JP2021144353A - Voice processing device, voice processing system, voice processing method and program - Google Patents

Abstract

To provide a voice processing device, a voice processing system, a voice processing method and a program, with which, when inputting data by voice having been measured with respect to an object, it is possible to immediately confirm the contents of items filled by voice input, even when there is a large number of input items.SOLUTION: Provided is a voice processing device for inputting data by voice. The voice processing device comprises: a first acquisition unit for acquiring the voice data of a voice command for inputting data by voice; a transmission unit for transmitting voice data and a request for voice recognition processing to a voice recognition service; a second acquisition unit for acquiring the recognition result of the voice recognition processing; a first specification unit for specifying from the recognition result an input item that is the object of input; a data input unit for inputting data included in the recognition result to the input region of the specified input item; and a movement unit for moving input items and input regions so that the specified input item and the input region filled with input data are displayed in the display region of a display device.SELECTED DRAWING: Figure 4

Description

The present invention relates to a voice processing device, a voice processing system, a voice processing method and a program.

Data input processing is performed in each field in which a worker inputs data obtained by measuring a specific object into a form or an information processing device. For example, in recent years, it has become common to measure suits or shirts on a semi-order basis and purchase one that suits one's body shape. In this case, it is difficult for the measuring worker to write the measured value on the form by himself / herself while performing the measuring work. Therefore, at present, another worker adopts the method of writing the measured value on the form. ing.

Recently, instead of manually writing such measured (measured) values on forms, etc., voice recognition technology is used to input the measured values to information processing devices such as tablet terminals by voice input. It is said.

Such a data input system using voice recognition technology includes a user device for acquiring the voice of a measuring worker and an input support management device, and the input support management device is a voice including a measurement item and a voice of a measurement value. Generates measurement information corresponding to the measurement item based on the voice recognition result data of The measurement information input support screen including the above is displayed on the display device, the measurement information received from the input support management device is displayed on the measurement information input support screen, and the user device is further attached to the measurement object. Character recognition processing is performed on the image data acquired by shooting the tag, and tag information such as product identification information, country of origin, and material included in the tag is generated, and the generated tag information is used as a measurement information input support screen together with the measurement information. The system displayed in is disclosed (for example, Patent Document 1).

However, the technique described in Patent Document 1 improves the accuracy of voice recognition, and there is no mention of an efficient display method of the screen when voice input is used. Furthermore, for example, when creating a suit in semi-order, there are multiple measurement items for the suit, and when displayed on an information processing device such as a tablet terminal, all the items can be displayed on the screen at once due to the large number of items. Because it is not possible, if you input voice for any item, you must manually scroll to display the item in order to check whether the item was input properly. There is a problem that the above trouble is generated. The problem is not limited to the measurement work scene, but may occur in any scene in which the operator inputs the data obtained by the measurement of a specific object to the information processing device or the like by voice input.

The present invention has been made in view of the above, and it is necessary to immediately confirm the contents of the items for which voice input has been performed even when the number of input items is large when the data measured for the object is input by voice. It is an object of the present invention to provide a voice processing device, a voice processing system, a voice processing method and a program capable of improving work efficiency.

In order to solve the above-mentioned problems and achieve the object, the present invention is a voice processing device for inputting data by voice, and a first acquisition unit for acquiring voice data of a voice command for inputting the data by voice. And the transmission unit that transmits the voice data acquired by the first acquisition unit and the request for voice recognition processing for the voice data to the voice recognition service, and the recognition result of the voice recognition processing from the voice recognition service. The second acquisition unit to be acquired, the first specific unit that specifies an input item to be input to the data from the recognition result acquired by the second acquisition unit, and the first specific unit specified by the first specific unit. In the input area of the input item, the data input unit for inputting the voice-recognized data included in the recognition result, the input item specified by the first specific unit, and the data input by the data input unit. The input area is provided with an input item and a moving unit for moving the input area so that the input area is displayed in the display area of the display device.

According to the present invention, even when the number of input items is large when the data measured for an object is input by voice, the contents of the items for which voice input is performed can be immediately confirmed, thereby improving work efficiency. be able to.

FIG. 1 is a diagram showing an example of the overall configuration of the voice processing system according to the embodiment. FIG. 2 is a diagram showing an example of the hardware configuration of the user terminal according to the embodiment. FIG. 3 is a diagram showing an example of the hardware configuration of the business service according to the embodiment. FIG. 4 is a diagram showing an example of a functional block configuration of the voice processing system according to the embodiment. FIG. 5 is a diagram illustrating a measurement target. FIG. 6 is a diagram illustrating a configuration of a voice command. FIG. 7 is a diagram showing an example of the application screen of the measuring application. FIG. 8 is a diagram showing an example of the rule information URL table. FIG. 9 is a diagram showing an example of a rule information table. FIG. 10 is a diagram illustrating an operation in which a recognition result of voice recognition is generated from a voice command. FIG. 11 is a diagram showing an example of the reservation information table. FIG. 12 is a sequence diagram showing an example of the flow of initial processing of the voice processing system according to the embodiment. FIG. 13 is a diagram showing an example of a group ID input screen. FIG. 14 is a sequence diagram showing an example of the flow of voice input processing of the voice processing system according to the embodiment. FIG. 15 is a diagram illustrating a data flow of the voice processing system according to the embodiment. FIG. 16 is a flowchart showing an example of the flow of item input / display adjustment processing of the user terminal related to the execution liquid. FIG. 17 is a diagram illustrating an operation of moving an item for which a numerical value has been input by an item input / display adjustment process. FIG. 18 is a diagram illustrating an operation when a dimension correction value is input by a voice command. FIG. 19 is a diagram illustrating an operation when a tab is switched by a voice command and a dimension value is input. FIG. 20 is a diagram illustrating a data flow of the voice processing system according to the modified example.

Hereinafter, the voice processing apparatus, the voice processing system, the voice processing method, and the program according to the present invention will be described in detail with reference to the accompanying drawings. Further, the present invention is not limited by the following embodiments, and the components in the following embodiments include those easily conceived by those skilled in the art, substantially the same, and so-called equivalent ranges. Is included. Furthermore, various omissions, substitutions, changes and combinations of components can be made without departing from the gist of the following embodiments.

In addition, computer software refers to programs related to computer operations and other information used for processing by computers that are equivalent to programs (hereinafter, computer software is referred to as software). Application software is a general term for software used to perform a specific task in the classification of software. On the other hand, the operating system (OS) is software for controlling a computer and making computer resources available to application software and the like. The operating system performs basic computer management and control, such as input / output control, hardware management such as memory and hard disk, and process management. The application software operates by utilizing the functions provided by the operating system. Hereinafter, the application software (application) may be simply referred to as an "application". A program is a command to a computer that is combined so that one result can be obtained. In addition, a program-like thing cannot be called a program because it is not a direct command to the computer, but it has properties similar to a program in that it regulates the processing of the computer. For example, the data structure (the logical structure of data represented by the interrelationship between data elements) corresponds to a program.

The voice processing system according to the present embodiment can be widely applied to a process of inputting data obtained by a worker by measuring a specific object to an information processing device or the like by voice. , The case where the measured value (an example of measurement) is input by voice to clothes (suit, trousers, vest, shirt, etc.) will be described as an example.

(Overall configuration of voice processing system)
FIG. 1 is a diagram showing an example of the overall configuration of the voice processing system according to the embodiment. The overall configuration of the voice processing system 1 according to the present embodiment will be described with reference to FIG.

The voice processing system 1 shown in FIG. 1 is a system in which a value measured for clothes is input to the user terminal 10 by voice by voice recognition for a voice command from an operator. As shown in FIG. 1, the voice processing system 1 includes a user terminal 10, a voice terminal 20, a business service 30, a call service 40, a voice recognition service 50, and an information management service 60.

The user terminal 10 is an information processing device that displays a measurement value as voice input data based on the recognition result of voice recognition performed by the voice recognition service 50 for voice data of a voice command input to the voice terminal 20. (An example of a voice processing device). As shown in FIG. 1, the user terminal 10 has the call application 11 and the browser 12 installed. The user terminal 10 is an information processing device such as a PC (Personal Computer), a notebook PC, a smartphone or a tablet terminal, but will be described as being a tablet terminal in the present embodiment.

The call application 11 is an application for realizing a call between information terminals including the user terminal 10 in cooperation with the call service 40. The browser 12 is software that receives and interprets Web contents (Web page, Web application 13, etc.) from the Web server 31 of the business service 30 described later, and performs various processing and display processing. The Web application 13 is a Web application as Web content provided from the Web server 31 to the browser 12, and includes a script created by Javascript (registered trademark) or the like for execution on the user terminal 10.

The voice terminal 20 is a hearable device capable of inputting a worker's voice and wirelessly transmitting the voice as voice data to the user terminal 10.

The business service 30 is a service (for example, a cloud service) that relays the voice data input from the voice terminal 20 to the user terminal 10 via the call service 40. Further, the business service 30 stores rule information for interpreting a voice command input from the voice terminal 20. The business service 30 is realized by one or a plurality of server devices, but in the present embodiment, it will be described as being realized by one server device. The same applies to the call service 40, the voice recognition service 50, and the information management service 60.

The call service 40 is a service (for example, a cloud service) that realizes a call between information terminals including the user terminal 10 in cooperation with the call application 11 installed on the user terminal 10. Further, the call service 40 manages a group ID for realizing a call between a plurality of information terminals in a group unit.

The voice recognition service 50 is a service (for example, a cloud service) that executes voice recognition processing on input voice data to convert it into text. In particular, in the present embodiment, the voice recognition service 50 identifies the keyword by using the rule information acquired from the business service 30 for the voice command which is the input voice data, and extracts the numerical value from the part following the keyword. It is converted into text, and the identification information that identifies the keyword and the textualized numerical value are output as the recognition result.

The information management service 60 is a service (for example, a cloud service) that manages reservation information including customer information to be measured and measurement values input by voice.

The voice processing system 1 is not limited to including all of the user terminal 10, the voice terminal 20, the business service 30, the call service 40, the voice recognition service 50, and the information management service 60, and performs the core processing of the voice input processing. It can also be regarded as a system including a responsible part (for example, a user terminal 10 and a business service 30).

(Hardware configuration of user terminal)
FIG. 2 is a diagram showing an example of the hardware configuration of the user terminal according to the embodiment. The hardware configuration of the user terminal 10 according to the present embodiment will be described with reference to FIG.

As shown in FIG. 2, the user terminal 10 includes a CPU (Central Processing Unit) 801, a ROM (Read Only Memory) 802, a RAM (Random Access Memory) 803, and an EEPROM (Electrically Memory) 80 Be prepared.

The CPU 801 is an arithmetic unit that controls the operation of the entire user terminal 10. The ROM 802 is a non-volatile storage device that stores programs used for driving the CPU 801 such as the CPU 801 and the IPL (Initial Program Loader). The RAM 803 is a volatile storage device used as a work area of the CPU 801. The EEPROM 804 is a storage device that reads or writes various data such as a program for the user terminal 10 under the control of the CPU 801.

Further, the user terminal 10 includes a CMOS (Complementary Metal Oxide Sensor) 805, an image sensor I / F806, an acceleration / orientation sensor 807, a media I / F809, and a GPS (Global Positioning System) receiving unit 811. ..

The CMOS 805 is a built-in image sensor that captures an image of a subject and obtains image data under the control of the CPU 801. Instead of CMOS805, a CCD (Charge Coupled Device) image sensor may be used. The image sensor I / F806 is an interface circuit that controls the drive of the CMOS805.

The acceleration / orientation sensor 807 is a variety of sensors such as an electronic magnetic compass, a gyro compass, or an acceleration sensor that detects the geomagnetism. The media I / F809 is an interface circuit that controls reading or writing (storage) of data to a recording medium 808 such as a flash memory. The GPS receiving unit 811 is a device that receives GPS signals from GPS satellites.

Further, the user terminal 10 includes a long-distance communication circuit 812, an antenna 812a, a microphone 815, a speaker 816, a sound input / output I / F 817, a display 818, an external device connection I / F 819, and a short-range communication circuit. It includes an 820, an antenna 820a, and a touch panel 821.

The telecommunications circuit 812 is a circuit that communicates with other devices by the antenna 812a via a communication network. The microphone 815 is a built-in sound collecting device that converts sound into an electric signal. The speaker 816 is a built-in circuit that converts an electric signal into physical vibration to generate sounds such as music and voice. The sound input / output I / F 817 is an interface circuit that processes audio data input / output between the microphone 815 and the speaker 816 under the control of the CPU 801.

The display 818 is a liquid crystal display device or an organic EL (Electroluminescence) display device that displays an image of a subject, various icons, and the like. The external device connection I / F819 is an interface circuit for connecting various external devices to perform data communication.

The short-range communication circuit 820 is a communication circuit such as NFC (Near Field Communication) or Bluetooth (registered trademark), and wirelessly communicates with an external device via the antenna 820a. In the present embodiment, the short-range communication circuit 820 will be described as including at least a Bluetooth communication circuit.

The touch panel 821 is a kind of input device for operating the user terminal 10 by the user touching the display 818.

Further, the user terminal 10 includes a bus 810. The bus 810 is an address bus, a data bus, or the like for electrically connecting each component such as the CPU 801 shown in FIG.

The hardware configuration of the user terminal 10 shown in FIG. 2 is an example, and it is not necessary to include all the components shown in FIG. 2, or it may include other components.

(Hardware configuration of business services)
FIG. 3 is a diagram showing an example of the hardware configuration of the business service according to the embodiment. The hardware configuration of the business service 30 according to the present embodiment will be described with reference to FIG.

As shown in FIG. 3, the business service 30 includes a CPU 901, a ROM 902, a RAM 903, an auxiliary storage device 905, a media drive 907, a display 908, a network I / F 909, a keyboard 911, a mouse 912, and the like. It includes a DVD (Digital Versailles Disc) drive 914 and the like.

The CPU 901 is an arithmetic unit that controls the operation of the entire business service 30. The ROM 902 is a non-volatile storage device that stores a program for the business service 30. The RAM 903 is a volatile storage device used as a work area of the CPU 901.

As described above, the auxiliary storage device 905 stores non-volatile storage such as an HDD (Hard Disk Drive) or SSD (Solid State Drive) that stores rule information and the like for interpreting voice commands input from the voice terminal 20. It is a device. The media drive 907 is a device that controls reading and writing of data to a recording medium 906 such as a flash memory according to the control of the CPU 901.

The display 908 is a display device composed of a liquid crystal display, an organic EL, or the like that displays various information such as a cursor, a menu, a window, characters, or an image.

The network I / F 909 is an interface for data communication with an external device or system such as a user terminal 10, a call service 40, a voice recognition service 50, and an information management service 60 using a network. The network I / F909 is, for example, a NIC (Network Interface Card) or the like that supports Ethernet (registered trademark) and is capable of communication conforming to TCP (Transmission Control Protocol) / IP (Internet Protocol) or the like.

The keyboard 911 is an input device for selecting characters, numbers, various instructions, moving a cursor, and the like. The mouse 912 is an input device for selecting and executing various instructions, selecting a processing target, moving a cursor, and the like.

The DVD drive 914 is a device that controls reading and writing of data to a DVD 913 such as a DVD-ROM or a DVD-R (Digital Versatile Disc Recordable) as an example of a removable storage medium.

The CPU 901, ROM 902, RAM 903, auxiliary storage device 905, media drive 907, display 908, network I / F 909, keyboard 911, mouse 912 and DVD drive 914 described above can communicate with each other by a bus 910 such as an address bus and a data bus. It is connected.

The hardware configuration of the business service 30 shown in FIG. 3 is an example, and it is not necessary to include all the components shown in FIG. 3, or other components may be included. For example, when specializing in processing as a business service 30 and not requiring input / output of data directly from an input / output device to the business service 30, the business service 30 does not include a display 908, a keyboard 911, and a mouse 912. You may. Further, the business service 30 is not limited to being composed of a single information processing device (server device) shown in FIG. 3, but is composed of a plurality of network devices such as a plurality of information processing devices. May be good.

Further, the hardware configuration shown in FIG. 3 has been described as assuming that it is the hardware configuration of the business service 30, but the hardware configurations of the call service 40, the voice recognition service 50, and the information management service 60 are also shown in FIG. Follow the hardware configuration shown.

(Configuration and operation of functional blocks of voice processing system)
FIG. 4 is a diagram showing an example of a functional block configuration of the voice processing system according to the embodiment. FIG. 5 is a diagram illustrating a measurement target. FIG. 6 is a diagram illustrating a configuration of a voice command. FIG. 7 is a diagram showing an example of the application screen of the measuring application. FIG. 8 is a diagram showing an example of the rule information URL table. FIG. 9 is a diagram showing an example of a rule information table. FIG. 10 is a diagram illustrating an operation in which a recognition result of voice recognition is generated from a voice command. FIG. 11 is a diagram showing an example of the reservation information table. The functional block configuration and operation of the voice processing system 1 according to the present embodiment will be described with reference to FIGS. 4 to 11. The network 2 shown in FIG. 4 may include various LANs (Local Area Networks), leased lines, and the Internet, and may be wired or wireless.

As shown in FIG. 4, the voice terminal 20 has a voice receiving unit 201 and a communication unit 202.

The voice receiving unit 201 receives a voice command uttered by a worker (measurer) to input a measured value to clothes (suit, trousers, vest, shirt, etc.) by voice and converts it into voice data. It is a functional part. Here, FIG. 5 shows an example of measurement items of a suit jacket as an example of a measurement target. As shown in FIG. 5A, the measurement items include "shoulder width", "width of the body" which is the straight line distance under the bases of both sleeves, "sleeve width" which is the distance measured at right angles from the bases of the sleeves, and sleeves. There are "sleeve length" which is the length and "cuff width" which is the width of the cuffs. In addition, as shown in FIG. 5 (b), as a measurement item, the linear distance from the back neck point to the tip of the hem, which is the position of the spine that pops out when the neck at the base of the back of the neck is tilted forward, is used. There is a certain "length" etc.

Further, in the present embodiment, FIG. 6 shows an example configuration of a voice command for inputting a measurement value to the user terminal 10 by voice. As shown in FIG. 6, the voice command for voice input has a configuration in which a keyword and a numerical value (measurement value) are combined. For example, when the value measured for the sleeve length on the right side of the jacket is "23", the worker utters "Sodetake Migi Nijusan" (sleeve length right, 23) as a voice command.

The voice command shown in FIG. 6 is a voice command for inputting a measurement value by voice, but there is also a voice command for switching tabs in the measurement application which is the Web application 13, which will be described later.

The communication unit 202 is a functional unit that transmits the voice data of the voice command converted by the voice reception unit 201 to the user terminal 10 by wireless communication by Bluetooth or the like.

As shown in FIG. 4, the user terminal 10 includes a first communication unit 101, a second communication unit 102, an input unit 103, a voice communication control unit 104, an authentication request unit 105, and a connection request unit 106. Recognizing the reservation information acquisition unit 107, the voice acquisition unit 108 (first acquisition unit), the display content identification unit 109 (second specific unit), the rule information identification unit 110, and the voice transmission unit 111 (transmission unit). Result acquisition unit 112 (second acquisition unit), input item identification unit 113 (first identification unit), position determination unit 114 (determination unit), and display control unit 115 (data input unit, moving unit, highlighting unit). ), An input information transmission unit 116, and a storage unit 117.

The first communication unit 101 is a functional unit that transmits / receives data (mainly receives voice data) to / from the voice terminal 20 by wireless communication such as Bluetooth. The first communication unit 101 is realized by executing a program by the CPU 801 shown in FIG. 2 and by the short-range communication circuit 820 and the antenna 820a.

The second communication unit 102 is a functional unit that performs data communication with the business service 30, the call service 40, and the voice recognition service 50 via the network 2. The second communication unit 102 is realized by executing a program by the CPU 801 shown in FIG. 2 and by the telecommunications circuit 812 and the antenna 812a.

The input unit 103 is a functional unit that receives an operation input from an operator. The input unit 103 is realized by the touch panel 821 shown in FIG.

The voice communication control unit 104 transmits the voice data received from the voice terminal 20 by the first communication unit 101 to the call service 40 via the second communication unit 102 together with the group ID of the group in which the worker makes a call ( It is a functional unit that controls the operation of relaying. The voice communication control unit 104 is realized by executing a program (call application 11) by the CPU 801 shown in FIG.

The authentication request unit 105 is a functional unit that transmits a request for authentication processing for a worker to log in when using the user terminal 10 to the business service 30 via the second communication unit 102. The authentication request unit 105 is realized, for example, by executing a program (Web application 13 running on the browser 12) by the CPU 801 shown in FIG.

The connection requesting unit 106 connects to the call service 40 via the business service 30 including the group ID of the group in which the worker makes a call for the call realized by the cooperative operation between the call application 11 and the call service 40. It is a functional part that sends a request. The connection request unit 106 is realized, for example, by executing a program (Web application 13 running on the browser 12) by the CPU 801 shown in FIG.

The reservation information acquisition unit 107 is a functional unit that acquires reservation information about the measuring work from the information management service 60 via the business service 30. The reservation information acquisition unit 107 is realized, for example, by executing a program (Web application 13 running on the browser 12) by the CPU 801 shown in FIG.

The voice acquisition unit 108 is a functional unit that acquires voice data of the voice uttered by the worker from the business service 30 via the second communication unit 102. Specifically, the voice uttered by the operator is collected (received) by the voice receiving unit 201 of the voice terminal 20 and received as voice data by the first communication unit 101 of the user terminal 10 via the communication unit 202. Will be done. Then, the voice communication control unit 104 of the user terminal 10 transmits the voice data received by the first communication unit 101 to the call service 40 via the second communication unit 102. The call control unit 402 of the call service 40 transmits the voice data received from the user terminal 10 by the communication unit 401 to the business service 30 via the communication unit 401. The communication unit 301 of the business service 30 transmits the voice data received from the call service 40 to the user terminal 10, and the voice data is acquired by the voice acquisition unit 108 via the second communication unit 102. The voice acquisition unit 108 is realized, for example, by executing a program (Web application 13 running on the browser 12) by the CPU 801 shown in FIG.

When the voice data is acquired by the voice acquisition unit 108, the display content specifying unit 109 sets the input item of which tab on the screen of the measurement application which is the Web application 13 displayed on the display 818 by the display control unit 115. It is a functional part that identifies whether it is displayed. The display content specifying unit 109 is realized, for example, by executing a program (Web application 13 running on the browser 12) by the CPU 801 shown in FIG.

The rule information specifying unit 110 stores a rule information URL (Uniform Resource Locator) as shown in FIG. 8 stored in the storage unit 117 in order to specify the rule information corresponding to the tab specified by the display content specifying unit 109. It is a functional part that refers to the table and specifies the URL of the rule information corresponding to the tab. That is, the rule information specifying unit 110 specifies the rule information by specifying the URL of the rule information corresponding to the tab specified by the display content specifying unit 109.

As shown in FIG. 8, the rule information URL table manages the tab name in the measuring application and the URL (storage location in the business service 30) (rule information URL) in which the rule information is stored in association with each other. In the rule information URL table shown in FIG. 8, corresponding rule information URLs are associated with each of "Kamigami", "Kumishita", and "Best" as tab names. For example, it is shown that the rule information URL corresponding to the tab name "Kumishita" is "https: // ○○○ / kumishita.rule".

The rule information specifying unit 110 is realized, for example, by executing a program (Web application 13 running on the browser 12) by the CPU 801 shown in FIG.

The voice transmission unit 111 transmits the voice data of the voice command acquired by the voice acquisition unit 108 to the voice recognition service 50 via the second communication unit 102 together with the rule information URL specified by the rule information identification unit 110. It is a functional part. The voice transmission unit 111 is realized, for example, by executing a program (Web application 13 running on the browser 12) by the CPU 801 shown in FIG.

The recognition result acquisition unit 112 is a functional unit that acquires the recognition result of the voice recognition process performed by the voice recognition service 50 via the second communication unit 102.

Here, FIG. 10 shows an example of the recognition result of the voice recognition process output from the voice recognition service 50. The example shown in FIG. 10 shows a recognition result when the voice command of the voice data transmitted by the voice transmission unit 111 is "Sodetake Migi Nijusan". As shown in FIG. 10, the recognition result is converted into text of identification information (rule name) for identifying which input item on which tab of the measurement application and a numerical value (measurement value) of voice commands. Includes information and information.

The recognition result acquisition unit 112 is realized, for example, by executing a program (Web application 13 running on the browser 12) by the CPU 801 shown in FIG.

The input item specifying unit 113 includes a tab displayed by the measuring application and an input item for which a numerical value (measured value) is input on the screen of the tab from the recognition result acquired by the recognition result acquisition unit 112. It is a functional part that identifies. The input item specifying unit 113 is realized, for example, by executing a program (Web application 13 running on the browser 12) by the CPU 801 shown in FIG.

The position determination unit 114 is a functional unit that determines whether or not the input item of the specific tab specified by the input item identification unit 113 is displayed on the application screen displayed on the display 818. The position determination unit 114 is realized, for example, by executing a program (Web application 13 running on the browser 12) by the CPU 801 shown in FIG.

The display control unit 115 is a functional unit that controls the display operation of the screen on the display 818.

Here, FIG. 7 shows an application screen 1001 which is an example of an application screen of a measuring application displayed on the display 818 by the display control unit 115. The application screen 1001 is a screen for manually inputting or voice inputting a numerical value measured for clothes. As shown in FIG. 7, the application screen 1001 includes a basic dimension input unit 1100, tabs 1111 to 1113, a gauge input unit 1120, dimension input units 1131 to 1134 (an example of an input area), 1136, and dimension correction input. Parts 1141 to 1146 (an example of an input area) and a registration button 1151 are included.

The basic dimension input unit 1100 is a field for inputting the basic dimension value of the person to be measured. In the example shown in FIG. 7, "bust", "middle movement", "OB" (overbust), "hip", "total length" and "P total length" can be input as the basic dimension input unit 1100. ing.

Tabs 1111-1113 are tabs for switching input items, respectively. Tab 1111 is a tab for displaying input items for "combination". The tab 1112 is a tab for displaying an input item for "combination". And the tab 1113 is a tab for displaying the input item for "best". The number and types of tabs that can be switched are not limited to these.

The gauge input unit 1120 is a combo box for inputting a model number, a body shape, and a number indicating a size for designating clothes design and the like. By these selective inputs, the reference value (gauge size) corresponding to the selected model number, body shape and size is displayed for each input item. For example, in FIG. 7, when "GM" is input as the model number, "Y" is input as the body type, and "4" is input as the number, the input items "length" are 71 and "sleeve length right" is 58. 5. 58.5 is displayed for "sleeve length left" and 43.4 is displayed for "shoulder width".

The dimension input units 1131 to 1134 and 1136 are fields for manually inputting or voice inputting measurement values corresponding to each input item. Specifically, the dimension input units 1131 to 1134 and 1136 are fields for inputting measurement values corresponding to the input items "length", "sleeve length right", "sleeve length left", "shoulder width", and "waist OW", respectively. Is.

The dimension correction input units 1141 to 1146 are fields for manually inputting or voice inputting a difference value (correction value) with respect to the gauge size. Specifically, the dimension correction input units 1141 to 1146 correspond to the input items "length", "sleeve length right", "sleeve length left", "shoulder width", "back width (side)", and "waist OW", respectively. This is a field for inputting the difference value (correction value) to be input. When a difference value is input to the dimension correction input units 1141 to 1146, addition with the gauge size is executed, and the addition result is automatically input to the corresponding dimension input unit.

The display area on which the input items, gauge size, dimension correction input unit (for example, dimension correction input unit 1141 to 1146) and dimension input unit (for example, dimension input unit 1131-1134, 1136) as described above are displayed is the touch panel 821. Scrolling is possible by flicking (swipe). That is, there are input items, gauge sizes, dimension correction input units, and dimension input units that are not displayed in the display area on the application screen 1001 shown in FIG. 7.

The registration button 1151 is a button for registering the measurement value input to each dimension input unit to the information management service 60.

The display control unit 115 is realized, for example, by executing a program (Web application 13 running on the browser 12) by the CPU 801 shown in FIG.

When the registration button 1151 is pressed on the application screen of the measurement application (for example, the application screen 1001 shown in FIG. 7), the input information transmission unit 116 measures the measurement value (dimension input unit) of each input item input by voice input or the like. It is a functional unit that transmits the value) as measurement information to the business service 30 via the second communication unit 102. The measurement information transmitted to the business service 30 is finally registered and stored in the information management service 60. The input information transmission unit 116 is realized, for example, by executing a program (Web application 13 running on the browser 12) by the CPU 801 shown in FIG.

The storage unit 117 is a functional unit that stores the rule information URL table and the like shown in FIG. 8 above. The storage unit 117 is realized by at least one of the ROM 802, the RAM 803, the EEPROM 804, and the media 808 via the media I / F809 shown in FIG.

The above-mentioned authentication request unit 105, connection request unit 106, reservation information acquisition unit 107, voice acquisition unit 108, display content identification unit 109, rule information specification unit 110, voice transmission unit 111, recognition result acquisition unit 112, input items. The specific unit 113, the position determination unit 114, the display control unit 115, and the input information transmission unit 116 are realized by executing the Web application 13 running on the browser 12, but are not limited to this, and are native. It may be realized by executing an application (dedicated application). Further, at least one of these functional parts may be realized by a dedicated hardware circuit (integrated circuit or the like).

Further, each functional unit of the user terminal 10 shown in FIG. 4 conceptually shows a function, and is not limited to such a configuration. For example, a plurality of functional units illustrated as independent functional units in the user terminal 10 shown in FIG. 4 may be configured as one functional unit. On the other hand, the function of one functional unit in the user terminal 10 shown in FIG. 4 may be divided into a plurality of functions and configured as a plurality of functional units.

As shown in FIG. 4, the business service 30 includes a communication unit 301, a Web server 302, an authentication unit 303, a reservation information management unit 304, a rule information management unit 305, and a storage unit 306.

The communication unit 301 is a functional unit that performs data communication with the user terminal 10, the call service 40, the voice recognition service 50, and the information management service 60 via the network 2. The communication unit 301 is realized by executing the program by the CPU 901 shown in FIG. 3 and the network I / F 909.

The Web server 302 is a functional unit that provides Web contents such as a Web application to the browser 12 of the user terminal 10. The Web server 302 corresponds to the Web server 31 shown in FIG. 1 and is realized by executing a program by the CPU 901 shown in FIG.

The authentication unit 303 is a functional unit that executes the authentication process by referring to the authentication information table stored in the storage unit 306 in accordance with the request of the authentication process from the authentication request unit 105 of the user terminal 10. The authentication information table is, for example, a table that manages a user ID that identifies an individual or an organization in association with a password. The authentication unit 303 is realized by executing the program by the CPU 901 shown in FIG.

The reservation information management unit 304 acquires the reservation information from the information management service 60 via the communication unit 301 in accordance with the request for the reservation information from the user terminal 10, and makes the reservation to the user terminal 10 via the communication unit 301. It is a functional unit that transmits information. The reservation information is, for example, list information such as the name of a customer who has a reservation for measurement and the scheduled visit date and time. The reservation information management unit 304 is realized by executing the program by the CPU 901 shown in FIG.

In response to a request from the voice recognition service 50 for the rule information table, the rule information management unit 305 reads the rule information table corresponding to the request from the storage unit 306 and transmits it to the voice recognition service 50 via the communication unit 301. It is a functional part. The rule information management unit 305 is realized by executing a program by the CPU 901 shown in FIG.

The storage unit 306 is a functional unit that stores the rule information table as shown in FIG. 9, the above-mentioned recognition information table, and the like.

As shown in FIG. 9, in the rule information table, a rule name indicating a tab and an input item, a recognition pattern indicating an interpretation method of a voice command, a keyword for identifying an input item from the voice command, and an input item are input. It is managed in association with a numerical range indicating an acceptable range as a numerical value to be used. Of FIGS. 9, FIG. 9A shows a rule information table corresponding to the “Assembly” tab (tab 1111) on the application screen of the measuring application. For example, in the rule information table shown in FIG. 9A, the rule name "kumiue-sodetakemigi" (set top / sleeve length right) has a recognition pattern "1", a keyword "Sodetakemigi", and a numerical range "0-". It is associated with "999". Further, in FIG. 9, FIG. 9B shows a rule information table corresponding to the tab (tab 1112) of the “grouping” on the application screen of the measuring application. For example, in the rule information table shown in FIG. 9B, the rule name "vest-waist" has the recognition pattern "1", the keyword "Uesuto", and the numerical range "0-999". Associated.

Further, the recognition pattern in the rule information table is a pattern indicating a method of interpreting a voice command input as a voice by the operator as described above, and in the case of "1", the voice command having the above-described configuration in FIG. 6 (that is, that is). , A voice command for inputting a measurement value by voice), and in the case of "2", it is interpreted as a voice command for instructing tab switching. The operation of interpreting the voice command according to such a recognition pattern will be described later as an operation of the voice recognition service 50.

The storage unit 306 is realized by the auxiliary storage device 905 shown in FIG.

The above-mentioned authentication unit 303, reservation information management unit 304, and rule information management unit 305 are realized by executing a program (software), but the present invention is not limited to this, and these functional units are not limited to this. At least one of them may be realized by a dedicated hardware circuit (integrated circuit or the like).

Further, each functional unit of the business service 30 shown in FIG. 4 conceptually shows a function, and is not limited to such a configuration. For example, a plurality of functional units illustrated as independent functional units in the business service 30 shown in FIG. 4 may be configured as one functional unit. On the other hand, in the business service 30 shown in FIG. 4, the function of one functional unit may be divided into a plurality of functions and configured as a plurality of functional units.

As shown in FIG. 4, the call service 40 includes a communication unit 401, a call control unit 402, a connection management unit 403, and a storage unit 404.

The communication unit 401 is a functional unit that performs data communication between the user terminal 10 and the business service 30 via the network 2. The communication unit 401 is realized by executing the program by the CPU 901 shown in FIG. 3 and the network I / F 909.

The call control unit 402 stores the voice data received from the user terminal 10 via the communication unit 401 in the storage unit 404, and transmits (transfers) the voice data based on the group ID received together with the voice data. This is a functional unit that identifies the business service 30 (destination) and relays (transfers) the voice data to the business service 30 via the communication unit 401. The call control unit 402 is realized by executing a program by the CPU 901 shown in FIG.

The connection management unit 403 is a functional unit that performs connection processing by referring to the group information stored in the storage unit 404 in response to a connection request by the group ID from the user terminal 10 via the business service 30. The group information is, for example, information that is managed by associating a group ID with an address of a terminal included in the group. The connection management unit 403 is realized by executing a program by the CPU 901 shown in FIG.

The storage unit 404 is a functional unit that stores the above-mentioned group information and the like. The storage unit 404 is realized by the auxiliary storage device 905 shown in FIG.

The above-mentioned call control unit 402 and connection management unit 403 are realized by executing a program (software), but the present invention is not limited to this, and at least one of these functional units is dedicated. It may be realized by a hardware circuit (integrated circuit, etc.) of.

Further, each functional unit of the call service 40 shown in FIG. 4 conceptually shows a function, and is not limited to such a configuration. For example, a plurality of functional units illustrated as independent functional units in the call service 40 shown in FIG. 4 may be configured as one functional unit. On the other hand, in the call service 40 shown in FIG. 4, the function of one functional unit may be divided into a plurality of functions and configured as a plurality of functional units.

As shown in FIG. 4, the voice recognition service 50 includes a communication unit 501, a voice acquisition unit 502, a voice recognition unit 503, a recognition result transmission unit 504, and a storage unit 505.

The communication unit 501 is a functional unit that performs data communication between the user terminal 10 and the business service 30 via the network 2. The communication unit 501 is realized by the execution of the program by the CPU 901 shown in FIG. 3 and the network I / F 909.

The voice acquisition unit 502 is a functional unit that acquires voice data of voice commands and a rule information URL from the user terminal 10 via the communication unit 501. The voice acquisition unit 502 is realized by executing a program by the CPU 901 shown in FIG.

The voice recognition unit 503 is a functional unit that executes a voice recognition process that interprets the voice command of the voice data acquired by the voice acquisition unit 502 based on the rule information table acquired from the business service 30 by the rule information URL. .. The voice recognition unit 503 is realized by executing a program by the CPU 901 shown in FIG.

Specifically, the voice recognition unit 503 acquires the rule information from the storage destination (storage unit 306 of the business service 30) of the rule information table indicated by the rule information URL acquired by the voice acquisition unit 502. Next, the voice recognition unit 503 converts the voice data acquired by the voice acquisition unit 502 into text. Next, the voice recognition unit 503 searches whether a predetermined number of character strings from the beginning of the text of the voice data matches any of the keywords in the acquired rule information table. Next, when the voice recognition unit 503 can search for a keyword that matches a predetermined number of character strings, the voice recognition unit 503 extracts a recognition pattern corresponding to the keyword.

When the extracted recognition pattern is "1", the voice recognition unit 503 determines that the voice command of the voice data acquired by the voice acquisition unit 502 is a command for inputting the measurement value by voice. In this case, the voice recognition unit 503 interprets the text behind the portion corresponding to the keyword of the text of the voice data as the text indicating the numerical value (measured value). Next, the voice recognition unit 503 determines whether or not the numerical value is included in the numerical range corresponding to the keyword in the rule information table. Then, the voice recognition unit 503 uses the rule name corresponding to the keyword in the rule information table as the identification information for identifying the tab and the input item of the measurement application, and uses the identification information and the above-mentioned numerical value (measurement value). A combination with the indicated text is generated as a recognition result.

For example, the rule information URL acquired by the voice acquisition unit 502 indicates the storage destination of the rule information table for "combination", and the voice command of the similarly acquired voice data indicates "Sodetake Migi ni" shown in FIG. Consider the case of "Ju-san". In this case, the voice recognition unit 503 acquires the rule information table for "combination" from the business service 30, and converts the voice data of the voice command "Sodetake Migi Nijusan" into text. Next, the voice recognition unit 503 searches to see if a predetermined number of character strings from the beginning of the text match any of the keywords in the acquired rule information table for "combination", and "Sodetake Migi". Records containing the keyword are searched. Then, the voice recognition unit 503 extracts "1" as a recognition pattern from the record. According to the recognition pattern, the voice recognition unit 503 interprets the text behind the part corresponding to the keyword "Sodetakemigi" in the text of the voice data as the text indicating the numerical value (measurement value) "23". .. Next, the voice recognition unit 503 determines that the numerical value "23" is included in the numerical range "0-999" corresponding to the keyword "Sodeakemigi" in the rule information table. Then, the voice recognition unit 503 identifies the rule name "kumiue-sodetakemigi" corresponding to the keyword "sodetakemigi" in the rule information table, and identifies the tab "combination" and the input item "sleeve length right" of the measuring application. As shown in FIG. 10, a combination of the identification information and the text indicating the above-mentioned numerical value (measurement value) "23" is generated as the recognition result.

If the numerical value is not included in the corresponding numerical range in the rule information table, the voice recognition unit 503 does not generate the recognition result, or generates the recognition result with the numerical value as the Null value, for example. do it.

On the other hand, when the extracted recognition pattern is "2", the voice recognition unit 503 determines that the voice command of the voice data acquired by the voice acquisition unit 502 is a command for instructing tab switching. In this case, the voice recognition unit 503 ignores the text behind the part corresponding to the keyword of the text of the voice data (usually, the text is not included in the back side). Then, the voice recognition unit 503 uses the rule name corresponding to the keyword in the rule information table as the identification information for identifying the tab to be switched to, and generates the recognition result including the identification information.

For example, consider a case where the rule information URL acquired by the voice acquisition unit 502 indicates the storage destination of the rule information table for "combination", and the voice command of the similarly acquired voice data is "Kumi". In this case, the voice recognition unit 503 acquires the rule information table for "combination" from the business service 30, and converts the voice data of the voice command "Kumi" into text. Next, the voice recognition unit 503 searches to see if a predetermined number of character strings from the beginning of the text match any of the keywords in the acquired rule information table for "combination", and the keyword "kumi" Records containing are searched. Then, the voice recognition unit 503 extracts "2" as a recognition pattern from the record. According to the recognition pattern, the voice recognition unit 503 ignores the text behind the part corresponding to the keyword "Kumi" in the text of the voice data. Then, the voice recognition unit 503 uses the rule name "kumiue-tab-kumisita" corresponding to the keyword "Kumita" in the rule information table as identification information for identifying the tab to be switched to, and recognizes including the identification information. Generate results.

The explanation will be continued by returning to FIG.

The recognition result transmission unit 504 is a functional unit that transmits the recognition result generated by the voice recognition process by the voice recognition unit 503 to the user terminal 10 via the communication unit 501. The recognition result transmission unit 504 is realized by executing the program by the CPU 901 shown in FIG.

The storage unit 505 is, for example, a functional unit for caching the rule information table acquired from the business service 30 by the voice recognition unit 503. That is, the voice recognition unit 503 caches the rule information table acquired from the business service 30 in the storage unit 505, and the next time the voice acquisition unit 502 acquires the voice data of the voice command, the voice recognition unit 503 newly acquires the voice data from the business service 30. Instead of acquiring the rule information table, the rule information table cached in the storage unit 505 may be used. The storage unit 505 is realized by the auxiliary storage device 905 shown in FIG.

The above-mentioned voice acquisition unit 502, voice recognition unit 503, and recognition result transmission unit 504 are realized by executing a program (software), but the present invention is not limited to this, and these functional units are not limited to this. At least one of them may be realized by a dedicated hardware circuit (integrated circuit or the like).

Further, each functional unit of the voice recognition service 50 shown in FIG. 4 conceptually shows a function, and is not limited to such a configuration. For example, a plurality of functional units illustrated as independent functional units in the voice recognition service 50 shown in FIG. 4 may be configured as one functional unit. On the other hand, in the voice recognition service 50 shown in FIG. 4, the function of one functional unit may be divided into a plurality of functions and configured as a plurality of functional units.

As shown in FIG. 4, the information management service 60 includes a communication unit 601, a reservation information management unit 602, and a storage unit 603.

The communication unit 601 is a functional unit that performs data communication with the business service 30 via the network 2. The communication unit 601 is realized by executing the program by the CPU 901 shown in FIG. 3 and the network I / F 909.

The reservation information management unit 602 receives a request for reservation information from the business service 30, and from the reservation information table stored in the storage unit 603, for example, a reservation that is list information such as a customer name having a measurement reservation and a scheduled visit date and time. It is a functional unit that reads out information and transmits it to the business service 30 via the communication unit 601. The reservation information management unit 602 is realized by executing the program by the CPU 901 shown in FIG.

The storage unit 603 is a functional unit that stores a reservation information table or the like as shown in FIG.

As shown in FIG. 11, the reservation information table shows the customer name that received the measurement reservation, the scheduled visit date and time, the measurement date and time when the measurement was actually performed, the measurement result which is a measured numerical group, and the measurement. Manage by associating with the basic information entered at the time. For example, in the reservation information table shown in FIG. 11, the customer name "Measuring Taro", the scheduled visit date and time "2020/02/27 15:30", and the measuring date and time "2020/02/27 15:56:00" And the measurement result of the assembly "length: 72 sleeve length right: 23 ..." and the like are associated with each other.

The storage unit 603 is realized by the auxiliary storage device 905 shown in FIG.

The reservation information management unit 602 described above is realized by executing a program (software), but is not limited to this, and is realized by a dedicated hardware circuit (integrated circuit, etc.). May be.

Further, each functional unit of the information management service 60 shown in FIG. 4 conceptually shows a function, and is not limited to such a configuration. For example, a plurality of functional units illustrated as independent functional units in the information management service 60 shown in FIG. 4 may be configured as one functional unit. On the other hand, in the information management service 60 shown in FIG. 4, the function of one functional unit may be divided into a plurality of functions and configured as a plurality of functional units.

Further, the above-mentioned rule information URL table (see FIG. 8), rule information table (see FIG. 9), authentication information table, and reservation information table (see FIG. 11) are assumed to be table-format information. It is not limited to. For example, at least one of the tables may be information in any format (for example, CSV (Comma-Separated Values) format) as long as the values of each column of the table can be managed in association with each other.

(Initial processing of voice processing system)
FIG. 12 is a sequence diagram showing an example of the flow of initial processing of the voice processing system according to the embodiment. FIG. 13 is a diagram showing an example of a group ID input screen. The flow of the initial processing of the voice processing system 1 according to the present embodiment will be described with reference to FIGS. 12 and 13.

<Step S11>
The worker (user) performs an operation of starting the measuring application, which is the Web application 13, via the input unit 103 of the user terminal 10.

<Steps S12, S13>
Then, the second communication unit 102 of the user terminal 10 transmits the Web application reading request to the business service 30 via the network 2. When the communication unit 301 of the business service 30 receives the Web application reading request, the Web server 302 transmits the Web content (HTML (HyperText Markup Language) data, JavaScript, etc.) of the Web application 13 or the like via the communication unit 301. Is transmitted to the user terminal 10 (“(1) Web content” in FIG. 15 described later).

<Steps S14, S15>
When the second communication unit 102 of the user terminal 10 receives the Web content such as the Web application 13, the display control unit 115 displays the application screen of the measuring application, which is the Web application 13, on the display 818, and displays the login screen. Display it.

<Steps S16, S17>
On the login screen, the operator performs a login operation for inputting authentication information necessary for login, such as a user name and a password, via the input unit 103. Then, the authentication request unit 105 of the user terminal 10 transmits a request for authentication processing including the input authentication information to the business service 30 via the second communication unit 102.

<Steps S18, S19>
When the communication unit 301 of the business service 30 receives the request for the authentication process, the authentication unit 303 executes the authentication process by referring to the authentication information table stored in the storage unit 306 in accordance with the request for the authentication process. , The authentication result is transmitted to the user terminal 10 via the communication unit 301. Here, it is assumed that the authentication is normally performed by the authentication process by the authentication unit 303.

<Steps S20, S21>
When the authentication is normally performed, the display control unit 115 of the user terminal 10 displays the group ID input screen 1200 as shown in FIG. 13 on the display 818.

The group ID input screen 1200 shown in FIG. 13 is for performing a connection process for establishing a session for transmitting and receiving voice data between the user terminal 10 and the call service 40 by the group ID of the group in which the worker makes a call. It is a screen. As shown in FIG. 13, the group ID input screen 1200 includes a group ID input unit 1201, a connection button 1202, and a cancel button 1203.

The group ID input unit 1201 is a field for inputting a group ID for identifying a group in which the worker makes a call. The connection button 1202 is a button for executing the above-mentioned connection process using the group ID input to the group ID input unit 1201. The cancel button 1203 is a button for canceling the connection process using the group ID.

<Steps S22 to S24>
On the group ID input screen 1200, the operator inputs the group ID to the group ID input unit 1201 via the input unit 103, and presses the connection button 1202 (tap operation). Then, the connection request unit 106 of the user terminal 10 is a group of groups in which the worker makes a call via the second communication unit 102 for the call realized by the cooperative operation between the call application 11 and the call service 40. A connection request including an ID is transmitted to the business service 30. When the communication unit 301 of the business service 30 receives the connection request including the group ID from the user terminal 10, the communication unit 301 transmits the connection request to the call service 40.

<Steps S25 to S27>
When the connection request is received by the call service 401 of the call service 40, the connection management unit 403 performs a connection process with reference to the group information stored in the storage unit 404 in response to the connection request, and the connection is OK. A connection result indicating that effect is transmitted to the business service 30 via the communication unit 401. When the communication unit 301 of the business service 30 receives the connection result indicating that the connection is OK, the communication unit 301 transmits the connection result to the user terminal 10. Further, the connection management unit 403 makes a connection with the call application 11 of the user terminal 10 (“(2) Connection confirmation” in FIG. 15 described later).

<Steps S28, S29>
When the connection (session) between the user terminal 10 and the call service 40 is established, the voice communication control unit 104 of the user terminal 10 notifies the operator of the completion of the connection via the display 818.

<Steps S30, S31>
The reservation information acquisition unit 107 of the user terminal 10 transmits a request for reservation information for acquiring reservation information for the measuring work to the business service 30 via the second communication unit 102. When the request for reservation information is received by the communication unit 301 of the business service 30, the reservation information management unit 304 transmits the request for the reservation information to the information management service 60 via the communication unit 301.

<Steps S32 and S33>
When the request for reservation information is received by the communication unit 601 of the information management service 60, the reservation information management unit 602 makes a reservation for measurement, for example, from the reservation information table stored in the storage unit 603 in accordance with the request for the reservation information. Reservation information, which is list information such as a certain customer name and scheduled visit date and time, is read out and transmitted to the business service 30 via the communication unit 601. When the reservation information is received by the communication unit 301 of the business service 30, the reservation information management unit 304 transmits the reservation information to the user terminal 10 via the communication unit 301 (“(3) Reservation” in FIG. 15 described later. Information acquisition").

<Steps S34 to S36>
The reservation information acquisition unit 107 of the user terminal 10 acquires reservation information via the second communication unit 102. Then, the display control unit 115 of the user terminal 10 displays the reservation information on the display 818. The operator selects and operates the reservation of the target customer from the reservation information displayed on the display 818 via the input unit 103.

<Steps S37 to S39>
Further, the operator displays basic information (for example, information of the basic dimension input unit 1100 and the gauge input unit 1120) on the application screen of the measuring application displayed on the display 818 (for example, the application screen 1001 shown in FIG. 7). input.

The initial processing of the voice processing system 1 is performed according to the flow of the above steps S11 to S39.

(Voice input processing of voice processing system)
FIG. 14 is a sequence diagram showing an example of the flow of voice input processing of the voice processing system according to the embodiment. FIG. 15 is a diagram illustrating a data flow of the voice processing system according to the embodiment. FIG. 16 is a flowchart showing an example of the flow of item input / display adjustment processing of the user terminal related to the execution liquid. FIG. 17 is a diagram illustrating an operation of moving an item for which a numerical value has been input by an item input / display adjustment process. FIG. 18 is a diagram illustrating an operation when a dimension correction value is input by a voice command. FIG. 19 is a diagram illustrating an operation when a tab is switched by a voice command and a dimension value is input. The flow of the voice input processing of the voice processing system 1 according to the present embodiment will be described with reference to FIGS. 14 to 19. In the following description, it is assumed that the tab 1111 of "Assembly" is selected on the application screen 1001 after the initial processing of the voice processing system 1 of the higher-level technique.

<Step S51>
The worker (user) wearing the voice terminal 20 measures the over waist of the clothes to be measured, and when the measured value (an example of data) is "88", the voice command is "Uesuto Odaburi". "Yuhachijuhachi" is uttered. The voice receiving unit 201 of the voice terminal 20 receives the voice of the voice command and converts it into voice data. Then, the communication unit 202 of the voice terminal 20 transmits the converted voice command voice data to the user terminal 10 by wireless communication.

<Step S52>
When the voice data of the voice command is received by the first communication unit 101 of the user terminal 10 by wireless communication, the voice communication control unit 104 transfers the voice data together with the group ID of the group in which the worker makes a call. It is transmitted (relayed) to the call service 40 via the communication unit 102 (“(4) voice data” in FIG. 15).

<Steps S53 to S55>
When the voice data and the group ID are received by the communication unit 401 of the call service 40, the call control unit 402 stores the voice data in the storage unit 404 and based on the group ID received together with the voice data. The business service 30 that is the transmission destination (transfer destination) of the voice data is specified, and the voice data is relayed (transferred) to the business service 30 via the communication unit 401. When the communication unit 301 of the business service 30 receives the voice data, the communication unit 301 transmits the voice data to the user terminal 10 (“(5) voice data” in FIG. 15).

<Step S56>
The voice acquisition unit 108 of the user terminal 10 acquires voice data of a voice command from the business service 30 via the second communication unit 102. Next, when the voice data is acquired by the voice acquisition unit 108, the display content specifying unit 109 is displayed on the display 818 by the display control unit 115 on the application screen 1001 of the measuring application which is the Web application 13. Identify whether the tab input items are displayed (which tab is selected). Then, the rule information specifying unit 110 is stored in the storage unit 117 in order to specify the rule information table corresponding to the tab specified by the display content specifying unit 109 (here, the tab 1111 which is the "combination" tab). With reference to the rule information URL table (see FIG. 8), the rule information URL corresponding to the tab (here, the URL indicating the rule information table for "assembly") is specified. That is, the rule information specifying unit 110 specifies the rule information table by specifying the rule information URL corresponding to the tab specified by the display content specifying unit 109.

<Step S57>
As a voice recognition request, the voice transmission unit 111 of the user terminal 10 uses the voice data of the voice command acquired by the voice acquisition unit 108 together with the rule information URL specified by the rule information identification unit 110, and the second communication unit 102. It is transmitted to the voice recognition service 50 via the above (“(6) Voice recognition request” in FIG. 15).

<Steps S58 and S59>
The voice acquisition unit 502 of the voice recognition service 50 acquires the voice data of the voice command and the rule information URL from the user terminal 10 via the communication unit 501. Next, the voice recognition unit 503 of the voice recognition service 50 acquires the rule information table from the storage destination (storage unit 306 of the business service 30) of the rule information table indicated by the rule information URL acquired by the voice acquisition unit 502. The request for this is transmitted to the business service 30 via the communication unit 501. When a request for the rule information table is received by the communication unit 301 of the business service 30, the rule information management unit 305 responds to the request and responds to the request with the rule information table (here, FIG. 9A). The rule information table for "assembly") is read from the storage unit 306 and transmitted to the voice recognition service 50 via the communication unit 301 ("(7) rule information acquisition" in FIG. 15).

<Steps S60, S61>
When the communication unit 501 of the voice recognition service 50 receives the rule information table for "combination", the voice recognition unit 503 converts the voice data acquired by the voice acquisition unit 502 into text. Next, the voice recognition unit 503 searches whether a predetermined number of character strings from the beginning of the text of the voice data match any of the keywords in the acquired rule information table for "combination". Here, it is assumed that the voice recognition unit 503 has searched for a keyword that matches the character string "Uesuto Odaburyu" in the voice data, and extracts "1" as a recognition pattern corresponding to the keyword. According to the recognition pattern, the voice recognition unit 503 determines that the text behind the part corresponding to the keyword "Uesuto Odaburyu" in the text of the voice data is a text indicating a numerical value (measurement value) "88". Interpret. Next, the voice recognition unit 503 assumes that the numerical value "88" is included in the numerical range "0-999" corresponding to the keyword "Uesuto Odaburyu" in the rule information table for "combination". judge. Then, the voice recognition unit 503 sets the rule name "kumiue-waitow" corresponding to the keyword "Uesutoodaburyu" in the rule information table for "Kumigami" to the tab "Kumigami" of the measuring application and The identification information for identifying the input item "waist OW" is used, and a combination of the identification information and the text indicating the above-mentioned numerical value (measurement value) "88" is generated as a recognition result. Then, the recognition result transmission unit 504 of the voice recognition service 50 transmits the recognition result generated by the voice recognition process by the voice recognition unit 503 to the user terminal 10 via the communication unit 501 (“(8)) in FIG. Recognition result ").

<Step S62>
When the recognition result is received by the second communication unit 102 of the user terminal 10, the item input / display adjustment process by the recognition result acquisition unit 112, the input item identification unit 113, the position determination unit 114, and the display control unit 115 shown in FIG. Is executed. The item input / display adjustment process will be described with reference to FIG.

<< Step S621 >>
The recognition result acquisition unit 112 of the user terminal 10 acquires the recognition result of the voice recognition process performed by the voice recognition service 50 via the second communication unit 102. Then, the input item identification unit 113 of the user terminal 10 acquires the identification information from the recognition result acquired by the recognition result acquisition unit 112. Then, the process proceeds to step S622.

<< Step S622 >>
The input item specifying unit 113 identifies the tab displayed by the measuring application and the input item to which the numerical value (measured value) is input on the screen of the tab from the acquired identification information. Specifically, the input item specifying unit 113 specifies the tab 1111 which is the "assembly" tab, and specifies the input item of "waist OW" as an input target. Then, the process proceeds to step S623.

<< Step S623 >>
Further, the input item specifying unit 113 acquires the text “88” of the numerical value (measured value) from the recognition result. Then, the process proceeds to step S624.

<< Step S624 >>
Then, the display control unit 115 of the user terminal 10 enters the text acquired by the input item specifying unit 113 in the dimension input unit (field) (input area) of the input item "waist OW" specified by the input item specifying unit 113. Enter "88". At this point, as in the application screen 1001 shown in FIG. 17A, the input item "waist OW", the gauge size, the dimension correction input unit, and the dimension input unit (field) in which "88" is input are displayed. Not displayed in the area. Then, the process proceeds to step 625.

<< Step S625 >>
Then, in the position determination unit 114 of the user terminal 10, at least the input item "waist OW" and the dimension input unit (field) of the "assembly" tab specified by the input item identification unit 113 are displayed on the display 818. Determine if it is completely displayed in the display area of the application screen. When the input item "waist OW" and the dimension input part (field) are completely displayed in the display area (step S625: Yes), the process proceeds to step S627 and the input item is not completely displayed (that is, only a part). Is displayed or not completely displayed) (step S625: No), the process proceeds to step S626.

<< Step S626 >>
The display control unit 115 automatically scrolls in the display area so that the dimension input unit (field) in which at least the input items "waist OW" and "88" are input is completely displayed in the display area. For example, in the display control unit 115, as in the application screen 1001 shown in FIG. 17A, the dimension input unit (field) in which the input items “waist OW” and “88” are input is completely displayed in the display area. The contents of the display area are automatically scrolled (moved) upward from the state where the display area is not set, and as shown in FIG. 17 (b), the dimension input in which the input items "waist OW" and "88" are input. The part (field) (dimension input part 1136) is completely displayed in the display area. If possible, the display control unit 115 scrolls the dimension input unit (field) (dimension input unit 1136) into which the input items "waist OW" and "88" are input so as to be located at the center of the display area. It is desirable to let it. Then, the process proceeds to step S627.

<< Step S627 >>
Further, as shown in FIG. 17B, the display control unit 115 inputs a portion of the dimension input unit (field) into which the input items “waist OW” and “88” are input (a portion of a line including these). , Highlight by highlighting, etc. The highlighting is not limited to the highlighting, and may be highlighted by, for example, making the input items and the numerical values input to the dimension input unit bold or changing the color. Further, in addition to the highlighting, the speaker 816 may output a sound for notifying the operator that a numerical value (measured value) has been properly input by voice. Then, the process proceeds to step S63 in FIG.

In step S625, the position determination unit 114 determines whether or not at least the input item and the dimension input unit (field) are completely displayed in the display area of the application screen, but the determination process is skipped. It may be the one to do. In this case, the scroll operation by the display control unit 115 in step S626 is always performed.

<Step S63>
As a result of voice input of the measurement value by uttering a voice command, the operator can completely display the measurement value on the application screen 1001 of the measurement application in the display area by the display control unit 115 without scrolling by hand. As a result of automatic scrolling, it can be confirmed that the uttered "88" is input in the field (dimension input unit 1136) of the input item "waist OW". Further, since the display control unit 115 highlights the part of the dimension input unit (field) in which the input items "waist OW" and "88" are input, the input item "waist OW" and the dimension input unit 1136 have "" It can be quickly confirmed that "88" is input.

The above steps S51 to S63 are repeated for the number of input items that require voice input by the operator.

In steps S51 to S63 described above, the operation of directly inputting the measurement value by voice to the dimension input unit on the application screen 1001 has been described, but the present invention is not limited to this, and the dimension correction input unit is from the gauge size. The difference value (correction value) may be input by voice. The voice recognition operation and the automatic scrolling operation on the application screen 1001 in this case are the same as those in steps S51 to S63 described above. FIG. 18 shows a display state when a difference value (correction value) “-1” is input by voice in the dimension correction input unit of the input item “length” on the application screen 1001. In this case, when the difference value "-1" is input to the dimension correction input section of the input item "length", the addition with the gauge size "71" is executed, and the addition result "70" corresponds to the dimension input section. Is automatically entered in. Then, as shown in FIG. 18, the dimension correction input unit (field) in which the input items "length" and "-1" are input is automatically scrolled so as to be completely displayed in the display area, and It will be highlighted.

<Step S64>
The operator presses the registration button 1151 after completing the voice input of all the measurement values for the necessary input items.

<Steps S65, S66>
Then, the input information transmission unit 116 of the user terminal 10 uses the measurement value (value of the dimension input unit) of each input item input by voice input or the like as the measurement information, together with the basic information and the measurement date and time, and the second communication unit 102. It is transmitted to the business service 30 via. Then, when the measurement information, the basic information, and the measurement date and time are received by the communication unit 301 of the business service 30, the reservation information management unit 304 transmits these information to the information management service 60 via the communication unit 301.

<Steps S67 to S69>
When the measurement information, the basic information, and the measurement date and time are received by the communication unit 601 of the information management service 60, the reservation information management unit 602 of the information management service 60 responds in the reservation information table (see FIG. 11) of the storage unit 603. Register the received measurement information, basic information, and measurement date and time in each column of the measurement result, basic information, and measurement date and time of the customer name record. Then, the reservation information management unit 602 transmits the fact that the registration is completed to the business service 30 via the communication unit 601. When the communication unit 301 of the business service 30 receives the notification of registration completion, the reservation information management unit 304 transmits the registration completion to the user terminal 10 via the communication unit 301.

<Steps S70, S71>
When the second communication unit 102 of the user terminal 10 receives the notification of registration completion, the voice communication control unit 104 notifies the operator of the registration completion via the display 818.

According to the flow of steps S51 to S71 described above, the voice input process of the voice processing system 1 is performed.

As described above, even in the case of a voice command for instructing tab switching, the processing is the same as in steps S51 to S63 of FIG. 14, and in step S62, the recognition result acquisition unit 112 of the user terminal 10 , Acquire the identification information for identifying the tab from the recognition result. Then, the display control unit 115 switches to the display of the tab indicated by the acquired identification information. For example, when the acquired identification information indicates the "Assembly" tab, the display control unit 115 sets the input items, the gauge size, and the dimensional correction corresponding to the "Assembly" tab (tab 1112) as shown in FIG. The display is switched to the input unit (dimension correction input unit 1175 in FIG. 19) and the dimension input unit (dimension input unit 1161 to 1164 in FIG. 19). Then, when the voice command of the measurement value for the target input item is uttered in the state where the "Assembly" tab is displayed, the processes of steps S51 to S63 of FIG. 14 are executed. For example, when a voice command for inputting the measurement value of the input item "hip up" by voice is uttered, the display control unit 115 inputs at least the input item "hip up" and the measurement value as shown in FIG. Automatically scroll in the display area so that the dimension input section (field) is completely displayed in the display area. Then, as shown in FIG. 19, the display control unit 115 highlights the input item “hip up” and the dimension input unit (field) in which the measurement value is input (the part of the line including these). Highlight by etc.

Further, instead of the manual pressing operation of the registration button 1151 in step S64 described above, the registration process may be executed by a voice command for instructing registration. In this case, for example, if the rule name for the registration process is registered as the recognition pattern "2" (identifying only the keyword) in the rule information table, the same process can be performed in the flow of steps S51 to S63. be.

As described above, in the voice processing system 1 according to the present embodiment, when the data (measurement value) measured by the voice command is input by voice to the input item of the displayed tab, the data input by voice is input. If the input item and the input part (field) where the data is input are not displayed at least completely, the display area is automatically scrolled to display at least the input item and the input part where the data is input. Make it completely visible in the area. As a result, even when the number of input items is large when the data measured for the object is input by voice, the contents of the items for which the voice input is performed can be immediately confirmed, so that the work efficiency can be improved. ..

Further, in the voice processing system 1, at least when the input item and the input unit in which the data is input are automatically scrolled so as to be completely displayed in the display area, the input item and the input in which the data is input are input. The part (field) part (the part of the line including these) is highlighted by highlighting or the like. As a result, it is possible to quickly confirm that data has been input to the input item and the input unit.

In the present embodiment, the rule information table used in the voice recognition process is switched (specified) by the user terminal 10 according to the selected tab, but the present invention is not limited to this. In the above-described embodiment, it is assumed that the tabs are switched on the same application screen (application screen 1001 or the like), but for example, the screen itself is switched such as a screen for "combination" and a screen for "combination". You can think of a case. In this case, the rule information table may be switched (specified) by the user terminal 10 according to the currently displayed screen. Further, for example, on the same application screen, it is conceivable that each input item of "combination", "combination" and "best" is included. In this case, the rule information table may be switched (specified) by the user terminal 10 according to the scroll position of the input item currently displayed on the screen. That is, as described above, the selected tab, the switched screen, and the scroll position of the input item specify the measurement target (measurement target) such as "set up", "set down", and "best". Will be done.

Further, in step S13 in FIG. 12, the user terminal 10 may not only receive only the Web content from the business service 30, but also receive each rule information table stored in the storage unit 306 in advance. .. In this case, in step S57 in FIG. 14, the user terminal 10 may transmit the rule information table itself to the voice recognition service 50 instead of the URL of the rule information table corresponding to the selected tab.

Further, due to the system configuration shown in FIG. 1, the voice data of the worker received from the voice terminal 20 to the user terminal 10 is received again by the user terminal 10 via the call service 40 and the business service 30. However, it is not limited to this. That is, the voice data of the worker received from the voice terminal 20 to the user terminal 10 may be received again to the user terminal 10 via, for example, only the call service 40, or the user from the voice terminal 20. The voice data received by the terminal 10 may be transmitted to the voice recognition service 50 as it is and used for the voice recognition process.

Further, the user terminal 10 plays both a role as a terminal on which the call application 11 for relaying a call is installed and as a terminal for displaying a measured value input by voice, but is not limited thereto. That is, the terminal on which the call application 11 that relays the call is installed and the terminal that displays the measured value input by voice may be different information processing devices.

Further, the voice command uttered by the worker is received by the voice terminal 20 and transmitted as voice data to the user terminal 10, but the present invention is not limited to this. That is, the user terminal 10 may directly receive the voice command uttered by the operator by using the voice input function by the microphone 815 of the user terminal 10.

Further, in the above-described embodiment, the operation of inputting the measurement value by voice for each input item on the application screen (application screen 1001 or the like) has been described, but the measurement value is manually input directly via the touch panel 821. Is also possible. In this case, when manually inputting the measurement value, the target input item is naturally displayed in the display area of the application screen, so that the scroll movement and highlighting (highlight display, etc.) as described above in FIG. 14 are performed. No action is required. By enabling both voice input and manual input in this way, it is possible to give diversity to data input, and it is possible to switch the data input method depending on the situation of the measuring work.

(Modification example)
The voice processing system 1 according to this modification will be described focusing on the differences from the voice processing system 1 according to the above-described embodiment.

FIG. 20 is a diagram illustrating a data flow of the voice processing system according to the modified example. The voice processing system 1 according to this modification will be described with reference to FIG.

In the voice processing system 1 according to the above-described embodiment, the user terminal 10 acquires voice data (“(5) voice data” in FIG. 15), and sends the voice data and the rule information URL to the business service 30 to the voice recognition service 50. A voice recognition request is made by transmitting (“(6) voice recognition request” in FIG. 15), and the voice recognition service 50 acquires a rule information table from the business service 30 (“(7) rule information acquisition” in FIG. 15). ), The recognition result of the voice recognition process is transmitted to the user terminal 10 (“(8) recognition result” in FIG. 15). However, the operation is not limited to such an operation, and may be an operation as shown in FIG. 20, for example.

As shown in FIG. 20, after the business service 30 receives the voice data from the call service 40 (“(5) voice data” in FIG. 20), the voice data and the rule information table stored by itself are voiced. A voice recognition request is made by transmitting to the recognition service 50 (“(6) Voice recognition request” in FIG. 20). Then, the voice recognition service 50 transmits the recognition result of the voice recognition process to the business service 30 (“(7) recognition result” in FIG. 20), and the business service 30 acquires the identification information and the numerical value from the recognition result. The web page of the application screen that has been scrolled and highlighted by inputting into the dimension input section (field) indicated by the identification information of the application screen is transmitted to the user terminal 10 (“(8) Screen update information” in FIG. 20). ..

Even with the above operation, the same effect as that of the voice processing system 1 according to the above-described embodiment can be obtained.

As described above, the voice processing system 1 according to the above-described embodiment and modification is not limited to the case where the measurement value obtained in the measurement work is input by voice, and the operator obtains it by measuring a specific object. It can be widely applied to the process of inputting the data to an information processing device or the like by voice. For example, in the quality inspection of a product or an agricultural product, it can be applied to a situation where measurement data measured by operating a measuring device is input by voice. Further, for example, in the inspection of structures such as roads, bridges and tunnels, it can be applied to a situation where data obtained by operating an inspection device is input by voice.

Further, each function of the above-described embodiment and modification can be realized by one or a plurality of processing circuits. Here, the "processing circuit" is a processor programmed to execute each function by software such as a processor implemented by an electronic circuit, or an ASIC (Application Special Integrated) designed to execute each function described above. Devices including devices such as Circuits, DSPs (Digital Signal Processors), FPGAs (Field-Programmable Gate Arrays), SoCs (System on a Chips), GPUs (Graphics Processing Units), and conventional circuit modules.

Further, in the above-described embodiments and modifications, when at least one of the functional units of the user terminal 10 or the business service 30 is realized by executing a program, the program is provided by being incorporated in a ROM or the like in advance. .. Further, the program executed by the user terminal 10 and the business service 30 according to the above-described embodiment and modification is a CD-ROM (Compact Disc Read Only Memory) or a flexible disk in an installable format or an executable format file. It may be configured to be recorded and provided on a computer-readable recording medium such as (FD), CD-R (Compact Disk-Recordable), DVD or SD (Secure Digital) card. Further, the program executed by the user terminal 10 and the business service 30 according to the above-described embodiment and modification is stored on a computer connected to a network such as the Internet and provided by downloading via the network. It may be configured. Further, the program executed by the user terminal 10 and the business service 30 according to the above-described embodiment and modification may be configured to be provided or distributed via a network such as the Internet. Further, the program executed by the user terminal 10 and the business service 30 according to the above-described embodiment and modification has a module configuration including at least one of the above-mentioned functional units, and is actually hardware. When the CPU reads a program from the above-mentioned storage device and executes it, each of the above-mentioned functional units is loaded on the main storage device and generated.

1 Voice processing system 2 Network 10 User terminal 11 Call application 12 Browser 13 Web application 20 Voice terminal 30 Business service 31 Web server 40 Call service 50 Voice recognition service 60 Information management service 101 1st communication unit 102 2nd communication unit 103 Input unit 104 Voice communication control unit 105 Authentication request unit 106 Connection request unit 107 Reservation information acquisition unit 108 Voice acquisition unit 109 Display content specification unit 110 Rule information specification unit 111 Voice transmission unit 112 Recognition result acquisition unit 113 Input item specification unit 114 Position determination unit 115 Display control unit 116 Input information transmission unit 117 Storage unit 201 Voice reception unit 202 Communication unit 301 Communication unit 302 Web server 303 Authentication unit 304 Reservation information management unit 305 Rule information management unit 306 Storage unit 401 Communication unit 402 Call control unit 403 Connection Management unit 404 Storage unit 501 Communication unit 502 Voice acquisition unit 503 Voice recognition unit 504 Recognition result transmission unit 505 Storage unit 601 Communication unit 602 Reservation information management unit 603 Storage unit 801 CPU
802 ROM
803 RAM
804 EEPROM
805 CMOS
806 Image sensor I / F
807 Acceleration / Direction Sensor 808 Media 809 Media I / F
810 Bus 811 GPS receiver 812 telecommunications circuit 812a Antenna 815 Microphone 816 Speaker 817 Sound input / output I / F
818 Display 819 External device connection I / F
820 Near field communication circuit 820a Antenna 821 Touch panel 901 CPU
902 ROM
903 RAM
905 Auxiliary storage device 906 Recording media 907 Media drive 908 Display 909 Network I / F
910 Bus 911 Keyboard 912 Mouse 913 DVD
914 DVD drive 1001, 1002 App screen 1100 Basic dimension input section 1111-1113 Tab 1120 Gauge input section 1131-1134, 1136 Dimension input section 1141-1146 Dimension correction input section 1151 Registration button 1161-1164 Dimension input section 1175 Dimension correction input section 1200 Group ID input screen 1201 Group ID input unit 1202 Connection button 1203 Cancel button

Japanese Unexamined Patent Publication No. 2019-09960

Claims (10)

A voice processing device that inputs measured data by voice.
The first acquisition unit that acquires the voice data of the voice command for inputting the data by voice, and
A transmission unit that transmits the voice data acquired by the first acquisition unit and a request for voice recognition processing for the voice data to the voice recognition service.
A second acquisition unit that acquires the recognition result of the voice recognition process from the voice recognition service, and
From the recognition result acquired by the second acquisition unit, a first specific unit that specifies an input item to be input to the data, and a first specific unit.
A data input unit for inputting the voice-recognized data included in the recognition result into the input area of the input item specified by the first specific unit.
The input item and the input area are displayed so that the input item specified by the first specific unit and the input area in which the data is input by the data input unit are displayed in the display area of the display device. The moving part to move and
A voice processing device equipped with. The voice processing apparatus according to claim 1, further comprising a highlighting unit that highlights the input item and the input area moved by the moving unit. The voice processing device according to claim 1 or 2, further comprising an input unit for directly inputting the data into the input area by a manual operation. A determination unit for determining whether or not the input item specified by the first specific unit and the input area into which the data is input is completely displayed in the display area is further provided.
When the determination unit determines that the input item and the input area are not completely displayed in the display area, the moving unit completely displays the input item and the input area in the display area. The voice processing device according to any one of claims 1 to 3, which is moved so as to be displayed. The moving unit is such that the input item specified by the first specific unit and the input area in which the data is input by the data input unit are located in the center of the display area. The voice processing device according to any one of claims 1 to 4, wherein the input area is moved. A second specific unit for specifying which input item to be measured is displayed on the display device is further provided.
The transmission unit transmits the voice data and information that specifies the specified information that defines the interpretation method of the voice command corresponding to the measurement target specified by the second specific unit to the voice recognition service. The voice processing device according to any one of claims 1 to 5. The second specific unit corresponds to a tab selected on the screen displayed on the display device, a screen displayed on the display device, or a scroll position of an input item displayed on the display device. The voice processing device according to claim 6, wherein an input item to be measured is specified. A voice processing system that inputs measured data by voice.
The first acquisition unit that acquires the voice data of the voice command for inputting the data by voice, and
A transmission unit that transmits the voice data acquired by the first acquisition unit and a request for voice recognition processing for the voice data to the voice recognition service.
A second acquisition unit that acquires the recognition result of the voice recognition process from the voice recognition service, and
From the recognition result acquired by the second acquisition unit, a first specific unit that specifies an input item to be input to the data, and a first specific unit.
A data input unit for inputting the voice-recognized data included in the recognition result into the input area of the input item specified by the first specific unit.
The input item and the input area are displayed so that the input item specified by the first specific unit and the input area in which the data is input by the data input unit are displayed in the display area of the display device. The moving part to move and
A voice processing system equipped with. It is a voice processing method that inputs the measured data by voice.
The first acquisition step of acquiring the voice data of the voice command for inputting the data by voice, and
A transmission step of transmitting the acquired voice data and a request for voice recognition processing for the voice data to the voice recognition service, and
A second acquisition step of acquiring the recognition result of the voice recognition process from the voice recognition service, and
From the acquired recognition result, a specific step for specifying an input item to be input to the data, and
A data input step of inputting the voice-recognized data included in the recognition result into the input area of the specified input item, and
A moving step of moving the input item and the input area so that the specified input item and the input area into which the data is input are displayed in the display area of the display device.
A voice processing method having. On the computer
The first acquisition step of acquiring the voice data of the voice command for inputting the measured data by voice, and
A transmission step of transmitting the acquired voice data and a request for voice recognition processing for the voice data to the voice recognition service, and
A second acquisition step of acquiring the recognition result of the voice recognition process from the voice recognition service, and
From the acquired recognition result, a specific step for specifying an input item to be input to the data, and
A data input step of inputting the voice-recognized data included in the recognition result into the input area of the specified input item, and
A moving step of moving the input item and the input area so that the specified input item and the input area into which the data is input are displayed in the display area of the display device.
A program to execute.

Images