Conversation processing method and device, electronic equipment and computer readable storage medium

Abstract

The embodiment of the invention discloses a dialogue processing method and device, electronic equipment and a computer readable storage medium, and the method comprises the steps that terminal equipment obtains dialogue content information of a dialogue request in response to the received dialogue request of a target user; generating target dialogue information for the dialogue content information according to target content information currently output by the terminal equipment; and outputting the target dialogue information. The target dialogue information for the user dialogue content information is generated based on the target content information currently output by the terminal equipment, so that the generation of the target dialogue information can consider the current scene, the matching degree between the target dialogue information and the user expectation is improved, and the user experience is improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computer technology, and specifically to a conversation processing method, device, electronic device, and computer-readable storage medium. Background Art

[0002] With the development of smart devices, the interaction capabilities between smart devices and users are constantly improving, the effects of content recommendation, dialogue generation and response control based on user needs are constantly being optimized, and users' dependence on smart devices is constantly increasing.

[0003] However, currently the interaction with smart devices is still mainly limited to simple content recommendation and dialogue generation, with less attention paid to the current scenario of the smart device, resulting in the quality of content recommendation or dialogue generation needs to be improved. Summary of the invention

[0004] The embodiments of the present application provide a dialogue processing method, device, electronic device and computer-readable storage medium, which can improve the matching degree between the output content of the terminal device and the user's expectations and improve the user experience.

[0005] In a first aspect, an embodiment of the present application provides a conversation processing method, which is applied to a terminal device, and the method includes:

[0006] In response to receiving a conversation request from a target user, acquiring conversation content information of the conversation request;

[0007] generating target conversation information for the conversation content information according to the target content information currently output by the terminal device;

[0008] The target dialogue information is output.

[0009] In a second aspect, an embodiment of the present application further provides a conversation processing device, applied to a terminal device, the device comprising:

[0010] A response module, configured to obtain the conversation content information of the conversation request in response to receiving the conversation request of the target user;

[0011] A generating module, configured to generate target conversation information for the conversation content information according to the target content information currently output by the terminal device;

[0012] An output module is used to output the target dialogue information.

[0013] Optionally, in some embodiments of the present application, generating target conversation information for the conversation content information according to the target content information currently output by the terminal device includes:

[0014] Determine content details and related information of the target content information by using the knowledge graph;

[0015] generating content data information according to the content detail information and the associated information;

[0016] Target dialog information for the dialog content information is generated based on the content data information.

[0017] Optionally, in some embodiments of the present application, generating target dialogue information for the dialogue content information according to the content data information includes:

[0018] Determining a dialogue processing model, wherein the dialogue processing model includes a model trained based on at least one regional cultural data set;

[0019] Extracting user portrait information of the target user, wherein the user portrait information at least represents the cultural characteristics of the target user;

[0020] The content data information, the conversation content information, the user portrait information and the context information are input into the conversation processing model to obtain target conversation information that conforms to the cultural characteristics of the target user.

[0021] Optionally, in some embodiments of the present application, the target content information includes film and television information, and the generating target dialogue information for the dialogue content information according to the target content information currently output by the terminal device includes:

[0022] Generating target dialogue information for the dialogue content information according to the video information currently output by the terminal device;

[0023] The target dialogue information includes at least one of plot explanation information, narrative background description information, tidbits information, subsequent plot prediction information, character profile information, hot comment information or review information.

[0024] Optionally, in some embodiments of the present application, the outputting the target dialogue information includes:

[0025] Determining a target virtual image and timbre information of the target virtual image according to the user portrait information of the target user;

[0026] The target dialogue information is output based on the target avatar and the timbre information.

[0027] Optionally, in some embodiments of the present application, generating target conversation information for the conversation content information according to the target content information currently output by the terminal device includes:

[0028] Acquire a facial image of the target user;

[0029] Determining current user emotion information of the target user according to the facial image and the conversation content information;

[0030] Target dialogue information for the dialogue content information is generated according to the user emotion information and the target content information currently output by the terminal device.

[0031] Optionally, in some embodiments of the present application, the dialogue content information includes segment generation indication information, and the target content information includes film and television information;

[0032] The generating target dialogue information for the dialogue content information according to the target content information currently output by the terminal device includes:

[0033] Extracting a segment from the film and television information according to the segment generation indication information to obtain film and television segment information;

[0034] The video clip information is used as target dialogue information.

[0035] In a third aspect, an embodiment of the present application further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps in the above-mentioned dialogue processing method when executed by the processor.

[0036] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the above-mentioned dialogue processing method are implemented.

[0037] In a fifth aspect, the embodiments of the present application further provide a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. The processor of the computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the method provided in various optional implementations described in the embodiments of the present application.

[0038] In response to receiving a conversation request from a target user, the terminal device of an embodiment of the present application obtains conversation content information of the conversation request, generates target conversation information for the conversation content information based on the target content information currently output by the terminal device, and outputs the target conversation information.

[0039] Among them, by generating target dialogue information for user dialogue content information based on the target content information currently output by the terminal device, the generation of the target dialogue information can take into account the current scenario, improve the matching degree between the target dialogue information and the user's expectations, and improve the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0041] Figure 1 is a schematic diagram of a scenario in which a terminal device according to an embodiment of the present application executes the conversation processing method;

[0042] Figure 2 It is a flowchart of a conversation processing method provided in an embodiment of the present application;

[0043] Figure 3 is a structural diagram of a conversation processing device provided in an embodiment of the present application;

[0044] Figure 4 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in this application to clearly and completely describe the technical solutions in this application. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments in the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0046] The embodiments of the present application provide a method, device, electronic device and computer-readable storage medium for dialogue processing. Specifically, the embodiments of the present application provide a dialogue processing device suitable for an electronic device, which is used to generate target dialogue information for a user dialogue request based on the currently output target content information, and output the target dialogue information to the user. Specifically, the electronic device includes a terminal device or a server, and the terminal device includes but is not limited to mobile phones, tablet computers, laptop computers, televisions and other devices. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks (CDN, Content Delivery Network), and basic cloud computing services such as big data and artificial intelligence platforms, etc. The server can be directly or indirectly connected via wired or wireless communication.

[0047] See also Figure 1 , Figure 1: is a schematic diagram of a scenario in which a terminal device according to an embodiment of the present application executes the conversation processing method, wherein the specific execution process of the terminal device executing the conversation processing method is as follows:

[0048] In response to receiving a conversation request from a target user, the terminal device 10 obtains conversation content information of the conversation request, generates target conversation information for the conversation content information according to the target content information currently output by the terminal device, and outputs the target conversation information.

[0049] For example, taking the terminal device as a smart TV, after receiving the user's conversation request, the smart TV parses and obtains the conversation content information, and then generates target conversation information for the conversation content information based on the currently playing video content, and outputs the target conversation information to the user.

[0050] In summary, the embodiment of the present application generates target conversation information for user conversation content information based on the target content information currently output by the terminal device, so that the generation of the target conversation information can take into account the current scenario, improve the matching degree between the target conversation information and the user's expectations, and improve the user experience.

[0051] It should be noted that the order of description of the following embodiments is not intended to limit the priority order of the embodiments.

[0052] See also Figure 2 , Figure 2 A flowchart of a conversation processing method provided in an embodiment of the present application. Although a logical sequence is shown in the flowchart, in some cases, the steps shown or described may be performed in an order different from that shown in the flowchart. Specifically, the conversation processing method is executed by a terminal device, and the process of the terminal device executing the conversation processing method specifically includes:

[0053] 101. In response to receiving a conversation request from a target user, obtain conversation content information of the conversation request.

[0054] It is understandable that the terminal device includes but is not limited to mobile phones, smart TVs, etc. The present application embodiment is described by taking a smart TV as an example.

[0055] It is understandable that the conversation request is usually for voice. For example, when a user interacts with a smart TV through voice, a conversation request is obtained by receiving the user's voice, and then the conversation content information is obtained by parsing the conversation request. The conversation content information includes the user's conversation demand information, for example, the conversation content information includes "please turn on XX TV series, play YY music", etc.

[0056] In the embodiment of the present application, a prompt word may also be displayed in the interface of the terminal device, and the prompt word may be generated based on the user's common instructions, habits or preferences.

[0057] 102. Generate target conversation information for the conversation content information according to the target content information currently output by the terminal device.

[0058] Among them, the target content information refers to the content information currently output by the terminal device, and the target content information includes film and television information, audio music information, etc. For example, if the terminal device (smart TV) is currently playing a TV series, then the TV series is the target content information; if the terminal device (smart TV) is currently playing music, then the music is the target content information.

[0059] It is understandable that the target dialogue information is generated based on the target content information currently being output by the terminal device, and the target dialogue information is information related to the target content information or generated with reference to the target content information. For example, the target dialogue information includes evaluation of film and television content, explanation of film and television content, switching to a new music song, etc.

[0060] 103. Output the target dialogue information.

[0061] Among them, by outputting the target dialogue information, feedback on the user dialogue is achieved, completing the human-computer interaction based on dialogue.

[0062] In summary, the embodiment of the present application generates target conversation information for user conversation content information based on the target content information currently output by the terminal device, so that the generation of the target conversation information can take into account the current scenario, improve the matching degree between the target conversation information and the user's expectations, and improve the user experience.

[0063] Optionally, in order to improve the accuracy of the target conversation information and further improve the matching degree between the target conversation information and the user's expectations, other information related to the target content information or more detailed information of the target content information may be considered to generate the target conversation information. That is, optionally, in some embodiments of the present application, the step of "generating the target conversation information for the conversation content information according to the target content information currently output by the terminal device" includes:

[0064] Determine content details and related information of the target content information by using the knowledge graph;

[0065] generating content data information according to the content detail information and the associated information;

[0066] Target dialog information for the dialog content information is generated based on the content data information.

[0067] Among them, the knowledge graph is pre-established and contains information related to the target content information, and the content details information is more detailed information for the target content information. For example, for movies and TV shows, if the target content information is the name of the movie, the playback progress, the current scene and other information, then the content details information includes more specific information about the movie and TV content, such as the movie introduction, the movie type, the movie language, the movie duration, the number of episodes, the story background, the shooting technique, the special effects type, etc. Among them, the associated information is information associated with the target content information, for example, the associated information includes user rating information, copyright information, the release area, the creative team, the actor information and other information related to the movie and TV content.

[0068] The content data information is relatively complete and comprehensive information including content detail information and associated information. For example, the content data information is obtained by combining the content detail information and the associated information.

[0069] Among them, by generating target dialogue information based on more detailed and relevant information, the accuracy of the generated target dialogue information is improved, and the matching degree between the generated target dialogue information and the user's expectations is further improved.

[0070] Optionally, in an embodiment of the present application, the target dialogue information may be generated by deep learning, machine learning or an artificial intelligence large model, that is, optionally, in some embodiments of the present application, the step of “generating target dialogue information for the dialogue content information according to the content data information” includes:

[0071] Determining a dialogue processing model, wherein the dialogue processing model includes a model trained based on at least one regional cultural data set;

[0072] Extracting user portrait information of the target user, wherein the user portrait information at least represents the cultural characteristics of the target user;

[0073] The content data information, the conversation content information, the user portrait information and the context information are input into the conversation processing model to obtain target conversation information that conforms to the cultural characteristics of the target user.

[0074] Among them, the dialogue processing model is obtained after training and optimization based on deep learning, machine learning or artificial intelligence large models. By using the dialogue processing model to generate dialogues, the relevance and matching of the dialogue content are improved. Compared with the traditional text matching solution based on a preset text library, the embodiment of the present application improves the fluency of the dialogue and improves the user experience. For example, the dialogue processing model includes a large model, which refers to a large language model (LLM, Large Language Model). The large language model is a natural language processing model based on deep learning technology, such as GPT-4, BERT, etc. It usually has a large number of parameters and complex structures, and can be trained on large-scale text data, so as to have a wide range of language understanding and generation capabilities.

[0075] Among them, the dialogue processing model is trained based on the regional cultural data set, so that the dialogue processing model can adapt to the characteristics of various regional cultures, which helps to meet the needs of users with different cultural backgrounds. Generating target dialogue information based on user portrait information that represents the cultural characteristics of the target user helps to generate target dialogue information that matches the cultural background of the target user and improves the quality of target dialogue information generation.

[0076] Among them, user portrait information is a comprehensive description of user characteristics, usually including the user's basic information, behavior data, interest preferences or cultural background, etc. User portraits are used for personalized recommendations and content generation.

[0077] The context information includes the surrounding text or context information of the conversation, such as the conversation text of the previous moments or the user's conversation habits and preferences.

[0078] For example, taking the terminal device currently playing a film or TV work as an example, the target dialogue information includes information for the film or TV work, that is, optionally, in some embodiments of the present application, the target content information includes film or TV information, and the step of "generating target dialogue information for the dialogue content information according to the target content information currently output by the terminal device" includes:

[0079] Generating target dialogue information for the dialogue content information according to the video information currently output by the terminal device;

[0080] The target dialogue information includes at least one of plot explanation information, narrative background description information, tidbits information, subsequent plot prediction information, character profile information, hot comment information or review information.

[0081] Therein, different target dialogue information corresponds to different dialogue content information, that is, the terminal device feeds back corresponding different response information based on different dialogue contents (such as questions).

[0082] Among them, the plot explanation information includes interpretation information for the plot. For example, in the case of a high-depth plot, the plot is explained based on the content that has been played or the content that has not been played, so that users can better understand the plot content. Correspondingly, the dialogue content information includes similar descriptions such as interpreting the current plot or explaining the current content.

[0083] Among them, the narrative background description information refers to the description of the relevant narrative background of the current plot. For example, the background of the current plot segment is explained to help users connect the previous story content. It is especially suitable for the situation where the previous playback content continues to be played after a long interval. The output of the narrative background description information helps users to associate with the previous story plot and enhance the viewing experience.

[0084] Among them, the behind-the-scenes information includes the behind-the-scenes information of the film and television work, which refers to the unused clips, actor's mistakes, improvisations, and behind-the-scenes anecdotes shot during the production process of the film and television work. These contents are usually edited into a separate video outside the official work for the audience to entertain and understand the other side of the production process. Among them, by showing the behind-the-scenes information corresponding to the currently playing video clip, it helps users to easily understand the shooting background of the current video clip, feel the shooting story behind the video clip, and enhance the user's immersion in the video information.

[0085] The subsequent plot prediction information refers to information predicting the subsequent plot direction based on the current video clip, for example, predicting the subsequent content or results that may occur based on the current plot judgment, etc. By responding to the user's plot prediction instructions and outputting the predicted direction based on the current plot content, anthropomorphic communication and discussion with the user on the plot direction is achieved, achieving the effect of accompanying the viewing of the movie.

[0086] Among them, the character profile information is information about the character profile. By outputting the character profile information, it helps users to understand the character's background in a timely manner. Among them, the character profile information not only includes the background introduction of the character in the plot, but also includes the relevant background information of the actor of the role, such as the relevant background of the real person.

[0087] Among them, the hot comment information is the current popular comment information of each user on the film and television work. By outputting the hot comment information, it is convenient for users to understand the evaluation content of the general users. The review information is the evaluation information on the plot output by the terminal device, which makes the terminal device humanized, comments on the plot with the vision of a companion, shares the movie watching with users, and improves the user experience.

[0088] Optionally, when outputting the target dialogue information, it can also be output based on a virtual character to enhance the diversity of interactive forms and improve user experience. That is, optionally, in some embodiments of the present application, the step of “outputting the target dialogue information” includes:

[0089] Determining a target virtual image and timbre information of the target virtual image according to the user portrait information of the target user;

[0090] The target dialogue information is output based on the target avatar and the timbre information.

[0091] The target avatar is a avatar that matches the target user, and the avatar refers to a virtual character created by digital technology with a specific appearance, personality, and functions, such as a virtual person. The target user can choose the avatar according to personal preference.

[0092] The timbre information refers to the characteristics or sound quality of the sound emitted. By determining the timbre information that matches the target user, the user's listening comfort can be improved when the voice broadcasts the target dialogue information.

[0093] Among them, by outputting target dialogue information based on a virtual image and determined timbre information, the interaction is made more vivid and closer to the user, thereby enhancing the user's immersion and satisfaction.

[0094] Optionally, in order to further improve the quality of the target dialogue information, the target dialogue information may be generated in combination with the user's emotions. That is, optionally, in some embodiments of the present application, the step of "generating target dialogue information for the dialogue content information according to the target content information currently output by the terminal device" includes:

[0095] Acquire a facial image of the target user;

[0096] Determining current user emotion information of the target user according to the facial image and the conversation content information;

[0097] Target dialogue information for the dialogue content information is generated according to the user emotion information and the target content information currently output by the terminal device.

[0098] In an embodiment of the present application, the user's emotions are analyzed through facial image recognition, which can be achieved through image recognition tools or based on a deep learning model.

[0099] Optionally, in an embodiment of the present application, a work segment may be generated based on the user's segment generation demand in combination with the target content information currently output by the terminal device. That is, optionally, in some embodiments of the present application, the dialogue content information includes segment generation indication information, and the target content information includes film and television information. The step of "generating target dialogue information for the dialogue content information according to the target content information currently output by the terminal device" includes:

[0100] Extracting a segment from the film and television information according to the segment generation indication information to obtain film and television segment information;

[0101] The video clip information is used as target dialogue information.

[0102] Among them, the fragment generation indication information is indication information for generating fragments, that is, it reflects the requirements of the fragments to be generated, and the film and television fragment information refers to film and television fragments or video fragments. For example, based on the fragment generation indication information, a video fragment is extracted from the film and television work currently being played on the terminal device.

[0103] For example, on a smart TV, an optional viewing assistant function page will appear when the user is watching a movie. The user can click on this page to enable the interactive function with the personalized viewing assistant. At this time, the user can have a conversation with the viewing assistant about the currently playing film and television content, and all conversation content will be presented in the form of a conversation stream. For example, the viewing assistant can be used to output plot explanation information, subsequent plot prediction information, or cut film and television clips.

[0104] In summary, the embodiment of the present application generates target conversation information for user conversation content information based on the target content information currently output by the terminal device, so that the generation of the target conversation information can take into account the current scenario, improve the matching degree between the target conversation information and the user's expectations, and improve the user experience.

[0105] Among them, by combining more detailed content details information and related information of the target content information, it is helpful to improve the matching degree between the target dialogue information and the user expectations and improve the user experience.

[0106] Among them, by training a dialogue processing model based on a regional cultural data set, and performing dialogue generation processing based on the dialogue processing model to obtain target dialogue information, the generated target dialogue information can adapt to the needs of users with different cultural backgrounds and avoid communication barriers caused by cultural differences.

[0107] Among them, by using virtual images and voices to output target dialogue information, the diversity of interaction forms is improved, making the interaction more vivid and close to users, thereby enhancing immersion and satisfaction.

[0108] Among them, in the embodiment of the present application, the user portrait information and the dialogue processing model can be updated regularly to ensure that the latest language and cultural changes can be captured, thereby significantly improving the adaptability, accuracy and personalized service capabilities of the system. The system can be continuously optimized and improved to maintain efficient and accurate service quality.

[0109] Among them, in the embodiments of the present application, in addition to the dialogue processing model, predefined rules and dictionaries can also be used to process user needs of different languages ​​and cultural backgrounds, rather than relying on large-scale pre-trained language models to achieve dialogue content processing.

[0110] In addition, in some scenarios, multiple regional expert systems can be developed, each system specializing in processing the needs of users with specific cultural and language backgrounds, that is, dialogue processing sub-models for each cultural background are configured separately to specifically process content processing tasks related to the specific cultural background. Furthermore, the dialogue processing sub-model that matches the user's cultural background can be pre-selected to process dialogue tasks. Specifically, configuring the dialogue processing sub-models for each cultural background helps to conduct targeted training of the model, while reducing unnecessary training of the parts that do not match the user's cultural background.

[0111] In order to better implement the conversation processing method of the present application, the present application also provides a conversation processing device based on the above conversation processing method. The meanings of the terms are the same as those in the above conversation processing method, and the specific implementation details can refer to the description in the method embodiment.

[0112] See also Figure 3 , Figure 3 : is a structural diagram of a dialog processing device provided in an embodiment of the present application. The dialog processing device is applied to a terminal device. The dialog processing device may be specifically as follows:

[0113] A response module 201 is used for obtaining the conversation content information of the conversation request in response to receiving the conversation request of the target user;

[0114] A generating module 202, configured to generate target conversation information for the conversation content information according to the target content information currently output by the terminal device;

[0115] The output module 203 is used to output the target dialogue information.

[0116] Optionally, in some embodiments of the present application, generating target conversation information for the conversation content information according to the target content information currently output by the terminal device includes:

[0117] Determine content details and related information of the target content information by using the knowledge graph;

[0118] generating content data information according to the content detail information and the associated information;

[0119] Target dialog information for the dialog content information is generated based on the content data information.

[0120] Optionally, in some embodiments of the present application, generating target dialogue information for the dialogue content information according to the content data information includes:

[0121] Determining a dialogue processing model, wherein the dialogue processing model includes a model trained based on at least one regional cultural data set;

[0122] Extracting user portrait information of the target user, wherein the user portrait information at least represents the cultural characteristics of the target user;

[0123] The content data information, the conversation content information, the user portrait information and the context information are input into the conversation processing model to obtain target conversation information that conforms to the cultural characteristics of the target user.

[0124] Optionally, in some embodiments of the present application, the target content information includes film and television information, and the generating target dialogue information for the dialogue content information according to the target content information currently output by the terminal device includes:

[0125] Generating target dialogue information for the dialogue content information according to the video information currently output by the terminal device;

[0126] The target dialogue information includes at least one of plot explanation information, narrative background description information, tidbits information, subsequent plot prediction information, character profile information, hot comment information or review information.

[0127] Optionally, in some embodiments of the present application, the outputting the target dialogue information includes:

[0128] Determining a target virtual image and timbre information of the target virtual image according to the user portrait information of the target user;

[0129] The target dialogue information is output based on the target avatar and the timbre information.

[0130] Optionally, in some embodiments of the present application, generating target conversation information for the conversation content information according to the target content information currently output by the terminal device includes:

[0131] Acquire a facial image of the target user;

[0132] Determining current user emotion information of the target user according to the facial image and the conversation content information;

[0133] Target dialogue information for the dialogue content information is generated according to the user emotion information and the target content information currently output by the terminal device.

[0134] Optionally, in some embodiments of the present application, the dialogue content information includes segment generation indication information, and the target content information includes film and television information;

[0135] The generating target dialogue information for the dialogue content information according to the target content information currently output by the terminal device includes:

[0136] Extracting a segment from the film and television information according to the segment generation indication information to obtain film and television segment information;

[0137] The video clip information is used as target dialogue information.

[0138] In the embodiment of the present application, the response module 201 responds to receiving a conversation request from a target user and obtains the conversation content information of the conversation request. The generation module 202 is used to generate target conversation information for the conversation content information based on the target content information currently output by the terminal device, and the output module 203 outputs the target conversation information.

[0139] Among them, the embodiment of the present application generates target conversation information for user conversation content information based on the target content information currently output by the terminal device, so that the generation of the target conversation information can take into account the current scenario, improve the matching degree between the target conversation information and the user's expectations, and improve the user experience.

[0140] In addition, the present application also provides an electronic device, such as Figure 4 As shown, it shows a schematic diagram of the structure of the electronic device involved in this application, specifically:

[0141] The electronic device may include components such as a processor 301 with one or more processing cores, a memory 302 with one or more computer-readable storage media, a power supply 303, and an input unit 304. Those skilled in the art will appreciate that Figure 4 The electronic device structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0142] The processor 301 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. By running or executing software programs and / or modules stored in the memory 302, and calling data stored in the memory 302, it executes various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole. Optionally, the processor 301 may include one or more processing cores; preferably, the processor 301 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 301.

[0143] The memory 302 can be used to store software programs and modules. The processor 301 executes various functional applications and data processing by running the software programs and modules stored in the memory 302. The memory 302 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 302 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 302 may also include a memory controller to provide the processor 301 with access to the memory 302.

[0144] The electronic device also includes a power supply 303 for supplying power to various components. Preferably, the power supply 303 can be logically connected to the processor 301 through a power management system, so as to manage charging, discharging, and power consumption through the power management system. The power supply 303 can also include any components such as one or more DC or AC power supplies, recharging systems, power supply device debugging circuits, power converters or inverters, and power status indicators.

[0145] The electronic device may further include an input unit 304, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0146] Although not shown, the electronic device may further include a display unit, etc., which will not be described in detail herein. Specifically in this embodiment, the processor 301 in the electronic device will load the executable files corresponding to the processes of one or more application programs into the memory 302 according to the following instructions, and the processor 301 will run the application programs stored in the memory 302, thereby implementing the steps in any one of the dialogue processing methods provided in the embodiments of the present application.

[0147] In response to receiving a conversation request from a target user, the terminal device of an embodiment of the present application obtains conversation content information of the conversation request, generates target conversation information for the conversation content information based on the target content information currently output by the terminal device, and outputs the target conversation information.

[0148] Among them, by generating target dialogue information for user dialogue content information based on the target content information currently output by the terminal device, the generation of the target dialogue information can take into account the current scenario, improve the matching degree between the target dialogue information and the user's expectations, and improve the user experience.

[0149] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0150] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0151] To this end, the present application provides a computer-readable storage medium, on which a computer program is stored. The computer program can be loaded by a processor to execute the steps in any one of the dialogue processing methods provided in the present application.

[0152] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0153] The computer-readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0154] Since the instructions stored in the computer-readable storage medium can execute the steps in any dialogue processing method provided in the present application, the beneficial effects that can be achieved by any dialogue processing method provided in the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0155] The above is a detailed introduction to a dialogue processing method, device, electronic device and computer-readable storage medium provided by the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for processing a conversation, characterized in that: Applied to a terminal device, the method comprises: In response to receiving a conversation request from a target user, acquiring conversation content information of the conversation request; generating target conversation information for the conversation content information according to the target content information currently output by the terminal device; The target dialogue information is output.

2. The method for processing a conversation according to claim 1, characterized in that: The generating target dialogue information for the dialogue content information according to the target content information currently output by the terminal device includes: Determine content details and related information of the target content information by using the knowledge graph; generating content data information according to the content detail information and the associated information; Target dialog information for the dialog content information is generated based on the content data information.

3. The method for processing a conversation according to claim 2, characterized in that: The step of generating target dialogue information for the dialogue content information according to the content data information includes: Determining a dialogue processing model, wherein the dialogue processing model includes a model trained based on at least one regional cultural data set; Extracting user portrait information of the target user, wherein the user portrait information at least represents the cultural characteristics of the target user; The content data information, the conversation content information, the user portrait information and the context information are input into the conversation processing model to obtain target conversation information that conforms to the cultural characteristics of the target user.

4. The method for processing a conversation according to claim 1, characterized in that: The target content information includes film and television information, and the generating target dialogue information for the dialogue content information according to the target content information currently output by the terminal device includes: Generating target dialogue information for the dialogue content information according to the video information currently output by the terminal device; The target dialogue information includes at least one of plot explanation information, narrative background description information, tidbits information, subsequent plot prediction information, character profile information, hot comment information or review information.

5. The method for processing a conversation according to claim 1, characterized in that: The outputting the target dialogue information includes: Determining a target virtual image and timbre information of the target virtual image according to the user portrait information of the target user; The target dialogue information is output based on the target avatar and the timbre information.

6. The method for processing a conversation according to claim 1, characterized in that: The generating target dialogue information for the dialogue content information according to the target content information currently output by the terminal device includes: Acquire a facial image of the target user; Determining current user emotion information of the target user according to the facial image and the conversation content information; Target dialogue information for the dialogue content information is generated according to the user emotion information and the target content information currently output by the terminal device.

7. The method for processing a conversation according to claim 1, characterized in that: The dialogue content information includes segment generation indication information, and the target content information includes film and television information; The generating target dialogue information for the dialogue content information according to the target content information currently output by the terminal device includes: Extracting a segment from the film and television information according to the segment generation indication information to obtain film and television segment information; The video clip information is used as target dialogue information.

8. A dialogue processing device, characterized in that: Applied to a terminal device, the device comprises: A response module, configured to obtain the conversation content information of the conversation request in response to receiving the conversation request of the target user; A generating module, configured to generate target conversation information for the conversation content information according to the target content information currently output by the terminal device; An output module is used to output the target dialogue information.

9. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the dialogue processing method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the dialog processing method according to any one of claims 1 to 7 are implemented.

Images