control device for operation of the device 200, the number of physical input control devices (such as push buttons, dials, etc.) on the device 200 is reduced.

A predefined set of functions performed solely by the touch screen and/or the touch pad optionally includes navigation between user interfaces. In some embodiments, the touch pad, when touched by a user, navigates the device 200 from any user interface displayed on the device 200 to a main menu, home menu, or root menu. In such implementations, a touch pad is used to implement a "menu button". In some other embodiments, the menu buttons are physical push buttons or other physical input control devices, rather than touch pads.

Fig. 2B is a block diagram illustrating exemplary components for event processing according to some embodiments. In some embodiments, memory 202 (fig. 2A) or memory 470 (fig. 4) includes event sorter 270 (e.g., in operating system 226) and corresponding applications 236-1 (e.g., any of the aforementioned applications 237-251, 255, 480-490).

Event classifier 270 receives event information and determines an application view 291 of application 236-1 and application 236-1 to which to deliver the event information. Event sorter 270 includes event monitor 271 and event dispatcher module 274. In some embodiments, the application 236-1 includes an application internal state 292 that indicates one or more current application views that are displayed on the touch-sensitive display 212 when the application is active or executing. In some embodiments, the device/global internal state 257 is used by the event classifier 270 to determine which application(s) are currently active, and the application internal state 292 is used by the event classifier 270 to determine the application view 291 to which to deliver event information.

In some implementations, the application internal state 292 includes additional information, such as one or more of the following: restoration information to be used when the application 236-1 resumes execution, user interface state information indicating that the information is being displayed or ready for display by the application 236-1, a state queue for enabling the user to return to a previous state or view of the application 236-1, and a repeat/undo queue of previous actions taken by the user.

Event monitor 271 receives event information from peripheral interface 218. The event information includes information about sub-events (e.g., user touches on the touch sensitive display 212 as part of a multi-touch gesture). Peripheral interface 218 transmits information it receives from I/O subsystem 206 or sensors, such as proximity sensor 266, one or more accelerometers 268, and/or microphone 213 (via audio circuitry 210). The information received by the peripheral interface 218 from the I/O subsystem 206 includes information from the touch-sensitive display 212 or touch-sensitive surface.

In some embodiments, event monitor 271 sends requests to peripheral interface 218 at predetermined intervals. In response, peripheral interface 218 transmits the event information. In other embodiments, the peripheral interface 218 transmits event information only if there is a significant event (e.g., an input above a predetermined noise threshold is received and/or an input exceeding a predetermined duration is received).

In some implementations, the event classifier 270 also includes a hit view determination module 272 and/or an active event identifier determination module 273.

When the touch sensitive display 212 displays more than one view, the hit view determination module 272 provides a software process for determining where within one or more views a sub-event has occurred. The view is made up of controls and other elements that the user can see on the display.

Another aspect of the user interface associated with an application is a set of views, sometimes referred to herein as application views or user interface windows, in which information is displayed and touch-based gestures occur. The application view (of the respective application) in which the touch is detected corresponds to a level of programming within the application's programming hierarchy or view hierarchy. For example, the lowest horizontal view in which a touch is detected is referred to as the hit view, and the set of events that are considered to be correct inputs is determined based at least in part on the hit view of the initial touch that begins a touch-based gesture.

Hit view determination module 272 receives information related to sub-events of touch-based gestures. When an application has multiple views organized in a hierarchy, hit view determination module 272 identifies the hit view as the lowest view in the hierarchy that should process sub-events. In most cases, the hit view is the lowest level view in which the initiating sub-event (e.g., the first sub-event in a sequence of sub-events that form an event or potential event) occurs. Once the hit view is identified by the hit view determination module 272, the hit view typically receives all sub-events related to the same touch or input source for which it was identified as a hit view.

The activity event recognizer determination module 273 determines which view or views within the view hierarchy should receive a particular sequence of sub-events. In some implementations, the active event identifier determination module 273 determines that only the hit view should receive a particular sequence of sub-events. In other embodiments, the activity event recognizer determination module 273 determines that all views that include the physical location of the sub-event are actively engaged views and, thus, that all actively engaged views should receive a particular sequence of sub-events. In other embodiments, even if the touch sub-event is completely localized to an area associated with one particular view, the higher view in the hierarchy will remain the actively engaged view.

Event dispatcher module 274 dispatches event information to an event recognizer (e.g., event recognizer 280). In embodiments that include an active event recognizer determination module 273, the event dispatcher module 274 delivers event information to the event recognizer determined by the active event recognizer determination module 273. In some embodiments, the event dispatcher module 274 stores event information in event queues that is retrieved by the corresponding event receiver 282.

In some embodiments, operating system 226 includes event classifier 270. Alternatively, application 236-1 includes event classifier 270. In yet another embodiment, the event classifier 270 is a stand-alone module or part of another module stored in the memory 202 (such as the contact/motion module 230).

In some embodiments, the application 236-1 includes a plurality of event handlers 290 and one or more application views 291, each of which includes instructions for processing touch events that occur within a corresponding view of the user interface of the application. Each application view 291 of the application 236-1 includes one or more event recognizers 280. Typically, the respective application view 291 includes a plurality of event recognizers 280. In other embodiments, one or more of the event recognizers 280 are part of a separate module, which is a higher level object such as a user interface toolkit (not shown) or application 236-1 from which to inherit methods and other properties. In some implementations, the respective event handlers 290 include one or more of the following: the data updater 276, the object updater 277, the GUI updater 278, and/or the event data 279 received from the event classifier 270. Event handler 290 utilizes or invokes data updater 276, object updater 277 or GUI updater 278 to update the application internal state 292. Alternatively, one or more of the application views 291 include one or more corresponding event handlers 290. Additionally, in some implementations, one or more of the data updater 276, the object updater 277, and the GUI updater 278 are included in the respective application view 291.

The corresponding event identifier 280 receives event information (e.g., event data 279) from the event classifier 270 and identifies events from the event information. Event recognizer 280 includes event receiver 282 and event comparator 284. In some embodiments, event recognizer 280 further includes at least a subset of metadata 283 and event transfer instructions 288 (which include sub-event transfer instructions).

Event receiver 282 receives event information from event sorter 270. The event information includes information about sub-events such as touches or touch movements. The event information also includes additional information, such as the location of the sub-event, according to the sub-event. When a sub-event relates to the motion of a touch, the event information also includes the rate and direction of the sub-event. In some embodiments, the event includes rotation of the device from one orientation to another orientation (e.g., from a portrait orientation to a landscape orientation, or vice versa), and the event information includes corresponding information about a current orientation of the device (also referred to as a device pose).

Event comparator 284 compares the event information to predefined event or sub-event definitions and, based on the comparison, determines an event or sub-event, or determines or updates the state of the event or sub-event. In some embodiments, event comparator 284 includes event definition 286. Event definition 286 includes definitions of events (e.g., a predefined sequence of sub-events), such as event 1 (287-1), event 2 (287-2), and other events. In some embodiments, sub-events in event (287) include, for example, touch start, touch end, touch move, touch cancel, and multi-touch. In one example, the definition of event 1 (287-1) is a double click on the displayed object. For example, a double click includes a first touch on the displayed object for a predetermined length of time (touch start), a first lift-off on the displayed object for a predetermined length of time (touch end), a second touch on the displayed object for a predetermined length of time (touch start), and a second lift-off on the displayed object for a predetermined length of time (touch end). In another example, the definition of event 2 (287-2) is a drag on the displayed object. For example, dragging includes touching (or contacting) on the displayed object for a predetermined period of time, movement of the touch on the touch-sensitive display 212, and lifting of the touch (touch end). In some embodiments, the event also includes information for one or more associated event handlers 290.

In some embodiments, event definition 287 includes a definition of an event for a corresponding user interface object. In some implementations, event comparator 284 performs hit testing to determine which user interface object is associated with the sub-event. For example, in an application view that displays three user interface objects on touch-sensitive display 212, when a touch is detected on touch-sensitive display 212, event comparator 284 performs a hit test to determine which of the three user interface objects is associated with the touch (sub-event). If each displayed object is associated with a respective event handler 290, the event comparator uses the results of the hit test to determine which event handler 290 should be activated. For example, event comparator 284 selects the event handler associated with the sub-event and the object that triggered the hit test.

In some embodiments, the definition of the respective event (287) further includes a delay action that delays delivery of the event information until it has been determined that the sequence of sub-events does or does not correspond to an event type of the event recognizer.

When the respective event recognizer 280 determines that the sequence of sub-events does not match any of the events in the event definition 286, the respective event recognizer 280 enters an event impossible, event failed, or event end state after which subsequent sub-events of the touch-based gesture are ignored. In this case, the other event recognizers (if any) that remain active for the hit view continue to track and process sub-events of the ongoing touch-based gesture.

In some embodiments, the respective event recognizer 280 includes metadata 283 having configurable properties, flags, and/or lists that indicate how the event delivery system should perform sub-event delivery to the actively engaged event recognizer. In some embodiments, metadata 283 includes configurable attributes, flags, and/or lists that indicate how event recognizers interact or are able to interact with each other. In some embodiments, metadata 283 includes configurable attributes, flags, and/or lists that indicate whether sub-events are delivered to different levels in the view or programmatic hierarchy.

In some embodiments, when one or more particular sub-events of an event are identified, the corresponding event recognizer 280 activates an event handler 290 associated with the event. In some implementations, the respective event identifier 280 delivers event information associated with the event to the event handler 290. The activation event handler 290 is different from sending (and deferring) sub-events to the corresponding hit view. In some embodiments, event recognizer 280 throws a marker associated with the recognized event, and event handler 290 associated with the marker obtains the marker and performs a predefined process.

In some implementations, the event delivery instructions 288 include sub-event delivery instructions that deliver event information about the sub-event without activating the event handler. Instead, the sub-event delivery instructions deliver the event information to an event handler associated with the sub-event sequence or to an actively engaged view. Event handlers associated with the sequence of sub-events or with the actively engaged views receive the event information and perform a predetermined process.

In some embodiments, the data updater 276 creates and updates data used in the application 236-1. For example, the data updater 276 updates a telephone number used in the contact module 237, or stores a video file used in the video player module. In some embodiments, object updater 277 creates and updates objects used in application 236-1. For example, the object updater 277 creates a new user interface object or updates the location of the user interface object. GUI updater 278 updates the GUI. For example, the GUI updater 278 prepares display information and sends the display information to the graphics module 232 for display on a touch-sensitive display.

In some embodiments, event handler 290 includes or has access to data updater 276, object updater 277, and GUI updater 278. In some embodiments, the data updater 276, the object updater 277, and the GUI updater 278 are included in a single module of the respective application 236-1 or application view 291. In other embodiments, they are included in two or more software modules.

It should be appreciated that the above discussion regarding event handling of user touches on a touch sensitive display also applies to other forms of user inputs that utilize an input device to operate the multifunction device 200, not all of which are initiated on a touch screen. For example, mouse movements and mouse button presses optionally in conjunction with single or multiple keyboard presses or holds; contact movement on the touch pad, such as flicking, dragging, scrolling, etc.; stylus input; movement of the device; verbal instructions; detected eye movement; inputting biological characteristics; and/or any combination thereof is optionally used as input corresponding to sub-events defining the event to be identified.

Fig. 3 illustrates a portable multifunction device 200 with a touch screen 212 in accordance with some embodiments. The touch screen optionally displays one or more graphics within a User Interface (UI) 300. In this and other embodiments described below, a user can select one or more of these graphics by making a gesture on the graphics, for example, with one or more fingers 302 (not drawn to scale in the figures) or one or more styluses 303 (not drawn to scale in the figures). In some embodiments, selection of one or more graphics will occur when a user breaks contact with the one or more graphics. In some embodiments, the gesture optionally includes one or more taps, one or more swipes (left to right, right to left, up and/or down), and/or scrolling of a finger that has been in contact with the device 200 (right to left, left to right, up and/or down). In some implementations or in some cases, inadvertent contact with the graphic does not select the graphic. For example, when the gesture corresponding to the selection is a tap, a swipe gesture that swipes over an application icon optionally does not select the corresponding application.

The device 200 also includes one or more physical buttons, such as a "home" or menu button 304. As previously described, menu button 304 is used to navigate to any application 236 in a set of applications executing on device 200. Alternatively, in some embodiments, the menu buttons are implemented as soft keys in a GUI displayed on touch screen 212.

In some embodiments, device 200 includes a touch screen 212, menu buttons 304, a press button 306 for powering the device on/off and for locking the device, one or more volume adjustment buttons 308, a Subscriber Identity Module (SIM) card slot 310, a headset jack 312, and a docking/charging external port 224. Pressing button 306 is optionally used to turn on/off the device by pressing the button and holding the button in the pressed state for a predefined time interval; locking the device by depressing the button and releasing the button before the predefined time interval has elapsed; and/or unlock the device or initiate an unlocking process. In an alternative embodiment, device 200 also accepts voice input through microphone 213 for activating or deactivating certain functions. The device 200 also optionally includes one or more contact intensity sensors 265 for detecting the intensity of contacts on the touch screen 212 and/or one or more haptic output generators 267 for generating haptic outputs for a user of the device 200.

FIG. 4 is a block diagram of an exemplary multifunction device with a display and a touch-sensitive surface in accordance with some embodiments. The device 400 need not be portable. In some embodiments, the device 400 is a laptop computer, a desktop computer, a tablet computer, a multimedia player device, a navigation device, an educational device (such as a child learning toy), a gaming system, or a control device (e.g., a home controller or an industrial controller). Device 400 typically includes one or more processing units (CPUs) 410, one or more network or other communication interfaces 460, memory 470, and one or more communication buses 420 for interconnecting these components. Communication bus 420 optionally includes circuitry (sometimes referred to as a chipset) that interconnects and controls communications between system components. The device 400 includes an input/output (I/O) interface 430 with a display 440, typically a touch screen display. The I/O interface 430 also optionally includes a keyboard and/or mouse (or other pointing device) 450 and a touch pad 455, a tactile output generator 457 (e.g., similar to the tactile output generator 267 described above with reference to fig. 2A), a sensor 459 (e.g., an optical sensor, an acceleration sensor, a proximity sensor, a touch sensitive sensor, and/or a contact intensity sensor (similar to the contact intensity sensor 265 described above with reference to fig. 2A)) for generating a tactile output on the device 400. Memory 470 includes high-speed random access memory such as DRAM, SRAM, DDR RAM or other random access solid state memory devices; and optionally includes non-volatile memory such as one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, or other non-volatile solid state storage devices. Memory 470 optionally includes one or more storage devices located remotely from CPU 410. In some embodiments, memory 470 stores programs, modules, and data structures, or a subset thereof, similar to those stored in memory 202 of portable multifunction device 200 (fig. 2A). In addition, the memory 470 optionally stores additional programs, modules, and data structures not present in the memory 202 of the portable multifunction device 200. For example, the memory 470 of the device 400 optionally stores the drawing module 480, the presentation module 482, the word processing module 484, the website creation module 486, the disk editing module 488, and/or the spreadsheet module 490, while the memory 202 of the portable multifunction device 200 (fig. 2A) optionally does not store these modules.

Each of the above-described elements in fig. 4 are in some examples stored in one or more of the previously mentioned memory devices. Each of the above-described modules corresponds to a set of instructions for performing the above-described functions. The above-described modules or programs (e.g., sets of instructions) need not be implemented as separate software programs, procedures or modules, and thus various subsets of these modules are combined or otherwise rearranged in various embodiments. In some embodiments, memory 470 stores a subset of the modules and data structures described above. Further, the memory 470 stores additional modules and data structures not described above.

Attention is now directed to embodiments of user interfaces that may be implemented on, for example, portable multifunction device 200.

Fig. 5A illustrates an exemplary user interface of an application menu on the portable multifunction device 200 in accordance with some embodiments. A similar user interface is implemented on device 400. In some embodiments, user interface 500 includes the following elements, or a subset or superset thereof:

One or more wireless communications, such as one or more signal strength indicators 502 of cellular signals and Wi-Fi signals;

Time 504;

bluetooth indicator 505;

Battery status indicator 506;

Tray 508 with icons for commonly used applications, such as:

icon 516 of phone module 238 marked "phone", optionally including an indicator 514 of the number of missed calls or voice messages;

An icon 518 labeled "mail" for email client module 240, optionally including an indicator 510 of the number of unread emails;

icon 520 marked "browser" of browser module 247; and

Video and music player module 252 (also known as iPod (trademark of Apple inc.)

Module 252) icon 522 labeled "iPod"; and

Icons of other applications, such as:

Icon 524 of IM module 241 marked "message";

Icon 526 marked "calendar" of calendar module 248;

icon 528 of image management module 244 labeled "photo";

Icon 530 marked "camera" for camera module 243;

Icon 532 marked "online video" of online video module 255;

icon 534 marked "stock market" for stock market desktop applet 249-2;

icon 536 labeled "map" for map module 254;

icon 538 marked "weather" for weather desktop applet 249-1;

icon 540 marked "clock" for alarm desktop applet 249-4;

icon 542 labeled "fitness support" for fitness support module 242;

icon 544 labeled "notepad" for notepad module 253; and

The marked "set" icon 546 for setting applications or modules provides access to the settings of the device 200 and its various applications 236.

It should be noted that the iconic labels shown in fig. 5A are merely exemplary. For example, the icon 522 of the video and music player module 252 is optionally labeled "music" or "music player". Other labels are optionally used for various application icons. In some embodiments, the label of the respective application icon includes a name of the application corresponding to the respective application icon. In some embodiments, the label of a particular application icon is different from the name of the application corresponding to the particular application icon.

Fig. 5B illustrates an exemplary user interface on a device (e.g., device 400 of fig. 4) having a touch-sensitive surface 551 (e.g., tablet or touch pad 455 of fig. 4) separate from a display 550 (e.g., touch screen display 212). The device 400 also optionally includes one or more contact intensity sensors (e.g., one or more of the sensors 457) for detecting intensities of contacts on the touch-sensitive surface 551 and/or one or more tactile output generators 459 for generating tactile outputs for a user of the device 400.

While some of the examples that follow will be given with reference to inputs on touch screen display 212 (where the touch sensitive surface and the display are combined), in some embodiments the device detects inputs on a touch sensitive surface that is separate from the display, as shown in fig. 5B. In some implementations, the touch-sensitive surface (e.g., 551 in fig. 5B) has a primary axis (e.g., 552 in fig. 5B) that corresponds to the primary axis (e.g., 553 in fig. 5B) on the display (e.g., 550). According to these embodiments, the device detects contact (e.g., 560 and 562 in fig. 5B) with the touch-sensitive surface 551 at a location (e.g., 560 corresponds to 568 and 562 corresponds to 570 in fig. 5B) corresponding to the respective location on the display. In this way, user inputs (e.g., contacts 560 and 562 and their movements) detected by the device on the touch-sensitive surface (e.g., 551 in FIG. 5B) are used by the device to manipulate a user interface on the display (e.g., 550 in FIG. 5B) of the multifunction device when the touch-sensitive surface is separated from the device. It should be appreciated that similar approaches are optionally used for other user interfaces described herein.

Additionally, while the following examples are primarily given with reference to finger inputs (e.g., finger contacts, single-finger flick gestures, finger swipe gestures), it should be understood that in some embodiments one or more of these finger inputs are replaced by input from another input device (e.g., mouse-based input or stylus input). For example, a swipe gesture is optionally replaced with a mouse click (e.g., rather than a contact), followed by movement of the cursor along the path of the swipe (e.g., rather than movement of the contact). As another example, a flick gesture is optionally replaced by a mouse click (e.g., instead of detection of contact, followed by ceasing to detect contact) when the cursor is over the position of the flick gesture. Similarly, when multiple user inputs are detected simultaneously, it should be appreciated that multiple computer mice are optionally used simultaneously, or that the mice and finger contacts are optionally used simultaneously.

Fig. 6A illustrates an exemplary personal electronic device 600. The device 600 includes a body 602. In some embodiments, device 600 includes some or all of the features described with respect to devices 200 and 400 (e.g., fig. 2A-4). In some implementations, the device 600 has a touch sensitive display 604, hereinafter referred to as a touch screen 604. In addition to or in lieu of the touch screen 604, the device 600 has a display and a touch-sensitive surface. As with devices 200 and 400, in some implementations, touch screen 604 (or touch-sensitive surface) has one or more intensity sensors for detecting the intensity of a contact (e.g., touch) being applied. One or more intensity sensors of the touch screen 604 (or touch sensitive surface) provide output data representative of the intensity of the touch. The user interface of device 600 responds to touches based on touch strength, meaning that touches of different strengths may invoke different user interface operations on device 600.

Techniques for detecting and processing touch intensity may exist, for example, in related applications: international patent application PCT/US2013/040061 filed on day 5, 8, 2013, and international patent application PCT/US2013/069483 filed on day 11, 2013, and "Device,Method,and Graphical User Interface for Transitioning Between Touch Input to Display Output Relationships", each of which is incorporated herein by reference in its entirety.

In some embodiments, the device 600 has one or more input mechanisms 606 and 608. Input mechanisms 606 and 608 (if included) are in physical form. Examples of physical input mechanisms include push buttons and rotatable mechanisms. In some embodiments, the device 600 has one or more attachment mechanisms. Such attachment mechanisms, if included, may allow for attachment of the device 600 to, for example, a hat, glasses, earrings, necklace, shirt, jacket, bracelet, watchband, bracelet, pants, leash, shoe, purse, backpack, or the like. These attachment mechanisms allow the user to wear the device 600.

Fig. 6B illustrates an exemplary personal electronic device 600. In some embodiments, the apparatus 600 includes some or all of the components described with respect to fig. 2A, 2B, and 4. The device 600 has a bus 612 that operatively couples an I/O section 614 to one or more computer processors 616 and memory 618. The I/O section 614 is connected to a display 604, which may have a touch sensitive member 622 and optionally also a touch intensity sensitive member 624. In addition, the I/O portion 614 is connected to a communication unit 630 for receiving application and operating system data using Wi-Fi, bluetooth, near Field Communication (NFC), cellular, and/or other wireless communication technologies. The device 600 includes input mechanisms 606 and/or 608. For example, input mechanism 606 is a rotatable input device or a depressible input device and a rotatable input device. In some examples, input mechanism 608 is a button.

In some examples, input mechanism 608 is a microphone. The personal electronic device 600 includes, for example, various sensors, such as a GPS sensor 632, an accelerometer 634, an orientation sensor 640 (e.g., a compass), a gyroscope 636, a motion sensor 638, and/or combinations thereof, all of which are operatively connected to the I/O section 614.

The memory 618 of the personal electronic device 600 is a non-transitory computer-readable storage medium for storing computer-executable instructions that, when executed by the one or more computer processors 616, for example, cause the computer processors to perform the techniques and processes described above. The computer-executable instructions are also stored and/or transmitted, for example, within any non-transitory computer-readable storage medium, for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. The personal electronic device 600 is not limited to the components and configuration of fig. 6B, but may include other components or additional components in a variety of configurations.

As used herein, the term "affordance" refers to user-interactive graphical user interface objects displayed on the display screens of devices 200, 400, 600, 800, and/or 900 (fig. 2A, 4, 6A-6B, 8, 9A-9F, and 12). For example, images (e.g., icons), buttons, and text (e.g., hyperlinks) each constitute an affordance.

As used herein, the term "focus selector" refers to an input element for indicating the current portion of a user interface with which a user is interacting. In some implementations that include a cursor or other position marker, the cursor acts as a "focus selector" such that when the cursor detects an input (e.g., presses an input) on a touch-sensitive surface (e.g., touch pad 455 in fig. 4 or touch-sensitive surface 551 in fig. 5B) above a particular user interface element (e.g., a button, window, slider, or other user interface element), the particular user interface element is adjusted according to the detected input. In some implementations including a touch screen display (e.g., touch sensitive display system 212 in fig. 2A or touch screen 212 in fig. 5A) that enables direct interaction with user interface elements on the touch screen display, the contact detected on the touch screen acts as a "focus selector" such that when an input (e.g., a press input by a contact) is detected on the touch screen display at the location of a particular user interface element (e.g., a button, window, slider, or other user interface element), the particular user interface element is adjusted in accordance with the detected input. In some implementations, the focus is moved from one area of the user interface to another area of the user interface without a corresponding movement of the cursor or movement of contact on the touch screen display (e.g., by moving the focus from one button to another using a tab key or arrow key); in these implementations, the focus selector moves in accordance with movement of the focus between different areas of the user interface. Regardless of the particular form that the focus selector takes, the focus selector is typically controlled by the user in order to deliver a user interface element (or contact on the touch screen display) that is interactive with the user of the user interface (e.g., by indicating to the device the element with which the user of the user interface desires to interact). For example, upon detection of a press input on a touch-sensitive surface (e.g., a touchpad or touch screen), the position of a focus selector (e.g., a cursor, contact, or selection box) over a respective button will indicate that the user desires to activate the respective button (rather than other user interface elements shown on the device display).

As used in the specification and claims, the term "characteristic intensity" of a contact refers to the characteristic of a contact based on one or more intensities of the contact. In some embodiments, the characteristic intensity is based on a plurality of intensity samples. The characteristic intensity is optionally based on a predefined number of intensity samples or a set of intensity samples acquired during a predetermined period of time (e.g., 0.05 seconds, 0.1 seconds, 0.2 seconds, 0.5 seconds, 1 second, 2 seconds, 5 seconds, 10 seconds) relative to a predefined event (e.g., after detection of contact, before or after detection of lift-off of contact, before or after detection of start of movement of contact, before or after detection of end of contact, and/or before or after detection of decrease in intensity of contact). The characteristic intensity of the contact is optionally based on one or more of: maximum value of contact strength, average value of contact strength, value at the first 10% of contact strength, half maximum value of contact strength, 90% maximum value of contact strength, etc. In some embodiments, the duration of the contact is used in determining the characteristic intensity (e.g., when the characteristic intensity is an average of the intensity of the contact over time). In some embodiments, the characteristic intensity is compared to a set of one or more intensity thresholds to determine whether the user has performed an operation. For example, the set of one or more intensity thresholds includes a first intensity threshold and a second intensity threshold. In this example, contact of the feature strength that does not exceed the first threshold results in a first operation, contact of the feature strength that exceeds the first strength threshold but does not exceed the second strength threshold results in a second operation, and contact of the feature strength that exceeds the second threshold results in a third operation. In some implementations, a comparison between the feature strength and one or more thresholds is used to determine whether to perform one or more operations (e.g., whether to perform the respective operation or to forgo performing the respective operation) instead of being used to determine whether to perform the first operation or the second operation.

In some implementations, a portion of the gesture is identified for determining a feature strength. For example, the touch-sensitive surface receives a continuous swipe contact that transitions from a starting position and to an ending position where the intensity of the contact increases. In this example, the characteristic intensity of the contact at the end position is based only on a portion of the continuous swipe contact, rather than the entire swipe contact (e.g., the portion of the swipe contact located only at the end position). In some embodiments, a smoothing algorithm is applied to the intensity of the swipe contact before determining the characteristic intensity of the contact. For example, the smoothing algorithm optionally includes one or more of the following: an unweighted moving average smoothing algorithm, a triangular smoothing algorithm, a median filter smoothing algorithm, and/or an exponential smoothing algorithm. In some cases, these smoothing algorithms eliminate narrow spikes or depressions in the intensity of the swipe contact for the purpose of determining the characteristic intensity.

The intensity of the contact on the touch-sensitive surface is characterized relative to one or more intensity thresholds, such as a contact detection intensity threshold, a light press intensity threshold, a deep press intensity threshold, and/or one or more other intensity thresholds. In some embodiments, the tap strength threshold corresponds to a strength of: at this intensity the device will perform the operations normally associated with clicking a button of a physical mouse or touch pad. In some embodiments, the deep compression intensity threshold corresponds to an intensity of: at this intensity the device will perform an operation that is different from the operation normally associated with clicking a physical mouse or a button of a touch pad. In some implementations, when a contact is detected with a characteristic intensity below a light press intensity threshold (e.g., and above a nominal contact detection intensity threshold, a contact below the nominal contact detection intensity threshold is no longer detected), the device will move the focus selector according to movement of the contact over the touch-sensitive surface without performing an operation associated with the light press intensity threshold or the deep press intensity threshold. Generally, unless otherwise stated, these intensity thresholds are consistent across different sets of user interface drawings.

The increase in contact characteristic intensity from an intensity below the light press intensity threshold to an intensity between the light press intensity threshold and the deep press intensity threshold is sometimes referred to as a "light press" input. The increase in contact characteristic intensity from an intensity below the deep-press intensity threshold to an intensity above the deep-press intensity threshold is sometimes referred to as a "deep-press" input. The increase in the contact characteristic intensity from an intensity below the contact detection intensity threshold to an intensity between the contact detection intensity threshold and the light press intensity threshold is sometimes referred to as detecting a contact on the touch surface. The decrease in the contact characteristic intensity from an intensity above the contact detection intensity threshold to an intensity below the contact detection intensity threshold is sometimes referred to as detecting a lift-off of contact from the touch surface. In some embodiments, the contact detection intensity threshold is zero. In some embodiments, the contact detection intensity threshold is greater than zero.

In some implementations described herein, one or more operations are performed in response to detecting a gesture that includes a respective press input or in response to detecting a respective press input performed with a respective contact (or contacts), wherein a respective press input is detected based at least in part on detecting an increase in intensity of the contact (or contacts) above a press input intensity threshold. In some implementations, the respective operation is performed in response to detecting that the intensity of the respective contact increases above a press input intensity threshold (e.g., a "downstroke" of the respective press input). In some embodiments, the press input includes an increase in intensity of the respective contact above a press input intensity threshold and a subsequent decrease in intensity of the contact below the press input intensity threshold, and the respective operation is performed in response to detecting the subsequent decrease in intensity of the respective contact below the press input threshold (e.g., an "upstroke" of the respective press input).

In some implementations, the device employs intensity hysteresis to avoid accidental inputs, sometimes referred to as "jitter," in which the device defines or selects a hysteresis intensity threshold that has a predefined relationship to the compression input intensity threshold (e.g., the hysteresis intensity threshold is X intensity units lower than the compression input intensity threshold, or the hysteresis intensity threshold is 75%, 90%, or some reasonable proportion of the compression input intensity threshold). Thus, in some embodiments, the press input includes an increase in the intensity of the respective contact above a press input intensity threshold and a subsequent decrease in the intensity of the contact below a hysteresis intensity threshold corresponding to the press input intensity threshold, and the respective operation is performed in response to detecting that the intensity of the respective contact subsequently decreases below the hysteresis intensity threshold (e.g., an "upstroke" of the respective press input). Similarly, in some embodiments, a press input is detected only when the device detects an increase in contact intensity from an intensity at or below the hysteresis intensity threshold to an intensity at or above the press input intensity threshold and optionally a subsequent decrease in contact intensity to an intensity at or below the hysteresis intensity, and a corresponding operation is performed in response to detecting a press input (e.g., an increase in contact intensity or a decrease in contact intensity depending on the circumstances).

For ease of explanation, optionally, a description of operations performed in response to a press input associated with a press input intensity threshold or in response to a gesture comprising a press input is triggered in response to detecting any of the following: the contact strength increases above the compression input strength threshold, the contact strength increases from an intensity below the hysteresis strength threshold to an intensity above the compression input strength threshold, the contact strength decreases below the compression input strength threshold, and/or the contact strength decreases below the hysteresis strength threshold corresponding to the compression input strength threshold. In addition, in examples where the operation is described as being performed in response to the intensity of the detected contact decreasing below a press input intensity threshold, the operation is optionally performed in response to the intensity of the detected contact decreasing below a hysteresis intensity threshold that corresponds to and is less than the press input intensity threshold.

3. Digital assistant system

Fig. 7A illustrates a block diagram of a digital assistant system 700, according to various examples. In some examples, the digital assistant system 700 is implemented on a standalone computer system. In some examples, digital assistant system 700 is distributed across multiple computers. In some examples, some of the modules and functions of the digital assistant are divided into a server portion and a client portion, where the client portion is located on one or more user devices (e.g., devices 104, 122, 200, 400, 600, 800, or 900) and communicates with the server portion (e.g., server system 108) over one or more networks, for example, as shown in fig. 1. In some examples, digital assistant system 700 is a specific implementation of server system 108 (and/or DA server 106) shown in fig. 1. It should be noted that digital assistant system 700 is only one example of a digital assistant system, and that digital assistant system 700 has more or fewer components than shown, combines two or more components, or may have a different configuration or layout of components. The various components shown in fig. 7A are implemented in hardware, in software instructions for execution by one or more processors, in firmware (including one or more signal processing integrated circuits and/or application specific integrated circuits), or in combinations thereof.

The digital assistant system 700 includes a memory 702, an input/output (I/O) interface 706, a network communication interface 708, and one or more processors 704. These components may communicate with each other via one or more communication buses or signal lines 710.

In some examples, memory 702 includes non-transitory computer-readable media such as high-speed random access memory and/or non-volatile computer-readable storage media (e.g., one or more disk storage devices, flash memory devices, or other non-volatile solid state memory devices).

In some examples, the I/O interface 706 couples input/output devices 716 of the digital assistant system 700, such as a display, a keyboard, a touch screen, and a microphone, to the user interface module 722. The I/O interface 706, along with the user interface module 722, receives user input (e.g., voice input, keyboard input, touch input, etc.) and processes the input accordingly. In some examples, for example, when the digital assistant is implemented on a standalone user device, the digital assistant system 700 includes any of the components and I/O communication interfaces described with respect to the devices 200, 400, 600,800, or 900 in fig. 2A, 4, 6A-6B, 8, 9A-9F, and 12. In some examples, digital assistant system 700 represents a server portion of a digital assistant implementation and may interact with a user through a client-side portion located on a user device (e.g., device 104, 200, 400, 600,800, or 900).

In some examples, the network communication interface 708 includes one or more wired communication ports 712 and/or wireless transmit and receive circuitry 714. One or more wired communication ports receive and transmit communication signals via one or more wired interfaces, such as ethernet, universal Serial Bus (USB), FIREWIRE, etc. The wireless circuitry 714 receives and transmits RF signals and/or optical signals from and to a communication network and other communication devices. The wireless communication uses any of a variety of communication standards, protocols, and technologies, such as GSM, EDGE, CDMA, TDMA, bluetooth, wi-Fi, voIP, wi-MAX, or any other suitable communication protocol. Network communication interface 708 enables communication between digital assistant system 700 and other devices via a network, such as the internet, an intranet, and/or a wireless network, such as a cellular telephone network, a wireless Local Area Network (LAN), and/or a Metropolitan Area Network (MAN).

In some examples, memory 702 or a computer-readable storage medium of memory 702 stores programs, modules, instructions, and data structures, including all or a subset of the following: an operating system 718, a communication module 720, a user interface module 722, one or more application programs 724, and a digital assistant module 726. In particular, the memory 702 or a computer readable storage medium of the memory 702 stores instructions for performing the processes described above. One or more processors 704 execute these programs, modules, and instructions and read data from and write data to the data structures.

Operating system 718 (e.g., darwin, RTXC, LINUX, UNIX, iOS, OS X, WINDOWS, or an embedded operating system such as VxWorks) includes various software components and/or drivers for controlling and managing general system tasks (e.g., memory management, storage device control, power management, etc.), and facilitates communication between the various hardware, firmware, and software components.

The communication module 720 facilitates communication between the digital assistant system 700 and other devices via the network communication interface 708. For example, the communication module 720 communicates with the RF circuitry 208 of an electronic device (such as the device 200, 400, or 600 shown in fig. 2A, 4, 6A-6B, respectively). The communication module 720 also includes various components for processing data received by the wireless circuit 714 and/or the wired communication port 712.

The user interface module 722 receives commands and/or input from a user (e.g., from a keyboard, touch screen, pointing device, controller, and/or microphone) via the I/O interface 706 and generates user interface objects on a display. The user interface module 722 also prepares and communicates output (e.g., voice, sound, animation, text, icons, vibration, haptic feedback, illumination, etc.) to the user via the I/O interface 706 (e.g., through a display, audio channel, speaker, touch pad, etc.).

Application programs 724 include programs and/or modules configured to be executed by the one or more processors 704. For example, if the digital assistant system is implemented on a standalone user device, the applications 724 include user applications such as games, calendar applications, navigation applications, or mail applications. If the digital assistant system 700 is implemented on a server, the applications 724 include, for example, a resource management application, a diagnostic application, or a scheduling application.

The memory 702 also stores a digital assistant module 726 (or server portion of the digital assistant). In some examples, digital assistant module 726 includes the following sub-modules, or a subset or superset thereof: an input/output processing module 728, a Speech To Text (STT) processing module 730, a natural language processing module 732, a dialog flow processing module 734, a task flow processing module 736, a services processing module 738, and a speech synthesis processing module 740. Each of these modules has access to one or more of the following systems or data and models of digital assistant module 726, or a subset or superset thereof: ontology 760, vocabulary index 744, user data 748, task flow model 754, service model 756, and ASR system 758.

In some examples, using the processing modules, data, and models implemented in digital assistant module 726, the digital assistant may perform at least some of the following: converting the speech input into text; identifying a user intent expressed in natural language input received from a user; actively elicit and obtain information needed to fully infer the user's intent (e.g., by disambiguating words, games, intent, etc.); determining a task flow for satisfying the inferred intent; and executing the task flow to satisfy the inferred intent.

In some examples, as shown in fig. 7B, I/O processing module 728 may interact with a user via I/O device 716 in fig. 7A or interact with a user device (e.g., device 104, device 200, device 400, or device 600) via network communication interface 708 in fig. 7A to obtain user input (e.g., voice input) and provide a response to the user input (e.g., as voice output). The I/O processing module 728 optionally obtains contextual information associated with the user input from the user device along with or shortly after receiving the user input. The contextual information includes user-specific data, vocabulary, and/or preferences related to user input. In some examples, the context information further includes software state and hardware state of the user device at the time the user request is received, and/or information related to the user's surroundings at the time the user request is received. In some examples, the I/O processing module 728 also sends follow-up questions related to the user request to the user and receives answers from the user. When a user request is received by the I/O processing module 728 and the user request includes a voice input, the I/O processing module 728 forwards the voice input to the STT processing module 730 (or speech recognizer) for voice-to-text conversion.

The STT processing module 730 includes one or more ASR systems 758. The one or more ASR systems 758 may process speech input received through the I/O processing module 728 to produce recognition results. Each ASR system 758 includes a front-end speech pre-processor. The front-end speech pre-processor extracts representative features from the speech input. For example, the front-end speech pre-processor performs a fourier transform on the speech input to extract spectral features characterizing the speech input as a sequence of representative multidimensional vectors. In addition, each ASR system 758 includes one or more speech recognition models (e.g., acoustic models and/or language models) and implements one or more speech recognition engines. Examples of speech recognition models include hidden Markov models, gaussian mixture models, deep neural network models, n-gram language models, and other statistical models. Examples of speech recognition engines include dynamic time warping based engines and Weighted Finite State Transducer (WFST) based engines. The extracted representative features of the front-end speech pre-processor are processed using one or more speech recognition models and one or more speech recognition engines to produce intermediate recognition results (e.g., phonemes, phoneme strings, and sub-words), and ultimately text recognition results (e.g., words, word strings, or symbol sequences). In some examples, the voice input is processed at least in part by a third party service or on a device of the user (e.g., device 104, device 200, device 400, or device 600) to produce the recognition result. Once STT processing module 730 generates a recognition result that includes a text string (e.g., a word, or a sequence of words, or a sequence of symbols), the recognition result is passed to natural language processing module 732 for intent inference. In some examples, the STT processing module 730 generates a plurality of candidate text representations of the speech input. Each candidate text representation is a sequence of words or symbols corresponding to a speech input. In some examples, each candidate text representation is associated with a speech recognition confidence score. Based on the speech recognition confidence scores, the STT processing module 730 ranks the candidate text representations and provides the n best (e.g., the n highest ranked) candidate text representations to the natural language processing module 732 for intent inference, where n is a predetermined integer greater than zero. For example, in one example, only the highest ranked (n=1) candidate text representations are delivered to the natural language processing module 732 for intent inference. As another example, the 5 highest ranked (n=5) candidate text representations are passed to the natural language processing module 732 for intent inference.

Further details regarding speech-to-text processing are described in U.S. patent application Ser. No. 13/236,942, entitled "Consolidating Speech Recognition Results," filed on even date 20 at 9 in 2011, the entire disclosure of which is incorporated herein by reference.

In some examples, the STT processing module 730 includes a vocabulary of recognizable words and/or accesses the vocabulary via the phonetic-to-letter conversion module 731. Each vocabulary word is associated with one or more candidate pronunciations for the word represented in the speech recognition phonetic alphabet. In particular, the vocabulary of recognizable words includes words associated with a plurality of candidate pronunciations. For example, the vocabulary includes andAndThe word "match" associated with the candidate pronunciation of (c). In addition, the vocabulary words are associated with custom candidate pronunciations based on previous speech input from the user. Such custom candidate pronunciations are stored in the STT processing module 730 and are associated with a particular user via a user profile on the device. In some examples, the candidate pronunciation of the word is determined based on the spelling of the word and one or more linguistic and/or phonetic rules. In some examples, the candidate pronunciation is generated manually, e.g., based on a known standard pronunciation.

In some examples, candidate pronunciations are ranked based on their popularity. For example, candidate pronunciationRanking of higher thanAs the former is a more common pronunciation (e.g., for users in a particular geographic region, or for any other suitable subset of users, among all users). In some examples, candidate pronunciations are ranked based on whether the candidate pronunciations are custom candidate pronunciations associated with the user. For example, custom candidate pronunciations are ranked higher than standard candidate pronunciations. This can be used to identify proper nouns having unique pronunciations that deviate from the canonical pronunciation. In some examples, the candidate pronunciation is associated with one or more speech features such as geographic origin, country, or race. For example, candidate pronunciationAssociated with the United states and candidate pronunciationsAssociated with the uk. Further, the ranking of candidate pronunciations is based on one or more characteristics (e.g., geographic origin, country, race, etc.) of the user in a user profile stored on the device. For example, the user may be determined from a user profile to be associated with the united states. Candidate pronunciations based on the user being associated with the united statesComparable candidate pronunciations (associated with the united states)The ranking (associated with the uk) is higher. In some examples, one of the ranked candidate pronunciations may be selected as a predicted pronunciation (e.g., the most likely pronunciation).

Upon receiving a speech input, the STT processing module 730 is used to determine a phoneme corresponding to the speech input (e.g., using a voice model) and then attempt to determine a word that matches the phoneme (e.g., using a voice model). For example, if the STT processing module 730 first identifies a sequence of phonemes corresponding to a portion of the speech inputIt may then determine that the sequence corresponds to the word "match" based on the vocabulary index 744.

In some examples, STT processing module 730 uses fuzzy matching techniques to determine words in the utterance. Thus, for example, the STT processing module 730 determines a phoneme sequenceCorresponds to the word "key", even though the particular phoneme sequence is not a candidate phoneme sequence for that word.

The natural language processing module 732 of the digital assistant ("natural language processor") obtains the n best candidate textual representations ("word sequences" or "symbol sequences") generated by the STT processing module 730 and attempts to associate each candidate textual representation with one or more "actionable intents" identified by the digital assistant. "actionable intent" (or "user intent") represents a task that may be executed by a digital assistant and that may have an associated task flow implemented in task flow model 754. An associated task flow is a series of programmed actions and steps taken by the digital assistant to perform a task. The scope of the capabilities of the digital assistant depends on the number and variety of task flows that have been implemented and stored in the task flow model 754, or in other words, the number and variety of "actionable intents" identified by the digital assistant. However, the effectiveness of a digital assistant also depends on the ability of the assistant to infer the correct "one or more actionable intents" from user requests expressed in natural language.

In some examples, the natural language processing module 732 receives contextual information associated with the user request, for example, from the I/O processing module 728, in addition to the sequence of words or symbols obtained from the STT processing module 730. The natural language processing module 732 optionally uses the contextual information to clarify, supplement, and/or further define the information contained in the candidate text representations received from the STT processing module 730. The context information includes, for example, user preferences, hardware and/or software status of the user device, sensor information collected before, during, or shortly after a user request, previous interactions (e.g., conversations) between the digital assistant and the user, and so forth. As described herein, in some examples, the contextual information is dynamic and varies with time, location, content, and other factors of the conversation.

In some examples, natural language processing is based on, for example, ontology 760. Ontology 760 is a hierarchical structure that contains a number of nodes, each representing an "actionable intent" or "attribute" that is related to one or more of the "actionable intents" or other "attributes. As described above, "executable intent" refers to a task that a digital assistant is capable of performing, i.e., that the task is "executable" or can be performed. An "attribute" represents a parameter associated with a sub-aspect of an actionable intent or another attribute. The connections between the actionable intent nodes and the attribute nodes in ontology 760 define how the parameters represented by the attribute nodes pertain to the tasks represented by the actionable intent nodes.

In some examples, ontology 760 is composed of actionable intent nodes and attribute nodes. Within ontology 760, each actionable intent node is connected directly to or through one or more intermediate attribute nodes to one or more attribute nodes. Similarly, each attribute node is connected directly to or through one or more intermediate attribute nodes to one or more actionable intent nodes. For example, as shown in fig. 7C, ontology 760 includes a "restaurant reservation" node (i.e., an actionable intent node). The attribute nodes "restaurant", "date/time" (for reservation) and "party size" are each directly connected to the executable intent node (i.e., the "restaurant reservation" node).

Further, the attribute nodes "cuisine", "price section", "telephone number", and "location" are child nodes of the attribute node "restaurant", and are each connected to the "restaurant reservation" node (i.e., executable intention node) through the intermediate attribute node "restaurant". As another example, as shown in fig. 7C, ontology 760 also includes a "set reminder" node (i.e., another actionable intent node). The attribute nodes "date/time" (for setting reminders) and "topic" (for reminders) are both connected to the "set reminders" node. Since the attribute "date/time" is related to both the task of making a restaurant reservation and the task of setting a reminder, the attribute node "date/time" is connected to both the "restaurant reservation" node and the "set reminder" node in the ontology 760.

The actionable intent node, along with its linked attribute nodes, is described as a "domain". In this discussion, each domain is associated with a respective actionable intent and refers to a set of nodes (and relationships between those nodes) associated with a particular actionable intent. For example, ontology 760 shown in fig. 7C includes an example of restaurant reservation field 762 and an example of reminder field 764 within ontology 760. The restaurant reservation domain includes executable intent nodes "restaurant reservation," attribute nodes "restaurant," date/time, "and" party number, "and sub-attribute nodes" cuisine, "" price range, "" phone number, "and" location. The reminder field 764 includes executable intent nodes "set reminder" and attribute nodes "subject" and "date/time". In some examples, ontology 760 is composed of a plurality of domains. Each domain shares one or more attribute nodes with one or more other domains. For example, in addition to the restaurant reservation field 762 and the reminder field 764, a "date/time" attribute node is associated with many different fields (e.g., a travel reservation field, a movie ticket field, etc.).

Although fig. 7C shows two exemplary fields within ontology 760, other fields include, for example, "find movie," "initiate phone call," "find direction," "schedule meeting," "send message," and "provide answer to question," "read list," "provide navigation instructions," "provide instructions for task," and so forth. The "send message" field is associated with a "send message" actionable intent node and further includes attribute nodes such as "one or more recipients", "message type", and "message body". The attribute node "recipient" is further defined, for example, by sub-attribute nodes such as "recipient name" and "message address".

In some examples, ontology 760 includes all domains (and thus executable intents) that the digital assistant can understand and work with. In some examples, ontology 760 is modified, such as by adding or removing an entire domain or node, or by modifying relationships between nodes within ontology 760.

In some examples, nodes associated with multiple related actionable intents are clustered under a "superdomain" in ontology 760. For example, a "travel" super domain includes a cluster of travel-related attribute nodes and actionable intent nodes. Executable intent nodes associated with travel include "airline reservations," "hotel reservations," "car rentals," "get routes," "find points of interest," and so forth. An actionable intent node under the same super domain (e.g., a "travel" super domain) has multiple attribute nodes in common. For example, executable intent nodes for "airline reservations," hotel reservations, "" car rentals, "" get routes, "and" find points of interest "share one or more of the attribute nodes" start location, "" destination, "" departure date/time, "" arrival date/time, "and" party number.

In some examples, each node in ontology 760 is associated with a set of words and/or phrases that are related to the attribute or actionable intent represented by the node. The respective set of words and/or phrases associated with each node is a so-called "vocabulary" associated with the node. A respective set of words and/or phrases associated with each node is stored in a vocabulary index 744 associated with the attribute or actionable intent represented by the node. For example, returning to FIG. 7B, the vocabulary associated with the node of the "restaurant" attribute includes words such as "food," "drink," "cuisine," "hunger," "eat," "pizza," "fast food," "meal," and the like. As another example, words associated with a node that "initiates a telephone call" may perform intent include words and phrases such as "call," "make a call to … …," "call the number," "make a phone call," and the like. The vocabulary index 744 optionally includes words and phrases in different languages.

The natural language processing module 732 receives the candidate text representations (e.g., one or more text strings or one or more symbol sequences) from the STT processing module 730 and, for each candidate representation, determines which nodes the words in the candidate text representation relate to. In some examples, a word or phrase in the candidate text representation "triggers" or "activates" those nodes if it is found to be associated (via the vocabulary index 744) with one or more nodes in the ontology 760. Based on the number and/or relative importance of activated nodes, the natural language processing module 732 selects one of the executable intents as a task that the user intends the digital assistant to perform. In some examples, the domain with the most "triggered" nodes is selected. In some examples, the domain with the highest confidence (e.g., based on the relative importance of its respective triggered node) is selected. In some examples, the domain is selected based on a combination of the number and importance of triggered nodes. In some examples, additional factors are also considered in selecting the node, such as whether the digital assistant has previously properly interpreted a similar request from the user.

The user data 748 includes user-specific information such as user-specific vocabulary, user preferences, user addresses, user's default second language, user's contact list, and other short-term or long-term information for each user. In some examples, the natural language processing module 732 uses user-specific information to supplement information contained in the user input to further define the user intent. For example, for a user request "invite my friends to my birthday party," the natural language processing module 732 can access the user data 748 to determine what the "friends" are and when and where the "birthday party" will be held without requiring the user to explicitly provide such information in his request.

It should be appreciated that in some examples, the natural language processing module 732 is implemented with one or more machine learning mechanisms (e.g., a neural network). In particular, the one or more machine learning mechanisms are configured to receive a candidate text representation and context information associated with the candidate text representation. Based on the candidate text representations and the associated context information, the one or more machine learning mechanisms are configured to determine an intent confidence score based on a set of candidate executable intents. The natural language processing module 732 may select one or more candidate actionable intents from a set of candidate actionable intents based on the determined intent confidence scores. In some examples, an ontology (e.g., ontology 760) is also utilized to select one or more candidate actionable intents from a set of candidate actionable intents.

Additional details of searching for ontologies based on symbol strings are described in U.S. patent application Ser. No. 12/341,743 entitled "Method and Apparatus for Searching Using An Active Ontology," filed on 12/22 of 2008, the entire disclosure of which is incorporated herein by reference.

In some examples, once the natural language processing module 732 identifies an actionable intent (or domain) based on a user request, the natural language processing module 732 generates a structured query to represent the identified actionable intent. In some examples, the structured query includes parameters for one or more nodes within the domain of the actionable intent, and at least some of the parameters are populated with specific information and requirements specified in the user request. For example, the user says "help me reserve a seat at 7 pm at sushi store. "in this case, the natural language processing module 732 is able to correctly identify the actionable intent as" restaurant reservation "based on user input. According to the ontology, the structured query of the "restaurant reservation" field includes parameters such as { cuisine }, { time }, { date }, { party number }, and the like. In some examples, based on the speech input and text derived from the speech input using STT processing module 730, natural language processing module 732 generates a partially structured query for the restaurant reservation domain, where the partially structured query includes parameters { cuisine = "sushi class" }, and { time = "7 pm" }. However, in this example, the user utterance contains insufficient information to complete the structured query associated with the domain. Thus, based on the currently available information, other necessary parameters such as { party number } and { date } are not specified in the structured query. In some examples, the natural language processing module 732 populates some parameters of the structured query with the received contextual information. For example, in some examples, if the user requests a "nearby" sushi store, the natural language processing module 732 populates { location } parameters in the structured query with GPS coordinates from the user device.

In some examples, the natural language processing module 732 identifies a plurality of candidate actionable intents for each candidate text representation received from the STT processing module 730. Additionally, in some examples, a respective structured query is generated (partially or wholly) for each identified candidate executable intent. The natural language processing module 732 determines an intent confidence score for each candidate actionable intent and ranks the candidate actionable intents based on the intent confidence scores. In some examples, the natural language processing module 732 communicates the generated one or more structured queries (including any completed parameters) to the task flow processing module 736 ("task flow processor"). In some examples, one or more structured queries for the m best (e.g., m highest ranked) candidate executable intents are provided to the task flow processing module 736, where m is a predetermined integer greater than zero. In some examples, one or more structured queries for the m best candidate actionable intents are provided to the task flow processing module 736 along with the corresponding one or more candidate text representations.

Other details of inferring user intent based on a plurality of candidate actionable intents determined from a plurality of candidate textual representations of a speech input are described in U.S. patent application Ser. No. 14/298,725, entitled "SYSTEM AND Method for Inferring User Intent From Speech Inputs," filed 6/2014, the entire disclosure of which is incorporated herein by reference.

Task flow processing module 736 is configured to receive one or more structured queries from natural language processing module 732, complete the structured queries (if necessary), and perform the actions required to "complete" the user's final request. In some examples, the various processes necessary to accomplish these tasks are provided in the task flow model 754. In some examples, the task flow model 754 includes a process for obtaining additional information from a user, as well as a task flow for performing actions associated with executable intents.

As described above, to complete a structured query, task flow processing module 736 needs to initiate additional conversations with the user in order to obtain additional information and/or ascertain possibly ambiguous utterances. When such interactions are necessary, the task flow processing module 736 invokes the dialog flow processing module 734 to engage in a dialog with the user. In some examples, the dialog flow processor module 734 determines how (and/or when) to request additional information from the user and receives and processes user responses. Questions are provided to and answers are received from users through I/O processing module 728. In some examples, the dialog flow processing module 734 presents dialog outputs to the user via audible and/or visual outputs and receives input from the user via verbal or physical (e.g., click) responses. Continuing with the example above, when task flow processing module 736 invokes dialog flow processing module 734 to determine "party number" and "date" information for a structured query associated with the domain "restaurant reservation," dialog flow processing module 734 generates a query such as "several digits in a row? "and" what day to subscribe? "and the like. Upon receipt of an answer from the user, the dialog flow processing module 734 populates the structured query with missing information or passes information to the task flow processing module 736 to complete the missing information based on the structured query.

Once the task flow processing module 736 has completed the structured query for the executable intent, the task flow processing module 736 begins executing the final tasks associated with the executable intent. Accordingly, the task flow processing module 736 performs the steps and instructions in the task flow model according to the specific parameters contained in the structured query. For example, a task flow model for an actionable intent "restaurant reservation" includes steps and instructions for contacting a restaurant and actually requesting a reservation for a particular party number at a particular time. For example, using structured queries such as: { restaurant reservation, restaurant=abc cafe, date=3/12/2012, time=7pm, party number=5 }, the task flow processing module 736 can perform the following steps: (1) Logging into a server of an ABC cafe or such as(2) Entering date, time, and dispatch information in the form of a web site, (3) submitting a form, and (4) forming calendar entries for reservations in the user's calendar.

In some examples, the task flow processing module 736 completes the tasks requested in the user input or provides the informational answers requested in the user input with the aid of a service processing module 738 ("service processing module"). For example, the service processing module 738 initiates a telephone call, sets up a calendar entry, invokes a map search, invokes or interacts with other user applications installed on the user device, and invokes or interacts with third party services (e.g., restaurant reservation portals, social networking sites, banking portals, etc.) on behalf of the task flow processing module 736. In some examples, the protocols and Application Programming Interfaces (APIs) required for each service are specified by a corresponding service model in service models 756. The service processing module 738 accesses an appropriate service model for a service and generates requests for the service according to the service model in accordance with the protocols and APIs required for the service.

For example, if a restaurant has enabled an online booking service, the restaurant submits a service model that specifies the necessary parameters to make the booking and communicates the values of the necessary parameters to the API of the online booking service. Upon request by the task flow processing module 736, the service processing module 738 can use the Web address stored in the service model to establish a network connection with the online booking service and send the necessary parameters of the booking (e.g., time, date, party number) to the online booking interface in a format according to the API of the online booking service.

In some examples, the natural language processing module 732, the dialog flow processing module 734, and the task flow processing module 736 are used collectively and repeatedly to infer and define a user's intent, to obtain information to further clarify and refine the user's intent, and to ultimately generate a response (i.e., output to the user, or complete a task) to satisfy the user's intent. The generated response is a dialog response to the voice input that at least partially satisfies the user's intent. Additionally, in some examples, the generated response is output as a speech output. In these examples, the generated response is sent to a speech synthesis processing module 740 (e.g., a speech synthesizer), where the generated response can be processed to synthesize the dialog response in speech form. In other examples, the generated response is data content related to satisfying a user request in a voice input.

In examples where the task flow processing module 736 receives a plurality of structured queries from the natural language processing module 732, the task flow processing module 736 first processes a first structured query of the received structured queries in an attempt to complete the first structured query and/or perform one or more tasks or actions represented by the first structured query. In some examples, the first structured query corresponds to the highest ranked executable intent. In other examples, the first structured query is selected from structured queries received based on a combination of the corresponding speech recognition confidence score and the corresponding intent confidence score. In some examples, if task flow processing module 736 encounters an error during processing of the first structured query (e.g., due to an inability to determine the necessary parameters), task flow processing module 736 can continue to select and process a second one of the received structured queries that corresponds to a lower-ranked executable intent. The second structured query is selected, for example, based on a speech recognition confidence score for the corresponding candidate text representation, an intent confidence score for the corresponding candidate actionable intent, a requisite parameter for a miss in the first structured query, or any combination thereof.

The speech synthesis processing module 740 is configured to synthesize speech output for presentation to a user. The speech synthesis processing module 740 synthesizes a speech output based on text provided by the digital assistant. For example, the generated dialog response is in the form of a text string. The speech synthesis processing module 740 converts the text string into audible speech output. The speech synthesis processing module 740 uses any suitable speech synthesis technique to generate speech output from text, including but not limited to: stitching synthesis, unit selection synthesis, diphone synthesis, domain-specific synthesis, formant synthesis, pronunciation synthesis, hidden Markov Model (HMM) based synthesis, and sine wave synthesis. In some examples, the speech synthesis processing module 740 is configured to synthesize individual words based on the phoneme strings corresponding to the words. For example, the phoneme string is associated with a word in the generated dialog response. The phoneme string is stored in metadata associated with the word. The speech synthesis processing module 740 is configured to directly process the phoneme strings in the metadata to synthesize words in speech form.

In some examples, instead of (or in addition to) using the speech synthesis processing module 740, speech synthesis is performed on a remote device (e.g., server system 108) and the synthesized speech is sent to a user device for output to a user. For example, this may occur in some implementations in which the output of the digital assistant is generated at a server system. And since the server system typically has more processing power or more resources than the user equipment, it is possible to obtain a higher quality speech output than would be achieved by the client-side synthesis.

Additional details regarding digital assistants can be found in U.S. patent application Ser. No. 12/987,982, entitled "INTELLIGENT AUTOMATED ASSISTANT", filed 1/10/2011, and U.S. patent application Ser. No. 13/251,088, entitled "GENERATING AND Processing TASK ITEMS THAT REPRESENT TASKS to Perform", filed 9/2011, the disclosures of which are incorporated herein by reference in their entireties.

4. Speech recognition in digital assistant systems

Fig. 8, 9A-9F, 10A-10H, and 11A-11B illustrate exemplary processes and user interactions with an electronic device. These figures illustrate some exemplary processes described below, including processes 1300 and 1400 of fig. 13A-13G and 14A-14E, respectively.

Although some of the processes below are described as being performed by a particular device (e.g., device 800, 900), in some examples, the processes are performed using a client-server system (e.g., system 100), where device 800 and/or 900 is implemented as a client device in communication with a server, e.g., as shown in fig. 1. In some examples, the process is divided in any manner between the client device and the server. In some examples, the process is performed by only a client device, or by only a plurality of client devices (e.g., 800, 900).

The processes described below are performed using software, hardware, or a combination of software and hardware to perform the principles described herein. The hardware and software components may be distributed in any manner among devices and/or systems (e.g., 800, 900, 100) that perform the processes. For example, the processes are optionally implemented as computer-executable instructions stored in memory 702 and/or using digital assistant system 700 or any component thereof operating on a device and/or system executing the processes. Those skilled in the art will understand how to perform other processes using the components of fig. 1-4, 6A-6B, and 7A-7C.

Fig. 8 illustrates user interactions with an electronic device 800 according to some examples. The device 800 includes the modules and functions of the digital assistant described above in fig. 7A-7C. Device 800 is, for example, the same as or similar to device 400 or 600 discussed above. In the example of fig. 8, device 800 is a smart speaker. However, device 800 may be any type of device, such as a phone, a laptop, a desktop computer, a tablet, a wearable device (e.g., a smart watch), a television, a speaker, or any combination thereof.

The device 800 receives natural language speech input (e.g., from a user) and provides a response to the speech input. According to the techniques discussed below, the response is personalized for the user identified based on the received voice input. For example, FIG. 8 shows a user (e.g., stephen) providing a voice input "hey, siri," read out My message "to a device (e.g., to a digital assistant operating on the device). The digital assistant recognizes the user based on the received voice input and provides a personalized response "good, stephen, read your message: first message: corey states a2 o' clock face.

In some examples, device 800 receives multiple speaker profiles for multiple users (e.g., registered users) from an external electronic device. In some examples, the plurality of speaker profiles are received prior to receiving speech input based on which the user is identified. In some examples, registered users form a group of interrelated users, such as users in the same household, users registered in a particular software application, user-defined groups of users, or combinations or sub-combinations thereof. Thus, in some examples, the external electronic device is a respective electronic device of each of the registered users. For example, when the home includes four users, the external electronic devices are four respective electronic devices (e.g., phone, laptop, watch, tablet) for each user in the home. Thus, in some examples, four electronic devices each send a speaker profile of their respective users to device 800.

In the example of fig. 8, device 800 has received a speaker profile of a user (e.g., stephen) from an external electronic device 900 (e.g., stephen's phone). In some examples, device 900 is the same or similar to device 400 or 600 and is a phone, a laptop, a desktop computer, a tablet, a wearable device (e.g., a smart watch), a television, a speaker, or any combination thereof. In some examples, device 900 includes the modules and functions of the digital assistant discussed above with respect to fig. 7A-7C. Device 800 also receives a speaker profile of another user (e.g., stephen's friend Corey) from another user's external electronic device (e.g., corey's device, not shown). Device 800 identifies a user using the received speaker profile in accordance with the techniques discussed below.

In some examples, each speaker profile of the plurality of received speaker profiles includes a plurality of representations of the voice of the respective user. In some examples, at least one representation of the plurality of representations is determined based on the utterance of the respective user. In some examples, the utterance is received at an external electronic device (e.g., external to device 800) associated with the respective user. In some examples, the utterance includes a trigger phrase for triggering the digital assistant, such as "hey, siri" or "wake up. In some examples, the utterance is spoken by a respective user as part of a registration session of the digital assistant (e.g., a registration session in which the user speaks a trigger phrase several times to register in a voice-triggered system of the digital assistant).

In some examples, a digital assistant operating on an external device (e.g., device 900) determines a representation of a received utterance in accordance with the techniques discussed herein. In some examples, the determined representations are included in a speaker profile for the respective user. In some examples, a digital assistant operating on an external device causes the determined representation (and/or speaker profile) to be sent to another device (e.g., device 800).

For example, the speaker profile of Stephen received by device 800 includes multiple representations of the sound of Stephen. The multiple representations are determined based on the Stephen utterance "hey, siri" at the device 900. The digital assistant operating on device 900 causes a plurality of representations of speaker profiles that form Stephen to be sent to device 800.

In some examples, the representation of the utterance includes a deterministic embedding of the utterance. In some examples, the embedding includes a vector (e.g., a set of values) representing the user's voice. In some examples, the speaker model is used to determine the embedding, e.g., implemented as executable instructions stored in a memory of device 800 and/or 900. In some examples, the speaker model includes a neural network, a hidden markov model, and/or other models known in the art for speaker recognition, and is trained to determine an embedding based on a received utterance (e.g., speech input). In some examples, the speaker model is trained to determine an embedding that emphasizes speaker-specific features while attenuating environmental and semantic factors (e.g., environmental noise, specific words spoken) and changes in the voice of a specific speaker (e.g., tired voice of the speaker, angry voice of the speaker, etc.). In some examples, the speaker model is trained to determine an embedding that minimizes variability of the same speaker (e.g., the embedding of utterances from the same speaker is the same or similar), while maximizing variability between speakers (e.g., the embedding of utterances from different speakers is different). In this way, the determined embedding may accurately represent the sound of a particular speaker. Thus, the determined embedding may be compared with other embeddings (e.g., for a particular speaker and for other speakers) to identify the speaker. For example, if the first embedding is proximate (e.g., within a predefined threshold measured by cosine distance between vectors) to a second embedding that represents the sound of a particular speaker, an utterance corresponding to the first embedding may be received from the particular speaker.

In some examples, the speaker model is trained using utterances of various users (e.g., young users, old users, male users, female users). In some examples, utterances of various users are received at various electronic devices, such as telephones, computers, speakers, and tablet devices. Training the speaker model based on such utterances may allow the speaker model to determine accurate and robust embedding to represent the speaker's voice. In particular, because the same utterance may have different features when recorded by different types of electronic devices (e.g., due to different device microphone configurations/types), it may be advantageous to train a speaker model to determine an accurate embedding of the utterance, regardless of the device receiving the utterance.

In some examples, the speaker model is trained using utterances of various phrases (e.g., "hey, siri", "set timer", "how do today's weather. This may allow for the accurate embedding of various utterances to be determined. For example, the speaker model may be trained initially based on the utterances "hey, siri", but further training with other utterances may allow the speaker model to accurately determine the embedding of various utterances (e.g., "call me mom"). In this way, the user may be identified based on a different speech utterance (e.g., "call me mom") than the utterance (e.g., "hey, siri") used to train the speaker model. Exemplary speaker models and techniques for training speaker models are discussed in the following documents:

·“Personalized Hey Siri.”Apple Machine Learning Journal,vol.1,no.

9, april 2018; and

·E.Marchi,S.Shum,K.Hwang,S.Kajarekar,S.Sigtia,H.Richards,R.

Haynes,Y.Kim,and J.Bridle."Generalised Discriminative Transformvia Curriculum Learning for Speaker Recognition."Proceedings of theIEEE International Conference on Acoustics,Speech,and SignalProcessing(ICASSP),April 2018.

The contents of these publications are hereby incorporated by reference in their entirety.

In some examples, device 800 determines a plurality of likelihoods that the speech input corresponds to a plurality of users (e.g., registered users), respectively, based on comparing the received natural language speech input to a plurality of speaker profiles. In some examples, each of the plurality of possibilities includes a score (e.g., a numerical value) indicating a degree of match between the received speech input and the corresponding speaker profile. For example, in fig. 8, device 800 determines a first likelihood that the speech input corresponds to Stephen based on comparing the speech input to a speaker profile of Stephen and determines a second likelihood that the speech input corresponds to Corey based on comparing the speech input to a speaker profile of Corey. The second likelihood is less than the first likelihood, which indicates that the device 800 is more confident that the voice input corresponds to Stephen.

In some examples, determining the likelihood that the speech input corresponds to the user includes comparing a representation of the speech input to each of a plurality of representations of the user's voice. For example, device 800 determines a representation of the speech input (e.g., an embedding) and compares the determined embedding to each of a plurality of (e.g., 40) embeddings included in the user's speaker profile. For example, for each of a plurality of embeddings, device 800 calculates a distance metric (e.g., a normalized cosine distance) between the respective embedment and the determined embedment. The device 800 then averages the determined distance metrics to calculate an average score indicative of the degree of match between the speech input and the user's speaker profile. In some examples, device 800 then determines a likelihood that the speech input corresponds to the user based on the average score.

In some examples, device 800 determines whether the likelihood that the voice input corresponds to the user exceeds (or does not exceed) one or more thresholds. For example, the device 800 determines whether the likelihood exceeds a first threshold (e.g., an upper threshold). In some examples, a likelihood of exceeding an upper threshold indicates that the speech input corresponds to a user represented by the likelihood with a high confidence. In some examples, the device 800 determines whether the likelihood is below a second threshold (e.g., a lower threshold). In some examples, a likelihood of being below the lower threshold indicates that the speech input corresponds to the user with a low confidence. In some examples, the device 800 determines whether the likelihood is between two thresholds (such as a lower threshold and an upper threshold). In some examples, a likelihood between the two thresholds indicates that the speech input corresponds to a user with a medium confidence. In the example of fig. 8, device 800 determines that the likelihood that the speech input corresponds to Stephen exceeds the upper threshold. The device 800 determines that the likelihood that the voice input corresponds to Corey is below the lower threshold.

In some examples, device 800 determines whether a likelihood that the voice input corresponds to the first user and a likelihood that the voice input corresponds to the second user are within a threshold (e.g., a difference threshold). In some examples, having the first likelihood and the second likelihood within the difference threshold means that the device 800 is unable to distinguish between the first user and the second user with sufficient confidence (e.g., because the likelihoods are very close). In some examples, having the first likelihood and the second likelihood not within the difference threshold means that the device 800 can distinguish users (e.g., because the likelihoods are far apart). In the example of fig. 8, device 800 determines that the likelihood that the voice input corresponds to Stephen and the likelihood that the voice input corresponds to Corey are not within the score difference threshold, which means, for example, that device 800 has distinguished the sound of Stephen from the sound of Corey.

In some examples, device 800 determines that the natural language voice input corresponds to a user (e.g., identifies the user). In some examples, identifying the user includes determining a representation of the voice input, determining a likelihood, determining whether the likelihood that the voice input corresponds to the user exceeds or does not exceed one or more thresholds (e.g., upper threshold, lower threshold), determining that the likelihood is higher or lower than other likelihood, and determining that the likelihood is not within a difference threshold of any other likelihood determined, or a combination or sub-combination thereof. For example, the device 800 recognizes Stephen because the likelihood that the voice input "hey, siri, read my message" corresponds to Stephen exceeds the upper threshold, because the likelihood that the voice input corresponds to Stephen is the highest determined likelihood, and/or because the likelihood that the voice input corresponds to Stephen and the likelihood that the voice input corresponds to Corey are not within the difference threshold.

In some examples, identifying the user includes determining a likely user corresponding to the voice input, e.g., a plurality of likely users. In some examples, the likely user may be determined from a registered user of device 800. In some examples, possible users include users for which device 800 has at least low, medium, or high confidence. In some examples, possible users include users that the device 800 cannot distinguish with sufficient confidence. For example, if device 800 highly believes that the speech input corresponds to both Corey and Stephen, and is unable to distinguish between Corey and Stephen, corey and Stephen are determined to be two possible users.

In some examples, one or more possible users are non-registered users, e.g., users for whom device 800 did not receive a corresponding speaker profile. In some examples, a non-registered user is determined to be a likely user when device 800 determines that the voice input corresponds to a non-registered user having a high, medium, or low confidence. For example, device 800 stores a speaker profile of a non-registered user, such as a generic human speaker profile, and determines that the speech input corresponds to the non-registered user with high, medium, or low confidence.

In some examples, device 800 provides a response to the voice input based on identifying the user, for example, using I/O processing module 728. In some examples, the response to the voice input is personalized to the identified user. For example, the response is determined based on personal information of the identified user (discussed further below with respect to FIG. 12). In some examples, providing a response to the voice input includes determining a user intent based on the voice input (e.g., using natural language processing module 732), determining a task based on the user intent (e.g., using task flow processing module 736), and providing a result based on the task (e.g., using input/output processing module 728). Further details regarding providing personalized responses are discussed below with respect to fig. 12.

In some examples, the response to the voice input includes one or more words indicating personalization of the identified user. For example, the response includes the name and/or words/phrases of the identified user, such as "you", "personal", "personalized" or "just you". This may advantageously indicate that the device has correctly (or incorrectly) identified the user. For example, in fig. 8, device 800 recognizes Stephen and provides a personalized response to Stephen, "good Stephen, read your message: first message: corey states a 2 o' clock face.

Sometimes, repeatedly providing the user's name (e.g., in response to each user voice input) may be undesirable because it may be annoying to the user and extend the length of the device output. Thus, in some examples, device 800 provides the name of the user identified in response to the voice input by which the user was initially identified, but does not provide the name in subsequent responses to voice input from the same user. For example, after device 800 provides a personalized response "good, stephen, read your message," Stephen provides another voice input to device 800 (e.g., "hey, siri, make phone call to mom"). Device 800 still recognizes Stephen in accordance with the techniques discussed herein, but does not provide a response that includes the name Stephen. Instead, device 800 responds to, for example, "good, place a call to the mother. However, if the voice input (e.g., "hey, siri, make a phone call to mom") is provided by another user (e.g., corey), the response to the voice input may include the name of the other user (e.g., "good, corey, make a phone call to mom").

In some examples, device 800 updates a speaker profile of the identified user based on the voice input according to the identified user. For example, device 800 determines an embedding of the utterance (e.g., using a speaker model) and adds the determined embedding to a speaker profile of the particular user. For example, device 800 determines the embedding "hey, siri, reads out my message" and adds the embedding to Stephen's speaker profile.

Updating the speaker profile in this manner may improve user recognition based on future speech input. For example, because more representations of the user's voice (e.g., embedded) may be included in the updated speaker profile, the updated speaker profile may be used to more accurately identify the user. Further, the added representation may represent the user's voice as received by device 800 more accurately than other representations in the user's speaker profile (e.g., because other representations may be determined based on utterances received at a device other than device 800, as discussed above).

In some examples, after (or while) providing a personalized response to the voice input, device 800 receives an input (e.g., user voice input) indicating a recognition error. Exemplary inputs indicating an identification error include "that is not me", "not, stopped", "i are others", and so forth. In some examples, upon receiving an input indicating an identification error, device 800 terminates providing a personalized response and/or forgoes updating the speaker profile of the identified user. In some examples, upon receiving an input indicating a recognition error, device 800 determines information indicating that the determined representation of the initial speech input is incorrect for the (incorrectly) recognized user. In some examples, such information is used to train a speaker model to determine a more accurate representation of the speech input.

For example, if device 800 responds with "good, corey, read your message … …" in response to the Stephen's voice input "hey, siri, read my message", then Stephen will provide the input "that is not me". Upon receiving such input, device 800 terminates providing "good, corey, read your message … …" and does not update the Corey's speaker profile based on the representation of the utterance "hey, siri, read My message" (because the utterance is actually spoken by Stephen).

In some examples, the device 800 determines (e.g., using the natural language processing module 732) a user intent associated with the received natural language voice input. In some examples, the device 800 determines (e.g., using the natural language processing module 732) whether the user intent includes (e.g., is) one of a plurality of types of user intent. In some examples, the multiple types of user intents include personal intent, semi-personal intent, and non-personal intent. As discussed below, the manner in which the device 800 interacts with the user (and whether user identification is performed) may depend on the type of intent determined.

In some examples, the personal intent includes an intent that requires user identification to provide a personalized response. Exemplary personal intents include the following:

Retrieving communications (e.g., email, text message, instant message, voice mail)

(E.g., associated with entering "read my message", "read Corey to my email");

sending a communication (e.g., email, phone call, text message, instant message) to the personal contact (e.g., associated with entering "make phone call to mom");

user identification (e.g., associated with the input "who is me";

retrieving and/or modifying contact information, recent caller information, health information, financial information, or a combination thereof (e.g., associated with entering "help me find contact information for Corey", "how many calories i burn today;

Retrieving and/or modifying calendar and/or reminder information (e.g., associated with entering "add appointment to my calendar", "remind me to make a call to mom");

Retrieving and/or modifying the user's notes and/or lists (e.g., user-created text memo, voice memo) (e.g., associated with entering "create new notes", "add this to my shopping list");

Activating and/or deactivating a security feature of the user's home (e.g., associated with entering "unlock my door", "sound my alarm");

modifying the user's personal media account (e.g., associated with entering "add this to my playlist", "purchase ARIANA GRANDE's 'thank u next'", "subscribe to CNN news");

locate the user's electronic device (e.g., associated with entering "find my phone", "where my watch is); and

Initiate a personalized voice shortcut command (e.g., associated with a user-defined input that causes the digital assistant to perform a user-defined task).

An exemplary technique for personalizing voice shortcut commands is discussed in U.S. patent application 16/146,963 entitled "ACCELERATED TASK PERFORMANCE" (accelerating task execution) filed on 9 and 28 in 2018.

In some examples, the semi-personal intent includes an intent that may be desired for user identification but may not be needed to provide a response. Exemplary semi-personal intents include an intention to play media (e.g., associated with the input "play ARIANA GRANDE 'thank u next'"), an intention to provide news (e.g., associated with the input "what news. For example, for semi-personal intent, user identification may be required to play a favorite version of the requested media of the identified user (or to provide news from a preferred news source of the identified user), but user identification may not be necessary as the device may provide the requested media (or provide news) without identifying the user.

In some examples, non-personal intent includes intent that does not require (or even is not desirable for) user identification to provide a response. Exemplary non-personal intents include the following:

retrieving weather information (e.g., associated with the input "how weather today is;

Retrieving sports information (e.g., associated with the input "is the patriot team won;

setting a timer, alarm clock, and/or stopwatch (e.g., associated with entering "set 15 minute timer");

Adjusting media playback (e.g., associated with the inputs "turn down volume", "pause", "stop", "rewind");

Perform information search (e.g., associated with entering "search bar for hong kong", "search for Abraham Lincoln on Wikipedia";

Navigation (e.g., associated with the input "bring me to Cupertino", "where the golden gate bridge is; and

Adjust certain device settings (e.g., associated with the input "highlight display brightness").

While some intents are described above as specific types of intents (e.g., personal, semi-personal, non-personal), in other examples, the intents may be different types of intents. For example, the intent to retrieve sports information may be a semi-personal intent (e.g., to provide sports information from favorite sports content providers of the identified user) rather than a non-personal intent. As another example, the intent to play media may be personal intent (e.g., if the voice input is "play my music"), rather than half personal intent. Thus, in some examples, the intents discussed above may not be limited to the type to which they were originally assigned, as they may vary depending on the content of the associated voice input and/or whether a personalized response may be provided for the intent.

In some examples, device 800 determines an identification frequency for each user. In some examples, device 800 provides a response that is personalized for the most frequently identified user when the user cannot positively identify. For example, a user may not be positively identified when the voice input corresponds to the user having a low or medium confidence and/or is unable to distinguish the user from other users. For example, if device 800 determines that a plurality of possible users correspond to voice input, device 800 provides a response to the voice input that is personalized to the most frequently identified of the possible users. In some examples, device 800 operates in a manner that is associated with half a person's intent in accordance with a determination that the current speech input is associated with half a person's intent. For example, if the user speaks "play latest sports news" to the device 800 and the device 800 has a low confidence that the voice input corresponds to the user (even that the voice input corresponds to other users with a lower confidence), the device 800 provides a response that is personalized for the most frequently identified user. For example, device 800 provides the latest sports news from the most frequently identified sports news provider that the user prefers.

In some examples, device 800 determines the most recently identified user. In some examples, when the user cannot positively identify, the device 800 provides a response that is personalized to the most recently identified user. For example, if device 800 determines that a plurality of possible users correspond to voice input, device 800 provides a response to the voice input that is personalized to the most recently identified user (if he or she is a possible user). In some examples, device 800 operates in a manner that is associated with half a person's intent in accordance with a determination that the current speech input is associated with half a person's intent. For example, if the user speaks "play music" into the device 800 and the device 800 has a low confidence that the speech input corresponds to the user (even that the speech input corresponds to other users with a lower confidence), the device 800 provides a response that is personalized to the most recently identified user. For example, device 800 plays music from a media collection associated with a recently identified user.

Sometimes, a user interacts with a digital assistant operating on device 800 for multiple rounds. In some examples, the multi-round interactions include interactions in which multiple exchanges with the digital assistant may be required to perform the requested task. For example, a user says "send message" to device 800, device 800 responds with "who i want to send your message to? The user then speaks "give John, tell him that me will be late", and the device 800 responds with "good, i am sent a message", which is a multiple round of interaction. In some examples, the multi-round interactions include interactions in which a user provides multiple related requests to a digital assistant, for example, for a short duration such as 5 seconds, 10 seconds, 15 seconds, or 30 seconds. For example, the user says "what is the weather in new york? The device responds with "70 degrees, sunny day", the user then says "paris? The device responds "56 degrees, raining", which is a multiple round of interaction.

In some examples, device 800 only determines whether the first speech input of the multiple rounds of interaction corresponds to a certain user. In other examples, device 800 determines whether each voice input (or a subset of voice inputs) of the multiple rounds of interaction corresponds to the same user. In some examples, device 800 operates in a manner that includes a personal intent in accordance with a determination that a user intent associated with a voice input (e.g., a first voice input). For example, suppose Stephen says "send message to Corey" to device 800 (associated with personal intent), device 800 responds with "what should me say to Corey? ", stephen responds with" i will delay. The device 800 determines whether each voice input of the multiple rounds of interaction corresponds to the same user.

In some examples, if subsequent voice inputs in the multiple rounds of interaction are determined not to correspond to the same user, device 800 identifies the user in accordance with the methods discussed below before providing further responses. For example, if the subsequent speech input corresponds to the same user with low confidence, the subsequent speech input does not correspond to the same user. For example, if in the above interaction, a non-registered user (rather than Stephen) says "i am late", then device 800 may output "you must send the message using your phone". In this way, device 800 may monitor consistent user identities in multiple rounds of interactions (e.g., for interactions associated with personal intent, where user identification may be required).

In some examples, device 800 identifies a user using techniques other than identifying the user based on an initial voice input (e.g., "hey, siri, read my message"). For example, device 800 may identify a user using other techniques in accordance with determining that it has a medium or low confidence for a particular user and/or determining that the user cannot be distinguished from other users. As discussed below with respect to fig. 9A-9F, other techniques for identifying a user may depend on the type of user intent, the content of the voice input, and/or the confidence that the user has been identified. Exemplary other techniques for identifying users are now discussed.

In some examples, other techniques for identifying a user include providing an output (e.g., a voice output, a displayed output) indicative of a request for a user identity, and identifying the user based on a user's response to the output. In some examples, the output indicating a request for user identity includes a request for the user to identify himself, e.g., "who is you? "," please complain me about who you are. In some examples, the output indicating a request for the user's identity includes a request for the user to confirm his identity, e.g., "do you be Stephen? "," is you Stephen, is you to? ". In some examples, the output request indicating a request for user identity disambiguates a user between two or more registered users, e.g., "you are Stephen or Corey? "

In some examples, device 800 receives a voice input (e.g., natural language voice input) in response to providing an output indicating a request for a user identity. In some examples, device 800 determines whether the voice input corresponds to a user. In some examples, if device 800 determines that the voice input corresponds to a user, device 800 identifies the user.

In some examples, if device 800 requests that the user identify itself (e.g., ask "please complain of who you are. In some examples, device 800 then determines whether the voice input corresponds to a user. For example, device 800 processes the voice input (e.g., determines a likelihood score, etc.) in accordance with the techniques discussed above to determine whether the voice input corresponds to a user. As another example, device 800 (e.g., using modules 730 and/or 732) determines whether the voice input includes a name of the user. For example, in fig. 10A and 10B, the user speaks "read my message" to the device 800. The device 800 cannot distinguish the user from other registered users, and thus outputs "please complain about who you are. The user then responds with "i am Stephen", based on which the device 800 recognizes Stephen.

In some examples, if device 800 requests the user to confirm his identity (e.g., "do you be Stephen, do you do. In some examples, device 800 then determines that the voice input corresponds to the user by determining that the voice input includes a positive response (e.g., "yes," "i am", "one," etc.). In some examples, device 800 determines that the voice input does not correspond to the user by determining that the voice input includes a negative response or other non-positive response (e.g., "not," "i am not" etc.).

In some examples, if device 800 requests disambiguation of a user between two or more registered users (e.g., "you are Stephen or Corey. In some examples, device 800 determines that the voice input corresponds to the user by determining that the voice input includes the user's name.

In some examples, providing an output indicative of the request for the user identity includes causing an external electronic device to provide the output. In some examples, the output includes a confirmation request confirming an action (e.g., reading out a message) included in the initial voice input. In some examples, device 800 also outputs a request for the user to confirm the confirmation request (e.g., via an audio output or a displayed output). For example, as shown in FIG. 10C, the user speaks "read My message" to device 800. Device 800 then causes device 900 (e.g., an external electronic device associated with the user) to provide a displayed output "read your message? "along with the selectable options" yes "and" no ". The device 800 also outputs "please confirm on your phone".

In some examples, the external electronic device receives a user confirmation of the confirmation request. In some examples, user confirmation of the confirmation request is received via a display of the external device (e.g., the user taps the selectable "yes" option in fig. 10C), via audio input at the external device (e.g., the user responds to the request "read your message. In some examples, the external device sends an indication of user confirmation of the confirmation request to another device. For example, device 900 sends an indication of user acknowledgement of the acknowledgement request to device 800, and device 800 receives an indication of user acknowledgement of the acknowledgement request.

In some examples, device 800 determines that the voice input corresponds to a user acknowledging the confirmation request in accordance with receiving an indication of user acknowledgment of the confirmation request. For example, in fig. 10C, after the user selects "yes," device 800 identifies the user who speaks "read my message" (e.g., the user of device 900). In this way, the user may use his external electronic device to confirm his identity, and device 800 may identify the user.

Fig. 9A-9F illustrate a flow chart of a process 902 for responding to voice input according to various examples. Process 902 is performed, for example, using device 800 and/or 900 or using any component thereof. In some examples, process 902 is performed using a client-server system (e.g., 100) and the blocks of the process are partitioned in any manner between a server (e.g., DA server 106) and one or more client devices (e.g., 800 and 900). Thus, while portions of process 902 are described herein as being performed by a particular device of a client-server system, it should be understood that the process is not so limited. In process 902, some blocks are optionally combined, the order of some blocks is optionally changed, and some blocks are optionally omitted. In some examples, additional steps may be performed in connection with process 902. For example, process 902 may include the additional step of device 800 receiving one or more speaker profiles for one or more users from one or more external electronic devices, as discussed above. In some examples, additional steps are performed prior to block 903, as discussed below.

At block 903, the device 800 receives a voice input.

At block 904, the device 800 determines whether it has any registered users. As discussed, the registered user is, for example, a user having a corresponding speaker profile received by device 800. If the device 800 does not have any registered users, the device 800 provides a response to the voice input as described above in FIGS. 7A-7C. If the device 800 has one or more registered users, the process 902 proceeds to block 905.

At block 905, the device 800 determines whether to identify the user based on the voice input. In some examples, determining to identify the user includes determining that the user intent associated with the voice input includes a personal intent or a semi-personal intent. In some examples, determining to identify the user includes (e.g., using modules 730 and/or 732) determining that the speech input includes one or more words that indicate personalization. Exemplary words indicating personalization include "my", "personal", "my own", "me", and the like. In some examples, determining not to identify the user includes determining that the user intent associated with the voice input includes a non-personal intent.

If the device 800 determines that the user is not identified, the device 800 provides a non-personalized response to the voice input, as shown in block 953. The non-personalized response may be a response that is not determined based on personal information of any user. For example, in fig. 10D, the user asks the device 800 "how is today's weather? ". The device 800 determines that the user is not identified based on the voice input and provides a non-personalized response "70 degrees, sunny" to the voice input.

If the device 800 determines that the user is identified, the process 902 proceeds to block 906. At block 906, the device 800 determines (e.g., using modules 730 and/or 732) whether the voice input includes a reference to an entity, such as a third person reference. In some examples, the reference to an entity includes a name, such as the name of the registered user. For example, stephen can say "read Stephen message". In some examples, references to an entity include words other than the name of the entity, such as "my mom", "my dad", "my boss", "his", "her", "their", and so forth. In some examples, if the voice input includes a reference to an entity, the process 902 proceeds to block 907. In some examples, if the voice input does not include a reference to an entity, the process 902 proceeds to block 932.

At block 907, the device 800 determines (e.g., using the natural language processing module 732) whether the speech input is associated with a predetermined intent category. Exemplary predetermined intent categories include intent to locate an electronic device (e.g., "where is Stephen's phone. In some examples, if the voice input is associated with a predetermined intent category, the process 902 proceeds to block 932.

In some examples, if the voice input is associated with a predetermined intent category, the digital assistant initiates a corresponding task based on the reference to the entity, e.g., if the device 800 determines that the voice input corresponds to the user. For example, parameters of the task initiated by the task flow processing module 736 are based on the reference to the entity. For example, for a voice input "how do i mom's weather? The digital assistant performs a task of obtaining weather information, where the task has the parameters { location = mom's of the identified user }.

In some examples, if the voice input is not associated with a predetermined intent category, the process 902 proceeds to block 908. At block 908, process 909 (a sub-process of process 902) is performed.

Turning to fig. 9C-9D (process 909), at block 910, the device 800 determines whether the voice input is associated with a personal domain. For example, using the natural language processing module 732, the device 800 determines the domain associated with the voice input and determines whether the domain is a personal domain or a non-personal domain. In some examples, the personal domain is associated with a personal intent (e.g., an actionable intent), as discussed above. Exemplary personal fields include a message field (e.g., associated with an intent to retrieve message information for a user), a phone field (e.g., associated with an intent to call/deliver a message to a user's contacts), a notes field (e.g., associated with an intent to retrieve/modify a user's notes), an awake field, a calendar field, a health field (e.g., associated with an intent to retrieve/modify user health data), and a device location field (e.g., associated with an intent to locate a user's electronic device). In some examples, the non-personal domain is associated with a non-personal intent (e.g., an actionable intent). Exemplary non-personal domains include media domains (e.g., associated with an intent to provide/modify media content) and sports domains (e.g., associated with an intent to provide sports information). In some examples, if the domain is a non-personal domain, the device 800 provides a response to the voice input based on the determined domain, e.g., as discussed with respect to fig. 7A-7C. In some examples, if the domain is a personal domain, process 909 proceeds to block 911.

At block 911, device 800 determines whether there is only one registered user (e.g., only one user's speaker profile is received). In some examples, if there is only one registered user, process 909 proceeds to block 912. In some examples, if there is not only one registered user, process 909 proceeds to block 913.

At block 912, the device 800 determines whether the voice input corresponds to only one user. For example, in accordance with the techniques discussed above, the device 800 determines a confidence (e.g., high, medium, low) that the speech input corresponds to only one user. In some examples, if the confidence is high or medium, the device 800 determines that the voice input corresponds to only one user. In some examples, if the confidence level is low, the device 800 determines that the voice input does not correspond to only one user. In some examples, if device 800 determines that the voice input corresponds to only one user, device 800 provides a response to the voice input. For example, suppose Stephen is the only registered user of device 800 and say "read Stephen's message" to device 800. The device 800 determines that the speech corresponds to Stephen with high confidence and thus provides a Stephen message.

If the device 800 determines that the voice input does not correspond to only one user, the device 800 provides a response (e.g., audio output, displayed output) indicating an error. For example, device 800 provides a response indicating that the user was not identified (e.g., "i don't determine who you are", "sorry, i cannot do so"). Thus, if Stephen is the only registered user and the non-registered user speaks "read Stephen message" to device 800, device 800 does not undesirably provide Stephen's message.

Turning to block 913, the device 800 (e.g., using modules 730 and/or 732) determines whether the reference to the entity included in the voice input matches the name of any registered user. If the reference matches the name of the registered user, process 909 proceeds to block 914. If the reference does not match the registered user's name, the process 909 proceeds to block 916.

At block 914, the device 800 determines a confidence that the voice input corresponds to a registered user that matches the reference to the entity. For example, in accordance with the techniques discussed above, device 800 determines a confidence that the voice input corresponds to the registered user. If the confidence level is high, the device 800 provides a response to the voice input, as indicated in block 952. For example, in FIG. 10E, stephen speaks "I are Stephen" to device 800, reading out My messages ". The device 800 determines that the voice input corresponds to a message that Stephen has a high confidence and thus provides Stephen.

If the confidence is medium or low, the process 909 proceeds to block 915. At block 915, the device 800 requests the user to confirm his identity and determines whether the response to the request corresponds to the user. In some examples, if device 800 determines that the response corresponds to a user (e.g., confirms a user), device 800 provides a response to the voice input. For example, if Stephen requests device 800, "do you be Stephen? "responds yes" and device 800 provides a response that is personalized for Stephen, such as a message providing Stephen. In some examples, if device 800 determines that the response does not correspond to the user (e.g., does not confirm the user), device 800 provides a response indicating an error (e.g., "sorry, i cannot do so").

At block 916, process 917 is performed (a sub-process of process 902). Turning to fig. 9E (process 917), at block 918, the device 800 determines whether a previous input (e.g., prior to voice input at block 903) is associated with an identity domain. In some examples, the previous input is the second most recent user input, where the speech input in block 903 is the most recent input. For example, an identity domain is associated with executable intent that identifies a user and/or asks for the user's identity. For example, input "who is me? And the inputs "i are name" provided (e.g., in response to device 800 outputting "please complain me you are who" are each associated with an identity domain.

In some examples, if the previous input is associated with an identity domain, process 917 returns an indication to confirm the user. In some examples, if process 917 returns an indication to confirm the user, device 800 then requests the user to confirm his identity (e.g., ask "do you be a name. In some examples, the name is determined based on previous inputs, and the device 800 knows the name of the user because the device has recently identified the user based on previous inputs. In some examples, if the user confirms his identity, the device 800 determines the identity (e.g., name) of the user. For example, if jessa previously said "i am jessa" to device 800, then the device may ask "you are jessa, is you to? "(instead of" who is you. If the jessary answers "yes," device 800 determines the identity of the jessary. In this way, the device 800 may not undesirably query the user again for identity, as the user may have just identified himself/herself.

If the previous input is not associated with an identity domain, process 917 proceeds to block 919. At block 919, device 800 determines whether the previous input includes an identity correction. For example, device 800 determines whether the previous input is associated with a user intent to correct the user identity. For example, assume that in a previous user-device interaction, device 800 incorrectly identified jessaca, e.g., a voice input "read my message" to jessaca, responded with "good, stephen, read your message". Thus, jessary may provide the input "no, i am jessary".

If the previous input includes an identity correction, process 917 returns an indication to confirm the user, as discussed above.

If the previous input does not include identity correction, process 917 proceeds to block 920. At block 920, device 800 provides an output requesting the user to identify himself, e.g., "do you tell me who you are? ". At block 920, device 800 also receives a voice input (e.g., "i are jessaca") responsive to the output and determines whether the voice input includes a name, as discussed above. If the voice input does not include a name (or otherwise does not indicate the identity of the user), device 800 provides a response to the voice input. For example, if device 800 asks "please complain me about who you are," and the user says "calculate bar," device 800 may output "good" and stop responding to the user.

If the voice input includes a name, process 917 proceeds to block 921. At block 921, the device 800 determines whether the name matches the name of the registered user. If the name matches the registered user's name, process 917 returns the registered user's identification. For example, if jessary says "i am jessary" and jessary is a registered user, process 917 will return the identity of jessary.

If the name does not match the name of the registered user, process 917 proceeds to block 922. At block 922, device 800 determines whether the voice input (received at block 903) is associated with a personal domain, as discussed above. In some examples, if the request is not associated with a personal domain, process 917 returns an identification of the name (e.g., the name does not match the name of the registered user) and an indication that the voice input is not associated with a personal domain.

If the voice input is associated with a personal domain, device 800 provides a response indicating that the user was not identified (e.g., "sorry, i don't determine who you are").

Returning to fig. 9C-9D (process 909), if block 916 returns an indication to confirm the user, process 917 repeats without performing blocks 918, 919, and/or 920. For example, process 917 proceeds directly to block 921 where device 800 determines whether the confirmed name (e.g., jessa confirms her name by answering "yes" to device 800 asking "you are jessa.

If block 916 returns the identity of the registered user, process 909 proceeds to block 923. At block 923, device 800 determines whether the identity of the registered user matches a reference to an entity included in the voice input (e.g., received at block 903). If the acquired identity of the registered user does not match the reference, process 909 returns an indication that user identification based on voice input is required and the digital assistant should initiate a task based on the reference.

As an example of the process 902 so far, assume jessa requires "read out a message of Nancy," where Nancy is not a registered user of device 800. Thus, the device 800 asks "do you tell me who you are? "Jessary responds to this with" I are Jessary "(e.g., process 917). The device 800 determines that "jessaca" does not match "Nancy". For example, jessa is requesting a message from Nancy to her. Thus, device 800 determines whether the voice input "read Nancy message" corresponds to Jessary, and if so, initiates the task of providing a Nancy to Jessary message.

If the acquired identity of the registered user matches the reference to the entity, then process 909 proceeds to block 924. At block 924, the device 800 determines that the speech input received at block 920 (e.g., "i are" names ") corresponds to a confidence level for the designation of the entity included in the speech input received at block 903.

If the confidence level is medium or high, the device 800 provides a response to the voice input received at block 903.

If the confidence is low, the process 909 proceeds to block 925. At block 925, the device 800 determines whether the user whose name was included in the voice input received at block 920 has recently confirmed his identity using his external electronic device, as discussed above. For example, prior to receiving voice input at block 920 or block 903, the device 800 determines whether the user has confirmed his identity within a predetermined duration (e.g., 5 seconds, 10 seconds, 15 seconds, 30 seconds, 60 seconds, 2 minutes, 5 minutes).

If the user has not recently confirmed his identity using his external electronic device, process 909 returns an indication that user confirmation is required. As discussed below with respect to fig. 9F, if user confirmation is required, the device 800 may attempt to confirm the identity of the user using the user's external electronic device. For example, suppose jessa says "read message of Harry" to device 800, where Harry is not a registered user of device 800. Thus, the device 800 asks "do you tell me who you are? "Jesseica responds to this with" I are Harry ". For example, jessa does not attempt to access a message from Harry that is of her own, but does not attempt to access a message from Harry. Device 800 determines that the voice input "i am Harry" corresponds to Harry with low confidence and further determines that Harry has not recently confirmed his identity using his external device. Thus, device 800 may cause Harry's external device to ask "do you read your message? ", harry may respond with a" no "to this. In this way, a user (e.g., jessaca) cannot undesirably access personal information (e.g., harry's message) of another user.

If the user has recently confirmed his identity using his external electronic device, device 800 provides a response to the voice input received at block 903.

Returning to fig. 9A-9B (process 902), if process 909 returns an indication that user recognition based on voice input is required, process 902 proceeds to block 932, as discussed below.

If process 909 returns an indication that user confirmation is required, process 902 proceeds to block 926. At block 926, process 927 (a sub-process of process 902) is performed.

Turning now to fig. 9F (process 927), at block 928, the device 800 determines a confidence that the speech input corresponds to a name (e.g., a user with a name). In some examples, the speech input is the speech input received at block 903. In some examples, the voice input is a voice input provided (e.g., at block 920) in response to a request for a user identity. In some examples, device 800 determines a name based on a voice input (e.g., "i are" name ") received at block 920 in response to an output indicating a request for a user identity.

If the confidence that the voice input corresponds to the name is medium or high, the device 800 provides a response to the voice input received at block 903.

If the confidence that the voice input corresponds to the name is low, process 927 proceeds to block 929. At block 929, device 800 determines a domain associated with the voice input received at block 903. In some examples, if the domain is a first type of domain (such as a device location domain), the device 800 provides a response indicating an error. For example, device 800 provides a response indicating that the user is not identified, such as "dumb, unlike your voice. In some examples, if the domain is a second type of domain (such as a domain associated with an executable intent to provide media content), the device 800 provides a response to the voice input received at block 903 (e.g., provides the media content). In some examples, if the domain is a third type of domain (such as a personal domain), then process 927 proceeds to block 930.

At block 930, device 800 causes the external electronic device to provide a confirmation request, as discussed above. In some examples, in block 928, the external electronic device is a device associated with the name (e.g., associated with a user having the name).

At block 931, the device 800 determines whether the user has acknowledged the acknowledgement request. For example, device 800 determines whether it has received an indication of user confirmation of the confirmation request. If the user has acknowledged the confirmation request, a response is provided to the voice input received at block 903, as shown in block 950. In some examples, device 800 provides a response. In some examples, the external electronic device provides the response. For example, suppose jessa speaks "read my message" to device 800 and then confirms the confirmation request "do you read your message? ". The device 800 and/or jessary handset may then provide jessary messages.

If the user does not acknowledge the confirmation request (e.g., responds to the confirmation request with a "no" or otherwise denies the request), process 927 ends (and 902). For example, device 800 does not provide any further response to the voice input received at block 903.

Returning to fig. 9A-9B, at block 932, device 800 identifies one or more users corresponding to the voice input received at block 903. For example, device 800 determines a respective likelihood that the voice input corresponds to each registered user and/or a likelihood that the voice input corresponds to a non-registered user. In some examples, at block 932, device 800 also determines a confidence that the voice input corresponds to each of the registered users and/or a confidence that the voice input corresponds to a non-registered user based on the determined likelihoods. In some examples, at block 932, device 800 determines that a plurality of possible users correspond to voice input.

In some examples, device 800 determines that there are more than two possible users. For example, device 800 determines that the voice input corresponds to each of the more than two users with at least a high confidence or mid-confidence, and/or that the more than two users cannot be distinguished from one another.

In some examples, device 800 determines that there are two (e.g., exactly two) possible users. For example, device 800 determines that the voice input corresponds to each of the two users with at least a high confidence level or mid-set confidence level and/or that the two users cannot be distinguished from one another.

In some examples, device 800 determines that there is one (e.g., exactly one) possible user. For example, device 800 determines that (1) the speech input corresponds to one user having the highest confidence level, (2) the speech input corresponds to one user having at least a medium confidence level or a high confidence level, and/or (3) one user may be distinguished from other users. As another example, device 800 determines that the one user is the only user for which a likelihood is determined.

In some examples, device 800 determines that there are no possible users (e.g., the voice input does not correspond to any user). For example, device 800 determines that it has low confidence that the voice input corresponds to any of the registered users.

If the device 800 determines that there are more than two possible users, the process 902 proceeds to block 933. At block 933, process 917 is performed, as discussed above. If process 917 returns an indication to confirm the user, process 902 proceeds to block 939, as discussed below. If process 917 returns an identification of a name and an indication that the voice input is not associated with a personal domain, device 800 provides a response to the voice input.

If process 917 returns the acquired identity of the registered user, process 902 proceeds to block 934 (process 927, as discussed above). For example, suppose Stephen speaks "hey, siri" to device 800, reads out my message. The device 800 determines that more than two possible users correspond to voice input. The device 800 then asks "do you tell me who you are? "Stephen responds to this with" I are Stephen ". The appliance 800 determines that "i am Stephen" corresponds to a message that Stephen has a high confidence (block 928) and thus provides Stephen.

If the device 800 determines that there are no possible users, the process 902 proceeds to block 935. At block 935, the device 800 determines whether the voice input received at block 903 is associated with a personal domain. If the voice input is associated with a personal domain, the device 800 provides an output indicating that the user is not identified, as shown in block 951. For example, in fig. 10F, a non-registered user speaks "read my message" to device 800. The device 800 responds with "i don't determine who you are, you can only do so on your cell phone".

If the voice input is not associated with a personal domain, the process 902 proceeds to block 936 (process 917, as discussed above). If block 936 returns an indication to confirm the user, the process 902 proceeds to block 939, as discussed below. If block 936 returns an identification of a name and an indication that the voice input is not associated with a personal domain, device 800 provides a response to the voice input.

If block 936 returns the acquired identity of the registered user, process 902 proceeds to block 937 (process 927, as discussed above).

If the device 800 determines that there are no possible users, the process 902 proceeds to block 938. At block 938, the device 800 determines whether the confidence that the speech input received at block 903 corresponds to a user is high, medium, or low.

If the confidence that the speech input corresponds to a user is high, the device 800 provides a response to the speech input, as shown in block 949. For example, assuming jessay says "remind me to buy vegetables" device 800 determines jessay is the only possible user and the voice input has a high confidence level for jessay. Thus, the device 800 creates a reminder entry of "tomorrow buy" in the reminder of jessa and outputs "good, jessa, i will remind you.

If the confidence that the speech input corresponds to one user is medium, the process 902 proceeds to block 939. At block 939, the device 800 requests the user to confirm his identity. For example, device 800 asks "do you be [ name ]? "where [ name ] is the name of a user. At block 939, the device 800 also determines whether the response to the request corresponds to a user (e.g., confirms the user). For example, device 800 determines whether the response comprises a positive response or a negative response.

If the device confirms the user, the device 800 provides a response to the voice input received at block 903. For example, assuming jessay says "remind me to buy vegetables" device 800 determines jessay is the only possible user and the voice input has a medium confidence corresponding to jessay. The device 800 then asks "you are jessaca, is you to? ", jessa answers" yes "to this. Thus, the device 800 creates a reminder entry of "tomorrow buy" in the reminder of jessa and outputs "good, jessa, i will remind you.

If the user does not confirm his name, process 902 proceeds to block 940 (process 917, discussed above). In some examples, if the user does not confirm his name, device 800 provides an output indicating an apostrophe (e.g., "don't care, me must have misidentified you").

If block 940 returns an indication to confirm the user, block 940 repeats without performing blocks 918, 919, and/or 920. For example, as discussed above, the device 800 determines whether the name corresponding to the request for the user to confirm its name in process 917 matches the name of the registered user (block 921). For example, suppose jessa speaks "read my voicemail" to device 800. The device 800 (incorrectly) determines that Stephen is the only possible user corresponding to the voice input and that the voice input has a medium confidence level corresponding to Stephen. The device 800 then asks "do you be Stephen, is you to? ", stephen replies no thereto. Then, device 800 determines that jessary previously tells device 800 that she is jessary, thus asking "do you be jessary, is you to? "(e.g., process 917 returns an indication to confirm the user). The jessay replies yes, and the device 800 then determines whether jessay is the name of the registered user (block 921).

If block 940 returns an identification of the name and an indication that the voice input is not associated with a personal domain, device 800 provides a response to the voice input received at block 903. For example, assume that non-registered user Joe speaks "play My music" to device 800. The device 800 (incorrectly) determines that Stephen is the only possible user corresponding to the voice input and that the voice input has a medium confidence level corresponding to Stephen. The device 800 then asks "do you be Stephen, is you to? ", joe reverts to no for this. Then, the device 800 asks "please complain me about who you are", and Joe replies to this "i am Joe". Device 800 determines that Joe is not a registered user and that voice input "play my music" is not associated with the personal domain. The device 800 thereby plays music (e.g., music from a default account associated with the device, as discussed below).

If block 940 returns the acquired identification of the registered user, process 902 proceeds to block 941 (process 927), as discussed above. For example, suppose jessa speaks "read my voicemail" to device 800. The device 800 (incorrectly) determines that Stephen is the only possible user corresponding to the voice input and that the voice input has a medium confidence level corresponding to Stephen. The device 800 then asks "do you be Stephen, is you to? ", jesseca replies to this as" no ". The device 800 then asks "do you tell me who you are? ", jessa replies to this" i am jessa ". The device 800 determines that the voice input "i am jessaca" has a high confidence level corresponding to jessaca. Thus, device 800 provides jessary voice mail.

If the confidence that the speech input corresponds to a user is low, the process 902 proceeds to block 942. At block 942, the device 800 determines whether a user has recently confirmed his identity using his external electronic device. For example, prior to receiving voice input at block 903, device 800 determines whether a user has recently confirmed his identity using his external electronic device within a predetermined duration (e.g., 5 seconds, 10 seconds, 15 seconds, 30 seconds, 60 seconds, 2 minutes, 5 minutes). If a user has recently confirmed his identity, device 800 provides a response to the voice input. For example, suppose jessa asks device 800 "what is my credit card balance? ". The device 800 determines that jessaca is the only possible user, but that the voice input has low confidence that corresponds to jessaca. However, device 800 determines that jessa has recently confirmed her identity using her external electronic device. Thus, device 800 provides a response such as "your credit card balance is $200".

If a user has not recently confirmed his identity, process 902 proceeds to block 933, as discussed above.

If the device 800 determines that there are two possible users, the process 902 proceeds to block 943. At block 943, the device 800 determines if there are more than two registered users. If there are more than two registered users, the process 902 proceeds to block 933.

If there are not more than two registered users, the process 902 proceeds to block 944. At block 944, the device 800 determines whether the non-registered user is one of two possible users.

If device 800 determines that the non-registered user is one of two possible users, process 902 proceeds to block 945 (process 917). If block 945 returns an indication to confirm the user, the process 902 proceeds to block 939. If block 945 returns an identification of the name and an indication that the voice input is not associated with a personal domain, device 800 provides a response to the voice input. If block 945 returns the acquired identity of the registered user, process 902 proceeds to block 946 (process 927).

If device 800 determines that the non-registered user is not one of two possible users, in some examples, process 902 proceeds to block 947. In other examples, process 902 proceeds to block 945.

At block 947, the device 800 provides an output requesting disambiguation of the user between two possible users and receiving a response to the output. In some examples, the output includes names of two possible users. At block 947, the device 800 also determines whether the response disambiguates between two possible users. For example, a response that includes "[ name ]" (where [ name ] is the name of one of two possible users) would disambiguate between the two possible users.

If the response is not disambiguated between two possible users, then the process 902 proceeds to block 933. For example, when "[ name ]" is not the name of one of two possible users, or in response to disambiguation between users for other reasons, the process 902 proceeds to block 933. For example, assume that Corey query device 800 "finds My phone". Device 800 incorrectly determines that jessaca and Stephen are two possible users corresponding to voice input. Thus, device 800 asks "whose handset, jessaca or Stephen", corey replies "none" to this. Thus, the device 800 may ask "do you tell me who you are? "(block 920 in process 917).

If the response does disambiguate between the two possible users, then process 902 proceeds to block 948 (process 927, as discussed above). For example, suppose Stephen interrogation device 800 "found my phone". Device 800 determines Stephen and jessa are two possible users corresponding to voice input. Thus, device 800 asks "who calls, stephen or jessa? "Stephen responds to this with" Stephen ". Thus, device 800 may provide the location of Stephen's phone, e.g., output "Stephen, your phone is in your office. "

5. Providing personalized media content

11A-11B illustrate a flow diagram of a process 1100 for providing media content according to some examples. Process 1100 is performed, for example, using device 800 and/or 900 or using any component thereof. In some examples, process 1100 is performed using a client-server system (e.g., 100) and the blocks of the process are partitioned in any manner between a server (e.g., DA server 106) and one or more client devices (e.g., 800 and 900). Thus, while portions of process 1100 are described herein as being performed by a particular device of a client-server system, it should be understood that the process is not so limited. In process 1100, some blocks are optionally combined, the order of some blocks is optionally changed, and some blocks are optionally omitted. In some examples, additional steps may be performed in connection with process 1100.

At block 1102, the device 800 receives a voice request. In some examples, the voice request includes a voice media request for media content (such as songs, albums, artists, videos, books, news, podcasts, playlists, stations, etc.). Exemplary requests for media content include "play my music", "play tab of Taylor Swift off", "play workout playlist", "what is news? "play wounded music", "play jessa music", "play THIS AMERICAN LIFE", "switch to NBC news", "play i favorite station", etc. In some examples, the voice media request includes a request to modify media content of the user, such as purchasing media content, adding/removing media content to/from a media collection (e.g., a playlist), switching content providers (e.g., news providers), subscribing to content providers, liking or disliking media content, or otherwise modifying media content associated with the user.

In some examples, the voice media request includes a name of the user (e.g., registered user). In some examples, the name is different from the name of the user providing the voice media request. For example, stephen in fig. 8 can say "play music of jessa". In this way, the user of device 800 may request media content associated with other registered users of the device.

In some examples, the voice media request includes a name of the media collection. In some examples, the media collection is associated with a different user than the user providing the voice media request. For example, if jessa has a playlist named "fitness" and Stephen does not, stephen can say "play fitness playlist". In this way, a user of device 800 may request a media collection associated with other users.

At block 1104, the device 800 determines whether the voice request includes a media request. For example, device 800 uses module 732 to determine whether the voice request corresponds to a media domain, e.g., a domain associated with an executable intent to provide and/or modify media content. If the device 800 determines that the voice request includes a media request (e.g., corresponding to a media domain), the process 1100 proceeds to block 1106. If device 800 determines that the voice request does not include a media request (e.g., does not correspond to a media domain), the voice request is processed as discussed above with respect to fig. 9A-9F.

At block 1106, the device 800 determines that a plurality of possible users correspond to the voice request in accordance with the techniques discussed above. For example, device 800 determines whether a user of the plurality of registered users corresponds to a voice request. In some examples, device 800 determines that a first user (e.g., exactly one user) of the plurality of registered users corresponds to the voice request. For example, device 800 determines that the voice request corresponds to the first user with a high confidence level, the first user has been distinguished from other registered users, and the voice request corresponds to the first user with the highest confidence level. In accordance with a determination that the first user corresponds to a voice request, process 1100 proceeds to block 1108.

At block 1108, device 800 provides a response to the voice request. In some examples, the response is personalized for the identified user (first user). In some examples, the response to the voice request includes one or more words indicating personalization of the identified user. For example, the response includes the name of the identified user and/or words such as "for you only", "you", "your person", and the like.

In some examples, the response to the voice request includes playing back a media item from a media account (e.g., a personal media account) associated with the user. A media account associated with a user includes media content that belongs to the user. In some examples, a media account is associated with the identified user. For example, as shown in fig. 10G, jessay says "play life of ED SHEERAN", and the device 800 recognizes jessay. Thus, device 800 plays a live version of the song "Perfect" included in the personal media account of Jesseica.

In some examples, providing a response to the voice request includes updating the media account. In some examples, a media account is associated with the identified user. In some examples, updating the media account includes modifying the user's media content, as discussed above. For example, if jessa says "add Shake it off to My exercise playlist," device 800 adds the song to jessa's exercise playlist. As another example, if jessay says "subscribe THIS AMERICAN LIFE", device 800 would update the personal media account of jessay to subscribe to podcast "THIS AMERICAN LIFE".

In some examples, updating the media account includes updating media preferences (e.g., media preferences of the identified user) based on the voice request. The media preferences indicate various user-specific media preferences such as favorite/dislike media content, favorite/dislike media types, number of plays of media content, skipped media content, and the like. The user's media preferences may be used to provide user-preferred media (e.g., when the user is identified). For example, if jessa says "shift it off to play Taylor shift", device 800 may increase the count of jessa play song "shift it off", update jessa's media preferences to indicate preferences for streaming music, and/or update media preferences to indicate preferences for Taylor shift. Thus, the next time a jessay requests media content, the device 800 may provide the media content based on the jessay updated preferences (e.g., biasing the media content toward popular music).

In some examples, updating the media preferences includes updating the content provider preferences based on the voice request. Content provider preferences indicate content providers (e.g., news sources, websites) that are preferred by the user. For example, when device 800 provides media content from a first content provider (e.g., fox news), jessa requests a switch to a second content provider (e.g., say "switch to CNN"). Device 800 then indicates that the content provider has been switched (e.g., outputs "good, which is some news from CNN" and/or provides news from CNN). In some examples, the device 800 further updates the content provider preferences of jessaca to the second content provider. Thus, when jessa subsequently requests news, device 800 provides a message from the updated content provider (e.g., CNN).

In some examples, the response to the voice request includes playing back a media item associated with a user other than the user providing the voice request. In some examples, device 800 obtains media items from media accounts associated with different users. For example, if Stephen speaks "play music of jessaca," and device 800 recognizes Stephen, device 800 retrieves and provides media content from the media account of jessaca.

In some examples, the response to the voice request includes playing back media items from a media collection associated with a user other than the user providing the voice request. In some examples, the device 800 obtains media items from media collections associated with different users. For example, if Stephen speaks "play workout playlist" and jessa is the only registered user with a playlist named "workout", device 800 plays media content from the jessa's "workout" playlist.

As discussed, the present disclosure contemplates allowing users to access media content associated with other users. Thus, it may be desirable for the device 800 to select the correct media account (associated with the correct user) from which to provide media content. Exemplary techniques for selecting a media account are now discussed.

In some examples, selecting the media account includes determining whether the requested media content matches media content in the media account or media database. For example, using the STT processing techniques discussed with respect to fig. 7A-7C, the device 800 determines a score indicating how well a voice request (or portion thereof) matches media content in a media account. If the score is high (e.g., greater than a threshold), the device 800 determines that the requested media is in the media account and/or provides best matching media content from the media account. If the score is low (e.g., less than the threshold), the device 800 determines that the requested media is not in the media account and/or does not provide media content from the media account. In some examples, words representing media content (e.g., song names, artist names, playlist names, subscription podcasts names, news provider names, etc.) of media accounts associated with registered users are included in the vocabulary 744. In some examples, the STT processing module 730 uses the vocabulary to determine the score, as discussed with respect to fig. 7A-7C.

In some examples, device 800 first determines whether the requested media content matches media content in a media account (personal media account) of the identified user. For example, the device 800 determines a score, as discussed above. In some examples, if the score is higher, the device 800 determines that the requested media content is in the media account of the identified user and provides the requested media content from the account. In some examples, if the score is low, the device 800 determines that the requested media content is not in the media account of the identified user and does not provide the requested media content from the account. For example, the personal media account of jessa includes the song "shift it off" of Taylor shift, so the score determined for the voice request "shift it off" of play Taylor shift of jessa may be higher.

In some examples, the device 800 determines whether the requested media content matches media content in a media database that is not associated with any particular user. In some examples, the media database includes a large amount of media content available through a media provider, such as Apple Music (from Apple inc.)SoundCloud, etc. In contrast, a media account associated with a particular user includes a limited amount of media content, such as media content selected by the user. In some examples, device 800 determines whether the requested media content matches content in the media database (e.g., by determining a score, as discussed above) in accordance with determining that the requested media content is not in the account of the identified user. In this way, the device 800 may first determine whether the personal media account of the identified user includes the requested content and, if not, whether the larger media database includes such content. For example, if jessa says "Hello plays Adele" and the personal account of jessa does not include the song "Hello," device 800 may provide (e.g., stream) the song from the media database.

In some examples, device 800 determines whether the requested media content matches media content in a default media account associated with device 800. In some examples, the default media account is a media account associated with a registered user of device 800 and is specified by the user during the setup process of device 800. In some examples, the default account subscribes to the media provider such that media content provided by the media provider is available to (e.g., included in) the default account. In some examples, device 800, in accordance with a determination that the requested media content is not in the media account of the identified user and/or in the media database, determines whether the requested media content matches media content in a default media account. For example, the device 800 determines the media content in the default account that best matches the requested media content and provides the best matching media content.

In some examples, device 800 determines whether the requested media content matches media content in a media account other than the media account of the identified user (other media accounts). In some examples, the other media account is a personal media account associated with another registered user of device 800. In some examples, device 800 determines whether the requested media content is in another media account in accordance with determining that the requested media content is not in the media account of the identified user and/or is not in the media database. For example, if the album requested by jessaca is not in its media account nor in the media database, but another registered user's account includes the album, device 800 may provide the album.

In some examples, the voice request includes the user's name (e.g., "play Stephen's playlist of workouts"). In some examples, in accordance with a determination that the voice request includes a name of the user, device 800 determines whether the requested media content matches media content in a media account associated with the user. In this way, the user may request media content from both his own media account and from the media accounts of other registered users. For example, if jessa says "play Stephen's workout playlist," device 800 may provide media content from Stephen's workout playlist.

Returning to block 1106, in some examples, device 800 determines that no user of the plurality of registered users corresponds to a voice request. For example, in accordance with the techniques discussed above, device 800 determines that any of the registered users have low confidence that they correspond to a voice request. In some examples, in accordance with a determination that none of the plurality of registered users corresponds to the voice request, device 800 foregoes updating any media preferences of any user based on the voice request.

At block 1110, in accordance with a determination that none of the plurality of registered users corresponds to a voice request, device 800 determines whether the voice request includes a personal request (e.g., a personal media request). In some examples, the personal request includes a request that the device 800 should highly trust that the request corresponds to a particular user performing an associated task. Exemplary personal requests include "add this to my playlist", "purchase this song", "subscribe to this podcast", "play my music", "play me favorite playlist", and so forth. In some examples, determining that the voice request includes a personal request includes determining that the voice request includes a request to modify media content of the user. In some examples, determining that the voice request includes a personal request includes determining that the voice request includes one or more words that indicate personalization. Exemplary words indicating personalization include registered user names, pronouns such as "me", "my", "his", "her" and words such as "personal", "personalization", "only for me" and "favorites". In some examples, determining that the voice request includes a personal request includes determining that the voice request is associated with a predetermined type of user intent (e.g., personal intent, semi-personal intent), as discussed above.

In accordance with a determination that the voice request includes a personal request, device 800 obtains an identification of a user providing the voice request at block 1112. For example, device 800 obtains the identity of the user using any of the techniques discussed above (other than identifying the user based on a voice request). For example, device 800 provides an output indicating a request for user identity, such as "who is you? ". In some examples, device 800 receives a voice input, such as "i am jessaca," in response to providing an output indicating a request for a user identity. In some examples, device 800 obtains an identification of a user (e.g., jessaca) based on voice input according to the techniques discussed above.

In some examples, device 800 provides a response to the voice request based on the acquisition identification, as shown in block 1108. In some examples, the response is personalized for the identified user.

In some examples, device 800 may not be able to obtain an identification of the user providing the voice user request. For example, the user may not respond to the output of device 800 indicating a request for the user identity for a predetermined duration. In some examples, device 800 determines that the user providing the voice user request is not a registered user. For example, the non-registered user Bob responds to the device 800 output "who is you? "say" I are Bob ". In some examples, process 1100 proceeds to block 1114 in accordance with failing to obtain the user's identification and/or in accordance with a determination that the user is not a registered user.

At block 1114, the device 800 (e.g., using module 732) determines whether the voice request includes a request to provide media content, such as providing a song, video, podcast, playlist, or the like. In some examples, in accordance with a determination that the voice request includes a request to provide media content, process 1100 proceeds to block 1116, as discussed below. In some examples, in accordance with a determination that the voice request does not include a request to provide media content, device 800 provides an output indicating an error, e.g., "don't care, i can only do so for registered users. "for example, if the device 800 determines that the voice request includes a request to modify the user's media content (media content is not provided), the device 800 provides an output indicating an error.

At block 1116, in accordance with a determination that the voice request does not include a personal request, the device 800 determines whether a first type of media account (e.g., a default account) is associated with the device. In some examples, in accordance with a determination that a first type of media account is associated with the device, the device 800 provides a response to the voice request, as shown in block 1118. In some examples, the response is based on a first type of media account. For example, device 800 provides media content from a default account that best matches the media content requested by the voice request. For example, in fig. 10H, the unregistered user speaks "play ED SHEERAN's Perfect" to the device 800 (not personal request). Thus, device 800 provides a certain version of the song "Perfect" (e.g., a studio version) from a default account associated with the device.

At block 1120, in accordance with a determination that the first type of media account is not associated with the electronic device, the device 800 provides a response to the voice request. In some examples, the response is based on a second type of media account different from the first type. In some examples, the second type of media account is a rollback account that is different from the default account. In some examples, the rollback account is selected by the device 800 (or by the media provider) from the registered user's media account and is the same account for each voice request. In some examples, the rollback account subscribes to a media provider (e.g., apple Music of Apple inc.) such that media content provided by the media provider is available to the rollback account. For example, if the device 800 is not associated with a default account, the device 800 provides media content from the rollback account that best matches the voice request.

In some examples, the voice request requests media content that is not in the default account. In such examples, if the media content in the rollback account matches the requested media content, for example, device 800 provides the media content from the rollback account even though the device has a default account. For example, if the user speaks "Poker Face of play Lady Gaga" and the default account associated with device 800 does not include the song, device 800 still provides the song from the rollback account.

In some examples, device 800 is not associated with a default account. In such examples, device 800 may provide media content from the rollback account that best matches the voice request (e.g., process 1100 proceeds from block 1110 to block 1120 without performing blocks 1116 or 1118). In some examples, device 800 provides media content from a media account associated with a recently identified user, for example, when device 800 determines that no registered user corresponds to a voice request and that the voice request does not include a personal request. In some examples, device 800 provides media content from a media account associated with the most frequently identified user, for example, when device 800 determines that no registered user corresponds to a voice request and that the voice request does not include a personal request.

Returning to block 1106, in some examples, device 800 determines that a plurality of users (possible users) of the plurality of registered users correspond to the voice request. For example, in accordance with the techniques discussed above, device 800 determines that the voice request corresponds to each possible user with a high confidence and/or determines that the possible users cannot be distinguished from one another.

In some examples, at block 1122, in accordance with a determination that the plurality of users correspond to a voice request, device 800 determines whether the voice request includes a personal request in accordance with the techniques discussed above. In some examples, in accordance with a determination that the voice media request does not include a personal request, process 1100 proceeds to block 1116, as discussed above.

At block 1124, in accordance with a determination that the voice media request comprises a personal request, the device 800 determines whether it is associated with a first type of media account (e.g., a default account). In some examples, in accordance with determining that device 800 is not associated with a first type of media account, process 1100 proceeds to block 1112, as discussed above.

At block 1126, in accordance with determining that the device 800 is associated with a media account of a first type, the device 800 determines whether the user associated with the media account of the first type is a possible user. In some examples, in accordance with a determination that the user associated with the first type of media account is a likely user, device 800 provides a response to the voice request, as shown in block 1128. In some examples, the response to the voice request is based on a media account of a first type. For example, device 800 provides media content from a first type of media account that best matches the voice request. For example, assume that jessay says "play my music" and device 800 cannot distinguish jessay from other registered users. However, device 800 determines that jessaca is the likely user corresponding to the voice request. Thus, device 800 provides media content from a personal media account of jessaca.

In some examples, in accordance with a determination that the user associated with the media account is not a likely user, process 1100 proceeds to block 1112, as discussed above.

In some examples, device 800 is not associated with a media account of a first type. In such examples, device 800 may determine whether a user associated with a second type of media account (e.g., a rollback account) is a possible user and/or provide a response to a voice request based on the second type of media account, similar to the techniques discussed above.

In some examples where device 800 is not associated with a media account of the first type, in accordance with a determination that the voice request includes a personal request (block 1122), device 800 determines whether the most recently identified user or the most frequently identified user is a likely user. In some examples, in accordance with a determination that the most recently identified user is a likely user, device 800 provides a response to the voice request based on a media account associated with the most recently identified user. In some examples, in accordance with a determination that the most frequently identified user is a likely user, device 800 provides a response based on the media account associated with the most frequently identified user. For example, assume that jessay says "add this song to my workout playlist" and device 800 cannot distinguish jessay from other registered users. However, device 800 determines jessary is the likely user and determines jessary to be the most frequently identified user. Thus, device 800 adds the currently playing song to the fitness playlist of jessaca.

6. Acquiring information to provide personalized response

As discussed, one aspect of the present technology includes providing a response that is personalized for the identified user. Exemplary techniques for obtaining information to provide personalized responses (e.g., personal information) will now be discussed.

Fig. 12 illustrates an exemplary system 1200 for acquiring personal information. System 1200 includes device 800, external device 900, and digital assistant server 1202. In some examples, system 1200 includes other external electronic devices (not shown) associated with other users (e.g., users other than the user associated with device 900). Other external electronic devices may be similar to device 900. For example, other external electronic devices are implemented as devices 400 or 600 and/or as modules and functions including a digital assistant.

In some examples, digital assistant server 1202 is implemented using system 108 of fig. 1, and device 800 and device 900 are in communication with server 1202, e.g., as shown in fig. 1. In some examples, device 800 obtains personal information from server 1202, device 900, other external electronic devices, or a combination or sub-combination thereof, in accordance with the techniques discussed below.

Each external electronic device stores personal information associated with a respective user. Exemplary personal information includes user's contact information (e.g., contact name, address, phone number), communication data and/or metadata (e.g., text message, email, call history, voice mail, instant message, message sender, message time), speaker profile and corresponding digital assistant identifiers (discussed below), calendar and/or reminder information (e.g., calendar items, reminder items), notes (e.g., user-created text memos and/or voice memos), media data (e.g., music, video, photos, audio books, media preferences (e.g., favorite songs, dislike songs), media account data), health data (e.g., travel distance, vital sign data, calories burned), financial data (e.g., credit card balance, bank account balance, recent purchases), application data (e.g., internet search history, installed applications, social media data (e.g., posts, friends list)), location data (e.g., locations of external devices), data associated with the user's home (e.g., number of locks, whether a thermostat is an on or off), and shortcut data.

In some examples, the external electronic device sends certain personal information to server 1202 and/or device 800. In some examples, the external electronic device sends such information only upon user approval (e.g., through user settings, through informed user approval). The sent personal information includes a speaker profile, information associated with the user's contacts (e.g., contact names), user calendar and/or reminder information (e.g., reminder list names), or a combination or sub-combination thereof.

In some examples, the user's speaker profile corresponds to (e.g., maps to) the digital assistant identifier. In some examples, the information sent to server 1202 also includes a digital assistant identifier. A digital assistant identifier is associated with the user and identifies an instance of the digital assistant associated with the user. For example, the digital assistant identifier "DA id #1" may identify an instance of the digital assistant associated with the first user (e.g., operating on the first user's device 900). In some examples, the digital assistant identifier associated with the user is determined by identifying the user using a speaker profile of the user (e.g., using a mapping between the speaker profile and the digital assistant identifier). The device 800 uses the digital assistant identifier to obtain personal information in accordance with techniques discussed below.

In some examples, device 800 obtains a digital assistant identifier associated with a user. In some examples, obtaining the digital assistant identifier includes receiving a voice input and identifying a user according to techniques described herein. For example, device 800 determines a likelihood that the received voice input corresponds to a registered user and sends the likelihood to server 1202. In some examples, device 800 sends the received voice input to server 1202. Based on the received likelihood and/or voice input, the server 1202 identifies the user according to the techniques discussed herein. In some examples, server 1202 determines a digital assistant identifier associated with the identified user (e.g., using a mapping between the identified user's speaker profile and the digital assistant identifier) and sends the digital assistant identifier to device 800. For example, as shown in step 1210, the device 800 obtains the digital assistant identifier "DA id #1" associated with the first identified user from the server 1202.

In some examples, device 800 determines a digital assistant identifier (e.g., without using server 1202). For example, based on the received voice input, device 800 identifies the user using the user's speaker profile in accordance with the techniques discussed herein. The device 800 then uses the mapping between the speaker profile of the identified user and the digital assistant identifier to determine, for example, the digital assistant identifier associated with the identified user.

In some examples, device 800 determines or obtains a digital assistant identifier associated with a user other than the identified user. For example, if the voice input includes a reference to a person (e.g., "where is my phone. For example, using STT processing module 730 and/or natural language processing module 732, server 1202 determines the name of the person (and thus their speaker profile) and determines the digital assistant identifier associated with the person (e.g., the mother of the user) based on a mapping between the speaker profile and the digital assistant identifier. In some examples, server 1202 then sends the digital assistant identifier to device 800.

In some examples, device 800 determines a communication identifier corresponding to the acquired digital assistant identifier. The communication identifier identifies a particular electronic device that is operating an instance of the digital assistant. In some examples, device 800 stores a mapping of digital assistant identifiers to communication identifiers and uses such mapping to determine the communication identifier corresponding to the acquired digital assistant identifier. For example, the device 800 obtains the digital assistant identifier "DA id #1" and determines the corresponding communication identifier "Com id #1" that identifies the device 900 (e.g., the device of the first user). In this way, device 800 can map the acquired digital assistant identifier associated with the user to a communication identifier that identifies the user device.

In some examples, using the communication identifier, device 800 establishes a communication session with the device identified by the communication identifier. For example, using the communication identifier "Com id #1", device 800 establishes a communication session with device 900, thereby enabling exchange of data and/or commands between the devices. In some examples, data and/or commands are exchanged via one or more of the communication protocols discussed above with respect to RF circuitry 208.

In some examples, steps 1220 and 1230 are performed according to establishing a communication session, as shown in fig. 12. In some examples, performing steps 1220 and 1230 enable device 800 to obtain personal information to provide a response personalized for the user.

At step 1220, the device 800 sends a command to an external device (e.g., 900). In some examples, the command requests the external device to perform an action associated with a task determined based on the received voice input. For example, server 1202 and/or device 800 determines tasks based on received voice input in accordance with the techniques discussed herein. In examples where the server 1202 determines a task, the server 1202 sends the determined task (e.g., executable instructions for performing the task) to the device 800. In some examples, device 800 determines a command based on the determined task and sends the command to an external device. For example, from the voice input "hey, siri, read my message" determines the task of getting the Stephen's message, and device 800 determines the command requesting device 900 (e.g., stephen's device) to provide the Stephen's message. As another example, "where is my phone? "determine task of obtaining the location of the external device associated with the mother of the identified user, and device 800 determines a command requesting the external device to provide its location.

In some examples, upon receiving a command, the external device performs an action requested by the command and provides a result based on the action to device 800. For example, at step 1230, the external device provides personal information to device 800. The device 800 receives the personal information and uses the personal information to provide a response that is personalized for the identified user, as discussed herein. For example, upon receiving a command requesting to provide a message of Stephen, the device 900 retrieves the message of Stephen and provides the message to the device 800. Using the received message, device 800 provides a response "good, stephen, read your message: first message: corey speaks 2 o' clock, for example, as shown in FIG. 8.

In some examples, device 800 receives personal information from server 1202. As discussed, in some examples, server 1202 stores a limited type and/or amount of personal information (e.g., reminder list names) associated with a user, while many personal information (e.g., message content) of a user may be stored on a corresponding device (e.g., 900) of the user. Thus, in examples where personal information stored on server 1202 is available to provide personalized responses, server 1202 sends the personal information to device 800 (e.g., with or without an external device that sent the personal information). For example, based on the received voice input, the server 1202 identifies the user and determines the task. Based on the identified user and the determined task, server 1202 determines user personal information applicable to the task and sends the personal information to device 800. For example, based on voice input (e.g., received by device 800)? The server 1202 identifies the user and determines the task of providing the name of the user's reminder list. The server 1202 determines the name of the reminder list for the identified user and provides the name to the device 800.

7. Process for responding to voice input

Fig. 13A-13G illustrate a process 1300 for responding to voice input according to various examples. Process 1300 is performed, for example, using one or more electronic devices implementing a digital assistant. In some examples, process 1300 is performed using a client-server system (e.g., system 100) and the blocks of process 1300 are partitioned in any manner between a server (e.g., DA server 106) and a client device. In other examples, the blocks of process 1300 are divided between a server and a plurality of client devices (e.g., mobile phone and smart watch). Thus, although portions of process 1300 are described herein as being performed by a particular device of a client-server system, it should be understood that process 1300 is not limited thereto. In other examples, process 1300 is performed using only a client device (e.g., user device 104) or only a plurality of client devices. In process 1300, some blocks are optionally combined, the order of some blocks is optionally changed, and some blocks are optionally omitted. In some examples, additional steps may be performed in connection with process 1300.

At block 1302, a plurality of speaker profiles for a plurality of users are received from one or more external electronic devices. In some examples, the plurality of speaker profiles includes a first speaker profile for a first user, the first speaker profile including a plurality of representations of the first user's voice, and a second speaker profile for a second user, the second speaker profile including a plurality of representations of the second user's voice. In some examples, at least one representation of a plurality of representations of a sound of a first user is determined based on a first utterance of the first user, wherein the first utterance is received by a first external electronic device of the one or more external electronic devices, and wherein the first external electronic device is associated with the first user. In some examples, at least one representation of a plurality of representations of a sound of a second user is determined based on a second utterance of the second user, wherein the second utterance is received by a second external electronic device of the one or more external electronic devices, and wherein the second external electronic device is associated with the second user.

At block 1304, natural language speech input is received (e.g., block 903).

At block 1306, a representation of the natural language speech input is determined, for example, using a speaker model, according to some examples.

At block 1308, a first likelihood that the natural language speech input corresponds to a first user of the plurality of users and a second likelihood that the natural language speech input corresponds to a second user of the plurality of users is determined based on comparing the natural language speech input to the plurality of speaker profiles (e.g., block 932). In some examples, the second likelihood is less than the first likelihood. In some examples, determining the first likelihood includes comparing a representation of the natural language speech input to each of a plurality of representations of the first user's voice, as shown in block 1310. In some examples, determining the second likelihood includes comparing the representation of the natural language speech input to each of a plurality of representations of the second user's voice, as shown in block 1312.

At block 1314, it is determined whether the first likelihood and the second likelihood are within a first threshold (e.g., a difference threshold) (e.g., block 932).

At block 1316, in some examples, it is determined whether the first likelihood is greater than a second threshold (e.g., an upper threshold) (e.g., block 938).

At block 1318, in accordance with a determination that the first likelihood and the second likelihood are not within the first threshold, a response to the natural language voice input is provided, the response being personalized to the first user (e.g., block 949). In some examples, providing the response is performed further in accordance with determining that the first likelihood is greater than the second threshold. In some examples, the natural language voice input includes a request to provide a message associated with the first user, and providing a response to the natural language voice input includes providing the message. In some examples, the natural language voice input includes a request to provide media, and providing a response to the natural language voice input includes providing media associated with the first user. In some examples, the natural language voice input includes a request to communicate with a contact associated with the first user (e.g., "call mom"), and providing a response to the natural language voice input includes providing an output indicating communication with the contact (e.g., "call mom is being made"). In some examples, the response to the natural language voice input includes a fourth name of the first user.

At block 1320, in some examples, in accordance with determining that the first likelihood and the second likelihood are within a threshold: an output is provided indicating a request for the user identity (e.g., blocks 920, 930, 939, and/or 947).

At block 1322, in some examples, a third natural language speech input is received (e.g., blocks 920, 939, and/or 947) in response to providing an output indicative of a request for a user identity.

At block 1324, in some examples, it is determined whether the third natural language voice input corresponds to the first user. In some examples, determining that the third natural language voice input corresponds to the first user includes determining that the third natural language voice input includes a name of the first user, as shown in block 1326 (e.g., blocks 920 and/or 921). In some examples, the output indicating the request for the user identity includes a request for the first user to confirm his identity, the request including the second name of the first user (e.g., block 939). In some examples, determining that the third natural language voice input corresponds to the first user includes determining that the third natural language voice input includes a positive response (e.g., block 939), as shown in block 1328. In some examples, the output indicating the request for the user identity includes a request for user disambiguation between the first user and the second user, the request including a third name of the first user and a name of the second user (e.g., block 947). In some examples, determining that the third natural language voice input corresponds to the first user includes determining that the third natural language voice input includes a third name of the first user (e.g., block 947), as shown in block 1330.

At block 1332, in some examples, in accordance with a determination that the third natural language voice input corresponds to the first user, a response to the natural language voice input is provided.

At block 1334, in some examples, in accordance with determining that the first likelihood and the second likelihood are within the threshold, a third external electronic device of the plurality of external electronic devices is caused to provide a confirmation request, the third external electronic device being associated with the first user (e.g., block 930).

At block 1336, in some examples, an indication of a user confirmation of the confirmation request is received from a third external electronic device (e.g., block 931).

At block 1338, in some examples, a response to the natural language voice input is provided (e.g., block 950) in accordance with receiving an indication of user confirmation of the confirmation request.

At block 1340, in some examples, it is determined whether the first likelihood is less than a third threshold (e.g., a lower threshold) (e.g., block 932).

At block 1342, in some examples, in accordance with a determination that the first likelihood is less than the third threshold, the providing of the response is aborted. In some examples, in accordance with a determination that the first likelihood is less than the third threshold, a response is provided indicating that the user was not identified, as shown in block 1344 (e.g., block 951). In some examples, the response to the natural language voice input is performed further in accordance with determining that the first likelihood is not less than a third threshold.

At block 1346, in some examples, a second natural language speech input is received.

At block 1348, in some examples, it is determined whether the second natural language voice input corresponds to the first user or the second user.

At block 1350, in some examples, in accordance with a determination that the second natural language voice input corresponds to the first user, the first speaker profile is updated based on the second natural language voice input. At block 1352, in some examples, in accordance with a determination that the second natural language voice input corresponds to the second user, a second speaker profile is updated based on the second natural language voice input.

At block 1354, in some examples, it is determined whether the natural language voice input includes a reference to a person (e.g., block 906).

At block 1356, in some examples, in accordance with a determination that the natural language voice input includes a reference to a person: a determination is made as to whether the reference to the person matches the fifth name of the first user (e.g., block 913).

At block 1358, in some examples, in accordance with a determination that the reference to the person matches the fifth name of the first user, a third response to the natural language voice input is provided, the third response being personalized to the first user (e.g., block 952). In some examples, providing the response to the natural language voice input is performed in accordance with a determination that the natural language voice input does not include a reference to a person.

At block 1360, a digital assistant identifier associated with the first user is acquired. In some examples, obtaining the digital assistant identifier includes providing a first likelihood to the external electronic device, as shown in block 1362. In some examples, obtaining the digital assistant identifier includes receiving the digital assistant identifier from the external electronic device, wherein the digital assistant identifier is determined by the external electronic device based on the first likelihood, as shown in block 1364.

At block 1366, in some examples, a communication identifier corresponding to the acquired digital assistant identifier is determined. The communication identifier identifies a fourth external electronic device of the plurality of external electronic devices, the fourth external electronic device being associated with the first user.

At block 1368, in some examples, a communication session is established with the fourth external electronic device using the communication identifier.

At block 1370, in some examples, data associated with a response to the natural language voice input is obtained from a fourth external electronic device in accordance with establishing the communication session. In some examples, providing the response to the natural language voice input is performed in accordance with retrieving data associated with the response to the natural language voice input.

At block 1372, in some examples, a determination is made whether to identify the user based on natural language speech input (e.g., block 905). In some examples, determining the first likelihood and the second likelihood is performed in accordance with a determination that the user is identified.

In some examples, determining whether to identify the user includes determining a user intent associated with the natural language voice input, as shown in block 1374. In some examples, determining whether to identify the user includes identifying the user based on determining that the intent includes a personal intent or a semi-personal intent, as shown in block 1376. In some examples, determining whether to identify the user includes determining not to identify the user based on determining that the intent includes a non-personal intent, as shown in block 1378.

At block 1380, in some examples, in accordance with a determination that the user is not identified, the provision of a response to the natural language voice input is abandoned.

At block 1382, in some examples, in accordance with a determination that the user is not identified, a second response to the natural language voice input is provided (e.g., block 953). In some examples, providing a response to the natural language voice input is performed in accordance with a determination to identify the user.

The operations described above with reference to fig. 13A-13G are optionally implemented by the components depicted in fig. 1-4, 6A-6B, 7A-7C, 8, 10A-10H, and 12. For example, the operations of process 1300 may be implemented by device 800, device 900, system 1200, or any combination or sub-combination thereof. It will be apparent to one of ordinary skill in the art how to implement other processes based on the components depicted in fig. 1-4, 6A-6B, 7A-7C, 8, 10A-10H, and 12.

8. Process for providing media content

Fig. 14A-14E illustrate a process 1400 for providing media content according to various examples. Process 1400 is performed, for example, using one or more electronic devices implementing a digital assistant. In some examples, process 1400 is performed using a client-server system (e.g., system 100) and the blocks of process 1400 are partitioned in any manner between a server (e.g., DA server 106) and a client device. In other examples, the blocks of process 1400 are divided between a server and a plurality of client devices (e.g., mobile phones and smart watches). Thus, while portions of process 1400 are described herein as being performed by a particular device of a client-server system, it should be understood that process 1300 is not so limited. In other examples, process 1400 is performed using only a client device (e.g., user device 104) or only a plurality of client devices. In process 1400, some blocks are optionally combined, the order of some blocks is optionally changed, and some blocks are optionally omitted. In some examples, additional steps may be performed in connection with process 1400.

At block 1402, a voice media request is received (e.g., block 1102).

At block 1404, a determination is made as to whether a user of the plurality of registered users corresponds to a voice media request (e.g., block 1106).

At block 1406, in accordance with a determination that a first user of the plurality of registered users corresponds to the voice media request, a first response to the voice media request is provided, the first response being personalized for the first user (e.g., block 1108). In some examples, the voice media request includes a name of a second user of the plurality of registered users. In some examples, a second user of the plurality of registered users is different from a first user of the plurality of registered users. In some examples, the first response to the voice media request includes playing back a media item associated with the second user. In some examples, the voice media request includes a name of a media collection associated with a third user of the plurality of registered users. In some examples, a third user of the plurality of registered users is different from the first user of the plurality of registered users. In some examples, the first response to the voice media request includes playing back media items from a media collection associated with a third user.

In some examples, the first response to the voice media request includes one or more words indicating personalization of the first user. In some examples, the one or more terms include a name of the first user. In some examples, the first response to the voice media request includes playing back a media item from a first media account associated with the first user. In some examples, providing the first response to the voice media request includes updating a second media account associated with the first user.

At block 1408, in some examples, in accordance with a determination that a first user of the plurality of registered users corresponds to a voice media request: the media preferences of the first user are updated based on the voice user request. In some examples, the voice media request includes a request to switch content providers. In some examples, the first response to the voice media request indicates that the content provider has been switched. In some examples, updating the media preferences of the first user includes updating the content provider preferences of the first user based on the voice media request, as shown in block 1410.

At block 1412, in some examples, in accordance with a determination that none of the plurality of registered users corresponds to the voice media request, updating any media preferences of any user based on the voice media request is relinquished.

At block 1414, in accordance with a determination that none of the plurality of registered users corresponds to a voice media request: a determination is made as to whether the voice media request includes a personal media request (e.g., block 1110).

In some examples, determining whether the voice media request includes a personal media request includes: the determination that the voice media request includes one or more words indicating personalization, as shown in block 1416. In some examples, determining whether the voice media request includes a personal media request includes: it is determined that the voice media request is associated with a predetermined type of user intent, as shown in block 1418.

At block 1420, in accordance with a determination that the voice media request includes a personal media request: an identification of a user providing a voice media request is obtained (e.g., block 1112). In some examples, obtaining an identification of a user providing a voice media request includes: in response to providing an output indicative of a request for a user identity, a voice input is received (block 1424) and an identification is obtained based on the voice input (block 1426) to provide an output indicative of the request for the user identity (block 1422).

At block 1428, according to the acquisition identity: a second response to the voice media request is provided, the second response being personalized for the user providing the voice media request (e.g., block 1108).

At block 1430, in some examples, in accordance with a determination that no user of the plurality of registered users corresponds to a voice media request and in accordance with a determination that the voice media request does not include a personal media request, a determination is made as to whether a first type of media account is associated with the electronic device (e.g., block 1116).

At block 1432, in some examples, in accordance with a determination that a first type of media account is associated with an electronic device: a third response to the voice media request is provided, the third response based on the first type of media account (e.g., block 1118).

At block 1434, in some examples, in accordance with a determination that the first type of media account is not associated with the electronic device: a fourth response to the voice media request is provided, the fourth response based on a second type of media account different from the first type (e.g., block 1120).

At block 1436, in some examples, it is determined that a plurality of the plurality of registered users correspond to a voice media request (e.g., block 1106).

At block 1438, in some examples, in accordance with a determination that the plurality of users correspond to a voice media request: a determination is made as to whether the voice media request includes a personal request (e.g., block 1122).

At block 1440, in some examples, in accordance with a determination that the voice media request includes a personal request: a determination is made as to whether a third type of media account is associated with the electronic device (e.g., block 1124).

At block 1442, in some examples, in accordance with a determination that a third type of media account is associated with the electronic device, a determination is made as to whether the user associated with the third type of media account is a user of the plurality of users (e.g., block 1126).

At block 1444, in some examples, in accordance with a determination that the user associated with the third type of media account is a user of the plurality of users, a fifth response to the voice media request is provided, the fifth response based on the third type of media account (e.g., block 1128).

At block 1446, in some examples, in accordance with a determination that the voice media request does not include a personal request: a sixth response to the voice media request is provided, the sixth response based on the media account associated with the electronic device (e.g., block 1118 or 1120).

The operations described above with reference to fig. 14A-14E are optionally implemented by the components depicted in fig. 1-4, 6A-6B, 7A-7C, 8, 10A-10H, and 12. For example, the operations of process 1400 may be implemented by device 800, device 900, system 1200, or any combination or sub-combination thereof. It will be apparent to one of ordinary skill in the art how to implement other processes based on the components depicted in fig. 1-4, 6A-6B, 7A-7C, 8, 10A-10H, and 12.

According to some implementations, a computer-readable storage medium (e.g., a non-transitory computer-readable storage medium) is provided that stores one or more programs for execution by one or more processors of an electronic device, the one or more programs including instructions for performing any of the methods or processes described herein.

According to some implementations, an electronic device (e.g., a portable electronic device) is provided that includes means for performing any of the methods and processes described herein.

According to some implementations, an electronic device (e.g., a portable electronic device) is provided that includes a processing unit configured to perform any of the methods and processes described herein.

According to some implementations, an electronic device (e.g., a portable electronic device) is provided that includes one or more processors and memory storing one or more programs for execution by the one or more processors, the one or more programs including instructions for performing any of the methods and processes described herein.

Some exemplary aspects of the disclosure will be described below.

Aspect 1. A method for responding to voice input, the method comprising:

At an electronic device having a memory and one or more processors:

Receiving a plurality of speaker profiles for a plurality of users from one or more external electronic devices;

receiving natural language voice input;

Determining based on comparing the natural language speech input to the plurality of speaker profiles:

The natural language speech input corresponding to a first user of the plurality of users; and

A second likelihood that the natural language speech input corresponds to a second user of the plurality of users, the second likelihood being less than the first likelihood;

Determining whether the first likelihood and the second likelihood are within a first threshold; and

In accordance with a determination that the first likelihood and the second likelihood are not within the first threshold:

providing a response to the natural language voice input, the response being personalized to the first user.

Aspect 2 the method of aspect 1, wherein the plurality of speaker profiles comprises:

a first speaker profile for the first user, the first speaker profile comprising a plurality of representations of sounds of the first user; and

A second speaker profile for the second user, the second speaker profile comprising a plurality of representations of sounds of the second user.

Aspect 3. The method according to aspect 2, wherein:

Determining at least one representation of the plurality of representations of the sound of the first user based on a first utterance of the first user, wherein the first utterance is received by a first external electronic device of the one or more external electronic devices, and wherein the first external electronic device is associated with the first user; and

At least one representation of the plurality of representations of the sound of the second user is determined based on a second utterance of the second user, wherein the second utterance is received by a second external electronic device of the one or more external electronic devices, and wherein the second external electronic device is associated with the second user.

Aspect 4. The method according to any one of aspects 2-3, further comprising:

determining a representation of the natural language speech input; and wherein:

determining the first likelihood includes comparing the representation of the natural language speech input with each of the plurality of representations of the sound of the first user; and

Determining the second likelihood includes comparing the representation of the natural language speech input with each of the plurality of representations of the sound of the second user.

Aspect 5 the method according to any one of aspects 2 to 4, further comprising:

receiving a second natural language speech input;

determining whether the second natural language voice input corresponds to the first user or the second user; and

In accordance with a determination that the second natural language voice input corresponds to the first user:

Updating the first speaker profile based on the second natural language voice input; and

In accordance with a determination that the second natural language voice input corresponds to the second user:

The second speaker profile is updated based on the second natural language voice input.

Aspect 6 the method of any one of aspects 1-5, further comprising:

it is determined whether the first likelihood is greater than a second threshold.

Aspect 7 the method of aspect 6, wherein providing the response is further based on the determination

Determining that the first likelihood is greater than the second threshold.

Aspect 8 the method of any one of aspects 1-7, further comprising:

in accordance with a determination that the first likelihood and the second likelihood are within the threshold:

providing an output indicative of a request for a user identity;

Receiving a third natural language speech input in response to providing said output indicative of said request for user identity;

Determining whether the third natural language voice input corresponds to the first user; and

In accordance with a determination that the third natural language voice input corresponds to the first user:

providing the response to the natural language speech input.

Aspect 9. The method of aspect 8, wherein:

determining that the third natural language voice input corresponds to the first user includes determining that the third natural language voice input includes a name of the first user.

Aspect 10. The method of aspect 8, wherein:

Said output indicating said request for user identity comprises a request for said first user to confirm its identity, said request comprising a second name of said first user; and is combined with

And is also provided with

Determining that the third natural language voice input corresponds to the first user includes determining that the third natural language voice input includes a positive response.

Aspect 11. The method of aspect 8, wherein:

the output indicating the request for user identity comprises a request for user disambiguation between the first user and the second user, the request comprising a third name of the first user and a name of the second user; and

Determining that the third natural language voice input corresponds to the first user includes determining that the third natural language voice input includes the third name of the first user.

Aspect 12 the method according to any one of aspects 1 to 11, further comprising:

Causing a third external electronic device of the plurality of external electronic devices to provide a confirmation request, the third external electronic device being associated with the first user;

receiving an indication of user confirmation of the confirmation request from the third external electronic device; and

Providing the response to the natural language voice input in accordance with the indication of receipt of user confirmation of the confirmation request.

Aspect 13. The method of any one of aspects 1-12, further comprising:

Determining whether the first likelihood is less than a third threshold; and

In accordance with a determination that the first likelihood is less than the third threshold:

discarding the provision of the response to the natural language speech input; and

Providing a response indicating an unidentified user; and

Wherein providing the response to the natural language speech input is performed further in accordance with determining that the first likelihood is not less than the third threshold.

Aspect 14 the method of any one of aspects 1-13, wherein the natural language speech is

The response to the voice input includes a fourth name of the first user.

Aspect 15. The method of any one of aspects 1-14, further comprising:

determining whether to identify a user based on the natural language voice input; and

Wherein determining the first and second likelihoods is performed in accordance with a determination to identify the user.

Aspect 16. The method of aspect 15, wherein determining whether to identify the user comprises:

Determining an intent of a user associated with the natural language voice input; and

Determining to identify the user in accordance with a determination that the intent includes a personal intent or a semi-personal intent; and

In accordance with a determination that the intent includes a non-personal intent, it is determined that the user is not identified.

Aspect 17 the method of any one of aspects 15 or 16, further comprising:

In accordance with a determination that the user is not identified:

Providing a second response to the natural language speech input,

Wherein providing the response to the natural language voice input is performed in accordance with a determination that the user is identified.

Aspect 18 the method according to any one of aspects 1 to 17, wherein:

The natural language voice input includes a request to provide a message associated with the first user; and

Providing the response to the natural language voice input includes providing the message.

Aspect 19 the method of any one of aspects 1-18, wherein:

The natural language voice input includes a request to provide media; and

Providing the response to the natural language voice input includes providing media associated with the first user.

Aspect 20 the method of any one of aspects 1-19, wherein:

the natural language voice input includes a request to communicate with a contact associated with the first user;

providing the response to the natural language voice input includes providing an output indicating communication with the contact.

Aspect 21 the method of any one of aspects 1-20, further comprising:

determining whether the natural language voice input includes a reference to a person;

In accordance with a determination that the natural language voice input includes the reference to the person:

determining whether the reference to the person matches a fifth name of the first user;

In accordance with a determination that the reference to the person matches the fifth name of the first user:

Providing a third response to the natural language voice input, the third response being personalized to the first user; and

Wherein providing the response to the natural language voice input is performed in accordance with a determination that the natural language voice input does not include the reference to the person. Aspect 22. The method of any one of aspects 1-21, further comprising:

Obtaining a digital assistant identifier associated with the first user;

Determining a communication identifier corresponding to the acquired digital assistant identifier, the communication identifier identifying a fourth external electronic device of the plurality of external electronic devices, the fourth external electronic device being associated with the first user;

establishing a communication session with the fourth external electronic device using the communication identifier; and

In accordance with establishing the communication session:

obtaining data associated with the response to the natural language voice input from the fourth external electronic device; and

Wherein providing the response to the natural language voice input is performed in accordance with receiving the data associated with the response to the natural language voice input.

Aspect 23 the method of aspect 22, wherein obtaining the digital assistant identifier comprises:

Providing the first possibility to an external electronic device; and

The digital assistant identifier is received from the external electronic device, wherein the digital assistant identifier is determined by the external electronic device based on the first likelihood. Aspect 24. An electronic device, comprising:

One or more processors;

a memory; and

One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs

The program includes instructions for:

receiving natural language voice input;

Aspect 25. A non-transitory computer readable storage medium storing one or more programs, the program comprising

The one or more programs include instructions, which when executed by one or more processors of an electronic device, cause the electronic device to:

receiving natural language voice input;

Based on entering the natural language speech input with the plurality of speaker profiles

Row comparison to determine:

determining whether the first likelihood and the second likelihood are within a first threshold;

And

According to the determination that the first likelihood and the second likelihood are not at the first threshold

Values within:

Aspect 26. An electronic device comprising means for:

receiving natural language voice input;

Row comparison to determine:

And

Values within:

Aspect 27. An electronic device, comprising:

One or more processors;

a memory; and

The program comprises instructions for performing the method according to any one of aspects 1 to 23. Aspect 28. A non-transitory computer readable storage medium storing one or more programs, the program comprising

The one or more programs include instructions, which when executed by one or more processors of an electronic device, cause the electronic device to perform the method of any of aspects 1-23.

Aspect 29. An electronic device, comprising:

means for performing the method of any one of aspects 1 to 23.

Aspect 30. A method for providing media content, the method comprising:

At an electronic device having a memory and one or more processors:

Receiving a voice media request;

determining whether a user of a plurality of registered users corresponds to the voice media request;

in accordance with a determination that a first user of the plurality of registered users corresponds to the voice media request:

providing a first response to the voice media request, the first response being personalized for the first user; and

In accordance with a determination that none of the plurality of registered users corresponds to the voice media request:

Determining whether the voice media request includes a personal media request;

In accordance with a determination that the voice media request includes a personal media request:

acquiring an identification of a user providing the voice media request; and

According to the identification: providing a second response to the voice media request, the second response being personalized for the user providing the voice media request.

Aspect 31. The method of aspect 30, further comprising:

In accordance with a determination that none of the plurality of registered users corresponds to the voice media request, and in accordance with a determination that the voice media request does not include a personal media request:

Determining whether a first type of media account is associated with the electronic device;

in accordance with a determination that the first type of media account is associated with the electronic device:

providing a third response to the voice media request, the third response based on the media account of the first type; and

In accordance with a determination that the first type of media account is not associated with the electronic device:

a fourth response to the voice media request is provided, the fourth response being based on a second type of media account different from the first type. Aspect 32 the method of any one of aspects 30 or 31, further comprising:

determining that a plurality of users of the plurality of registered users correspond to the voice media request;

In accordance with a determination that the plurality of users correspond to the voice media request:

A determination is made as to whether the voice media request includes a personal request.

Aspect 33 the method of aspect 32, further comprising:

in accordance with a determination that the voice media request includes a personal request:

Determining whether a third type of media account is associated with the electronic device; and

In accordance with a determination that the third type of media account is associated with the electronic device:

Determining whether a user associated with the media account of the third type is a user of the plurality of users; and

In accordance with a determination that the user associated with the media account of the third type is a user of the plurality of users, a fifth response to the voice media request is provided, the fifth response being based on the media account of the third type.

Aspect 34 the method of any one of aspects 32 or 33, further comprising:

in accordance with a determination that the voice media request does not include a personal request:

a sixth response to the voice media request is provided, the sixth response based on a media account associated with the electronic device.

Aspect 35 the method of any one of aspects 30-34, wherein the voice media is determined

Whether the request includes a personal media request includes:

determining that the voice media request includes one or more words indicating personalization. Aspect 36 the method of any one of aspects 30-35, wherein the voice media is determined

Whether the request includes a personal media request includes:

The voice media request is determined to be associated with an intent of a predetermined type of user.

Aspect 37 the method of any one of aspects 30-36, wherein the obtaining provides the speech

The identification of the user of a media request includes:

providing an output indicative of a request for a user identity;

receiving a voice input in response to providing the output indicative of the request for user identity; and

The identification is obtained based on the voice input.

Aspect 38 the method of any one of aspects 30-37, wherein:

the voice media request includes a name of a second user of the plurality of registered users;

the second user of the plurality of registered users is different from the first user of the plurality of registered users; and

The first response to the voice media request includes playing back a media item associated with the second user.

Aspect 39 the method of any one of aspects 30-38, wherein:

the voice media request includes a name of a media collection associated with a third user of the plurality of registered users;

The third user of the plurality of registered users is different from the first user of the plurality of registered users; and

The first response to the voice media request includes playing back media items from the media collection associated with the third user.

Aspect 40. The method of any one of aspects 30-39, further comprising:

in accordance with a determination of the first user and the voice media of the plurality of registered users

The volume request corresponds to:

updating media preferences of the first user based on the voice media request; and

In accordance with a determination that none of the plurality of registered users has requested the voice media

Corresponding to:

any media preferences of any user are forgone to be updated based on the voice media request.

Aspect 41. The method of aspect 40, wherein:

the voice media request includes a request to switch content providers;

The first response to the voice media request indicates that the content provider has been switched; and

Updating the media preferences of the first user includes updating content provider preferences of the first user based on the voice media request.

Aspect 42 the method of any one of aspects 30-41, wherein the voice media is

The first response to the request includes one or more words indicating personalization for the first user.

Aspect 43 the method of aspect 42, wherein the one or more terms include the

The name of the first user.

Aspect 44 the method of any one of aspects 1-43, wherein the voice media is

The first response to the request includes playback of a media item from a first media account associated with the first user.

Aspect 45 the method of any one of aspects 1-44, wherein providing the voice media

The first response to the volume request includes updating a second media account associated with the first user.

Aspect 46, an electronic device, comprising:

One or more processors;

a memory; and

The program includes instructions for:

Receiving a voice media request;

Determining whether the voice media request includes a personal media request;

acquiring an identification of a user providing the voice media request; and

Aspect 47. A non-transitory computer readable storage medium storing one or more programs, the program comprising

The one or more programs include instructions, which when executed by one or more processors of a first electronic device, cause the first electronic device to:

Receiving a voice media request;

in accordance with a determination that a first user of the plurality of registered users is engaged with the voice media

The corresponding steps are as follows:

Corresponding to:

Determining whether the voice media request includes a personal media request;

Acquiring an identification of a user providing the voice media request; and according to the obtaining of the identification: providing a second response to the voice media request, the second response being personalized for the user providing the voice media request.

Aspect 48. An electronic device comprising means for:

Receiving a voice media request;

Determining whether the voice media request includes a personal media request;

Aspect 49, an electronic device, comprising:

One or more processors;

a memory; and

One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising instructions for performing the method of any of aspects 30-45.

Aspect 50. A non-transitory computer-readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by one or more processors of an electronic device, cause the electronic device to perform the method of any of aspects 30-45.

Aspect 51. An electronic device, comprising:

Means for performing the method of any one of aspects 30-45.

The foregoing description, for purposes of explanation, has been described with reference to specific embodiments. However, the illustrative discussions above are not intended to be exhaustive or to limit the disclosure to the precise forms disclosed. Many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the techniques and their practical applications. Those skilled in the art will be able to best utilize the techniques and various embodiments with various modifications as are suited to the particular use contemplated.

While the present disclosure and examples have been fully described with reference to the accompanying drawings, it is to be noted that various changes and modifications will become apparent to those skilled in the art. It should be understood that such variations and modifications are considered to be included within the scope of the disclosure and examples as defined by the claims.

As described above, one aspect of the present technology is to collect and use available data from various sources to identify users to provide personalized responses. The present disclosure contemplates that in some examples, such collected data may include personal information data that uniquely identifies or may be used to contact or locate a particular person. Such personal information data may include demographic data, location-based data, telephone numbers, email addresses, tweet IDs, home addresses, data or records related to the health or wellness level of the user (e.g., vital sign measurements, medication information, exercise information), birth dates, or any other identifying or personal information.

The present disclosure recognizes that the use of such personal information data in the disclosed technology may be used to benefit users. For example, personal information data may be used to identify a user and provide information related to the identified user. Thus, the use of such personal information data enables the device to provide a personalized response. In addition, the present disclosure contemplates other uses for personal information data that are beneficial to the user. For example, health and fitness data may be used to provide insight into the overall health of a user, or may be used as positive feedback to individuals using technology to pursue health goals.

The present disclosure contemplates that entities responsible for collecting, analyzing, disclosing, transmitting, storing, or otherwise using such personal information data will adhere to established privacy policies and/or privacy practices. In particular, such entities should exercise and adhere to privacy policies and practices that are recognized as meeting or exceeding industry or government requirements for maintaining the privacy and security of personal information data. Such policies should be readily accessible to the user and should be updated as the collection and/or use of the data changes. Personal information from users should be collected for legal and reasonable use by entities and not shared or sold outside of these legal uses. In addition, such collection/sharing should be performed after informed consent is received from the user. Moreover, such entities should consider taking any necessary steps to defend and secure access to such personal information data and to ensure that others having access to the personal information data adhere to their privacy policies and procedures. In addition, such entities may subject themselves to third party evaluations to prove compliance with widely accepted privacy policies and practices. In addition, policies and practices should be adjusted to collect and/or access specific types of personal information data and to suit applicable laws and standards including specific considerations of jurisdiction. For example, in the united states, the collection or acquisition of certain health data may be governed by federal and/or state law, such as the health insurance flow and liability act (HIPAA); while health data in other countries may be subject to other regulations and policies and should be processed accordingly. Thus, different privacy practices should be maintained for different personal data types in each country.

In spite of the foregoing, the present disclosure also contemplates embodiments in which a user selectively prevents use or access to personal information data. That is, the present disclosure contemplates that hardware elements and/or software elements may be provided to prevent or block access to such personal information data. For example, in the case of collecting a user's speaker profile, the disclosed techniques may be configured to allow the user to choose to "opt-in" or "opt-out" to participate in the collection of personal information data during or at any time after the registration service. As another example, the user may choose not to provide the speaker profile (and/or other personal information). As another example, the user may choose to limit the length of time the speaker profile is maintained, or to prohibit the development of the speaker profile altogether. In addition to providing the "opt-in" and "opt-out" options, the present disclosure contemplates providing notifications related to accessing or using personal information. For example, the user may be notified that his personal information data will be accessed when the application is downloaded, and then be reminded again just before the personal information data is accessed by the application.

Further, it is an object of the present disclosure that personal information data should be managed and processed to minimize the risk of inadvertent or unauthorized access or use. Once the data is no longer needed, risk can be minimized by limiting the data collection and deleting the data. In addition, and when applicable, included in certain health-related applications, the data de-identification may be used to protect the privacy of the user. De-identification may be facilitated by removing a particular identifier (e.g., date of birth, etc.), controlling the amount or characteristics of data stored (e.g., collecting location data at a city level rather than an address level), controlling the manner in which data is stored (e.g., aggregating data among users), and/or other methods, where appropriate.

Thus, while the present disclosure broadly covers the use of personal information data to implement one or more of the various disclosed embodiments, the present disclosure also contemplates that the various embodiments may be implemented without accessing such personal information data. That is, various embodiments of the disclosed technology do not fail to function properly due to the lack of all or a portion of such personal information data. For example, a response to a user's voice input may be provided based on non-personal information data or absolute minimum amount of personal information, such as content requested by a device associated with the user, other non-personal information available to the device, or publicly available information.

Claims

1. A method for providing media content, the method comprising:

at an electronic device having one or more processors and memory:

Receiving a voice media request;

Determining whether the voice media request includes a personal media request;

acquiring an identification of a user providing the voice media request; and

2. The method of claim 1, further comprising:

a fourth response to the voice media request is provided, the fourth response being based on a second type of media account different from the first type.

3. The method of any of claims 1-2, further comprising:

4. A method according to claim 3, further comprising:

in accordance with a determination whether the voice media request includes a personal request:

5. The method of any of claims 3-4, further comprising:

A sixth response to the voice media request is provided, the sixth response being based on a media account associated with the electronic device.

6. The method of any of claims 1-5, wherein determining whether the voice media request comprises a personal media request comprises:

determining that the voice media request includes one or more words indicating personalization.

7. The method of any of claims 1-6, wherein determining whether the voice media request comprises a personal media request comprises:

The voice media request is determined to be associated with a predetermined type of user intent.

8. The method of any of claims 1-7, wherein obtaining the identification of the user providing the voice media request comprises:

providing an output indicative of a request for a user identity;

The identification is obtained based on the voice input.

9. The method of any one of claims 1-8, wherein:

10. The method of any one of claims 1-9, wherein:

11. The method of any of claims 1-10, further comprising:

in accordance with a determination that the first user of the plurality of registered users corresponds to the voice media request:

12. The method according to claim 11, wherein:

the voice media request includes a request to switch content providers;

13. The method of any of claims 1-12, wherein the first response to the voice media request includes one or more words indicating personalization for the first user.

14. The method of claim 13, wherein the one or more terms include a name of the first user.

15. The method of any of claims 1-14, wherein the first response to the voice media request includes playing back a media item from a first media account associated with the first user.

16. The method of any of claims 1-15, wherein providing the first response to the voice media request includes updating a second media account associated with the first user.

17. An electronic device, comprising:

One or more processors;

a memory; and

One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising instructions for performing the method of any of claims 1-16.

18. A computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by one or more processors of an electronic device, cause the electronic device to perform the method of any of claims 1-16.