Assistant Recommendation Method, Device, Client, and Storage Medium

Abstract

Embodiments of the present invention provide an assistant recommendation method, apparatus, client, and storage medium. The method includes: in response to a question related to a first vertical scenario sent by a user in a general scenario dialogue interface, generating a first recommendation message card for the first vertical scenario assistant and displaying it in the general scenario dialogue interface; the general scenario dialogue interface is a dialogue interface between the user and the general scenario assistant, and the first recommendation message card is used to display the first text recommendation information and the chat control of the first vertical scenario assistant. In the embodiments of the present invention, the client automatically generates a recommendation message card for a suitable scenario assistant in response to the question sent by the user. The user can call the scenario assistant through the recommendation message card and obtain a more professional reply content for the question. At the same time, such an interaction method can achieve a fast and convenient switch between different scenario assistants, thereby improving the user experience.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of artificial intelligence technology, and in particular, to a method, device, client, and storage medium for assistant recommendation.

Background Art

[0002] With the continuous development of the field of artificial intelligence (AI for short), human-computer dialogue systems based on AI have gradually been applied in various fields. In related technologies, the human-computer dialogue system replies to the questions sent by users through a single model. However, the reply ability of the single model is limited. If the training process of the single model lacks training related to the question, the single model cannot provide a more in-depth answer for users. Moreover, different models are independent of each other, and it is rather cumbersome for users to switch to other models, resulting in a poor user experience and low user satisfaction.

Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a method, device, client, and storage medium for assistant recommendation to solve the problem of poor user experience and low user satisfaction in related technologies.

[0004] In a first aspect, an embodiment of the present invention provides a method for assistant recommendation, which is applied to a human-computer dialogue application program based on generative artificial intelligence AIGC. The method is characterized in that a general scenario assistant and at least one vertical scenario assistant are included in the human-computer dialogue application program, and the method includes:

[0005] In response to a question involving a first vertical scenario sent by a user in a general scenario dialogue interface, generating a first recommendation message card for the first vertical scenario assistant and displaying it in the general scenario dialogue interface; the general scenario dialogue interface is the dialogue interface between the user and the general scenario assistant, and the first recommendation message card is used to display the first text recommendation information and the chat control of the first vertical scenario assistant.

[0006] In a possible implementation manner, the method further includes:

[0007] In response to an operation of the user clicking the chat control of the first vertical scenario assistant, entering the first vertical scenario dialogue interface and generating a reply content corresponding to the question of the first vertical scenario; the first vertical scenario dialogue interface is the dialogue interface between the user and the first vertical scenario assistant.

[0008] In a possible implementation manner, after generating a reply content corresponding to the question of the first vertical scenario by entering the first vertical scenario dialogue interface in response to an operation of the user clicking the chat control of the first vertical scenario assistant, the method further includes:

[0009] In response to a question sent by a user in the first vertical scenario dialogue interface that involves a general scenario or a second vertical scenario, generate a second recommended message card for the general scenario assistant or the second vertical scenario assistant and display it in the first vertical scenario dialogue interface; the second recommended message card is used to display the second text recommendation information and the chat control of the general scenario assistant or the second vertical scenario assistant, and the second vertical scenario is different from the first vertical scenario;

[0010] In response to an operation where the user clicks on the chat control of the general scenario assistant or the second vertical scenario assistant, switch to the dialogue interface with the general scenario assistant or the second vertical scenario dialogue interface, and generate a reply content corresponding to the question of the general scenario or the second vertical scenario; the second vertical scenario dialogue interface is the dialogue interface between the user and the second vertical scenario assistant.

[0011] In one possible implementation, the first recommended message card further includes a business card control of the first vertical scenario assistant, and the method further includes:

[0012] In response to an operation where the user clicks on the business card control, enter the business card introduction interface of the first vertical scenario assistant, and the business card introduction interface is used to display the assistant information of the first vertical scenario assistant.

[0013] In one possible implementation, when the question involves multiple different first vertical scenarios, the first recommended message card is used to display the first text recommendation information and the chat controls of multiple first vertical scenario assistants; the chat controls of multiple first vertical scenario assistants are arranged in descending order of relevance between the question and multiple first vertical scenarios.

[0014] In one possible implementation, the method further includes:

[0015] In response to an operation where the user first invokes the general scenario assistant, display an introduction message card; the introduction message card includes the introduction message of the general scenario assistant, the introduction messages of at least one vertical scenario assistant, and a relationship introduction message; the relationship introduction message is used to explain the relationship between the general scenario assistant and at least one vertical scenario assistant.

[0016] In one possible implementation, the method further includes:

[0017] Display an assistant center control;

[0018] In response to an operation where the user clicks on the assistant center control, enter the assistant center interface; the assistant center interface is used to display the assistant information of the general scenario assistant and the assistant information of at least one vertical scenario assistant associated with the general scenario assistant.

[0019] Second aspect, an embodiment of the present invention provides an assistant recommendation device, which is applied to a human-machine dialogue application program based on generative artificial intelligence AIGC. In the human-machine dialogue application program, there is a general scenario assistant and at least one vertical scenario assistant. The general scenario assistant and the vertical scenario assistant are respectively trained by different large language models. The device includes:

[0020] A first generation module, configured to generate a first recommendation message card of the first vertical scenario assistant and display it on the general scenario dialogue interface in response to a question involving the first vertical scenario sent by the user in the general scenario dialogue interface; the general scenario dialogue interface is the dialogue interface between the user and the general scenario assistant, and the first recommendation message card is used to display the first text recommendation information and the chat control of the first vertical scenario assistant.

[0021] Third aspect, an embodiment of the present invention provides a client, including: a display screen; one or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions, when the instructions are executed by the client, the client is made to execute the assistant recommendation method in the first aspect or any possible implementation manner of the first aspect.

[0022] Fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, the computer-readable storage medium includes a stored program, wherein, when the program runs, it controls the device where the computer-readable storage medium is located to execute the assistant recommendation method in the first aspect or any possible implementation manner of the first aspect.

[0023] In the technical solution provided by the embodiment of the present invention, the client automatically generates a recommendation message card of a suitable scenario assistant in response to a question sent by the user. The user can call the scenario assistant through the recommendation message card and obtain a more professional reply content for the question. At the same time, such an interaction method can achieve a fast and convenient switch between different scenario assistants, thereby improving the user experience.

Description of the Drawings

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0025] Figure 1 It is a flowchart of an assistant recommendation method provided by an embodiment of the present invention;

[0026] Figure 2Schematic diagram of a general scenario dialogue interface provided by an embodiment of the present invention;

[0027] Figure 3a Schematic diagram of an assistant center interface provided by an embodiment of the present invention;

[0028] Figure 3b Schematic diagram of another assistant center interface provided by an embodiment of the present invention;

[0029] Figure 4a Schematic diagram of a first vertical category scenario dialogue interface provided by an embodiment of the present invention;

[0030] Figure 4b Schematic diagram of another first vertical category scenario dialogue interface provided by an embodiment of the present invention;

[0031] Figure 4c Schematic diagram of another first vertical category scenario dialogue interface provided by an embodiment of the present invention;

[0032] Figure 5 Schematic diagram of the structure of an assistant recommendation device provided by an embodiment of the present invention;

[0033] Figure 6 Schematic diagram of a client provided by an embodiment of the present invention.

Detailed implementation manners

[0034] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0035] It should be clear that the described embodiments are only some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0036] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The singular forms of "a", "the", and "said" used in the embodiments of the present invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0037] It should be understood that the term "and / or" used herein is merely a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Additionally, the character " / " in this text generally indicates that the associated objects before and after are in an "or" relationship.

[0038] Depending on the context, as used herein, the word "if" can be interpreted as "when" or "while" or "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrase "if determined" or "if detected (stated condition or event)" can be interpreted as "when determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)".

[0039] Figure 1 The flowchart of an assistant recommendation method provided by an embodiment of the present invention is as Figure 1 shown, and the method includes:

[0040] Step 101, in response to a question involving a first vertical scenario sent by a user in a general scenario dialogue interface, generate a first recommendation message card for the first vertical scenario assistant and display it in the general scenario dialogue interface.

[0041] Each step of the embodiment of the present invention can be executed by a client. Among them, the client includes but is not limited to mobile phones, tablets, portable PCs, desktop computers, etc.

[0042] The embodiment of the present invention is applied to a human-machine dialogue application program based on generative artificial intelligence (Artificial Intelligence Generated Content, abbreviated as AIGC). In the human-machine dialogue application program, there is a general scenario assistant and at least one vertical scenario assistant.

[0043] AIGC is a general artificial intelligence (AGI) focused on generating or creating new content. It generates new data such as text, program code, images, videos, and sounds through machine learning based on existing large-scale multimodal datasets. It can handle various different tasks and be applied to various different scenarios, such as text summarization, text generation, machine translation, question answering, etc., with a high level of generalization. The application of AIGC technology can improve the efficiency of content generation, save time and costs for creators and enterprises, and at the same time expand the possibilities of content creation. The basic support of AIGC is the large language model (LLM). The LLM is a language model containing billions or more parameters that generates human-like text by learning to understand a large amount of text data and context data. For example, LLMs include Generative Pre-Trained Transformer (GPT)-3, GPT-4, Baichuan2-7B, Baichuan2-13B, etc. The LLM has undergone comprehensive training including pre-training, supervised fine-tuning (SFT), and reinforcement learning from human feedback (RLHF). Among them, in the pre-training stage, the model learns the language structure, grammar, and factual knowledge in the text data through a large amount of text data. In the SFT stage, the pre-trained LLM is fine-tuned with labeled data to make it more suitable for performing a specific task. In the RLHF stage, the method of reinforcement learning is used to directly optimize the language model using human feedback signals.

[0044] Specifically, different vertical scenario assistants are applied to different vertical scenarios. For example, vertical scenarios include medical scenarios, legal scenarios, travel scenarios, learning scenarios, game scenarios, and financial management scenarios. Correspondingly, vertical scenario assistants include medical assistants, legal assistants, travel assistants, learning assistants, game assistants, and financial management assistants.

[0045] It should be noted that different scenario assistants correspond to different large language models. There are both connections and differences between different large language models. The connections are as follows: different large language models are obtained based on the same base model, and the base model is the foundation of the above-mentioned large language models. The differences are as follows: different vertical scenario assistants are obtained by training the base model based on the SFT technology and a large amount of training data in different vertical scenarios. For example, the large models corresponding to the above-mentioned medical assistants, legal assistants, game assistants, etc. are all based on the base model Baichuan2-13B. At the same time, the prompts and responses formed by data in scenarios such as medical, legal, and game are used to perform supervised fine-tuning training on the base model. Therefore, the vertical scenario assistant can reply to users' questions more professionally in the vertical scenario, solving the problem of insufficient professionalism of the responses generated by the general scenario assistant in the vertical scenario. Moreover, in the embodiments of the present invention, the switching between different scenario assistants can be conveniently implemented, improving the user experience.

[0046] Figure 2 FIG. is a schematic diagram of a general scenario dialogue interface provided by an embodiment of the present invention, as Figure 2 shown, the general scenario dialogue interface is a dialogue interface between the user and the general scenario assistant. The first recommended message card is used to display the first text recommendation information and the chat control of the first vertical scenario assistant. The nickname of the general scenario assistant is displayed at the top of the general scenario dialogue interface, and a text input box and a voice input control are set at the bottom of the interface. Among them, the user can input questions in text form through the text input box, or input questions in voice form through the voice input control. As an optional solution, when the question sent by the user involves a first vertical scenario, the first recommended message card is used to display the first text recommendation information and the chat control of a first vertical scenario assistant. For example, when the question sent by the user involves the travel scenario, the first text recommendation information is the text information "My partner is very professional in travel, and you can consult him for more travel information", and the chat control includes the chat control of the travel assistant.

[0047] As another alternative, when the question sent by the user involves multiple different first vertical category scenarios, the first recommended message card is used to display the first text recommendation information and the chat controls of multiple first vertical category scenario assistants. Among them, the chat controls of multiple first vertical category scenario assistants are arranged in descending order of the relevance between the question and multiple first vertical category scenarios. Optionally, the client can also highlight the chat control corresponding to the first vertical category scenario with a higher relevance to the question. The relevance can be represented by a correlation coefficient. The larger the correlation coefficient, the greater the relevance between the question and the first vertical category scenario; the smaller the correlation coefficient, the smaller the relevance between the question and the first vertical category scenario; when the correlation coefficient is zero, it indicates that the question is not relevant to the vertical category scenario. The client can obtain the correlation coefficient between the question and the first vertical category scenario through the vector method. Specifically, the client converts the question input by the user into a vector, and performs a correlation operation between this vector and the vertical category vectors corresponding to different first vertical category scenarios to obtain the correlation coefficient. Alternatively, the client can obtain the correlation coefficient between the question and the first vertical category scenario through a calculation method. Specifically, the client identifies the semantics of the question sent by the user, calculates the relevance between the semantics of the question and the semantics of different first vertical category scenarios, and obtains the correlation coefficient. For example, the question sent by the user involves the learning scenario and the financial management scenario. Among them, the correlation coefficient between the question and the learning scenario is 0.8, and the correlation coefficient with the financial management scenario is 0.6. That is, the relevance between the question and the learning scenario is higher, and the relevance with the financial management scenario is lower. Then, the chat control of the learning assistant and the chat control of the financial management assistant are displayed in sequence on the first recommended card. Optionally, the client can also highlight the chat control of the learning assistant.

[0048] Optionally, when the question sent by the user involves multiple first vertical category scenarios, after generating the first recommended message card of the first vertical category scenario assistant and displaying it in the general scenario dialogue interface, it can also include: displaying a group chat creation control, and in response to the user's operation of clicking the group chat creation control, creating a group chat and inviting multiple first vertical category scenario assistants to join the group chat. The group chat participants include the user and the above-mentioned multiple first vertical category scenario assistants. For example, the question involves the learning scenario and the medical scenario. The user clicks the group chat creation control, and the client responds to the user's operation of clicking the group chat creation control, creates a group chat, and invites the learning assistant and the medical assistant to join the group chat. At this time, the group chat participants include the user, the learning assistant, and the medical assistant.

[0049] Optionally, the first recommended message card also includes a business card control of the first vertical category scenario assistant. The client responds to the user's operation of clicking the business card control and enters the business card introduction interface of the first vertical category scenario assistant. The business card introduction interface is used to display the assistant information of the first vertical category scenario assistant.

[0050] It should be noted that when the user first enters the general scenario dialogue interface, that is, when the user first calls the general scenario assistant, the client responds to the user's operation of first calling the general scenario assistant and displays an introduction message card; the introduction message card includes the introduction message of the general scenario assistant, the introduction messages of at least one vertical scenario assistant, and a relationship introduction message; the relationship introduction message is used to explain the relationship between the general scenario assistant and at least one vertical scenario assistant. Specifically, the general scenario assistant, at least one vertical scenario assistant, and the user are in a partnership relationship with each other, and the general scenario assistant and at least one vertical scenario assistant work together to solve problems for the user. Among them, the general scenario assistant is an all-round partner for the user and can answer questions in various fields; each vertical scenario assistant is a professional partner for the user and can provide more professional and in-depth answers for the user in its own professional field.

[0051] In the embodiments of the present invention, assistant center controls are provided on the general scenario dialogue interface, the first vertical scenario dialogue interface, and the second vertical scenario dialogue interface. When the user clicks on the assistant center control, the client responds to the user's operation of clicking on the assistant center control and enters the assistant center interface; the assistant center interface is used to display the assistant information of the general scenario assistant and the assistant information of at least one vertical scenario assistant associated with the general scenario assistant. Among them, the assistant information includes a nickname, an avatar, a signature, a set introduction, and a chat control. The assistant information can reflect the personified characteristics of the scenario assistant to a certain extent, and different scenario assistants have different personified characteristics. For example, if the travel assistant has a warm and cheerful personified characteristic, then the assistant information and the reply content style of the travel assistant will reflect the warm and cheerful characteristics to improve the affinity of the travel assistant. Another example is that if the medical assistant has a rigorous and responsible personified characteristic, then the assistant information and the reply content style of the medical assistant will reflect the rigorous and responsible characteristics to improve the credibility of the medical assistant and thus improve the user experience.

[0052] In the embodiments of the present invention, the assistant center interface can display the assistant information of each assistant in the form of a card or a list.

[0053] Figure 3a is a schematic diagram of an assistant center interface provided by an embodiment of the present invention. As Figure 3a shown, the assistant center interface displays the assistant information of each assistant in the form of a card. The assistant center interface is used to display an assistant information card, and each assistant information card is used to display the assistant information of one assistant. When the user swipes the assistant information card, the client responds to the user's operation of swiping the assistant information card and displays the corresponding assistant information card.

[0054] As Figure 3aAs shown, the assistant center interface also includes a first form switching control. When the user clicks the first form switching control, the client switches the display form of the assistant information to a list form in response to the user clicking the first form switching control.

[0055] Figure 3b A schematic diagram of another assistant center interface provided by an embodiment of the present invention, such as Figure 3b As shown, the assistant center interface displays the assistant information of each assistant in a list format. The assistant center interface includes multiple assistant information areas displayed in a list format, and each assistant information area is used to display the assistant information of an assistant.

[0056] like Figure 3b As shown, the assistant center interface also includes a second form switching control. The user clicks the second form switching control, and the client switches the display form of the assistant information to the card form in response to the user clicking the second form switching control.

[0057] Step 102: In response to the user clicking the chat control of the first vertical scenario assistant, enter the first vertical scenario dialogue interface and generate reply content corresponding to the question of the first vertical scenario.

[0058] Figure 4a A schematic diagram of a first vertical scenario dialogue interface provided by an embodiment of the present invention, such as Figure 4a As shown, the first vertical scenario dialogue interface is a dialogue interface between the user and the first vertical scenario assistant. The nickname of the first vertical scenario assistant is displayed at the top of the first vertical scenario dialogue interface. After entering the first vertical scenario dialogue interface, the client will directly generate the reply content corresponding to the question of the first vertical scenario, without the user having to re-enter the question related to the first vertical scenario in the first vertical scenario dialogue interface, which simplifies the question-asking process, reduces the user's waiting time, and thus improves the user's dialogue experience.

[0059] Figure 4b A schematic diagram of another first vertical scenario dialogue interface provided by an embodiment of the present invention, such as Figure 4b As shown, after entering the first vertical scenario dialogue interface, the client first displays the introduction message of the first vertical scenario assistant, and then generates the reply content corresponding to the question of the first vertical scenario. By displaying the introduction message of the first vertical scenario assistant, the conversation is more in line with human daily conversation habits, thereby improving the user's conversation experience.

[0060] Figure 4c A schematic diagram of another first vertical scenario dialogue interface provided by an embodiment of the present invention, such as Figure 4cAs shown, after entering the first vertical scenario dialogue interface, the client first displays the questions related to the first vertical scenario, and then generates the response content corresponding to the questions of the first vertical scenario. Among them, the questions are completed through the interaction between the general scenario assistant and the first vertical scenario assistant, without the user entering the questions related to the first vertical scenario again in the first vertical scenario dialogue interface. While simplifying the question process and reducing the user's waiting time, the user can also see a relatively complete and clear dialogue process, thereby further improving the user's dialogue experience.

[0061] When the user first enters the vertical scenario dialogue interface, that is, when the user first invokes the vertical scenario assistant, the client responds to the user's operation of first invoking the vertical scenario assistant and displays the introduction message of the vertical scenario assistant.

[0062] In the embodiments of the present invention, it can be assisted in understanding by combining the specific application scenarios of each vertical scenario assistant. For example, the vertical scenario includes a medical scenario, the vertical scenario assistant includes a medical assistant, and the medical assistant has the professional consultation ability of multiple departments. It can simulate the real doctor consultation scenario through multiple rounds of consultation, provide users with consultations such as medication and nursing, and strictly protect the privacy and security of users to improve the user's medical experience.

[0063] For another example, the vertical scenario includes a legal scenario, the vertical scenario assistant includes a legal assistant, and the legal assistant is familiar with various legal provisions and regulations as well as various judicial and legal procedures, and can provide users with professional legal consultation services to improve the user's consultation experience.

[0064] [[ID=—12]]For another example, the vertical scenario includes a travel scenario, the vertical scenario assistant includes a travel assistant, and the travel assistant is familiar with the natural and cultural landscapes, hotels, cuisines, and local customs of each region. It can provide travel suggestions such as play time, accommodation, transportation, scenic spot recommendations, and food recommendations for different user needs to improve the user's travel experience.

[0065] For another example, the vertical scenario includes a learning scenario, the vertical scenario assistant includes a learning assistant, and the learning assistant supports text understanding, picture understanding, or file understanding, and can provide professional answers for users based on the established knowledge base. Specifically, the learning assistant can establish different knowledge bases for different user groups. For example, for user groups receiving pre-school education to high school education (kindergarten through twelfth grade, abbreviated as K12), establish a K12 knowledge base, and provide summary of knowledge points and examination points of various disciplines for this user group based on the K12 knowledge base. For another example, for user groups receiving university education, establish a thesis knowledge base and provide services such as thesis retrieval and thesis plagiarism checking for this user group, so as to meet the personalized learning needs of different user groups and improve the learning efficiency of users.

[0066] For another example, the vertical scenario includes a game scenario, the vertical scenario assistant includes a game assistant, and the game assistant is familiar with the game guides of various games and can provide game guidance to users in ways such as combo demonstrations and skill explanations to improve the users' game experience.

[0067] For another example, the vertical scenario includes a financial management scenario, the vertical scenario assistant includes a financial management assistant, and the financial management assistant can provide financial management suggestions such as stock analysis, stock recommendation, and statement analysis to improve the users' financial management experience. In addition, other vertical scenarios and corresponding vertical scenario assistants can be set, and the embodiments of the present invention do not limit this.

[0068] Step 103: In response to a question sent by the user in the first vertical scenario dialogue interface that involves a general scenario or a second vertical scenario, generate a second recommended message card for the general scenario assistant or the second vertical scenario assistant and display it in the first vertical scenario dialogue interface.

[0069] In this step, the second recommended message card is used to display the second text recommendation information and the chat control of the general scenario assistant or the second vertical scenario assistant. The second text recommendation information can be text information such as "I can't answer this question. My partner can help you. You can consult him." The second vertical scenario is different from the first vertical scenario.

[0070] Step 104: In response to the user's operation of clicking the chat control of the general scenario assistant or the second vertical scenario assistant, switch to the general scenario dialogue interface or the second vertical scenario dialogue interface and generate a reply content corresponding to the question of the general scenario or the second vertical scenario.

[0071] In this step, the second vertical scenario dialogue interface is the dialogue interface between the user and the second vertical scenario assistant.

[0072] In the technical solution provided by the embodiments of the present invention, the client automatically generates a recommended message card for a suitable scenario assistant in response to the question sent by the user. The user can call the scenario assistant through this recommended message card and obtain a more professional reply content for this question. At the same time, such an interaction method can achieve a fast and convenient switch between different scenario assistants, thereby improving the user experience.

[0073] Figure 5 is a schematic structural diagram of an assistant recommendation device provided by an embodiment of the present invention, as Figure 5As shown, it is applied to a human-computer dialogue application based on generative artificial intelligence AIGC. In the human-computer dialogue application, there is a general scenario assistant and at least one vertical scenario assistant. The general scenario assistant and the vertical scenario assistant are respectively trained by different large language models. The device includes: a first generation module 11, which is used to respond to a question involving the first vertical scenario sent by the user in the general scenario dialogue interface, generate a first recommended message card of the first vertical scenario assistant, and display it in the general scenario dialogue interface; the general scenario dialogue interface is the dialogue interface between the user and the general scenario assistant, and the first recommended message card is used to display the first text recommendation information and the chat control of the first vertical scenario assistant.

[0074] In an embodiment of the present invention, the device further includes a second generation module 12. The second generation module 12 is connected to the first generation module 11. The second generation module 12 is used for the operation of the user clicking the chat control of the first vertical scenario assistant, entering the first vertical scenario dialogue interface, and generating a reply content corresponding to the question of the first vertical scenario; the first vertical scenario dialogue interface is the dialogue interface between the user and the first vertical scenario assistant.

[0075] In an embodiment of the present invention, the device further includes a third generation module 13. The third generation module 13 is connected to the second generation module 12. The third generation module 13 is used to respond to a question involving a general non-vertical scenario or a second vertical scenario sent by the user in the first vertical scenario dialogue interface, generate a second recommended message card of the general scenario assistant or the second vertical scenario assistant, and display it in the first vertical scenario dialogue interface; the second recommended message card is used to display the second text recommendation information and the chat control of the general scenario assistant or the second vertical scenario assistant. The second vertical scenario is different from the first vertical scenario; in response to the operation of the user clicking the chat control of the general scenario assistant or the second vertical scenario assistant, switch to the dialogue interface with the general scenario assistant or the second vertical scenario dialogue interface, and generate a reply content corresponding to the question of the non-vertical general scenario or the second vertical scenario; the second vertical scenario dialogue interface is the dialogue interface between the user and the second vertical scenario assistant.

[0076] In the technical solution provided by the embodiment of the present invention, by judging whether the question sent by the user involves a vertical scenario, a recommended message card of a suitable scenario assistant is automatically generated. The user can call the scenario assistant through this recommended message card and obtain a more professional reply content for this question, thereby improving the user experience.

[0077] An embodiment of the present invention provides a computer-readable storage medium. The computer-readable storage medium includes a stored program. When the program runs, it controls the device where the computer-readable storage medium is located to execute the embodiment of the above-mentioned assistant recommendation method.

[0078] Figure 6 A schematic diagram of a client provided by an embodiment of the present invention, including: The client 3 of this embodiment includes: a processor 31, a memory 32, and a computer program 33 stored in the memory 32 and executable on the processor 31. When the computer program 33 is executed by the processor 31, it implements the assistant recommendation method in the embodiment. To avoid repetition, it will not be elaborated here one by one.

[0079] The client 3 includes, but is not limited to, a processor 31 and a memory 32. Those skilled in the art can understand that Figure 6 This is only an example of the client 3 and does not constitute a limitation on the client 3. It may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, the network device may also include input / output devices, network access devices, buses, etc.

[0080] The so-called processor 31 may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0081] The memory 32 may be an internal storage unit of the client 3, such as the hard disk or memory of the client 3. The memory 32 may also be an external storage device of the client 3, such as a plug-in hard disk equipped on the client 3, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory 32 may also include both the internal storage unit and the external storage device of the client 3. The memory 32 is used to store the computer program and other programs and data required by the network device. The memory 32 may also be used to temporarily store the data that has been output or will be output.

[0082] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated here again.

[0083] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0084] Any process or method description shown in the flowchart or described in other ways herein can be understood to represent a module, segment, or part of code including one or more executable instructions for implementing a customized logic function or process. And the scope of the preferred embodiments of the present invention includes additional implementations, where the functions can be executed in a substantially simultaneous manner or in the reverse order according to the involved functions, rather than in the order shown or discussed, which should be understood by those skilled in the art of the embodiments of the present invention.

[0085] Depending on the context, the word "if" as used herein can be interpreted as "when" or "while" or "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrase "if determined" or "if detecting (stated condition or event)" can be interpreted as "when determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)".

[0086] In several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point, the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of devices or units can be in electrical, mechanical or other forms.

[0087] The above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the scope of protection of the present invention.

Claims

1. An assistant recommendation method, applied to a human-computer dialogue application based on generative artificial intelligence (AIGC), characterized in that: The human-computer dialogue application includes a general scenario assistant and at least one vertical scenario assistant. The general scenario assistant has the function of answering questions in various fields. Different scenario assistants correspond to different large language models. The method includes: In response to a question related to a first vertical scenario sent by a user in a general scenario dialogue interface, a first recommendation message card of the first vertical scenario assistant is generated and displayed in the general scenario dialogue interface; the general scenario dialogue interface is a dialogue interface between the user and the general scenario assistant, and the first recommendation message card is used to display the first text recommendation information and the chat control of the first vertical scenario assistant; In response to the user clicking the chat control of the first vertical scenario assistant, the first vertical scenario dialogue interface is entered, and a reply content corresponding to the question of the first vertical scenario is generated; the first vertical scenario dialogue interface is a dialogue interface between the user and the first vertical scenario assistant; When the question involves multiple different first vertical scenarios, the first recommended message card is used to display the first text recommendation information and chat controls of multiple first vertical scenario assistants; the chat controls of the multiple first vertical scenario assistants are arranged in descending order according to the relevance of the question to the multiple first vertical scenarios.

2. The method according to claim 1, characterized in that After the user clicks on the chat control of the first vertical scenario assistant to enter the first vertical scenario dialogue interface and generates a reply content corresponding to the question of the first vertical scenario, the method further includes: In response to a question related to a general scenario or a second vertical scenario sent by a user in the first vertical scenario dialogue interface, a second recommendation message card of the general scenario assistant or the second vertical scenario assistant is generated and displayed in the first vertical scenario dialogue interface; the second recommendation message card is used to display second text recommendation information and a chat control of the general scenario assistant or the second vertical scenario assistant, and the second vertical scenario is different from the first vertical scenario; In response to the user clicking on the chat control of the general scenario assistant or the second vertical scenario assistant, switch to the dialogue interface with the general scenario assistant or the second vertical scenario dialogue interface, and generate reply content corresponding to the question of the general scenario or the second vertical scenario; the second vertical scenario dialogue interface is the dialogue interface between the user and the second vertical scenario assistant.

3. The method according to claim 1, characterized in that The first recommended message card further includes a business card control of the first vertical scenario assistant, and the method further includes: In response to the user clicking the business card control, the business card introduction interface of the first vertical scene assistant is entered, and the business card introduction interface is used to display the assistant information of the first vertical scene assistant.

4. The method according to claim 1, wherein The method further comprises: In response to the user's first call to the universal scene assistant, an introduction message card is displayed; the introduction message card includes an introduction message of the universal scene assistant, an introduction message of at least one vertical scene assistant, and a relationship introduction message; the relationship introduction message is used to explain the relationship between the universal scene assistant and the at least one vertical scene assistant.

5. The method according to claim 1, characterized in that The method further comprises: Show Assistant Center controls; In response to the user clicking on the assistant center control, the assistant center interface is entered; the assistant center interface is used to display the assistant information of the general scene assistant and the assistant information of at least one vertical scene assistant associated with the general scene assistant.

6. An assistant recommendation device, applied to a human-computer dialogue application based on generative artificial intelligence AIGC, characterized in that: The human-computer dialogue application includes a general scenario assistant and at least one vertical scenario assistant. The general scenario assistant has the function of answering questions in various fields. The general scenario assistant and the vertical scenario assistant are respectively trained by different large language models. The device includes: A first generation module is configured to generate a first recommendation message card of a first vertical scenario assistant in response to a question involving a first vertical scenario sent by a user in a general scenario dialogue interface and display the card in the general scenario dialogue interface; the general scenario dialogue interface is a dialogue interface between the user and the general scenario assistant, and the first recommendation message card is configured to display first text recommendation information and a chat control of the first vertical scenario assistant. When the question involves multiple different first vertical scenarios, the first recommendation message card is configured to display the first text recommendation information and chat controls of multiple first vertical scenario assistants; the chat controls of the multiple first vertical scenario assistants are arranged in descending order according to the relevance of the question to the multiple first vertical scenarios; The second generation module is connected to the first generation module and is used to enter the first vertical scenario dialogue interface in response to the user clicking the chat control of the first vertical scenario assistant, and generate reply content corresponding to the question of the first vertical scenario; the first vertical scenario dialogue interface is the dialogue interface between the user and the first vertical scenario assistant.

7. A client, characterized in that: include: Display screen; one or more processors; Memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions, which, when executed by the client, enable the client to perform the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method according to any one of claims 1 to 5.

Images