CN112786031B - Man-machine conversation method and system - Google Patents

Abstract

The invention discloses a man-machine conversation method and a man-machine conversation system, which are applied to intelligent terminal equipment with a screen, wherein the method comprises the following steps: starting a full-duplex dialogue mode after detecting the operation of starting a dialogue by a user; performing voice recognition on the detected current user sentence, so as to determine reply content corresponding to the current user sentence according to an obtained voice recognition result and present the reply content to a user; and if a new user sentence is detected before determining the reply content corresponding to the current user sentence and presenting the reply content to the user, determining new reply content responding to the current user according to the current user sentence and the new user sentence. The invention adopts a full-duplex dialogue mode, can detect new user sentences in real time while responding to the user sentences, and determines new response contents responding to the current user according to the current user sentences and the new user sentences, thereby more accurately and efficiently determining the response contents by simultaneously integrating the context.

Description

Man-machine dialogue method and system

technical field

The present invention relates to the technical field of man-machine dialogue, and in particular, to a man-machine dialogue method and system.

Background technique

At present, voice assistants running on smart TVs or OTT TV boxes on the market generally use half-duplex interaction for human-computer interaction. E.g:

1. Use the pickup board to add a wake-up word. You need to use the wake-up word for every conversation. You can interact after waking up. Wait for the VAD (voice detection) detection to end and stop picking up sounds.

2. Using the voice remote control, when the user presses the voice key, the dialogue starts and enters the voice pickup state. When the user lifts the voice key, the voice pickup stops and the dialogue output is output.

Half-duplex interaction can satisfy most simple operations, such as increasing the volume, changing TV channels, switching songs up and down, etc. But when dealing with complex scenarios, it will appear powerless. For example: the user first said "I want to watch a movie", then "is there a starring Andy Lau?", then "the fourth in the second line", and finally "want to listen to his songs".

The above scenario involves:

1. The following is a reduction of the scope of the above;

2. User intention to jump across domains (skills and skills are independent of each other, when skill A jumps to skill B, it is called cross-domain);

3. The keywords of the sentence are mentioned in the previous sentence, this sentence is the default and needs to be referred to according to the context;

4. The user prefers to input the next sentence immediately after the dialogue output of the previous sentence, rather than waiting for the completion of the TTS (text-to-speech) broadcast.

Half-duplex interaction has the following defects in the above scenarios:

1. Relying on the wake-up word or the remote control, each interaction requires pressing the remote control or saying the wake-up word;

2. The effect of instant interruption (termination of the current dialogue process) cannot be achieved, and the dialogue needs to be interrupted or waited for the end of the dialogue to enter the next round of dialogue;

3. In the scenario that requires message reference, it is impossible to infer user intent according to the context after cross-domain;

4. The operation mode is fixed, and the interactive experience is not good.

In order to solve the above problems and optimize the experience, the industry has the following solutions:

1. Multiple rounds of dialogue (it needs to be stated in multiple rounds, and the user may continue to clarify and improve their intentions during the dialogue): This function is that after the user arouses the dialogue, after the dialogue has output, it does not end the dialogue, but continues to monitor, This solution solves the need to wake up every time, the same skill, and the above-mentioned association within the skill, but there are defects: it cannot be interrupted immediately, and it does not support context cross-domain.

2. Wake-up words, in order to solve the need to wake up every time, after entering a specific scene, you can set the words that may be used in the scene as wake-up words. When the user speaks these keywords, the dialog is triggered, and the client only needs to parse The corresponding dialog starts action and executes the corresponding business logic. This solution exists, the number of wake-up words is limited, and the wake-up effect is not good.

SUMMARY OF THE INVENTION

Embodiments of the present invention provide a man-machine dialogue method and system, which are used to solve at least one of the above technical problems.

In a first aspect, an embodiment of the present invention provides a man-machine dialogue method, which is applied to an intelligent terminal device with a screen. The method includes:

After detecting the user's operation of opening a dialogue, start the full-duplex dialogue mode;

Perform speech recognition on the detected current user sentence, so as to determine the reply content corresponding to the current user sentence according to the obtained speech recognition result and present it to the user;

If a new user sentence is detected before the reply content corresponding to the current user sentence is determined and presented to the user, a new reply content in response to the current user is determined according to the current user sentence and the new user sentence .

In a second aspect, an embodiment of the present invention provides a human-machine dialogue system, which is applied to a screened intelligent terminal device, and the system includes:

The dialogue mode startup module is used to start the full-duplex dialogue mode after detecting the operation of the user to open the dialogue;

A speech recognition module, configured to perform speech recognition on the detected current user sentence, to determine the reply content corresponding to the current user sentence according to the obtained speech recognition result and present it to the user;

The reply content determination module is configured to, if a new user sentence is detected before the reply content corresponding to the current user sentence is determined and presented to the user, determine a response to the response according to the current user sentence and the new user sentence The new reply content for the current user.

In a third aspect, an embodiment of the present invention provides a storage medium, where one or more programs including execution instructions are stored in the storage medium, and the execution instructions can be used by an electronic device (including but not limited to a computer, a server, or a network). equipment, etc.) to read and execute, so as to execute any of the above-mentioned man-machine dialogue methods of the present invention.

In a fourth aspect, an electronic device is provided, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, The instructions are executed by the at least one processor to enable the at least one processor to execute any one of the above-mentioned human-machine dialogue methods of the present invention.

In a fifth aspect, an embodiment of the present invention further provides a computer program product, the computer program product includes a computer program stored on a storage medium, the computer program includes program instructions, and when the program instructions are executed by a computer, causes the The computer executes any one of the above man-machine dialogue methods.

The beneficial effect of the embodiment of the present invention is that: the embodiment of the present invention adopts a full-duplex dialogue mode, which can detect a new user sentence in real time while responding to the user sentence, and determine a new user sentence corresponding to the current user sentence. If a new user sentence is detected before the reply content is presented to the user, the new reply content in response to the current user is determined according to the current user sentence and the new user sentence, so that the context can be integrated at the same time to be more accurate and efficient. Determine the content of the answer.

Description of drawings

In order to illustrate the technical solutions of the embodiments of the present invention more clearly, the following briefly introduces the accompanying drawings used in the description of the embodiments. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained from these drawings without any creative effort.

FIG. 1 is a flowchart of an embodiment of a man-machine dialogue method of the present invention;

2 is a flowchart of another embodiment of the man-machine dialogue method of the present invention;

3 is a schematic block diagram of an embodiment of the man-machine dialogue system of the present invention;

FIG. 4 is a schematic structural diagram of an embodiment of an electronic device of the present invention.

Detailed ways

In order to make the purposes, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments These are some embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

It should be noted that the embodiments of the present invention and the features of the embodiments may be combined with each other under the condition of no conflict.

The invention may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, elements, data structures, etc. that perform particular tasks or implement particular abstract data types. The invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including storage devices.

In the present invention, "module", "device", "system", etc. refer to related entities applied to a computer, such as hardware, a combination of hardware and software, software or software in execution, and the like. In detail, for example, an element may be, but is not limited to, a process running on a processor, a processor, an object, an executable element, a thread of execution, a program, and/or a computer. Also, an application program or script program running on the server, and the server can be a component. One or more elements may be in a process and/or thread of execution and an element may be localized on one computer and/or distributed between two or more computers and may be executed from various computer readable media . Elements may also pass through a signal having one or more data packets, for example, a signal from one interacting with another element in a local system, in a distributed system, and/or with data interacting with other systems through a network of the Internet local and/or remote processes to communicate.

Finally, it should also be noted that in this document, relational terms such as first and second are used only to distinguish one entity or operation from another, and do not necessarily require or imply these entities or that there is any such actual relationship or sequence between operations. Furthermore, the terms "comprising" and "comprising" include not only those elements, but also other elements not expressly listed, or elements inherent to such a process, method, article or apparatus. Without further limitation, an element defined by the phrase "comprises" does not preclude the presence of additional identical elements in a process, method, article or apparatus that includes the element.

As shown in FIG. 1, it is a flow chart of an embodiment of the man-machine dialogue method of the present invention. The man-machine dialogue method is applied to a screen intelligent terminal device, and the screen intelligent terminal device can be a smart TV, a smart phone, a tablet A computer, a story machine with a display screen, a smart speaker with a display screen, etc., are not limited in the present invention. The man-machine dialogue method of the present invention comprises the following steps:

S10. After detecting the user's operation of opening the dialog, start the full-duplex dialog mode. Exemplarily, the operation of the user to open the dialogue may be by speaking a wake-up word, or by pressing a specific function button on the remote control.

S20, performing speech recognition on the detected current user sentence, to determine the reply content corresponding to the current user sentence according to the obtained speech recognition result and present it to the user;

S30. If a new user sentence is detected before the reply content corresponding to the current user sentence is determined and presented to the user, determine a new user sentence in response to the current user according to the current user sentence and the new user sentence Reply content.

The embodiment of the present invention adopts a full-duplex dialogue mode, which can detect new user sentences in real time while responding to user sentences, and detect the response content corresponding to the current user sentence before it is determined and presented to the user. If there is a new user sentence, the new reply content in response to the current user is determined according to the current user sentence and the new user sentence, so that the content of the reply can be determined more accurately and efficiently by synthesizing the context at the same time.

In some embodiments, if the interval between the detection of the new user sentence and the detection of the current user sentence does not exceed a preset duration threshold,

Then, determining the new reply content in response to the current user according to the current user sentence and the new user sentence includes: if it is determined that the new user sentence is a related sentence of the current user sentence, then according to the current user sentence The sentence and the new user sentence together determine the new reply content in response to the current user.

Exemplarily, the preset duration threshold is the maximum duration that a general user can endurely wait for a reply from the machine when conducting a man-machine dialogue, and the duration can be determined by collecting a large amount of man-machine dialogue process data for analysis and statistics. Exemplarily, the preset duration threshold may be 5 seconds, but the present invention does not limit the specific value of the preset duration threshold, and those skilled in the art can make appropriate adjustments according to actual needs, or according to the passage of time. The preset duration threshold determined by the collected massive man-machine dialogue process data will change.

If a new user sentence is detected within the preset duration threshold, it means that the response content corresponding to the current user sentence is presented to the user is still within the acceptable range, otherwise it is unacceptable and will no longer consider the current The reply content of the user statement.

Illustratively, the associated statement means that the new user statement is a statement that further defines the current user statement. For example, if the current user sentence is "I want to listen to a song", the new user sentence can be "Andy Lau's"; or, if the current user sentence is "I want to watch a movie", the new user sentence can be "Made in China"; or, The current sentence is "I want to watch XX variety show", the new user sentence is "Last week (or the latest)" and so on.

In this embodiment, when it is determined that the new user sentence is a related sentence of the current user sentence, a new reply content in response to the current user is jointly determined according to the current user sentence and the new user sentence. In this way, both the current user sentence and the new user sentence are taken into consideration, and finally new reply content is comprehensively determined to be presented to the user.

If the reply content corresponding to the current user sentence and the reply content corresponding to the new user sentence are respectively determined, and then the two reply contents are presented to the user in turn (for example, the "movie interface" is presented first, and then the presentation is refreshed again It is a "domestic movie interface"), it will appear that the entire interaction process is redundant and cumbersome, and it is repeated, especially for smart terminal devices with screens (for example, smart TVs), at least two page refreshes are required, which will seriously affect user experience.

By adopting the method of this embodiment, the final reply content can be presented to the user in a straightforward manner.

In some embodiments, if it is determined that the new user sentence is not a related sentence of the current user sentence, determining the first reply content in response to the current user according to the current user sentence, and determining according to the new user sentence In response to the second reply content of the current user.

In this embodiment, although the new user sentence is not a related sentence of the current user sentence, if the new user sentence is detected within the preset duration threshold, that is, whether the response content of the current user sentence is presented to the user or If the content is within the acceptable range, the determined first reply content and second reply content are respectively used for presentation to the user, which satisfies the user's needs to the greatest extent.

In some embodiments, if the interval between the detection of the new user sentence and the detection of the current user sentence exceeds a preset duration threshold,

Then, according to the current user sentence and the new user sentence, it is determined that the new reply content in response to the current user includes:

A new reply content in response to the current user is determined according to the new user sentence.

In this embodiment, since the interval between the detection of a new user sentence and the detection of the current user sentence exceeds the preset time length threshold, it indicates that the maximum waiting time of the user has been exceeded, and the user no longer cares about the sentence corresponding to the current user. content of the answer. If the first reply content and the second reply content corresponding to the current user sentence and the new user sentence are presented to the user respectively at this time, the user experience will be seriously affected.

A more intuitive performance is that the user first asked a question a, and the machine did not get a response within the preset time threshold due to delays due to poor network conditions or other possible reasons, and then the user asked another question b. (Question b has nothing to do with question a), if the response content corresponding to question a is presented to the user after the network delay, it will give the user a feeling that the answer is not what was asked.

The method based on this embodiment can achieve the effect of cross-domain jumping (the domain to which question a belongs to the domain to which question b belongs), and present the answer content of the question that the user really cares about at this time to the user.

As shown in FIG. 2, it is a flowchart of another embodiment of the man-machine dialogue method of the present invention, which includes the following steps:

1. The process starts;

2. Arouse the conversation through the remote control or wake-up word;

3. Start picking up sounds and send them to the cloud for identification;

4. Perform semantic analysis according to the recognition result. If the user has other valid semantic input at this time, interrupt the current link and re-enter the recognition link;

5. Dialogue eliminates the semantic analysis results, manages the dialogue, records the semantic slot value of the current dialogue, and outputs the dialogue result. If the user has other valid semantic input at this time, the current link is interrupted and the recognition link is re-entered;

6. If the dialogue service has speech synthesis, the speech synthesis is performed and sent to the client for broadcast. If the user has other valid semantic input at this time, the current link is interrupted and the recognition link is re-entered;

7. The user has no valid semantic analysis for a long time, or the user triggers the exit action, and the process ends.

Exemplarily, the present invention can be used for a smart TV or an OTT TV box to realize one-time wake-up and continuous dialogue, making the interaction easier and smoother, and closer to the voice assistant implementation solution of human-to-human interaction.

Scheme realization principle:

1. After arousing the dialogue, continue to pick up sounds for identification, and wait until the user explicitly quits or does not speak for a long time (no valid semantics) before quitting the dialogue;

2. Record key information during the dialogue service process. When there is a new voice input, it can be associated with the dialogue context recorded by the system to accurately predict the user's intention.

Advantages of this program:

1. You only need to wake up once, and you can interact continuously, avoiding the need to enter a wake-up word or press the voice key for each sentence;

2. Continuous pickup, which can be interrupted at any part of the dialogue process to avoid meaningless waiting for users;

3. Record the dialogue context, which is no longer limited to a single skill, and can achieve contextual association of cross-domain skills;

4. The audio recognition is performed only after the dialogue is aroused to reduce the occupation of system resources;

5. Optimize the interactive experience, so that the human-computer interaction is close to the human-human interaction.

In some embodiments, the user's operation of opening the dialogue is to speak a wake-up voice, and after the user's operation of opening the dialogue is detected, starting the full-duplex dialogue mode includes:

Determine the user feature information of the current user according to the detected wake-up word voice;

Querying the user feature information database to determine the dialogue mode suitable for the current user; wherein, the user feature information database stores the feature information of multiple users who have used the current smart terminal device with a screen, and records the plurality of users Conversation modes applicable to users respectively;

When the query result indicates that the dialogue mode corresponding to the user characteristic information of the current user is the full-duplex mode, the full-duplex dialogue mode is started.

In some embodiments, when the query result indicates that the dialog mode corresponding to the user characteristic information of the current user is the half-duplex mode, the half-duplex dialog mode is started.

This embodiment realizes the self-adaptive selection of the initial dialogue mode after the system is awakened, so as to be able to adapt to users with different applicable habits. For example, for the elderly or first-time users who are not familiar with the voice control of smart TVs, usually each step of the operation needs to be prompted by the system. Work conversation mode. For young people or people who are very familiar with the semantic control process of smart TVs, they usually do not listen to the system's prompt tone, and directly perform voice control according to what they see. At this time, the system needs to be configured as full dual Work conversation mode, so as to be able to interrupt the conversation at any time to meet the needs of the user group.

It should be noted that, for the sake of simple description, the foregoing method embodiments are all expressed as a series of actions combined, but those skilled in the art should know that the present invention is not limited by the described sequence of actions. As in accordance with the present invention, certain steps may be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention. In the above-mentioned embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

As shown in FIG. 3 , it is a schematic block diagram of an embodiment of the human-machine dialogue system 300 of the present invention, which is applied to an intelligent terminal device with a screen. The system 300 includes:

The dialogue mode starting module 310 is configured to start the full-duplex dialogue mode after detecting that the user's operation of opening the dialogue;

The speech recognition module 320 is configured to perform speech recognition on the detected current user sentence, so as to determine the reply content corresponding to the current user sentence according to the obtained speech recognition result and present it to the user;

The reply content determination module 330 is configured to determine a response according to the current user sentence and the new user sentence if a new user sentence is detected before the reply content corresponding to the current user sentence is determined and presented to the user New reply content for the current user.

In some embodiments, if the interval between the detection of the new user sentence and the detection of the current user sentence does not exceed a preset duration threshold,

Then, determining the new reply content in response to the current user according to the current user sentence and the new user sentence includes: if it is determined that the new user sentence is a related sentence of the current user sentence, then according to the current user sentence The sentence and the new user sentence together determine the new reply content in response to the current user.

In some embodiments, if it is determined that the new user sentence is not a related sentence of the current user sentence, determining the first reply content in response to the current user according to the current user sentence, and determining according to the new user sentence In response to the second reply content of the current user.

In some embodiments, if the interval between the detection of the new user sentence and the detection of the current user sentence exceeds a preset duration threshold,

Then, determining the new reply content in response to the current user according to the current user sentence and the new user sentence includes: determining the new reply content in response to the current user according to the new user sentence.

The man-machine dialogue system of the above embodiments of the present invention can be used to execute the man-machine dialogue method of the embodiments of the present invention, and correspondingly achieve the technical effects achieved by the man-machine dialogue method of the above-mentioned embodiments of the present invention, which will not be repeated here. In the embodiment of the present invention, the relevant functional modules may be implemented by a hardware processor (hardware processor).

FIG. 4 is a schematic diagram of the hardware structure of an electronic device for executing a man-machine dialogue method provided by another embodiment of the present invention. As shown in FIG. 4 , the device includes:

One or more processors 410 and a memory 420, one processor 410 is taken as an example in FIG. 4 .

The apparatus for performing the man-machine dialogue method may further include: an input device 430 and an output device 440 .

The processor 410, the memory 420, the input device 430, and the output device 440 may be connected through a bus or in other ways, and the connection through a bus is taken as an example in FIG. 4 .

The memory 420, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs and modules, such as programs corresponding to the man-machine dialogue method in the embodiment of the present invention Directive/Module. The processor 410 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 420, that is, to implement the man-machine dialogue method of the above method embodiments.

The memory 420 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the man-machine dialogue device, and the like. Additionally, memory 420 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, memory 420 may optionally include memory located remotely from processor 410, and these remote memories may be connected to the human-machine dialogue device via a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

The input device 430 can receive input numerical or character information, and generate signals related to user settings and function control of the man-machine dialogue device. The output device 440 may include a display device such as a display screen.

The one or more modules are stored in the memory 420, and when executed by the one or more processors 410, execute the man-machine dialogue method in any of the above method embodiments.

The above product can execute the method provided by the embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method. For technical details not described in detail in this embodiment, reference may be made to the method provided by the embodiment of the present invention.

The electronic device of the embodiment of the present invention exists in various forms, including but not limited to:

(1) Mobile communication equipment: This type of equipment is characterized by having mobile communication functions, and its main goal is to provide voice and data communication. Such terminals include: smart phones (eg iPhone), multimedia phones, feature phones, and low-end phones.

(2) Ultra-mobile personal computer equipment: This type of equipment belongs to the category of personal computers, has computing and processing functions, and generally has the characteristics of mobile Internet access. Such terminals include: PDAs, MIDs, and UMPC devices, such as iPads.

(3) Portable entertainment equipment: This type of equipment can display and play multimedia content. Such devices include: audio and video players (eg iPod), smart speakers, story machines, robots, handheld game consoles, e-books, as well as smart toys and portable car navigation devices.

(4) Server: A device that provides computing services. The composition of the server includes a processor, a hard disk, a memory, a system bus, etc. The server is similar to a general computer architecture, but due to the need to provide highly reliable services, the processing power, stability , reliability, security, scalability, manageability and other aspects of high requirements.

(5) Other electronic devices with data interaction function.

The device embodiments described above are only illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in One place, or it can be distributed over multiple network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

From the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a general hardware platform, and certainly can also be implemented by hardware. Based on this understanding, the above-mentioned technical solutions can be embodied in the form of software products in essence, or the parts that make contributions to related technologies, and the computer software products can be stored in computer-readable storage media, such as ROM/RAM, magnetic disks , optical disc, etc., including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform the methods described in various embodiments or some parts of the embodiments.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, but not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that it can still be The technical solutions described in the foregoing embodiments are modified, or some technical features thereof are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims (10)

1. A man-machine dialogue method, applied to a screen intelligent terminal device, the method comprising: After detecting the user's operation of opening a dialogue, start the full-duplex dialogue mode; performing speech recognition on the detected current user sentence, so as to determine the reply content corresponding to the current user sentence according to the obtained speech recognition result and present it to the user; If a new user sentence is detected before the reply content corresponding to the current user sentence is determined and presented to the user, a new reply content in response to the current user is determined according to the current user sentence and the new user sentence . 2. The method according to claim 1, wherein, if the interval duration from when the current user sentence is detected does not exceed a preset duration threshold when the new user sentence is detected, Then, according to the current user sentence and the new user sentence, it is determined that the new reply content in response to the current user includes: If it is determined that the new user sentence is a related sentence of the current user sentence, a new reply content in response to the current user is jointly determined according to the current user sentence and the new user sentence. 3. The method according to claim 2, wherein if it is determined that the new user sentence is not a related sentence of the current user sentence, determining the first reply content in response to the current user according to the current user sentence, according to The new user sentence determines the second reply content in response to the current user. 4. The method according to claim 1, wherein, if the interval duration from when the new user sentence is detected to when the current user sentence is detected exceeds a preset duration threshold, Then, according to the current user sentence and the new user sentence, it is determined that the new reply content in response to the current user includes: A new reply content in response to the current user is determined according to the new user sentence. 5. A man-machine dialogue system, applied to an intelligent terminal device with a screen, the system comprising: The dialogue mode startup module is used to start the full-duplex dialogue mode after detecting the operation of the user to open the dialogue; A speech recognition module, configured to perform speech recognition on the detected current user sentence, so as to determine the reply content corresponding to the current user sentence according to the obtained speech recognition result and present it to the user; The reply content determination module is configured to, if a new user sentence is detected before the reply content corresponding to the current user sentence is determined and presented to the user, determine a response to the user sentence according to the current user sentence and the new user sentence The new reply content for the current user. 6. The system according to claim 5, wherein, if the interval duration from when the current user sentence is detected does not exceed a preset duration threshold when the new user sentence is detected, Then, determining the new reply content in response to the current user according to the current user sentence and the new user sentence includes: if it is determined that the new user sentence is a related sentence of the current user sentence, then according to the current user sentence The sentence and the new user sentence together determine the new reply content in response to the current user. 7. The system according to claim 6, wherein if it is determined that the new user sentence is not a related sentence of the current user sentence, the first reply content in response to the current user is determined according to the current user sentence, according to The new user sentence determines the second reply content in response to the current user. 8. The system according to claim 5, wherein, if the interval duration from the time when the new user sentence is detected to when the current user sentence is detected exceeds a preset duration threshold, Then, determining the new reply content in response to the current user according to the current user sentence and the new user sentence includes: determining the new reply content in response to the current user according to the new user sentence. 9. An electronic device comprising: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor, the instructions Executed by the at least one processor to enable the at least one processor to perform the steps of the method of any of claims 1-4. 10. A storage medium on which a computer program is stored, characterized in that, when the program is executed by a processor, the steps of the method according to any one of claims 1-4 are implemented.

Images