Configuration method and device of conversation robot, electronic equipment, medium and product

Abstract

The invention relates to a configuration method and device of a dialogue robot, electronic equipment, a medium and a product, and relates to the technical field of artificial intelligence. The dialogue robot configuration method comprises the steps that a dialogue robot is created for a first user, and the dialogue robot is used for assisting the first user in dialogue with a second user; displaying a configuration interface of a dialogue robot of the first user; and through the configuration interface, a configuration instruction is sent to the dialogue robot, and the configuration instruction comprises a dialogue strategy.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, and in particular to a configuration method, device, electronic device, medium and product of a conversational robot. Background Art

[0002] With the development of artificial intelligence and machine learning technologies, machine learning models can be used to implement intelligent conversational robots. For example, intelligent conversational robots can serve as intelligent customer service and virtual friends, receiving inquiries sent by users and providing feedback on answers to users. Summary of the invention

[0003] This summary is provided to introduce concepts in a brief form that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0004] According to some embodiments of the present disclosure, a configuration method for a conversational robot is provided, comprising: creating a conversational robot for a first user, wherein the conversational robot is used to assist the first user in having a conversation with a second user; displaying a configuration interface of the conversational robot for the first user; and sending configuration instructions to the conversational robot through the configuration interface, wherein the configuration instructions include a conversation strategy.

[0005] According to some embodiments of the present disclosure, a configuration device for a conversational robot is provided, comprising: a creation module, configured to create a conversational robot for a first user, wherein the conversational robot is used to assist the first user in having a conversation with a second user; a display module, configured to display a configuration interface of the conversational robot for the first user; and a sending module, configured to send configuration instructions to the conversational robot through the configuration interface, wherein the configuration instructions include a conversation strategy.

[0006] According to some embodiments of the present disclosure, there is provided an electronic device, comprising: a memory; and a processor coupled to the memory, wherein the processor is configured to execute a configuration method of a conversational robot of any embodiment described in the present disclosure based on instructions stored in the memory.

[0007] According to some embodiments of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the configuration method of the conversational robot of any embodiment described in the present disclosure is performed.

[0008] According to some embodiments of the present disclosure, a computer program product is provided. When the computer program product is executed on a computer, the computer implements the configuration method of the conversational robot of any embodiment described in the present disclosure.

[0009] According to some embodiments of the present disclosure, a computer program is provided, comprising: instructions, which, when executed by a processor, cause the processor to execute the method for configuring a conversational robot according to any one of the embodiments described in the present disclosure.

[0010] Other features, aspects and advantages of the present disclosure will become apparent from the following detailed description of exemplary embodiments of the present disclosure with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The preferred embodiments of the present disclosure are described below with reference to the accompanying drawings. The drawings described herein are used to provide a further understanding of the present disclosure. Each of the drawings together with the following detailed description is included in this specification and forms a part of the specification, and is used to explain the present disclosure. It should be understood that the drawings described below only relate to some embodiments of the present disclosure and do not constitute a limitation on the present disclosure. In the drawings:

[0012] Figure 1 A flowchart of a method for configuring a conversational robot according to some embodiments of the present disclosure is shown.

[0013] Figure 2A A schematic diagram of an interface for a conversation between a first user and a second user according to some embodiments of the present disclosure is shown.

[0014] Figure 2B A schematic diagram of an interface for a conversation between a first user and a second user according to some other embodiments of the present disclosure is shown.

[0015] Figure 3A A schematic diagram of a creation interface for a conversational robot according to some embodiments of the present disclosure is shown.

[0016] Figure 3B A schematic diagram of a setting interface of a conversational robot according to some embodiments of the present disclosure is exemplarily shown.

[0017] Figure 3C A schematic diagram of a conversation interface between a first user and a conversation robot according to some embodiments of the present disclosure is shown.

[0018] Figure 3D A schematic diagram of an agent selection interface according to some embodiments of the present disclosure is shown.

[0019] Figure 3E A schematic diagram of a conversation interface between a conversation robot and an intelligent agent according to some embodiments of the present disclosure is shown.

[0020] Figure 4 A schematic diagram of a historical conversation record interface according to some embodiments of the present disclosure is shown.

[0021] Figure 5 A schematic diagram of the structure of a configuration device of a conversational robot according to some embodiments of the present disclosure is shown.

[0022] Figure 6 A schematic structural diagram of an electronic device according to some embodiments of the present disclosure is shown.

[0023] Figure 7 A schematic diagram of the structure of a computer system according to some embodiments of the present disclosure is shown.

[0024] It should be understood that, for ease of description, the sizes of the various parts shown in the drawings are not necessarily drawn according to the actual proportional relationship. The same or similar reference numerals are used in the various drawings to represent the same or similar parts. Therefore, once an item is defined in one drawing, it may not be further discussed in subsequent drawings. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure, but it is obvious that the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments. The following description of the embodiments is actually only illustrative and is by no means intended to limit the present disclosure and its application or use. It should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein.

[0026] It should be understood that the various steps recorded in the method embodiments of the present disclosure can be performed in different orders, and / or performed in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown in the execution. The scope of the present disclosure is not limited in this respect. Unless otherwise specifically stated, the relative arrangement, numerical expressions and numerical values ​​of the parts and steps set forth in these embodiments should be interpreted as being merely exemplary and do not limit the scope of the present disclosure.

[0027] The term "include" and its variations used in the present disclosure mean an open term that includes at least the following elements / features but does not exclude other elements / features, that is, "including but not limited to". In addition, the term "include" and its variations used in the present disclosure mean an open term that includes at least the following elements / features but does not exclude other elements / features, that is, "including but not limited to". Therefore, include is synonymous with include. The term "based on" means "based at least in part on".

[0028] References throughout this specification to "one embodiment," "some embodiments," or "an embodiment" mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. For example, the term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; and the term "some embodiments" means "at least some embodiments." Furthermore, the appearances of the phrases "in one embodiment," "in some embodiments," or "in an embodiment" in various places throughout this specification do not necessarily all refer to the same embodiment, but may do so.

[0029] It should be noted that the concepts of "first", "second", etc. mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units. Unless otherwise specified, the concepts of "first", "second", etc. are not intended to imply that the objects described in this way must be in a given order in time, space, ranking, or any other manner.

[0030] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0031] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0032] The embodiments of the present disclosure are described in detail below in conjunction with the accompanying drawings, but the present disclosure is not limited to these specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. In addition, in one or more embodiments, specific features, structures or characteristics can be combined in any suitable manner that will be clear from the present disclosure by a person of ordinary skill in the art.

[0033] It should be understood that the present disclosure does not limit how to obtain the image to be applied / processed. In one embodiment of the present disclosure, it can be obtained from a storage device, such as an internal memory or an external storage device. In another embodiment of the present disclosure, a photographic component can be mobilized to shoot. It should be noted that the acquired image can be a captured image or a frame of an image in a captured video, and is not particularly limited to this.

[0034] In the context of the present disclosure, an image may refer to any of a variety of images, such as a color image, a grayscale image, etc. It should be noted that in the context of the present specification, the type of image is not specifically limited. In addition, the image may be any appropriate image, such as an original image obtained by a camera device, or an image that has been subjected to specific processing, such as preliminary filtering, anti-aliasing, color adjustment, contrast adjustment, normalization, etc. It should be noted that the preprocessing operation may also include other types of preprocessing operations known in the art, which will not be described in detail here.

[0035] In the scenario of using intelligent conversational robots in related technologies, the robots are mainly provided by application developers and are used as a party to the conversation with the user, that is, the respondent of the message sent by the user. The robot can respond to the message sent by the user according to the user's input and its own knowledge base.

[0036] In the related art, robots can only communicate according to fixed configurations provided by the application side, and cannot be applied to each user's personalized online social scene. The embodiment of the present disclosure provides a robot configuration method, so that the configured robot can assist a user in communicating with other users.

[0037] Figure 1 FIG. 1 is a flow chart showing a method for configuring a conversational robot according to some embodiments of the present disclosure. Figure 1 As shown, this embodiment includes steps S102 to S106.

[0038] In step S102, a conversation robot is created for the first user, where the conversation robot is used to assist the first user in conversing with the second user.

[0039] This embodiment describes the process of creating a conversation robot for the first user to provide assistance in the conversation scenario between the first user and other users. Other users may be any user except the first user, or other designated users except the first user. For ease of description, the embodiment of the present disclosure refers to the user who has a conversation with the first user as the second user. The second user can be one or any one of a set of users. It should be noted that the conversation between the first user and the second user may include messages sent by both the first user and the second user, or may only include messages sent by the second user because the first user did not check and reply to the message in time, or may only include messages sent by the first user.

[0040] The first user can be understood as the user of the current application, so this embodiment can also be understood as a process in which the first user specifically configures the information under his account.

[0041] A conversation robot refers to a robot that can chat and talk with other subjects. The other subjects can be real people or other conversation robots. The conversation robot can generate corresponding response content based on the messages output by other subjects in the conversation scene. The robot in the embodiment of the present disclosure refers to an intelligent agent that can generate responses to input information, which can be implemented in software, hardware, or a combination of software and hardware. The robot can also be called a virtual agent of a digital person or a machine learning model. The robot can be implemented based on a machine learning model, such as a large language model (LLM) or a foundation model. The machine learning model can be a generative model, which is used to output target content based on input information. The information input by the generative model includes the processing basis of the generative model in the generation process, such as which information is referenced to perform the generation process, the requirements of the output target content, etc. The generative model includes, for example, a model generated based on text, or a model generated based on an image, and the output of the generative model can include text, images, or a combination of the two. Of course, the input or output of the generative model can also be data of other modalities, such as audio, video, or a combination of multiple types of data. The generative model can be a single-modal model, such as a model that generates text from text (referred to as the "text-to-text model") or a model that generates images from images (referred to as the "image-to-image model"). Alternatively, the generative model can be a cross-modal model, that is, a model whose input and output belong to different modalities, such as a model that generates images from text (referred to as the "text-to-image model"). Alternatively, the input of the generative model can include multiple modalities, and the output can also include multiple modalities.

[0042] Creating a conversational robot means generating a conversational robot object based on some basic information. Basic information includes, for example, name, avatar, voice, etc., and may further include the robot's personality, gender, age, etc. This basic information can be input by the user or generated randomly. The conversational robot can be created automatically, for example, with the authorization of the first user, in response to the account generation of the first user; or it can be started in response to the triggering operation of the first user on the creation process during the use of the application by the first user.

[0043] After the conversation robot is created, the conversation robot can be used directly to assist the conversation of the first user, or the conversation robot can be allowed to assist the conversation only after the conversation robot is configured for the conversation. In the former case, the default general configuration performed by the conversation robot can be used.

[0044] Assisting the first user to have a conversation with the second user means to have a conversation with other users on behalf of the first user; or to participate in the conversation between the first user and other users. That is, in the conversation scenario between the first user and the second user, the conversation robot can directly replace the first user, for example, as the "virtual avatar" (such as AI avatar) of the first user, and the conversation robot can have a conversation with the second user; or, in the conversation scenario between the first user and the second user, the conversation robot can directly participate in the conversation between the first user and the second user, and the result is similar to a "group chat" between the first user, the conversation robot, and the second user, so as to make communication with the first user and the second user smoother, or to improve the fun and richness of the chat between the first user and the second user.

[0045] In step S104, a configuration interface of the conversational robot of the first user is displayed.

[0046] The configuration interface is used to configure the dialogue strategy. The dialogue strategy refers to the way in which the robot should dialogue with the second user in a certain scenario, so that the robot can generate more reasonable, effective, or vivid responses for specific dialogue scenarios. The first user can configure one or more dialogue strategies. For example, the configuration of multiple dialogue strategies can be achieved through a single configuration process, or the configuration can be performed through multiple configuration processes.

[0047] The configuration interface is used to receive the specific content of the dialogue strategy input by the first user, feedback information of the existing dialogue strategy, reference dialogues that can be used to extract the dialogue strategy, or other forms of content, which are not limited in the embodiments of the present disclosure.

[0048] In step S106, a configuration instruction is sent to the dialogue robot through a configuration interface, and the configuration instruction includes a dialogue strategy.

[0049] In some embodiments, a dialog strategy is generated based on information received through the configuration interface, and configuration instructions are further generated based on the dialog strategy.

[0050] The configuration instruction may also include instruction information, such as for instructing the conversational robot to save the conversational strategy or information determined based on the conversational strategy, and to call the conversational strategy in the conversational scenario of the first user. After receiving the input information through the configuration interface, the robot may be instructed to perform corresponding configuration operations according to the received information, such as storing the conversational strategy, or adjusting the processing logic of the robot based on the conversational strategy, or fine-tuning the machine learning model on which the robot relies.

[0051] After the configuration is completed, the conversational robot can perform corresponding conversation-related operations according to the conversation strategy in the conversation scenario of the first user, such as participating in the conversation and sending conversation messages in a specific form or content.

[0052] It should be noted that the first user can create one or more dialogue robots, and the embodiments of the present disclosure can be used to perform the creation and dialogue strategy configuration process for each robot.

[0053] The above embodiment can use the conversation robot to assist the first user in the conversation process between the first user and other users. In order to realize the auxiliary function of the conversation robot, the above embodiment provides a configuration interface of the conversation strategy to instruct the robot to configure the conversation strategy. As a result, the conversation robot can provide more accurate and effective responses in various conversation scenarios of the first user, thereby improving the conversation effect of assisting the first user and the second user in the conversation.

[0054] In some embodiments, the configuration instruction includes a dialogue strategy for a specified dialogue scenario, the dialogue scenario including at least one of the dialogue between the first user and the second user including a specified dialogue topic, the second user belonging to a specified category, the second user being a specified user, and the dialogue state of the first user belonging to a specified state; the dialogue strategy includes a strategy for whether the dialogue robot participates in the dialogue between the first user and the second user, and at least one of the language style of the dialogue robot.

[0055] The conversation topic included in the conversation between the first user and the second user can be determined by keywords included in the conversation or semantic key information extracted after semantic processing of the conversation. That is, an exemplary scenario may be that when the first user and the second user discuss a specified content, a specific conversation strategy is used.

[0056] The category of the second user can be pre-specified by the first user, such as "family", "friend", "college classmate", etc., or it can be automatically determined based on the basic information of the second user. That is, an exemplary scenario can be that the first user uses a specific dialogue strategy when talking to a specific user. The specific user can be a user of a specific category or a user specified by the first user.

[0057] The conversation status of the first user is used to indicate the first user's current level of participation and whether the first user can reply to the message sent by the second user in a timely manner. In some embodiments, the conversation status of the first user can be determined based on the frequency of the first user's message sending and the duration of the message reply. For example, in a conversation between a first user and a second user, the last message comes from the second user, and the sending time of the last message exceeds a threshold from the current time, then the first user is considered to be in the specified state of "busy". For another example, if the first user can reply to most of the messages of the second user in a timely manner, then the first user is considered to be in the specified state of "online". Of course, the above states are only schematic, and those skilled in the art can set various conversation states and their names as needed.

[0058] The dialogue strategy includes a strategy for whether the dialogue robot participates in the dialogue between the first user and the second user, that is, a strategy for the dialogue robot to automatically "appear". Based on the configuration instructions, it can be indicated in which scenario the dialogue robot automatically appears and assists the first user in the dialogue.

[0059] The dialogue strategy includes the language style of the dialogue robot, that is, what language style the robot uses to assist the first user in the dialogue. The language style includes, for example, tone, catchphrase, regional style, etc. Based on the configuration instructions, the dialogue robot can be instructed to use the dialogue strategy corresponding to one or more dialogue scenarios.

[0060] For the same dialogue scenario, multiple strategies of different dimensions can be configured; for the same dialogue strategy, multiple dialogue scenarios can also be set, that is, the same dialogue strategy can be used in multiple dialogue scenarios. The following describes several combinations of dialogue scenarios and dialogue strategies by way of example.

[0061] In some embodiments, the first conversation scenario includes at least one of a conversation between the first user and the second user, including a specified conversation topic, the second user belonging to a specified category, the second user being a specified user, and the conversation state of the first user belonging to a specified state, and the conversation strategy for the specified conversation scenario includes: in response to detecting the first conversation scenario, participating in the conversation between the first user and the second user.

[0062] For example, in a conversation scenario between a first user and a second user, in response to a message sent by the first user or a message sent by the second user including a specified topic, or in response to a message sent by the first user and the second user both including a specified topic, the conversation robot is automatically called to participate in the conversation between the first user and the second user. Thus, the conversation robot can provide more information on the specified topic for the conversation between the first user and the second user. For example, when the first user and the second user are talking about a certain scenic spot, the conversation robot can participate in the conversation and provide some travel tips; for another example, when the first user and the second user are talking about a certain movie, the conversation robot can provide relevant information about the movie.

[0063] For another example, in a conversation scenario between a first user and a second user, in response to the second user belonging to a specified category or being a specified user, a conversation robot is automatically called to participate in the conversation between the first user and the second user. The conversation robot can be called when the first user sends a message to the second user for the first time, or when the time of the last conversation between the first user and the second user exceeds a specified threshold from the current time, the first user initiates a conversation with the second user again, and the conversation robot is automatically called. For example, the first user is not good at speaking, and the second user is more important to the first user. When talking to the second user, by calling the conversation robot, the conversation atmosphere between the first user and the second user can be enlivened.

[0064] For another example, in a conversation scenario between a first user and a second user, in response to the first user being in a specified state, a conversation robot is automatically called to participate in the conversation between the first user and the second user. For example, in response to the last message from the second user in the conversation between the first user and the second user, the sending time of the last message exceeds a threshold from the current time, which means that the first user has not replied to the second user for a long time. At this time, by calling the conversation robot to participate in the conversation, the conversation robot can reply to the second user instead of the first user. This can help the user in time when the first user is busy.

[0065] In some embodiments, the second dialogue scenario includes at least one of the second user belonging to a specified category and the second user belonging to a specified user, and the dialogue strategy for the specified dialogue scenario includes: in response to detecting the second dialogue scenario, determining a language style based on an identifier of the second user having a dialogue with the first user or a category to which the second user belongs. Thus, when the dialogue robot participates in a dialogue between the first user and the second user, the language style can be used to send messages.

[0066] For example, the conversation robot can use light-hearted and humorous language in messages sent to the first user's friends; it should avoid using teasing language in messages sent to the first user's boss, etc. Thus, the conversation robot can use different language styles to participate in conversations with different users, which improves the flexibility of the conversation robot.

[0067] In some embodiments, the third dialogue scenario includes that the topic of the dialogue belongs to a topic of a specified category, and the dialogue strategy for the specified dialogue scenario includes: in response to detecting the third dialogue scenario, determining a language style based on the topic of the dialogue between the first user and the second user, and participating in the dialogue based on the language style. For example, for topics related to life, light-hearted and humorous language can be used; for topics related to science, rigorous language can be used. Thus, the dialogue language style of the dialogue robot can be enriched.

[0068] Figure 2A FIG. 1 shows a schematic diagram of an interface for a conversation between a first user and a second user after configuring the conversation robot. Figure 2A As shown, the dialogue interface 21 of this embodiment includes a dialogue between user 1 and user 2, and the users are discussing the topic of where to go for vacation.

[0069] In some embodiments, the topic of the conversation can be determined to be a trip to Beijing by parsing the conversation content, and at this time, the conversation robot AA of user 1 can participate in the conversation. In some embodiments, by determining that user 2 who is talking to user 1 is a friend of user 1, the conversation robot AA can be called to appear in the conversation between the two and reply in a relaxed tone. In the conversation interface 21, control 221 can be used to indicate that the conversation robot AA is in a state of participating in the conversation, and control 222 can be used to indicate that the conversation robot CC is not in a state of participating in the conversation. User 1 can also manually control whether these conversation robots participate in the conversation by triggering these controls.

[0070] Figure 2B FIG. 2 shows a schematic diagram of an interface for a conversation between a first user and a second user according to some other embodiments of the present disclosure. Figure 2B As shown, the dialogue interface 22 of this embodiment is a dialogue interface between user 1 and user 2, and user 2 sent a message, but did not get a reply from user 1 after a period of time. By judging that user 1 is in the "busy" state, user 1's digital avatar (i.e., dialogue robot) AA is automatically called and replies. According to the setting information, another dialogue robot CC is also automatically called according to the dialogue scene, and replies in a teasing tone in the specified dialogue strategy. Controls 221 and 222 can be used in the dialogue interface 22 to respectively indicate that the two dialogue robots are in a state of participating in the dialogue.

[0071] The above is an exemplary description of the content of the configuration instruction. The following is an exemplary description of several implementations of the creation and configuration interface of the conversational robot.

[0072] Figure 3A The following is a schematic diagram of a creation interface of a conversational robot according to some embodiments of the present disclosure. Figure 3A As shown, the creation interface 31 of this embodiment is an image creation interface, including an image adding control 311 for the first user to upload an image. The upload control 311 can be used to read a local gallery or a network gallery with the authorization of the first user, or to call the camera of the first user's terminal to take a photo with the authorization of the first user.

[0073] The creation interface 31 may also include one or more image style controls 312 to 315 to generate an image of the robot (eg, avatar, portrait, full-body image) based on the image added by the user and the image style selected.

[0074] In some embodiments, the user may also input description information of the image style to process the added image more flexibly. For example, the image of the conversational robot may be generated based on the style description information input by the first user and the image from the first user authorized by the first user; the conversational robot may be created for the first user based on the image of the conversational robot. For example, the creation interface 31 may include an input control 316 for accepting the style description information input by the first user. After the user confirms the input content, the image added by the first user and the style description information may be input into the generative model for generating the image, so that the image added by the first user may be processed based on the style description information to generate an image with a corresponding style as the image of the conversational robot.

[0075] The creation interface 31 may also include a generation control 317 to preview the generated image of the conversation robot. According to the preview result, the first user may decide whether to regenerate the image of the conversation robot.

[0076] In some embodiments, based on the voice of the first user authorized by the first user, the voice information of the conversation robot is generated; based on the voice information of the conversation robot, the conversation robot is created for the first user. Thus, the created conversation robot can imitate the voice of the first user, and when playing the message sent by the conversation robot in an audible manner, the conversation robot can speak in a voice similar to the first user, thereby strengthening the attribute of the conversation robot as the digital avatar of the first user.

[0077] Figure 3BThe following is a schematic diagram of the setting interface of a conversational robot according to some embodiments of the present disclosure. Figure 3B As shown, the setting interface 32 is used to set the digital avatar robot AA created by the first user and display the set information, including a voice setting control 321. Through this control, the first user can upload his own voice or select other voices provided by the application. For example, the user's reading sample can be displayed, and the voice of the user speaking the reading sample can be collected with the user's authorization, and the voiceprint information can be extracted from it as the voiceprint information of the conversation robot.

[0078] The setting interface 32 may also include a permission setting control 322 to set which users the conversation robot is used to have conversation scenarios with.

[0079] The setting interface 32 may also include a setting information display control 323, which in this embodiment exemplarily includes the hobbies and birthday of the conversational robot. The setting information display control 323 may be directly input or modified by the user, or may be automatically generated based on the chat content between the first user and the conversational robot. This can improve the convenience of setting the conversational robot.

[0080] Figure 3C A schematic diagram of a conversation interface between a first user and a conversation robot according to some embodiments of the present disclosure is shown. Figure 3C As shown, interface 33 is a dialogue interface between the first user and the dialogue robot AA of the first user. In the dialogue interface of this embodiment, the message 331 on the left is sent by the dialogue robot, and the message 332 on the right is sent by the first user.

[0081] In this embodiment, the conversation robot AA actively asks the user "What are your hobbies?" to guide the user to send setting information. The first user sends "I usually read books, watch musicals, dance, exercise, and go out", so that the conversation robot AA, which is the digital avatar of the first user, can use this information as its own setting information, so as to assist the first user in the conversation based on the setting information.

[0082] The dialogue interface 33 may further include a test control 333. The avatar test control 333 may trigger the dialogue robot AA to chat with other agents (i.e., dialogue robots) so that the user can refer to whether the current dialogue strategy of the dialogue robot AA is ideal. The other agents may also be created by the first user, or may be from other users and publicly released or shared with the first user, or may be default agents provided by the application. In response to the user triggering the test control 333, a dialog box such as Figure 3DThe agent selection interface 334 shown includes one or more agents and confirmation controls corresponding to the agents. For example, when the first user selects the dialogue scene between the test dialogue robot AA and the "ex-boyfriend", the control 3341 can be triggered.

[0083] After the control 3341 is triggered, the following may be displayed: Figure 3E The interface shown. Figure 3E A schematic diagram of a dialogue interface between a dialogue robot and an intelligent agent according to some embodiments of the present disclosure is shown. Figure 3E As shown, in the dialogue interface 35, the dialogue robot AA can automatically conduct a dialogue with the intelligent agent "ex-boyfriend" according to the configured dialogue strategy. When a dialogue ends, the dialogue robot AA can continue to send the dialogue through the continue dialogue control 351. The automatic reply control 352 can be used to control whether the dialogue robot automatically replies to the content sent by the intelligent agent. In this dialogue, other intelligent agents can also be invited to test the group chat through the invitation control 353.

[0084] Back to Figure 3C The dialogue interface 33 may further include a control 334 for setting an image and a control 335 for setting a sound, so as to further set or adjust the basic information of the dialogue robot.

[0085] After creating a conversational robot, you can configure the conversational strategy of the conversational robot through various types of configuration interfaces.

[0086] In some embodiments, the configuration interface includes a first dialogue interface between the first user and the dialogue robot. Sending configuration instructions to the dialogue robot through the configuration interface includes: sending the dialogue sent by the first user in the first dialogue interface as the configuration instruction to the dialogue robot.

[0087] like Figure 3C As shown, the first user can send a message to the dialogue robot AA, such as "When you chat with my friend A, you can use more humorous language", etc. The dialogue robot can also record this or respond further. This method can be used as an implicit configuration method, so that the first user can configure the dialogue robot more flexibly and at will, and the form and language used are not restricted. Therefore, the efficiency of dialogue configuration can be improved.

[0088] In some embodiments, the configuration interface includes a form interface, which includes at least one of an input control and a selection control. Sending a configuration instruction to the conversational robot through the configuration interface includes: in response to a submission operation on the form interface, obtaining description information and input information of the controls of the form interface, the description information including information for guiding input and at least one of conversation strategy examples; determining the configuration instruction based on the description information and at least one of the input information; and sending the configuration instruction to the conversational robot.

[0089] For example, the configuration interface may include "Participate in the conversation when _____", the underlined part corresponds to an input control (such as a text input box) or a selection control for the user to input or select a conversation scenario, and the input control (such as a text input box) or the selection control may display "Please enter the conversation scenario" as the description information, and "Participate in the conversation" may also be used as the description information. In this example, if the content input or selected by the user is "When talking to user X", the generated configuration instruction includes "Participate in the conversation when talking to user X".

[0090] For another example, the configuration interface may include "When talking to user X, _____", the underlined part corresponds to an input control (such as a text input box) or a selection control for the user to input a dialogue strategy, and the input control (such as a text input box) or the selection control may display "Please enter a dialogue strategy" as the description information, and "When talking to user X" may also be used as the description information. In this example, if the content input or selected by the user is "Use a more serious tone", the generated configuration instruction includes "Use a more serious tone when talking to user X".

[0091] In some embodiments, a historical conversation record can be selected as a reference for the conversation strategy of the conversation robot. Through the configuration interface, the historical conversation record selected by the first user is determined, and the historical conversation record includes the conversation between the first user and the second user; a configuration instruction including the historical conversation record and a learning instruction is sent to the conversation robot, and the learning instruction is used to instruct the conversation robot to extract the conversation strategy of the first user in the conversation scenario of the historical conversation record.

[0092] The configuration interface may be any one of the above embodiments or a configuration interface implemented in other ways. For example, a selection control for historical conversation records may be provided in the configuration interface. Another implementation is that when viewing a historical conversation record page, a configuration operation may be triggered by selecting part of the historical conversation record.

[0093] When sending a configuration instruction, the sending can also be triggered by a specified control. For example, after selecting a historical conversation record, the generation of a configuration instruction is triggered by confirming the control, and the configuration instruction includes a learning instruction by default. Alternatively, in the conversation interface between the first user and the conversation robot, the user can first send the selected historical conversation record to the conversation robot, and then send a learning instruction through natural language, such as "next time when you encounter a similar situation, you can say it like I did in the conversation above."

[0094] After obtaining the conversation record, the conversation robot can perform semantic analysis on it based on the learning instructions, extract the conversation strategy from it and configure it.

[0095] This embodiment does not send a clear dialogue strategy to the dialogue robot, but instructs the dialogue robot to learn the dialogue strategy based on the existing historical dialogue records, thereby reducing the complexity of the user's dialogue configuration and improving the user's configuration efficiency.

[0096] In the process of the first user reviewing the application of the dialogue robot, that is, the dialogue between the dialogue robot and other users, feedback can be provided based on the dialogue that the dialogue robot has generated, so that the dialogue robot adjusts its dialogue strategy. In some embodiments, a second dialogue interface between the dialogue robot and the second user is displayed; in the second dialogue interface, feedback from the first user on the dialogue sent by the dialogue robot is received, and the feedback includes affirmation, negation or modification; based on the feedback, the dialogue strategy of the dialogue robot is adjusted.

[0097] Figure 4 FIG. 1 is a schematic diagram showing a historical conversation record interface according to some embodiments of the present disclosure. Figure 4 As shown, interface 40 is a historical conversation record interface between the conversation robot AA and the first user's friend BB. In the interface 40, there is a like mark 401 on the left side of the content sent by the conversation robot AA. In response to the first user triggering the like mark 401, it means that the first user affirms the conversation generated by the conversation robot AA, and further affirms the conversation strategy for generating the conversation. The conversation robot AA can continue to use the conversation strategy in similar conversation scenarios. If the first user believes that a message sent by the conversation robot AA has shortcomings or completely violates his original intention, he can modify it directly in the interface 40. For example, the control 402 where the message sent by the conversation robot AA is located can be triggered to be modified. However, the modification is not visible to user BB. In addition, a control for indicating negation (not shown in the figure) can also be set in the interface 40 for the first user to express his disagreement with the conversation strategy behind the message.

[0098] After the user configures the conversation robot based on the above-mentioned similar interface, the chat control 403 in the interface 40 can also be triggered to trigger the display of the conversation interface between the first user and the user BB, so that after the first user adjusts the conversation strategy of the conversation robot, he can initiate a conversation with the second user to actually test the adjustment effect.

[0099] The above embodiments provide exemplary descriptions of the configuration method of the conversational robot of the present disclosure. The following is an introduction to the embodiments of the related devices involved in the present disclosure.

[0100] Figure 5 FIG. 1 is a schematic diagram showing a configuration device of a conversational robot according to some embodiments of the present disclosure. Figure 5 As shown, the configuration device 50 of this embodiment includes: a creation module 501, configured to create a conversation robot for a first user, wherein the conversation robot is used to assist the first user in having a conversation with a second user; a display module 502, configured to display a configuration interface of the conversation robot of the first user; and a sending module 503, configured to send configuration instructions to the conversation robot through the configuration interface, wherein the configuration instructions include a conversation strategy.

[0101] In some embodiments, the configuration instructions include a dialogue strategy for a specified dialogue scenario, the dialogue scenario including at least one of a dialogue between a first user and a second user including a specified dialogue topic, the second user belonging to a specified category, the second user being a specified user, and the dialogue state of the first user belonging to a specified state, and the dialogue strategy includes a strategy for whether the dialogue robot participates in the dialogue between the first user and the second user, and at least one of the language style of the dialogue robot.

[0102] In some embodiments, the first conversation scenario includes a conversation between a first user and a second user, including at least one of a specified conversation topic, the second user belonging to a specified category, the second user being a specified user, and the conversation state of the first user belonging to a specified state, and the conversation strategy for the specified conversation scenario includes: in response to detecting the first conversation scenario, participating in the conversation between the first user and the second user.

[0103] In some embodiments, the second conversation scenario includes at least one of the second user belonging to a specified category and the second user belonging to a specified user, and the conversation strategy for the specified conversation scenario includes: in response to detecting the second conversation scenario, determining a language style based on an identifier or a category of the second user having a conversation with the first user, and participating in the conversation between the first user and the second user based on the language style.

[0104] In some embodiments, the third conversation scenario includes a topic of the conversation belonging to a specified category, and the conversation strategy for the specified conversation scenario includes: in response to detecting the third conversation scenario, determining a language style based on the topic of the conversation between the first user and the second user, and participating in the conversation based on the language style.

[0105] In some embodiments, the configuration interface includes a first dialogue interface between a first user and a dialogue robot, and the sending module 503 is further configured to: send the dialogue sent by the first user in the first dialogue interface as a configuration instruction to the dialogue robot.

[0106] In some embodiments, the configuration interface includes a form interface, which includes at least one of an input control and a selection control, and the sending module 503 is further configured to: in response to a submission operation on the form interface, obtain description information and input information of the controls of the form interface, the description information including information for guiding input and at least one of the dialogue strategy examples; determine configuration instructions based on at least one of the description information and the input information; and send configuration instructions to the dialogue robot.

[0107] In some embodiments, the sending module 503 is further configured to: determine the historical conversation record selected by the first user through the configuration interface, the historical conversation record including the conversation between the first user and the second user; send the configuration instructions including the historical conversation record and the learning instructions to the conversation robot, the learning instructions are used to instruct the conversation robot to extract the conversation strategy of the first user in the conversation scenario of the historical conversation record.

[0108] In some embodiments, the creation module 501 is further configured to: generate an image of the conversational robot based on the style description information input by the first user and the image from the first user authorized by the first user; and create a conversational robot for the first user based on the image of the conversational robot.

[0109] In some embodiments, the creation module 501 is further configured to: generate voice information of the dialogue robot based on the voice of the first user authorized by the first user; and create a dialogue robot for the first user based on the voice information of the dialogue robot.

[0110] In some embodiments, the configuration device 50 also includes an adjustment module 504, which is configured to: display a second dialogue interface between the dialogue robot and the second user; in the second dialogue interface, receive feedback from the first user on the dialogue sent by the dialogue robot, the feedback including affirmation, negation or modification; based on the feedback, adjust the dialogue strategy of the dialogue robot.

[0111] In some embodiments, assisting the first user in having a conversation with other users includes: having a conversation with other users on behalf of the first user; or participating in a conversation between the first user and other users.

[0112] It should be noted that the above-mentioned units are only logical modules divided according to the specific functions implemented by them, and are not used to limit the specific implementation methods. For example, they can be implemented in software, hardware, or a combination of software and hardware. In actual implementation, the above-mentioned units can be implemented as independent physical entities, or can also be implemented by a single entity (for example, a processor (CPU or DSP, etc.), an integrated circuit, etc.). In addition, the above-mentioned units are shown with dotted lines in the drawings to indicate that these units may not actually exist, and the operations / functions implemented by them can be implemented by the processing circuit itself.

[0113] In addition, although not shown, the device may also include a memory, which may store various information generated by the device, various units contained in the device during operation, programs and data for operation, data to be sent by the communication unit, etc. The memory may be a volatile memory and / or a non-volatile memory. For example, the memory may include, but is not limited to, a random access memory (RAM), a dynamic random access memory (DRAM), a static random access memory (SRAM), a read-only memory (ROM), and a flash memory. Of course, the memory may also be located outside the device. Optionally, although not shown, the device may also include a communication unit, which may be used to communicate with other devices. In one example, the communication unit may be implemented in a suitable manner known in the art, such as including communication components such as an antenna array and / or a radio frequency link, various types of interfaces, communication units, etc. It will not be described in detail here. In addition, the device may also include other components not shown, such as a radio frequency link, a baseband processing unit, a network interface, a processor, a controller, etc. It will not be described in detail here.

[0114] Some embodiments of the present disclosure also provide an electronic device. Figure 6 A schematic diagram of the structure of an electronic device according to some embodiments of the present disclosure is shown. For example, in some embodiments, the electronic device 6 can be various types of devices, for example, can include but not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. For example, the electronic device 6 can include a display panel for displaying data and / or execution results used in the scheme according to the present disclosure. For example, the display panel can be in various shapes, such as a rectangular panel, an elliptical panel, or a polygonal panel. In addition, the display panel can be not only a flat panel, but also a curved panel, or even a spherical panel.

[0115] like Figure 6 As shown, the electronic device 6 of this embodiment includes: a memory 61 and a processor 62 coupled to the memory 61. It should be noted that Figure 6 The components of the electronic device 6 shown are only exemplary and non-restrictive. The electronic device 6 may also have other components according to actual application requirements. The processor 62 may control other components in the electronic device 6 to perform desired functions.

[0116] In some embodiments, the memory 61 is used to store one or more computer-readable instructions. When the processor 62 is used to execute the computer-readable instructions, the computer-readable instructions are executed by the processor 62 to implement the method according to any of the above embodiments. For the specific implementation of each step of the method and the related explanation content, please refer to the above embodiments, and the repeated parts will not be repeated here.

[0117] For example, the processor 62 and the memory 61 may communicate with each other directly or indirectly. For example, the processor 62 and the memory 61 may communicate with each other through a network. The network may include a wireless network, a wired network, and / or any combination of a wireless network and a wired network. The processor 62 and the memory 61 may also communicate with each other through a system bus, which is not limited by the present disclosure.

[0118] For example, the processor 62 may be embodied as various appropriate processors, processing devices, etc., such as a central processing unit (CPU), a graphics processing unit (GPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The central processing unit (CPU) may be an X86 or ARM architecture, etc. For example, the memory 61 may include any combination of various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The memory 61 may include, for example, a system memory, which may store, for example, an operating system, an application, a boot loader (Boot Loader), a database, and other programs. Various applications and various data may also be stored in the storage medium.

[0119] In addition, according to some embodiments of the present disclosure, various operations / processes according to the present disclosure, when implemented by software and / or firmware, can be transmitted from a storage medium or a network to a computer system having a dedicated hardware structure, such as Figure 7The computer system 70 shown installs the programs constituting the software, and when the various programs are installed, the computer system can perform various functions, including the functions described above and the like. Figure 7 A schematic diagram of the structure of a computer system according to some embodiments of the present disclosure is shown.

[0120] exist Figure 7 In the embodiment, the central processing unit (CPU) 701 performs various processes according to the program stored in the read-only memory (ROM) 702 or the program loaded from the storage part 708 to the random access memory (RAM) 703. In the RAM 703, data required when the CPU 701 performs various processes, etc. are also stored as needed. The central processing unit is only exemplary, and it can also be other types of processors, such as the various processors described above. The ROM 702, RAM 703 and the storage part 708 can be various forms of computer-readable storage media, as described below. It should be noted that although Figure 7 ROM 702, RAM 703 and storage device 708 are shown separately in FIG. 7 , but one or more of them may be combined or located in the same or different memory or storage modules.

[0121] The CPU 701, the ROM 702, and the RAM 703 are connected to one another via a bus 704. An input / output interface 705 is also connected to the bus 704.

[0122] The following components are connected to the input / output interface 705: an input portion 706, such as a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output portion 707, including a display, such as a cathode ray tube (CRT), a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage portion 708, including a hard disk, a magnetic tape, etc.; and a communication portion 709, including a network interface card such as a LAN card, a modem, etc. The communication portion 709 allows communication processing to be performed via a network such as the Internet. It is easy to understand that although Figure 7 The various devices or modules in the computer system 70 are shown to communicate via a bus 704, but they may also communicate via a network or other means, wherein the network may include a wireless network, a wired network, and / or any combination of wireless networks and wired networks.

[0123] A drive 710 is also connected to the input / output interface 705 as needed. A removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory or the like is mounted on the drive 710 as needed so that a computer program read therefrom is installed into the storage section 708 as needed.

[0124] In the case where the above-described series of processing is implemented by software, a program constituting the software can be installed from a network such as the Internet or a storage medium such as the removable medium 711 .

[0125] According to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 709, or installed from a storage device 708, or installed from a ROM 702. When the computer program is executed by the CPU 701, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0126] It should be noted that in the context of the present disclosure, a computer-readable medium may be a tangible medium that may contain or store a program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. A computer-readable storage medium may be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that may be used by an instruction execution system, device or device or used in combination with it. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0127] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0128] In some embodiments, a computer program is further provided, comprising: instructions, which, when executed by a processor, cause the processor to execute any of the methods of the above embodiments. For example, the instructions may be embodied as computer program codes.

[0129] In embodiments of the present disclosure, computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or combinations thereof, including but not limited to object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or entirely on a remote computer or server. In situations involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0130] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0131] The modules, components or units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the names of the modules, components or units do not, in some cases, limit the modules, components or units themselves.

[0132] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0133] The above descriptions are only some embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, a technical solution formed by replacing the above features with the technical features with similar functions disclosed in the present disclosure (but not limited to).

[0134] In the description provided herein, many specific details are set forth. However, it is understood that embodiments of the present invention can be implemented without these specific details. In other cases, well-known methods, structures, and techniques are not presented in detail in order not to obscure the understanding of the description.

[0135] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0136] Although some specific embodiments of the present disclosure have been described in detail by way of example, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. It should be understood by those skilled in the art that the above embodiments may be modified without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A method for configuring a conversational robot, comprising: Creating a conversation robot for a first user, wherein the conversation robot is used to assist the first user in having a conversation with a second user; Displaying a configuration interface of the conversational robot of the first user; A configuration instruction is sent to the dialogue robot through the configuration interface, wherein the configuration instruction includes a dialogue strategy.

2. The configuration method according to claim 1, wherein: The configuration instruction includes a dialogue strategy for a specified dialogue scenario, the dialogue scenario including at least one of the dialogue between the first user and the second user including a specified dialogue topic, the second user belonging to a specified category, the second user being a specified user, and the dialogue state of the first user belonging to a specified state; the dialogue strategy includes a strategy for whether the dialogue robot participates in the dialogue between the first user and the second user, and at least one of the language style of the dialogue robot.

3. The configuration method according to claim 2, wherein: The first dialogue scenario includes at least one of the following: the dialogue between the first user and the second user includes a specified dialogue topic, the second user belongs to a specified category, the second user is a specified user, and the dialogue state of the first user belongs to a specified state, and the dialogue strategy for the specified dialogue scenario includes: In response to detecting the first conversation scenario, participating in a conversation between the first user and the second user.

4. The configuration method according to claim 2 or 3, wherein: The second dialogue scenario includes at least one of the following: the second user belongs to a specified category and the second user belongs to a specified user. The dialogue strategy for the specified dialogue scenario includes: In response to detecting the second conversation scenario, a language style is determined based on an identification or category of a second user having a conversation with the first user, and the first user participates in the conversation with the second user based on the language style.

5. The configuration method according to any one of claims 2 to 4, wherein: The third dialogue scenario includes that the topic of the dialogue belongs to a topic of a specified category, and the dialogue strategy for the specified dialogue scenario includes: In response to detecting the third conversation scenario, determining a language style based on a topic of a conversation between the first user and the second user, and participating in the conversation based on the language style.

6. The configuration method according to any one of claims 1 to 5, wherein: The configuration interface includes a first dialogue interface between the first user and the dialogue robot, and sending a configuration instruction to the dialogue robot through the configuration interface includes: The dialogue sent by the first user in the first dialogue interface is used as the configuration instruction and sent to the dialogue robot.

7. The configuration method according to any one of claims 1 to 6, wherein: The configuration interface includes a form interface, the form interface includes at least one of an input control and a selection control, and sending a configuration instruction to the conversational robot through the configuration interface includes: In response to a submission operation on the form interface, obtaining description information and input information of controls on the form interface, wherein the description information includes at least one of information for guiding input and a dialogue strategy example; Determine a configuration instruction based on at least one of the description information and the input information; The configuration instruction is sent to the conversational robot.

8. The configuration method according to any one of claims 1 to 7, wherein: The sending of configuration instructions to the conversational robot through the configuration interface includes: Determining, through the configuration interface, a historical conversation record selected by the first user, the historical conversation record including a conversation between the first user and the second user; A configuration instruction including the historical conversation record and a learning instruction is sent to the conversation robot, wherein the learning instruction is used to instruct the conversation robot to extract the conversation strategy of the first user in the conversation scenario of the historical conversation record.

9. The configuration method according to any one of claims 1 to 8, wherein: The creating a conversational robot for the first user comprises: generating an image of the conversational robot based on the style description information input by the first user and the image from the first user authorized by the first user; Based on the image of the conversational robot, the conversational robot is created for the first user.

10. The configuration method according to any one of claims 1 to 9, wherein: The creating a conversational robot for the first user comprises: generating voice information of the conversational robot based on the voice of the first user authorized by the first user; Based on the voice information of the conversation robot, the conversation robot is created for the first user.

11. The configuration method according to any one of claims 1 to 10, further comprising: Displaying a second dialogue interface between the dialogue robot and a second user; In the second dialogue interface, receiving feedback from the first user on the dialogue sent by the dialogue robot, wherein the feedback includes affirmation, negation or modification; Based on the feedback, the dialogue strategy of the dialogue robot is adjusted.

12. The configuration method according to any one of claims 1 to 11, wherein: The assisting the first user to have a conversation with other users comprises: Conducting a conversation with other users on behalf of the first user; or Participate in a conversation between the first user and other users.

13. A configuration device for a conversational robot, comprising: A creation module, configured to create a conversation robot for a first user, wherein the conversation robot is used to assist the first user in having a conversation with a second user; A display module, configured to display a configuration interface of the conversational robot of the first user; The sending module is configured to send configuration instructions to the dialogue robot through the configuration interface, and the configuration instructions include dialogue strategies.

14. An electronic device comprising: Memory; as well as A processor coupled to the memory, the processor being configured to execute the configuration method of the conversational robot according to any one of claims 1 to 12 based on instructions stored in the memory.

15. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the configuration method of the conversational robot according to any one of claims 1 to 12.

16. A computer program product, when the computer program product is run on a computer, enables the computer to implement the configuration method of the conversational robot according to any one of claims 1 to 12.

17. A computer program comprising: Instructions, when executed by a processor, cause the processor to execute the configuration method of the conversational robot according to any one of claims 1 to 12.

Images