Intelligent agent-based data processing method and device, equipment, medium and product

Abstract

Embodiments of the invention provide an agent-based data processing method and apparatus, a device, a medium and a product. The agent-based data processing method comprises the steps of displaying a session page with a target agent; the session page comprises session data of the target agent; and in response to a publishing operation on the session data, publishing the target published content, a cover image of the target published content being generated based on the session data, and a content page of the target published content including a session entry with the target agent. By adopting the embodiment of the invention, the cover image of the published content can be generated based on the session data of the intelligent agent, and the published content including the cover image is published, so that the utilization rate of the session data of the intelligent agent in the application program is improved, and the intelligent degree of the service function of the application program can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computers, and in particular to an agent-based data processing method and device, equipment, medium and product. BACKGROUND

[0002] With the rapid development of computer technology, the application scenarios of agents are becoming more and more rich, for example, a user can have a conversation with an agent in an application. At present, after having a conversation with an agent in an application, the use object of the application and the conversation data of the agent cannot be combined with the business function of the application itself, resulting in low utilization of the use object of the application and the conversation data of the agent in the application, and low intelligentization of the business function of the application itself. SUMMARY

[0003] The embodiments of the present application provide an agent-based data processing method and device, equipment, medium and product, which can generate a cover image of a published content based on conversation data of an agent, and publish the published content containing the cover image, thereby improving the utilization of the conversation data of the agent in an application, and improving the intelligentization of the business function of the application itself.

[0004] In one aspect, the embodiments of the present application provide an agent-based data processing method, which comprises:

[0005] In response to a conversation request for a target agent triggered in a parent application, obtaining page template data, the page template data being used to generate a conversation page for having a conversation with at least one agent, the target agent being any one of the at least one agent;

[0006] rendering the page template data to obtain a conversation page for the target agent, and displaying the conversation page;

[0007] In response to dialogue information input in the conversation page, generating reply information corresponding to the dialogue information by calling a conversation model corresponding to the target agent through a sub-application, the sub-application having a subordinate relationship with the parent application;

[0008] rendering the reply information to the conversation page.

[0009] Correspondingly, the embodiments of the present application provide an agent-based data processing device, which comprises:

[0010] The processing unit is configured to, in response to a session request for a target agent triggered in the parent application, acquire page template data, the page template data being used to generate a session page for a session with at least one agent, the target agent being any one of the at least one agent;

[0011] The display unit is configured to render the page template data to obtain the session page with the target agent, and display the session page.

[0012] The processing unit is further configured to, in response to dialogue information input in the session page, generate reply information corresponding to the dialogue information by calling a session model corresponding to the target agent through the sub-application, the sub-application having a subordinate relationship with the parent application.

[0013] The display unit is further configured to render the reply information to the session page.

[0014] In another aspect, an embodiment of the present application provides a data processing method based on an agent, which comprises:

[0015] The display unit is configured to display, through the sub-application, a session page with the target agent, the session page including session data between the target agent, the session data including dialogue information and reply information.

[0016] The processing unit is configured to, in response to a publishing operation on the session data, receive session data sent by the sub-application.

[0017] The processing unit is further configured to perform conversion processing on the session data through the parent application to obtain a plurality of to-be-published images, determine target publishing content including the plurality of to-be-published images, and publish the target publishing content; wherein the parent application has a subordinate relationship with the sub-application.

[0018] Correspondingly, an embodiment of the present application provides a data processing device based on an agent, which comprises:

[0019] The display unit is configured to display, through the sub-application, a session page with the target agent, the session page including session data between the target agent, the session data including dialogue information and reply information.

[0020] The processing unit is configured to, in response to a publishing operation on the session data, receive session data sent by the sub-application.

[0021] The processing unit is further configured to perform conversion processing on the session data through the parent application to obtain a plurality of to-be-published images, determine target publishing content including the plurality of to-be-published images, and publish the target publishing content; wherein the parent application has a subordinate relationship with the sub-application.

[0022] In an aspect, an embodiment of the present application provides a computer device, comprising: a processor adapted to execute a computer program; and a computer readable storage medium having stored therein the computer program, which, when executed by the processor, implements the above-mentioned agent-based data processing method.

[0023] In another aspect, an embodiment of the present application provides a computer readable storage medium having stored therein a computer program, which, when loaded and executed by a processor, implements the above-mentioned agent-based data processing.

[0024] In another aspect, an embodiment of the present application provides a computer program product comprising computer programs or computer instructions, which, when executed by a processor, implements the above-mentioned agent-based data processing method.

[0025] In an embodiment of the present application, in response to a session request for a target agent triggered in a parent application, page template data can be obtained, which can be used to generate a session page for a session with at least one agent; the page template data can be rendered to obtain a session page with the target agent, and the session page can be displayed; in response to dialogue information input in the session page, the dialogue information corresponding reply information can be generated by calling a session model corresponding to the target agent through a sub-application, the sub-application and the parent application have a subordinate relationship; and the reply information can be rendered to the session page. As can be seen, the application can be used as a parent application, and the agent can be accessed through a sub-application in the parent application, so that the agent can be accessed in the application; and after the agent is accessed in the application, in response to a session request for the agent triggered in the application, the session page with the agent can be rendered in the application, so that the agent can be conversed with in the application, that is, the session page with the agent can be directly displayed in the application and conversed with the agent without jumping from the application to other business platforms, which can improve the conversation efficiency with the agent in the application; in addition, at least one agent accessed in the parent application can be rendered to obtain a session page for a session with at least one agent based on the same page template data, so that the session page with at least one agent accessed in the parent application has a unified style, and the standardization degree of the agent accessing the application is improved. BRIEF DESCRIPTION OF DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, the accompanying drawings in the following description only only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0027] Figure 1a is a schematic diagram of the architecture of a data processing system provided by an embodiment of the present application;

[0028] Figure 1b is a schematic diagram of the architecture of another data processing system provided by an embodiment of the present application;

[0029] Figure 2 is a schematic diagram of the flow of a first data processing method based on an agent provided by an embodiment of the present application;

[0030] Figure 3a is a schematic diagram of an interface for triggering a conversation request with an agent from a personal page of a parent application provided by an embodiment of the present application;

[0031] Figure 3b is a schematic diagram of an interface for triggering a conversation request with an agent from a published content page of a parent application provided by an embodiment of the present application;

[0032] Figure 3c is a schematic diagram of an interface for triggering a conversation request with an agent from a message page of a parent application provided by an embodiment of the present application;

[0033] Figure 3d is a schematic diagram of an interface for triggering a conversation request with an agent from a search page of a parent application provided by an embodiment of the present application;

[0034] Figure 3e is a schematic diagram of an interface for triggering a conversation request with an agent from a comment page of a parent application provided by an embodiment of the present application;

[0035] Figure 4 is a schematic diagram of the flow of a second data processing method based on an agent provided by an embodiment of the present application;

[0036] Figure 5 is a schematic diagram of a calling process in a parent application client provided by an embodiment of the present application;

[0037] Figure 6 is a schematic diagram of a technical framework for conversing with an agent in a parent application client provided by an embodiment of the present application;

[0038] Figure 7FIG. 1 is a flowchart of a third embodiment of the method for processing data based on an intelligent agent provided by the present application;

[0039] Figure 8a FIG. 2 is a flowchart of a fourth embodiment of the method for processing data based on an intelligent agent provided by the present application;

[0040] Figure 8b FIG. 3 is an interface diagram of publishing session data as publishing content provided by an embodiment of the present application;

[0041] Figure 8c FIG. 4 is an interface diagram of selecting session data to be published provided by an embodiment of the present application;

[0042] Figure 8d FIG. 5 is an interface diagram of a fixed number of selectable session data groups provided by an embodiment of the present application;

[0043] Figure 8e FIG. 6 is an interface diagram of copying and deleting session data provided by an embodiment of the present application;

[0044] Figure 9 FIG. 7 is a flowchart of a fifth embodiment of the method for processing data based on an intelligent agent provided by the present application;

[0045] Figure 10 FIG. 8 is a technical framework diagram of accessing an intelligent agent in a parent application provided by an embodiment of the present application;

[0046] Figure 11 FIG. 9 is a diagram of a unified rendering standard provided by an embodiment of the present application;

[0047] Figure 12 FIG. 10 is another diagram of a unified rendering standard provided by an embodiment of the present application;

[0048] Figure 13 FIG. 11 is a diagram of a rendering result under a unified rendering standard provided by an embodiment of the present application;

[0049] Figure 14 FIG. 12 is a structural diagram of a data processing device based on an intelligent agent provided by an embodiment of the present application;

[0050] Figure 15 FIG. 13 is a structural diagram of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0051] With reference to the drawings, the technical solutions in the embodiments of the present application will be clearly and completely described below, obviously, the described embodiments are some of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all the other embodiments obtained by a person of ordinary skill in the art without creative effort belong to the protection scope of the present application.

[0052] The embodiment of the present application provides a data processing method based on an agent, which can take an application as a parent application, and access at least one agent in the parent application through a sub-application, so as to improve the intelligent degree of the parent application. In order to reduce the access cost of the agent, a chat box can be used to provide standardized open capabilities for the access of the at least one agent, so that the at least one agent can be standardized to access the parent application, and the chat box can uniformly manage the at least one agent according to a unified standard.

[0053] In addition, the data processing method based on the agent can respond to a session request for any accessed agent (for example, the accessed agent is a target agent) triggered in the parent application, render and present a session page of the target agent in the parent application through the sub-application, that is, the session page of the target agent can be directly displayed in the parent application without jumping to an agent service platform outside the application, so as to improve the session efficiency with the agent in the application.

[0054] In addition, the data processing method based on the agent can also combine the use object of the application and the session data of the agent with the business function of the application itself, for example, the content publishing function of the application can be combined, the session data of the agent can be published as publishing content (for example, note content or social dynamic content); for example, the sharing function of the application can be combined, the session data of the agent can be shared as chat content; and the like. By combining with the business function of the application itself, not only the utilization rate of the session data of the agent in the application can be improved, but also the intelligent degree of the business function of the application itself can be improved.

[0055] In the data processing method based on the agent provided in the embodiments of the present application, technical terms such as application, parent application, sub-application, agent, and chat box are involved, in order to facilitate understanding, these technical terms will be introduced first:

[0056] ①Application Program (APP) refers to a computer program developed for completing a specific task. The client corresponding to the application program can run in a terminal device, the use object of the application program can interact with the application program through the client corresponding to the application program, the client corresponding to the application program can provide local services for the use object of the application program in the terminal device, the client corresponding to the application program can communicate with the server corresponding to the application program through a communication network, and the server corresponding to the application program can provide service support for the client corresponding to the application program.

[0057] ②The parent application program and the child application program can have a subordinate relationship. The subordinate relationship refers to that one application program depends on another application program in terms of function, resource or data. The dependent application program can be referred to as a child application program (namely, a subordinate application), and the dependent application program can be referred to as a parent application program (namely, a master application). For example, a map service application program can be in the form of a small program and accessed into a social media application program, and the social media application program and the map service application program have a subordinate relationship.

[0058] Among them, the client corresponding to the parent application program can be referred to as a parent application client, and the server corresponding to the parent application program can be referred to as a parent application server. The client corresponding to the child application program can be referred to as a child application client, and the server corresponding to the child application program can be referred to as a child application server.

[0059] Based on the subordinate relationship between the parent application program and the child application program, the parent application client can provide a child application container for running the child application client for the child application client. The child application container is a kind of light application program container technology, which can be used to run the child application client in the parent application client. The child application container packs the child application client code and the runtime environment provided by the parent application program together to form a container that can run on the parent application client. When the use object of the parent application program opens the child application client on the parent application client, the parent application client can load the child application container and run the child application client code in the child application container, so as to run the child application client.

[0060] ③Agent refers to an intelligent system with autonomous perception, decision-making and execution capabilities, which can achieve goals through interaction with the environment. Its essence is a digital entity simulating human cognitive framework, with a closed-loop capability of "perception→planning→action". In the embodiments of the present application, Agent specifically refers to an AI (Artificial Intelligence) Agent, which is an Agent combined with AI. The basis for the Agent to have a conversation with the user of the parent application is the conversation model corresponding to the Agent. The conversation model corresponding to the Agent can be an AI model with language generation capability, which can be used to generate reply information corresponding to the conversation information of the user. The embodiments of the present application do not limit the type of conversation model. For example, the conversation model can be an LLM (Large Language Model).

[0061] ④Chatbox refers to a tool for providing the user of the parent application with the ability to have a conversation with the Agent in the parent application. To achieve this conversation capability, the chatbox can provide the parent application with standardized access capabilities of the Agent and standardized management capabilities of the Agent. In addition, the chatbox can be used to carry the conversation link between the Agent and the user of the parent application. The conversation link refers to the complete conversation process between the parent application and the conversation model corresponding to the Agent.

[0062] ⑤Published content refers to content published in the parent application. For example, the published content can include note content or social dynamic content published in the parent application.

[0063] ⑥In response to a condition or state on which the performed operation depends, when the dependent condition or state is met, the performed one or more operations can be real-time or have a set delay. In the absence of specific instructions, there is no restriction on the execution sequence of the multiple operations performed. For example, for "in response to a conversation request for the target Agent triggered in the parent application, obtaining page template data", the operation is "obtaining page template data", and the condition on which the operation depends is "a conversation request for the target Agent triggered in the parent application".

[0064] ⑦Trigger operation: The trigger operation refers to the operation performed by the user of the parent application (including the sub-application) on the parent application. For example, the trigger operation refers to the trigger operation performed by the user of the parent application on the control in the parent application. The trigger operation here can be, for example, single-click, double-click, and long press.

[0065] The architecture of the data processing system provided by the embodiments of the present application will be introduced below with reference to the accompanying drawings.

[0066] The agent can access the parent application through the sub-application. Specifically, the access mode can include any one of the following: first, one agent can access the parent application in the form of one sub-application; second, at least one agent can access the same sub-application of the parent application in the form of an agent instance, and one agent corresponds to one agent instance in the sub-application. Wherein, the agent instance refers to the access form of the agent in the sub-application, and the agent instance can provide interaction capability between the use object of the parent application and the agent in the sub-application. The architecture of the data processing system under the two access modes will be introduced respectively as follows:

[0067] The data processing system in which one agent accesses the parent application in the form of one sub-application can be shown in FIG. 1. Figure 1a The data processing system can include a terminal device 101, a sub-application server 102, a parent application server 103 and a service provider server 104. The devices that need to communicate can establish direct communication connection through wired communication, or can establish indirect communication connection through wireless communication, which is not limited by the embodiments of the present application. Wherein:

[0068] The terminal device 101 can run the client corresponding to the parent application (i.e. the parent application client), and the parent application client can run the client corresponding to the sub-application (i.e. the sub-application client). Taking the example that the first agent and the second agent access the parent application, the parent application client can run the client corresponding to the first sub-application corresponding to the first agent (hereinafter referred to as the first sub-application client), and the client corresponding to the second sub-application corresponding to the second agent (hereinafter referred to as the second sub-application client).

[0069] The sub-application server 102 can be used to provide service support for the sub-application client. Taking the example that the first agent and the second agent access the parent application, the sub-application server 102 can include the server 1021 corresponding to the first sub-application corresponding to the first agent (hereinafter referred to as the first sub-application server 1021), and the server 1022 corresponding to the second sub-application corresponding to the second agent (hereinafter referred to as the second sub-application server 1022). The parent application server 103 can be used to provide service support for the parent application client. Figure 1aThe data processing system shown takes the example that the sub-application server 102 and the parent application server 103 are integrated in different devices. Alternatively, the sub-application server 102 and the parent application server 103 can also be integrated in the same device. For example, the sub-application server 102 can be integrated in the parent application server 103. It can be understood that the sub-application server 102 can be integrated in the parent application server 103 as a service module of the parent application server 103.

[0070] The session model corresponding to the agent can be deployed in the application server (for example, can be deployed in the sub-application server 102), or the session model corresponding to the agent can be deployed in the service provider server providing the related service of the agent. Figure 1a The data processing system shown takes the example that the session model corresponding to the first agent is deployed in the first sub-application server 1021, and the session model corresponding to the second agent is deployed in the service provider server providing the related service of the second agent.

[0071] In Figure 1a In the data processing system shown, taking the first agent as an example (the second agent is similar to the first agent), the process of invoking the session page of the first agent in the parent application client can include: in response to the session request for the first agent triggered in the parent application client, obtaining page template data, rendering the page template data to obtain the session page of the first agent, and displaying the session page of the first agent.

[0072] In Figure 1a In the data processing system shown, taking the first agent as an example, the session process of the agent in the parent application program corresponding to the session model deployed in the sub-application server 102 can include: in response to the dialogue information input in the session page of the first agent, calling the session model corresponding to the first agent in the first sub-application server 1021 through the first sub-application client to generate reply information corresponding to the dialogue information; and rendering the reply information to the session page of the first agent.

[0073] In Figure 1aIn the data processing system shown, taking the second agent as an example, the session flow of the agent corresponding to the session model deployed in the business server 104 in the mother application can include: in response to the dialogue information input in the session page with the second agent, the dialogue information can be sent to the second sub-application server 1022 through the second sub-application client, and the second sub-application server 1022 can call the session model corresponding to the second agent in the business server 104 to generate reply information corresponding to the dialogue information; the second sub-application server 1022 can send the reply information to the second sub-application client, and the reply information can be rendered to the session page with the second agent.

[0074] In Figure 1a In the data processing system shown, taking the first agent as an example (the second agent is similar to the first agent), the process of publishing the session data with the first agent as publishing content in the mother application can include: in response to the publishing operation of the session data, the mother application client can receive the session data sent by the first sub-application client; the mother application client can send the session data to the mother application server 103, and the mother application server 103 can convert and process the session data to obtain multiple images to be published and determine the publishing content including the multiple images to be published; the mother application server 103 can send the publishing content to the mother application client, and the mother application client can render the publishing content to the publishing content page to publish the publishing content.

[0075] As can be seen, in Figure 1a In the data processing system shown, the agent can be accessed in the form of a sub-application in the mother application, one agent corresponds to one sub-application, and through the session request triggered in the mother application, the session page with the agent can be quickly invoked, so that the agent can be conversed with, and the session efficiency with the agent is improved. And the session data with the agent can also be published in the mother application, making the publishing content of the mother application intelligent and diversified.

[0076] The data processing system in which at least one agent accesses the same sub-application of the mother application in the form of an agent instance is as shown in Figure 1b The data processing system can include a terminal device 101, a sub-application server 102, a mother application server 103 and a business server 104, and the devices that need to communicate can establish direct communication connection through wired communication or indirect communication connection through wireless communication, which is not limited by the embodiments of the present application. Among them:

[0077] The terminal device 101 can run a client corresponding to the parent application (i.e., a parent application client), and the parent application client can run a client corresponding to the child application (i.e., a child application client). Taking the example of a first intelligent agent and a second intelligent agent being accessed in a same child application of a parent application, the child application client can include an intelligent agent instance corresponding to the first intelligent agent (hereinafter referred to as a first intelligent agent instance) and an intelligent agent instance corresponding to the second intelligent agent (hereinafter referred to as a second intelligent agent instance). The first intelligent agent instance can be used to provide an interaction capability between a user of the parent application and the first intelligent agent, and the second intelligent agent instance can be used to provide an interaction capability between the user of the parent application and the second intelligent agent.

[0078] The child application server 102 can be used to provide service support for the child application client, and the parent application server 103 can be used to provide service support for the parent application client. Figure 1b The data processing system shown takes the example of the child application server 102 and the parent application server 103 being integrated in different devices. Alternatively, the child application server 102 and the parent application server 103 can also be integrated in the same device. For example, the child application server 102 can be integrated in the parent application server 103. It can be understood that the child application server 102 can be integrated in the parent application server 103 as a service module of the parent application server 103.

[0079] The intelligent agent corresponding conversation model can be deployed in an application server (for example, deployed in the child application server 102), or the intelligent agent corresponding conversation model can be deployed in a service provider server providing a related service of the intelligent agent. Figure 1b The data processing system shown takes the example of the first intelligent agent corresponding conversation model being deployed in the child application server 102, and the second intelligent agent corresponding conversation model being deployed in the service provider server 104 providing a related service of the second intelligent agent.

[0080] In Figure 1b In the data processing system shown, taking the first intelligent agent as an example (the second intelligent agent is similar to the first intelligent agent), the process of invoking a conversation page with the first intelligent agent in the parent application client can include: obtaining page template data in response to a conversation request for the first intelligent agent triggered in the parent application client; rendering the page template data to obtain a conversation page with the first intelligent agent, and displaying the conversation page with the first intelligent agent.

[0081] In Figure 1bIn the data processing system shown, taking the first agent as an example, the session flow of the agent corresponding to the session model deployed in the sub-application server 102 in the mother application can include: in response to the dialogue information input in the session page with the first agent, the first agent instance in the sub-application client can call the first agent corresponding session model in the sub-application server 102 to generate reply information corresponding to the dialogue information; and the reply information can be rendered to the session page with the first agent.

[0082] In Figure 1b In the data processing system shown, taking the second agent as an example, the session flow of the agent corresponding to the session model deployed in the business server 104 in the mother application can include: in response to the dialogue information input in the session page with the second agent, the second agent instance in the sub-application client can send the dialogue information to the sub-application server 102, and the sub-application server 102 can call the second agent corresponding session model in the business server 104 to generate reply information corresponding to the dialogue information; and the reply information can be rendered to the session page with the second agent.

[0083] In Figure 1b In the data processing system shown, taking the first agent as an example (the second agent is similar to the first agent), the process of publishing the session data with the first agent as publishing content in the mother application can include: in response to the publishing operation of the session data, the mother application client can receive the session data sent by the first agent instance; the mother application client can send the session data to the mother application server 103, which can convert and process the session data to obtain multiple images to be published and determine the publishing content including the multiple images to be published; and the mother application server 103 can send the publishing content to the mother application client, which can render the publishing content to the publishing content page to publish the publishing content.

[0084] As can be seen, Figure 1b In the data processing system shown, at least one agent can be accessed in the same sub-application in the mother application, one agent corresponds to an agent instance in the sub-application, and through a session request triggered in the mother application, a session page with the agent can be quickly invoked, so that the agent can be conversed with, and the session efficiency with the agent is improved. Moreover, the session data with the agent can also be published in the mother application, making the publishing content of the mother application intelligent and diversified.

[0085] Figure 1a And Figure 1bThe data processing system of the illustrated embodiment is used to more clearly illustrate the technical solutions of the embodiments of the present application, and does not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art can know that, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0086] The terminal device mentioned in the embodiments of the present application includes but is not limited to: a smart phone, a tablet computer, a smart wearable device, a smart voice interaction device, a smart home appliance, a personal computer, a vehicle-mounted terminal, a smart camera, and the like. The present application does not limit this. The server can be a single physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and basic cloud computing services such as big data and artificial intelligence platforms, but is not limited thereto.

[0087] Next, the agent-based data processing method provided by the embodiments of the present application will be described in detail with reference to the accompanying drawings.

[0088] The embodiments of the present application propose an agent-based data processing method. The agent-based data processing method can include the technical process of triggering a conversation page with an agent from different pages of a parent application and conversing with the agent in the parent application. The agent-based data processing method can be executed by a terminal device, specifically by a parent application running in the terminal device. As shown in the figure, Figure 2 The agent-based data processing method can include but is not limited to the following steps S201-S204:

[0089] S201, in response to a conversation request for a target agent triggered in a parent application, obtaining page template data, the page template data being used to generate a conversation page for conversing with at least one agent, the target agent being any one of the at least one agent.

[0090] S202, rendering the page template data to obtain a conversation page with the target agent, and displaying the conversation page.

[0091] In steps S201-S202, a session request for the target agent can be triggered on different pages of the parent application (specifically, the parent application client). For example, a session request for the target agent can be triggered on any page of the parent application, such as the personal page, content posting page, message page, search page, and comment page, thereby triggering the display of the session page with the target agent. The triggering methods for session requests for the target agent on these pages are described below:

[0092] (1) Personal Page:

[0093] The target agent's personal page can be displayed through the parent application. A session request can be generated in response to a session trigger action on the personal page, triggering the display of the session page with the target agent. Here, the personal page refers to the page in the parent application used to display personal information and published content. The target agent's personal page refers to the page using the target agent as the account holder, used to display the target agent's introductory information and published content.

[0094] Session-triggered actions for a personal page can include any of the following: First, such as... Figure 3a As shown, the target agent's personal page 30 may include a session entry point 301 for the target agent. A session request can be generated in response to a triggering operation on the session entry point 301, triggering the display of the session page 80 with the target agent. The triggering operation here may include, for example, a single click, double click, and long press, etc., which are not limited in this embodiment. Secondly, during the display of the target agent's personal page in the parent application, a session request can be generated in response to a gravity sensing operation performed on the terminal device running the parent application. For example, the gravity sensing operation may include a shaking operation and a rotating operation, etc., which are not limited in this embodiment. Thirdly, a session request can be generated in response to a gesture triggering operation performed on the target agent's personal page. A gesture triggering operation refers to the operation of drawing a specific pattern on the personal page using a specific gesture, for example, drawing the letter "A" on the personal page using the index finger.

[0095] Optionally, in addition to being set on the target intelligent agent's personal page, the session entry point with the target intelligent agent can also be set on the personal page of any object in the parent application. In response to the triggering operation of the session entry point with the target intelligent agent on the personal page of any object, a session request can be generated, and a session can be initiated with the target intelligent agent. Alternatively, a session can be initiated with the target intelligent agent based on the content in the object's personal page.

[0096] (2) Content publishing page:

[0097] The publishing content page can be displayed through the parent application. This page can include a session entry point for the target agent and can generate a session request in response to a session trigger operation targeting that entry point. The publishing content page refers to the page within the parent application used to display the published content. More specifically, as... Figure 3b As shown, any object (e.g., Figure 3b The content page 31 of the first object in the process may include an agent initiation entry 311. In response to the triggering operation of the agent initiation entry 311, an agent entry list 312 may be displayed. The agent entry list 312 may include a session entry with at least one agent. The session entry with at least one agent may include a session entry 301 with the target agent. In response to the triggering operation of the session entry 301, a session request may be generated, triggering the display of the session page 80 with the target agent.

[0098] (3) Messages page:

[0099] like Figure 3c As shown, message page 32 can be displayed through the parent application. Message page 32 refers to a page in the parent application used to display conversation messages with at least one object. Message page 32 may include conversation messages with at least one object (e.g., a target agent and a first object). The at least one object may include a target agent. That is, the message page may include conversation message 321 with the target agent. A conversation request can be generated in response to a conversation triggering operation for the target agent in message page 32. Here, the conversation triggering operation may refer to the triggering operation for the conversation message 321 with the target agent in message page 32. This can trigger the display of conversation page 80 with the target agent.

[0100] (4) Search page:

[0101] A search page can be displayed through the parent application. This search page may include a session entry point for the target agent and can generate a session request in response to a session triggering action on that entry point. Here, the search page refers to the page within the application used to provide search functionality. More specifically, such as... Figure 3d As shown, the search page 33 of the parent application may include a list of agent entry points 312. The list of agent entry points 312 may include a session entry point with at least one agent. The session entry point with at least one agent may include a session entry point 301 with the target agent. In response to a triggering operation on the session entry point 301, a session request may be generated, triggering the display of the session page 80 with the target agent.

[0102] (5) Comments page:

[0103] The comment page can be displayed by the parent application, where the comment page refers to a page in the parent application for publishing comment content and conducting comment interaction; the comment page can include comment content of the target agent, and a conversation request can be generated in response to a conversation triggering operation on the target agent in the comment page. In detail, as shown in Figure 3e The comment page 34 of the parent application can include comment content 341 of the target agent, the comment content 341 of the target agent can include a conversation portal 301 of the target agent, and a conversation request can be generated in response to a triggering operation on the conversation portal 301 to trigger the display of the conversation page 80 with the target agent.

[0104] It can be seen that the embodiments of the present application can support triggering a conversation request for a target agent in different pages of a parent application, which can improve the efficiency of invoking an agent in a parent application, thereby improving the conversation efficiency with an agent in a parent application.

[0105] In step S201, page template data can be obtained in response to a conversation request for a target agent triggered in a parent application, and the page template data can be used to generate a conversation page for conversing with at least one agent. The page template data can be used to define a unified page framework of the conversation page for conversing with at least one agent, where the unified page framework refers to various regions included in the conversation page and information supported for display in each region, so that the page template data can be used to generate a conversation page for conversing with at least one agent according to a unified conversation page style, that is, the conversation page style of at least one agent is unified.

[0106] In detail, the page template data can include basic region data, conversation information region data, and input region data, and the unified page framework can include a basic region, a conversation information region, and an input region; where the basic region can be used to display global control controls for the agent (for example, controls for triggering reporting of the agent, viewing historical conversation data, etc.), the conversation information region can be used to display conversation data, and the input region can be used to display an input box for conversation information, conversation control controls (for example, a new conversation control and an extended function control (for example, a deep thinking control and a network search control)), and controls for triggering external sending functions (for example, controls for triggering sending of conversation information, and controls for triggering functions such as photo album and photo shooting).

[0107] In step S202, after obtaining the page template data, the page template data can be rendered to obtain the conversation page with the target agent, and the conversation page is displayed. In detail, the basic area data can be rendered to obtain the basic area of the conversation page with the target agent, the conversation information area data can be rendered to obtain the conversation information area of the conversation page with the target agent, and the input area data can be rendered to obtain the input area of the conversation page with the target agent. It can be seen that in this case, the conversation page with each agent is rendered based on the same page template data, so that the conversation page style of each agent is unified, and the page content of the conversation page with each agent is completely the same.

[0108] Optionally, the page content data corresponding to the target agent can also be obtained, and the page content data can include at least one of the following: configuration data corresponding to the target agent and historical conversation data with the target agent; wherein the configuration data corresponding to the target agent can be customized in the access process of the target agent, and the configuration data corresponding to the target agent can include but is not limited to: basic area configuration data corresponding to the target agent (for example, can include an identifier corresponding to the target agent displayed in the basic area), welcome information configuration data corresponding to the target agent (for example, can include a welcome message displayed when the target agent is first conversed), and extended function control configuration data corresponding to the target agent (for example, can include an extended function control displayed in the input area).

[0109] In this case, the page template data and the page content data corresponding to the target agent can be rendered to obtain the session page of the target agent. In detail, the base area data and the base area configuration data corresponding to the target agent can be rendered to obtain the base area of the session page of the target agent, the session information area data and the historical session data of the target agent (or the welcome information configuration data corresponding to the target agent) can be rendered to obtain the session information area of the session page of the target agent, and the input area data and the extended function control configuration data corresponding to the target agent can be rendered to obtain the input area of the session page of the target agent. It can be seen that in this case, the session pages of the agents are rendered based on the same page template data, so that the styles of the session pages of the agents are unified, and since the page content data corresponding to the agents is self-defined and configured, it can be different, so that the page content of the session pages of the agents can be different, for example, the identifiers of the agents in the base area are different, the historical session data of the agents in the session information area is different, the welcome words corresponding to the agents in the session information area can be different, and the extended function controls of the agents in the input area can be different, so that the flexibility of the agent access can be improved.

[0110] In S203, in response to the dialogue information input in the session page, the dialogue information corresponding reply information is generated by calling the session model corresponding to the target agent through the sub-application, and the sub-application and the parent application have a subordinate relationship.

[0111] Before S203, the dialogue information can be preprocessed by the sub-application to obtain preprocessed dialogue information. After preprocessing, in S203, the preprocessed dialogue information corresponding reply information can be generated by calling the session model corresponding to the target agent through the sub-application. The preprocessing refers to assembling information for the dialogue information which is helpful for the target agent corresponding session model to generate reply information. In the preprocessing process, the information assembled for the dialogue information can include reference information and / or answer mode. Wherein:

[0112] ① Reference information:

[0113] For the case of assembling reference information for dialogue information, the reference information can be obtained through the sub-application (specifically, the sub-application server), and the reference information and the dialogue information can be assembled and processed through the sub-application to obtain the preprocessed dialogue information, and then the dialogue information corresponding reply information can be generated by calling the session model corresponding to the target agent through the sub-application according to the reference information and the dialogue information.

[0114] The reference information refers to information referenced by the conversation model corresponding to the target intelligent agent when generating reply information corresponding to the dialogue information. The reference information can include, but is not limited to, at least one of the following: context information of interaction between the use object and the target intelligent agent (for example, historical conversation data between the use object and the target intelligent agent, and historical comment interaction data between the use object and the target intelligent agent, etc.), published content of the target intelligent agent, object feature information of the use object, and operation feature information of the use object (for example, published content historically accessed by the use object, etc.). By providing the reference information to the conversation model corresponding to the target intelligent agent, the conversation model corresponding to the target intelligent agent can learn the knowledge provided by the reference information, and generate reply information corresponding to the dialogue information based on the learned knowledge, thereby improving the accuracy of the reply information and the adaptation degree between the reply information and the use object.

[0115] In addition, the reference information can match the trigger scene corresponding to the conversation request. The trigger scene corresponding to the conversation request refers to a scene to which a page triggering the conversation request belongs, for example, a personal page scene, a message page scene, and a comment page scene, etc. The matching refers to that different trigger scenes can correspond to different reference information types, and the obtained reference information type corresponds to the trigger scene corresponding to the current conversation request. For example, the trigger scene corresponding to the conversation request is a personal page scene, and the obtained reference information can include published content of the target intelligent agent and historical conversation data between the use object and the target intelligent agent. For another example, the trigger scene corresponding to the conversation request is a comment page scene, and the obtained reference information can include historical comment interaction data between the use object and the target intelligent agent in the comment page. By stipulating that the reference information matches the trigger scene corresponding to the conversation request, the accuracy of the reference information can be improved, thereby improving the accuracy of the reply information.

[0116] ② Answer mode:

[0117] For the case of assembling an answer mode for dialogue information, the answer mode can be obtained through a sub-application program (specifically, a sub-application server), and the answer mode and the dialogue information are assembled and processed through the sub-application program to obtain preprocessed dialogue information. Then, the sub-application program can call the conversation model corresponding to the target intelligent agent to generate reply information corresponding to the dialogue information according to the answer mode.

[0118] The answer mode refers to an information mode of reply information, specifically refers to an information style of reply information, and can be used to instruct the target intelligent agent to generate reply information according to the specified information style. The answer mode can include but is not limited to any one of the following: chat mode (CHAT) and related word mode (RELATED_WORD); wherein the chat mode can instruct the target intelligent agent to return reply information in a more casual and lively style, and the related word mode can instruct the target intelligent agent to predict more content that the user wants to know according to the context information, generate at least one related text (each related text is not more than 16 characters), and separate the style by commas. By providing the answer mode to the target intelligent agent, the target intelligent agent can generate reply information in a specified style, which can improve the accuracy of the reply information.

[0119] In addition, the answer mode can match the conversation scene corresponding to the conversation page. The conversation scene corresponding to the conversation page refers to the conversation type triggered by the user in the conversation page, for example, the user manually inputs the dialogue information in the conversation page, which can trigger the chat type, and the conversation scene corresponding to the conversation page is the chat scene, for example, the user automatically inputs the dialogue information in the conversation page through some preset automatic question mode (for example, clicking the "learn more" control), which can trigger the related word scene, and the conversation scene corresponding to the conversation page is the related word scene. Match means that different conversation scenes can correspond to different answer modes, and the obtained answer mode corresponds to the conversation scene corresponding to the current conversation page, for example, the chat scene corresponds to the chat mode, and the related word scene corresponds to the related word mode. By regulating the answer mode to match the conversation scene corresponding to the conversation page, the adaptation degree of the answer mode and the conversation scene can be improved, thereby improving the accuracy of the reply information, so that the reply information is adapted to the conversation scene.

[0120] Optionally, at least one extended function control (included in the conversation operation control mentioned above) can also be displayed in the conversation page, each extended function control can correspond to an answer generation strategy respectively. The answer generation strategy refers to the strategy adopted by the conversation model when generating the reply information corresponding to the dialogue information, and can be used to indicate the thinking way adopted by the conversation model when generating the reply information corresponding to the dialogue information. For example, the at least one extended function control can include a deep thinking control and a network search control, the answer generation strategy corresponding to the deep thinking control is a deep thinking strategy, and the answer generation strategy corresponding to the network search control is a network search strategy. The deep thinking strategy can indicate that the conversation model can analyze the dialogue information based on the training knowledge base and logical reasoning when generating the reply information corresponding to the dialogue information, and provide logically rigorous and clear reply information. The network search strategy can indicate that the conversation model enhances the timeliness and data support of the answer by real-time acquisition of Internet information.

[0121] Based on this, the target agent can be called by the sub-application program to generate the reply information corresponding to the dialogue information according to the answer generation strategy corresponding to the target extended function control in response to the triggering operation of the target extended function control in the at least one extended function control and the dialogue information input in the conversation page.

[0122] As can be seen, the user can control whether to enable the answer generation strategy corresponding to the extended function control by triggering or not triggering the extended function control, so as to control whether the conversation model generates the reply information corresponding to the dialogue information according to the corresponding answer generation strategy. This can improve the controllability of the conversation between the user and the agent, and make the reply information more suitable for the needs of the user.

[0123] S204, rendering the reply information to the conversation page.

[0124] In step S204, the content type contained in the reply information can be determined, a rendering service matched with the content type contained in the reply information can be called to render the reply information, and the rendered reply information can be displayed in the conversation page.

[0125] That is, the embodiments of the present application can provide a plurality of rendering services, each rendering service can correspond to a content type, and each rendering service can be used to provide rendering capability of the corresponding content type. The rendering capability provided by the rendering service corresponding to the content type of the reply information can be called to render the reply information to the conversation page. As can be seen, by providing rendering capability for a plurality of content types, the reply information containing a plurality of content types can achieve better rendering effect.

[0126] For example, a Markdown content rendering service, a rich text content rendering service, a mind chain content rendering service, a thinking content rendering service, etc. can be provided. Among them: Markdown is a lightweight markup language, Markdown content refers to content written in Markdown, and the Markdown content rendering service can be used to provide rendering capabilities for Markdown content. Rich text is a form of text containing multiple format information, and rich text content is content written in rich text. The rich text content rendering service can be used to provide rendering capabilities for rich text content. Mind chain is an artificial intelligence technology that simulates human thinking steps, breaks down complex logical problems, and forms a complete thinking process through a series of logically related thoughts, enabling the corresponding conversation model of the intelligent agent to better understand the problem and provide answers. Mind chain content refers to content organized in the form of mind chain, and the mind chain rendering service can provide rendering capabilities for mind chain content. Thinking content refers to content used to describe the thinking process of the conversation model in generating reply information. The thinking content rendering service can be set for deep thinking strategies, and the thinking content rendering service can provide rendering capabilities for thinking content.

[0127] In the embodiments of the present application, the agent can be accessed in the parent application program through the sub-application program dependent on the parent application program, so that the conversation with the agent can be carried out in the parent application program without jumping out of the parent application program, and the conversation efficiency with the agent in the parent application program can be improved. Moreover, the conversation request for the target agent can be triggered in different pages of the parent application program, so that the efficiency of invoking the agent in the parent application program can be improved, thereby improving the conversation efficiency with the agent in the parent application program. The sub-application program can assemble reference information and / or answer model for the dialogue information input by the user, so that when the conversation model corresponding to the agent is called to generate reply information corresponding to the dialogue information, the conversation model corresponding to the agent can learn the indication in the reference information and / or generate the reply information according to the style indicated by the answer model, so that the accuracy of the reply information can be improved; and the reference information can be matched with the triggering scene of the conversation request, so that the reply information generated based on the reference information can be adapted to the triggering scene, thereby improving the generation effect of the reply information; the answer mode can be matched with the conversation scene of the conversation page, so that the reply information generated based on the answer mode can be adapted to the style of the conversation scene, thereby improving the generation effect of the reply information. In addition, the conversation page can also provide the user with an extended function control, and the user can control whether to enable or disable the answer generation strategy corresponding to the extended function control through the extended function control, so as to control whether the conversation model generates the reply information corresponding to the dialogue information according to the corresponding answer generation strategy, so that the reply information can better meet the needs of the user.

[0128] Embodiments of the present application provide a data processing method based on an agent. The data processing method based on an agent can include a rendering process and a session process in an access mode of an agent accessing a parent application in the form of a sub-application. Figure 4 As shown in the figure, the data processing method based on an agent can include the following steps S401-S404:

[0129] S401, in response to a session request for a target agent triggered in a parent application, calling a sub-application corresponding to the target agent to obtain page template data, the page template data being used to generate a session page for a session with at least one agent, the target agent being any one of the at least one agent.

[0130] In step S401, an agent accessing a parent application corresponds to a sub-application, that is, the agent accesses the parent application in the form of a sub-application. The page template data can be stored in a sub-application container or a session component. In response to a session request for a target agent triggered in a parent application (specifically, a parent application client), a sub-application (specifically, a sub-application client corresponding to the target agent) corresponding to the target agent can be called to obtain page template data from a sub-application container or a session component.

[0131] Optionally, the sub-application (specifically, the sub-application client corresponding to the target agent) corresponding to the target agent can also be called to obtain page content data corresponding to the target agent, that is, to obtain configuration data corresponding to the target agent and historical session data of the target agent (if there is historical session data of the target agent). The configuration data corresponding to the target agent can be managed by a sub-application server corresponding to the target agent, and the sub-application client corresponding to the target agent can be called to obtain the configuration data corresponding to the target agent from the sub-application server corresponding to the target agent. The historical session data of the target agent can be managed by a parent application (specifically, a parent application server), and the sub-application client corresponding to the target agent can be called to obtain the historical session data of the target agent from the parent application server, or the historical session data of the target agent can be managed by a sub-application server corresponding to the target agent, and the sub-application client corresponding to the target agent can be called to obtain the historical session data of the target agent from the sub-application server corresponding to the target agent.

[0132] S402, calling the sub-application corresponding to the target agent to render the page template data to obtain a session page corresponding to the target agent, and displaying the session page.

[0133] In step S402, the sub-application corresponding to the target agent (specifically, the sub-application client corresponding to the target agent) can be invoked to render the page template data and the page content data corresponding to the target agent to obtain the session page of the target agent, and the sub-application corresponding to the target agent (specifically, the sub-application client corresponding to the target agent) can be invoked to display the session page. The rendering process of the session page can be specifically referred to the related description of step S202 in the above-mentioned Figure 2 The related description of step S202 in the above-mentioned

[0134] The above steps S401-S402 introduce that the session page of the target agent can be rendered by the sub-application corresponding to the target agent, and optionally, the session page of the target agent can also be rendered by the parent application (specifically, the parent application client). Specifically, the parent application (specifically, the parent application client) can obtain the page template data and the page content data, and the page content data can include the configuration data corresponding to the target agent and the historical session data of the target agent (when the historical session data of the target agent exists); for the page template data, the parent application client can receive the page template data sent by the sub-application client corresponding to the target agent, or the parent application client can obtain the page template data from the parent application server, and the page template data can be stored in the parent application server after the parent application client first receives the page template data from the sub-application client corresponding to the target agent; for the configuration data corresponding to the target agent, the parent application client can obtain the configuration data corresponding to the target agent from the sub-application server corresponding to the target agent, or the parent application client can obtain the configuration data corresponding to the target agent from the parent application server, and the configuration data corresponding to the target agent is stored in the parent application server after the parent application client first obtains the configuration data corresponding to the target agent from the sub-application server corresponding to the target agent. For the historical session data of the target agent, the historical session data of the target agent can be managed by the parent application server, and the parent application client can obtain the historical session data of the target agent from the parent application server, or the historical session data of the target agent can be managed by the sub-application server corresponding to the target agent, and the parent application client can obtain the historical session data of the target agent from the sub-application server corresponding to the target agent. The parent application (specifically, the parent application client) can render the page template data and the page content data corresponding to the target agent to obtain the session page of the target agent. The rendering process of the session page can be specifically referred to the related description of step S202 in the above-mentioned Figure 2 The related description of step S202 in the above-mentioned

[0135] The contents of steps S401-S402 above introduce in detail the technical process of triggering display of a conversation page with the target intelligent agent in the parent application. It should be noted that in this technical process, the process of the parent application calling the sub-application corresponding to the target intelligent agent can include: the container of the parent application client (which can also be referred to as an end container) can pull up the container of the sub-application client (which can also be referred to as a sub-application container or a mini-program container), the container of the sub-application client can pull up a chat box, and the chat box can include the sub-application corresponding to each of the at least one intelligent agent, i.e., the chat box can include the sub-application corresponding to the target intelligent agent; wherein the container of the parent application client can be used to provide a running environment for the parent application client, and the container of the sub-application client can be used to provide a running environment for the sub-application client.

[0136] As shown in Figure 5 For example, in the case of triggering a conversation request for the target intelligent agent in the comment page of the parent application client, the user can interact with the target intelligent agent in the comment page, and after the user triggers the conversation entry with the target intelligent agent in the comment page, the container of the parent application client can be pulled up, the container of the sub-application client can be pulled up, the chat box can be pulled up, the sub-application corresponding to the target intelligent agent in the chat box can render the page template data and the page content data corresponding to the target intelligent agent to obtain the conversation page, or the sub-application corresponding to the target intelligent agent in the chat box can send the page template data and the page content data corresponding to the target intelligent agent to the parent application, and the parent application can render the page template data and the page content data corresponding to the target intelligent agent to obtain the conversation page. In addition, if there is historical conversation data between the user and the target intelligent agent, the sub-application client corresponding to the target intelligent agent can be called to obtain the historical conversation data from the sub-application server corresponding to the target intelligent agent, and the historical conversation data can be included in the page content data corresponding to the target intelligent agent.

[0137] Figure 5 For example, the chat box is a functional component in the container of the sub-application client. Alternatively, the chat box can also be a container of a native sub-application client in the parent application. In this case, the process of the parent application calling the sub-application corresponding to the target intelligent agent can include: the container of the parent application client (which can also be referred to as an end container) can pull up the container of the sub-application client (which can also be referred to as a sub-application container or a mini-program container, i.e., the chat box), and the container of the sub-application client can include the sub-application corresponding to each of the at least one intelligent agent, i.e., the container of the sub-application client can include the sub-application corresponding to the target intelligent agent.

[0138] S403, in response to the dialogue information input in the session page, calling the conversation model corresponding to the target intelligent agent through the sub-application program corresponding to the target intelligent agent to generate reply information corresponding to the dialogue information, and the sub-application program has a subordinate relationship with the parent application.

[0139] In step S403, the calling manner of the conversation model corresponding to the target intelligent agent by the sub-application program corresponding to the target intelligent agent can include any one of the following:

[0140] Firstly, the conversation model corresponding to the target intelligent agent can be deployed in the sub-application server corresponding to the target intelligent agent. In response to the dialogue information input in the session page of the sub-application client corresponding to the target intelligent agent, the sub-application client corresponding to the target intelligent agent can call the conversation model corresponding to the target intelligent agent in the sub-application server corresponding to the target intelligent agent to generate reply information corresponding to the dialogue information. The calling manner can include: sending the dialogue information from the sub-application client corresponding to the target intelligent agent to the sub-application server corresponding to the target intelligent agent, and calling the conversation model corresponding to the target intelligent agent in the sub-application server corresponding to the target intelligent agent to generate reply information corresponding to the dialogue information; or, the sub-application client corresponding to the target intelligent agent can call the conversation model corresponding to the target intelligent agent through the model calling interface provided by the sub-application server corresponding to the target intelligent agent to generate reply information corresponding to the dialogue information.

[0141] Secondly, the conversation model corresponding to the target intelligent agent can be deployed in the business server corresponding to the target intelligent agent. In response to the dialogue information input in the session page of the sub-application client corresponding to the target intelligent agent, the sub-application client corresponding to the target intelligent agent can send the dialogue information to the sub-application server corresponding to the target intelligent agent, and the sub-application server corresponding to the target intelligent agent can call the conversation model corresponding to the target intelligent agent in the business server to generate reply information corresponding to the dialogue information. The calling manner can include: sending the dialogue information from the sub-application server corresponding to the target intelligent agent to the business server, and calling the conversation model corresponding to the target intelligent agent in the business server to generate reply information corresponding to the dialogue information; or, the sub-application server corresponding to the target intelligent agent can call the conversation model corresponding to the target intelligent agent through the model calling interface provided by the business server to generate reply information corresponding to the dialogue information.

[0142] Optionally, the preprocessing process of the dialogue information can be performed by the sub-application server corresponding to the target intelligent agent. The preprocessing process of the dialogue information can be referred to the related description of step S203 in the above-mentioned embodiments, which will not be described here. Figure 2

[0143] S404, calling the sub-application program corresponding to the target intelligent agent to render the reply information to the session page. ​

[0144] In step S404, the sub-application corresponding to the target agent (specifically, the sub-application client corresponding to the target agent) can be invoked to obtain the reply information, and the reply information can be rendered onto the conversation page. The specific rendering process of the reply information can be found in the relevant description in step S204 above, and will not be repeated here.

[0145] Corresponding to the invocation method of the session model corresponding to the target agent, the method by which the sub-application client corresponding to the target agent obtains response information from the session model corresponding to the target agent may include any of the following:

[0146] The first approach involves deploying the session model corresponding to the target agent on a sub-application server. The sub-application client can then retrieve response information from this server. This retrieval can be achieved either by the sub-application client receiving response information from the sub-application server itself, or by the sub-application client retrieving response information through a model call interface provided by the sub-application server.

[0147] The second approach involves deploying the session model corresponding to the target agent on the business server corresponding to the target agent. The sub-application server corresponding to the target agent can obtain response information from the business server. This acquisition can be achieved either by the sub-application server receiving response information sent by the business server, or by the sub-application server obtaining response information through a model call interface provided by the business server. The sub-application client corresponding to the target agent can receive response information sent by the sub-application server corresponding to the target agent.

[0148] The above step S404 describes how the response information can be rendered by the sub-application corresponding to the target agent. Optionally, the response information can be rendered by the parent application (specifically, the parent application client). Specifically, the parent application client can receive the response information sent by the sub-application corresponding to the target agent, and the parent application client can render the response information onto the conversation page. For details on the rendering process of the response information, please refer to the above. Figure 2 The relevant description of step S204 in the illustrated embodiment will not be repeated here.

[0149] Steps S403-S404 above detail the technical process of conversing with the target agent in the parent application. It should be noted that in this technical process, the process of the parent application calling the child application may include: (e.g.) Figure 5As shown, the parent application client can pull up the conversation component, and the target intelligent agent corresponding sub-application program can call the target intelligent agent corresponding conversation model to generate reply information corresponding to the dialogue information, and can render the reply information to the conversation page.

[0150] Taking rendering by the target intelligent agent corresponding sub-application client as an example, the processes of steps S401-S404 can be summarized as Figure 6 As shown in the technical architecture: a user can trigger a conversation request for a target intelligent agent in a personal page, a content publishing page, or a message page of a parent application client, etc. In response to the conversation request, the parent application client can pull up the target intelligent agent corresponding sub-application client through a deep link, and call the target intelligent agent corresponding sub-application client to render and display a conversation page with the target intelligent agent, which can provide a conversation service (i.e., a conversation function) with the target intelligent agent, a sharing service (i.e., a sharing function) of conversation data with the target intelligent agent, and an association service (i.e., an association function) of generating associated text by the target intelligent agent. In response to dialogue information input by the user in the conversation page, the target intelligent agent corresponding sub-application client can send the dialogue information to the target intelligent agent corresponding sub-application server, the target intelligent agent corresponding sub-application server can preprocess the dialogue information, assemble reference information (i.e., context records) and / or answer patterns for the dialogue information to ensure the generation effect of the target intelligent agent corresponding conversation model, and the target intelligent agent corresponding sub-application server can call the target intelligent agent corresponding conversation model to generate reply information corresponding to the dialogue information, and send the reply information to the target intelligent agent corresponding sub-application client, and the target intelligent agent corresponding sub-application client can render and display the reply information in the conversation page.

[0151] In the embodiments of the present application, an intelligent agent can be accessed in a parent application program, and one intelligent agent can be accessed in the form of one sub-application program in the parent application program. After the intelligent agent is accessed in the parent application program, in response to a conversation request for the intelligent agent triggered in the parent application program, a conversation page with the intelligent agent can be rendered in the parent application program through the parent application program or calling the intelligent agent corresponding sub-application program, so that the user can have a conversation with the intelligent agent in the parent application program, that is, the user can directly display the conversation page with the intelligent agent in the parent application program and have a conversation with the intelligent agent without jumping from the parent application program to other business platforms, which can improve the conversation efficiency with the intelligent agent in the application program.

[0152] The embodiments of the present application provide a data processing method based on an intelligent agent, which can include rendering process and conversation process in the access mode of the same sub-application program of the parent application program by at least one intelligent agent in the form of an intelligent agent instance.Figure 7 As shown, the agent-based data processing method can include, but is not limited to, the following steps S701-S704:

[0153] S701, in response to a session request for a target agent triggered in a parent application, calling an agent instance corresponding to the target agent in a sub-application to obtain page template data, the page template data being used to generate a session page for a session with at least one agent, the target agent being any one of the at least one agent.

[0154] In step S701, the at least one agent can access the parent application by accessing the sub-application, and one agent of the sub-application corresponds to one agent instance. The page template data can be stored in a sub-application container or a session component, and can be obtained from the sub-application container or the session component by the agent instance corresponding to the target agent in the sub-application (specifically, a sub-application client) in response to a session request for the target agent triggered in the parent application (specifically, a parent application client).

[0155] Optionally, the agent instance corresponding to the target agent in the sub-application (specifically, a sub-application client) can also be called to obtain page content data corresponding to the target agent, i.e., to obtain configuration data corresponding to the target agent and historical session data with the target agent (if there is historical session data with the target agent). The configuration data corresponding to the target agent can be managed by a sub-application server, and the agent instance corresponding to the target agent can be called to obtain the configuration data corresponding to the target agent from the sub-application server. The historical session data with the target agent can be managed by the parent application (specifically, a parent application server), and the agent instance corresponding to the target agent can be called to obtain the historical session data with the target agent from the parent application server, or the historical session data with the target agent can be managed by the sub-application server, and the agent instance corresponding to the target agent can be called to obtain the historical session data with the target agent from the sub-application server.

[0156] S702, calling the agent instance corresponding to the target agent in the sub-application to render the page template data to obtain a session page corresponding to the target agent, and displaying the session page.

[0157] In step S702, the agent instance corresponding to the target agent in the sub-application (specifically, a sub-application client) can be called to render the page template data and the page content data corresponding to the target agent to obtain a session page with the target agent, and the agent instance corresponding to the target agent in the sub-application can be called to display the session page. The rendering process of the session page can be specifically referred to the above description. Figure 2The description of step S202 in the illustrated embodiment will not be repeated here.

[0158] The above steps S701-S702 introduce that the session page with the target agent can be rendered by the agent instance corresponding to the target agent in the sub-application. Alternatively, the session page with the target agent can be rendered by the parent application (specifically, the parent application client). Specifically, the parent application (specifically, the parent application client) can obtain page template data and page content data, and the page content data can include configuration data corresponding to the target agent and historical session data with the target agent (when the historical session data with the target agent exists). For the page template data, the parent application client can receive the page template data sent by the agent instance corresponding to the target agent, or the parent application client can obtain the page template data from the parent application server, and the page template data can be the page template data stored in the parent application server after the parent application client first receives the page template data from the agent instance corresponding to the target agent. For the configuration data corresponding to the target agent, the parent application client can obtain the configuration data corresponding to the target agent from the sub-application server, or the parent application client can obtain the configuration data corresponding to the target agent from the parent application server, and the configuration data corresponding to the target agent is stored in the parent application server after the parent application client first obtains the configuration data corresponding to the target agent from the sub-application server. For the historical session data with the target agent, the historical session data with the target agent can be managed by the parent application server, and the parent application client can obtain the historical session data with the target agent from the parent application server, or the historical session data with the target agent can be managed by the sub-application server, and the parent application client can obtain the historical session data with the target agent from the sub-application server. The parent application (specifically, the parent application client) can render the page template data and the page content data corresponding to the target agent to obtain the session page with the target agent.

[0159] Optionally, the session page with the target agent can also be rendered by the sub-application (specifically, the sub-application client). Specifically, the sub-application (specifically, the sub-application client) can obtain page template data and page content data, the page content data can include configuration data corresponding to the target agent and historical session data with the target agent (when the historical session data with the target agent exists); for the page template data, the sub-application client can obtain the page template data from the sub-application container or the session component; for the configuration data corresponding to the target agent, the sub-application client can obtain the configuration data corresponding to the target agent from the sub-application server. For the historical session data with the target agent, the historical session data with the target agent can be managed by the parent application server, and the sub-application client can obtain the historical session data with the target agent from the parent application server, or the historical session data with the target agent can be managed by the sub-application server, and the sub-application client can obtain the historical session data with the target agent from the sub-application server. The sub-application (specifically, the sub-application client) can render the page template data and the page content data corresponding to the target agent to obtain the session page with the target agent. The rendering process of the session page can be referred to the related description of step S202 in the above embodiment, which will not be repeated here. Figure 2

[0160] The above steps S701-S702 detail the technical process of triggering the display of the session page with the target agent in the parent application. It should be noted that in the technical process, the process of the parent application calling the agent instance corresponding to the target agent in the sub-application can include: the container (also referred to as the end container) of the parent application client can pull up the container (also referred to as the sub-application container or the applet container) of the sub-application client, the container of the sub-application client can pull up the sub-application client, the sub-application client can pull up the chat component, and the chat component can include the agent instance corresponding to each agent in the at least one agent, i.e., the chat component can include the agent instance corresponding to the target agent.

[0161] S703, in response to the dialogue information input in the session page, the agent instance corresponding to the target agent in the sub-application calls the conversation model corresponding to the target agent to generate reply information corresponding to the dialogue information, and the sub-application and the parent application have a subordinate relationship.

[0162] In step S703, the calling manner of the agent instance corresponding to the target agent to the conversation model corresponding to the target agent can include any one of the following:

[0163] ​The first kind, the session model corresponding to the target agent can be deployed in the sub-application server, and the agent instance corresponding to the target agent can call the session model corresponding to the target agent in the sub-application server to generate the reply information corresponding to the dialogue information in response to the dialogue information input in the session page of the sub-application client. The calling manner can include: sending the dialogue information to the sub-application server by the agent instance corresponding to the target agent, and generating the reply information corresponding to the dialogue information by the sub-application server calling the session model corresponding to the target agent; or the agent instance corresponding to the target agent can call the session model corresponding to the target agent through the model calling interface provided by the sub-application server to generate the reply information corresponding to the dialogue information.

[0164] The second kind, the session model corresponding to the target agent can be deployed in the business server corresponding to the target agent, and the agent instance corresponding to the target agent can send the dialogue information to the sub-application server in response to the dialogue information input in the session page of the sub-application client, and the sub-application server can call the session model corresponding to the target agent in the business server to generate the reply information corresponding to the dialogue information. The calling manner can include: sending the dialogue information to the business server by the sub-application server, and generating the reply information corresponding to the dialogue information by the business server calling the session model corresponding to the target agent; or the sub-application server can call the session model corresponding to the target agent through the model calling interface provided by the business server to generate the reply information corresponding to the dialogue information.

[0165] Optionally, the preprocessing process of the dialogue information can be performed by the sub-application server, and the preprocessing process of the dialogue information can refer to the related description of step S203 in the above embodiment, which will not be repeated here. Figure 2

[0166] S704, calling the agent instance corresponding to the target agent in the sub-application program to render the reply information to the session page.

[0167] In step S704, the agent instance corresponding to the target agent in the sub-application program can be called to obtain the reply information, and the agent instance corresponding to the target agent can be called to render the reply information to the session page. The rendering process of the reply information can refer to the related description in the above step S204, which will not be repeated here.

[0168] Corresponding to the calling manner of the session model corresponding to the target agent, the manner in which the agent instance corresponding to the target agent obtains the reply information from the session model corresponding to the target agent can include any one of the following:

[0169] ​In a first manner, the session model corresponding to the target agent can be deployed in the sub-application server, and the agent instance corresponding to the target agent can obtain the reply information from the sub-application server. The obtaining manner can include that the agent instance corresponding to the target agent can receive the reply information sent by the sub-application server, or the agent instance corresponding to the target agent can obtain the reply information through the model calling interface provided by the sub-application server. In a second manner, the session model corresponding to the target agent can be deployed in the business server corresponding to the target agent, and the sub-application server can obtain the reply information from the business server. The obtaining manner can include that the sub-application server can receive the reply information sent by the business server, or the sub-application server can obtain the reply information through the model calling interface provided by the business server. The agent instance corresponding to the target agent can receive the reply information sent by the sub-application server.

[0170] The content of the above step S704 introduces that the reply information can be rendered by the agent instance corresponding to the target agent in the sub-application program. Alternatively, the reply information can be rendered by the parent application program (specifically, the parent application client). Specifically, the sub-application client can receive the reply information sent by the agent instance corresponding to the target agent, the parent application client can receive the reply information sent by the sub-application client, and the parent application client can render the reply information into the session page. Alternatively, the reply information can also be rendered by the sub-application program (specifically, the sub-application client). Specifically, the sub-application client can receive the reply information sent by the agent instance corresponding to the target agent, and the sub-application client can render the reply information into the session page. The rendering process of the reply information can be referred to the related description of step S204 in the above embodiment, which will not be repeated here. Figure 2

[0171] The above steps S703-S704 introduce in detail the technical process of the session with the target agent in the parent application program. It should be noted that in the technical process, the process of calling the agent instance corresponding to the target agent by the parent application program can include that the parent application client can pull up the session component, the agent instance corresponding to the target agent can call the session model corresponding to the target agent to generate the reply information of the dialogue information, and the reply information can be rendered into the session page.

[0172] ​Taking rendering by the agent instance corresponding to the target agent as an example, the processes of the above steps S701-S704 can be summarized as follows: the object can trigger a session request for the target agent in a page such as a personal page, a content publishing page, or a message page of the parent application client; in response to the session request, the parent application client can pull up the child application client through a deep link, the child application client can pull up the agent instance corresponding to the target agent, call the agent instance corresponding to the target agent to render and display a session page with the target agent, and the session page can provide a session service (i.e., a session function) with the target agent, a sharing service (i.e., a sharing function) of session data with the target agent, and an association service (i.e., an association function) of triggering the target agent to generate associated text; in response to the dialogue information input by the object in the session page, the agent instance corresponding to the target agent can send the dialogue information to the child application server, the child application server can preprocess the dialogue information, assemble reference information and / or an answer mode for the dialogue information, to ensure the generation effect of the session model corresponding to the target agent; the child application server can call the session model corresponding to the target agent to generate reply information corresponding to the dialogue information, and send the reply information to the agent instance corresponding to the target agent, and the agent instance corresponding to the target agent can render and display the reply information in the session page.

[0173] In the embodiments of the present application, the agent can be accessed in the parent application program, and at least one agent can be accessed in the parent application program and placed in the same child application program. After the agent is accessed in the parent application program, in response to a session request for the agent triggered in the parent application program, a session page with the agent can be rendered in the parent application program through the parent application program, the child application program, or the agent instance corresponding to the agent, so that the session with the agent can be performed in the parent application program, that is, the session page with the agent can be directly displayed in the parent application program and the session with the agent can be performed without jumping from the parent application program to other business platforms, thereby improving the session efficiency with the agent in the application program.

[0174] The embodiments of the present application provide a data processing method based on an agent. The data processing method based on an agent can include a technical process of publishing session data with an agent as publishing content of a parent application program. The data processing method based on an agent can be executed by a terminal device, and specifically can be executed by a parent application program running in the terminal device. As shown in the figure, the data processing method based on an agent can include but is not limited to the following steps S801-S803: Figure 8a

[0175] ​S801, display, by the sub-application, a session page with the target agent, the session page including session data between the target agent, the session data including conversation information and reply information.

[0176] In step S801, the process of displaying, by the sub-application, a session page with the target agent is described above in the embodiment of Figure 2 In steps S201-S202 of the embodiment shown in the figure, the process of displaying, by the target agent, a session page is described above in the embodiment of Figure 4 In steps S401-S402 of the embodiment shown in the figure (corresponding to the case of displaying by the sub-application corresponding to the target agent), the process of displaying, by the target agent, a session page is described above in the embodiment of Figure 7 In steps S701-S702 of the embodiment shown in the figure (corresponding to the case of displaying by the agent instance corresponding to the target agent in the sub-application), the process of displaying, by the target agent, a session page is described above in the embodiment of Figure 2 、 Figure 4 and Figure 7 the embodiment shown in the figure, which will not be repeated here. The process of displaying, in the session page, the session data between the target agent is described in steps S203-S204 of the embodiment shown in the figure, the process of displaying, in the session page, the session data between the target agent is described above in the embodiment of Figure 2 In steps S401-S402 of the embodiment shown in the figure (corresponding to the case of displaying by the sub-application corresponding to the target agent), the process of displaying, by the target agent, a session page is described above in the embodiment of Figure 4 In steps S401-S402 of the embodiment shown in the figure (corresponding to the case of displaying by the sub-application corresponding to the target agent), the process of displaying, by the target agent, a session page is described above in the embodiment of Figure 7 In steps S701-S702 of the embodiment shown in the figure (corresponding to the case of displaying by the agent instance corresponding to the target agent in the sub-application), the process of displaying, by the target agent, a session page is described above in the embodiment of Figure 2 、 Figure 4 and Figure 7 the embodiment shown in the figure, which will not be repeated here. The process of displaying, in the session page, the session data between the target agent is described in steps S203-S204 of the embodiment shown in the figure, the process of displaying, in the session page, the session data between the target agent is described above in the embodiment of

[0177] S802, in response to the publishing operation on the session data, receiving the session data sent by the sub-application.

[0178] In step S802, the parent application can receive the session data sent by the sub-application in response to the publishing operation on the session data, specifically, the parent application client can receive the session data sent by the sub-application client. For the case of one agent accessing the parent application in the form of one sub-application, the parent application client can receive the session data sent by the sub-application client corresponding to the target agent; for the case of at least one agent accessing the same sub-application of the parent application, the parent application client can receive the session data sent by the agent instance corresponding to the target agent in the sub-application client.

[0179] The publishing operation on the session data can include any of the following: first, triggering operation on the publishing control in the session page with the target agent; in detail, as Figure 8bAs shown, the conversation page 80 of the target intelligent agent can contain conversation data 801 with the target intelligent agent, the sharing control 802 can be displayed in the conversation page 80 in response to a triggering operation (for example, a long press) on the conversation data 801, the publishing control 803 can be displayed in the conversation page 80 in response to a triggering operation (for example, a single click) on the sharing control 802, and the parent application can receive the conversation data sent by the child application in response to a triggering operation (for example, a single click) on the publishing control 803. Second, the parent application can receive the conversation data sent by the child application in response to a gravity sensing operation of the terminal device running the parent application after selecting the conversation data in the conversation page with the target intelligent agent; for example, the gravity sensing operation can include a shaking operation, a rotating operation, etc., which are not limited by the embodiments of the present application. Third, the parent application can receive the conversation data sent by the child application in response to a gesture triggering operation on the conversation page after selecting the conversation data in the conversation page with the target intelligent agent; the gesture triggering operation refers to an operation of drawing a specific pattern in the conversation page using a specific gesture, for example, an operation of drawing the letter "P" in the conversation page using the index finger.

[0180] The publishing operation on the conversation data can be a publishing operation on all or part of the conversation data in the conversation page, and the part of the conversation data can be the conversation data selected by the user. For the case of part of the conversation data, as shown in Figure 8c As shown, the user selects a group of conversation data composed of one dialogue information and one reply information as the conversation data to be published in the conversation page.

[0181] Optionally, the number of groups of conversation data that can be set to support as the conversation data to be published (for example, one group can be set) can be set, in which case, as shown in Figure 8d If a group of conversation data has been selected as the conversation data to be published, the selection control of other conversation data is set to an unselectable state (for example, Figure 8d is filled), and an unselectable prompt (for example, Figure 8d "Only one group of conversation data can be shared" in

[0182] Optionally, as shown in Figure 8e The conversation data can also be deleted, the delete control 804 can be displayed in the conversation page 80 in response to a triggering operation (for example, a long press) on the conversation data 801, and the conversation data 801 can be deleted in the conversation page 80 in response to a triggering operation (for example, a single click) on the delete control 804.

[0183] Optionally, as Figure 8e shown, copying of the session data can also be supported, in response to a triggering operation (here, the triggering operation can be, for example, a long press) on the session data 801, a copy control 805 can be displayed in the session page 80, in response to a triggering operation (here, the triggering operation can be, for example, a single click) on the copy control 805, the session data 801 can be copied, and a copy prompt (for example, Figure 8e “Copied” in the message) can be displayed.

[0184] S803, the session data is converted by the parent application, a plurality of to-be-published images are obtained, target publishing content including the plurality of to-be-published images is determined, and the target publishing content is published; wherein the parent application and the child application have a subordinate relationship.

[0185] In step S703, the session data can be converted by the parent application to obtain a plurality of to-be-published images; wherein the conversion process can include image conversion and image segmentation, the image conversion refers to converting the session data into an image containing the session data, and the image segmentation refers to segmenting the image according to the image standard of the publishing content to obtain a plurality of to-be-published images.

[0186] The parent application can determine the target publishing content including the plurality of to-be-published images, and publish the target publishing content. Wherein the process of determining the target publishing content can include: the parent application can obtain a cover image and description information, the cover image can be generated according to the conversation information in the session data, and the description information can be generated according to the conversation information in the session data, and the parent application generates the target publishing content according to the cover image, the plurality of to-be-published images and the description information.

[0187] In detail, in the process of publishing the session data as publishing content, the interaction process between the parent application client and the parent application server can include: the parent application client can send the session data to the parent application server, the session data can be converted by the parent application server to obtain a plurality of to-be-published images, and the target publishing content including the plurality of to-be-published images is determined; the parent application server can send the target publishing content to the parent application client, and the target publishing content is rendered to the publishing content page by the parent application client to publish the target publishing content.

[0188] The above step S703 introduces the technical process of converting the session data into the target publishing content, and in product presentation, as Figure 8bAs shown, the content editing page 81 can be displayed in response to a publishing operation on the session data, for example, the content editing page 81 can be displayed in response to a triggering operation (here, the triggering operation can refer to a click) on the publishing control 803, the content editing page 81 can include the target publishing content 811 and a publishing confirmation control 812, the publishing content page 82 of the use object can be displayed in response to a triggering operation (here, the triggering operation can refer to a click) on the publishing confirmation control 812, the publishing content page 82 can include the target publishing content 811.

[0189] Optionally, for the publishing content page taking the session data with the target agent as the publishing content, a session entry between the target agent can be included, the session page for the session with the target agent can be displayed in response to a triggering operation on the session entry, so that the session with the target agent can be performed, for example, in the publishing content page 82 as shown. Figure 8b As shown in the publishing content page 82, the session entry 301 with the target agent.

[0190] In the embodiments of the present application, the session data between the use object and the agent of the parent application can be combined with the business function provided by the parent application itself, for example, the session data can be combined with the content publishing function provided by the parent application itself, the session data can be converted into publishing content for publishing, so that the business function provided by the parent application itself can use the interaction content between the agent, and the intelligent degree of the business function provided by the parent application itself is improved.

[0191] The above Figure 2 , Figure 4 , Figure 7 and Figure 8a The content of the embodiments as shown is based on that the agent has been accessed in the parent application, the present application proposes a data processing method based on the agent, the content introduced by the data processing method based on the agent can include: a standard access mode and a unified management mode of the agent in the parent application. As shown, Figure 9 The data processing method based on the agent can include but is not limited to the following steps S901-S902:

[0192] S901, access at least one agent in the parent application, the target agent is any one of the at least one agent.

[0193] In step 901, in an implementation manner, an intelligent agent can access the parent application in the form of a sub-application, that is, at least one intelligent agent corresponding sub-application can be accessed in the parent application; in this case, the at least one intelligent agent corresponding sub-application can be specifically a session component in the sub-application container accessed to the parent application (corresponding to the case that the session component is contained in the sub-application container), as shown in Figure 10 , the at least one intelligent agent corresponding sub-application can be accessed in the session component; or the at least one intelligent agent corresponding sub-application can be specifically accessed in the sub-application container of the parent application, corresponding to the case that the session component is the sub-application container. In another implementation manner, the at least one intelligent agent can access the same sub-application of the parent application, and the intelligent agent instance corresponding to the at least one intelligent agent can be accessed in the sub-application of the parent application.

[0194] Accessing the intelligent agent (including the intelligent agent corresponding sub-application or the intelligent agent corresponding intelligent agent instance) involves front-end access of the intelligent agent, and the front-end access process of the intelligent agent can include downloading a sub-program IDE (Integrated Development Environment) and performing self-defined development, referring to the code issuing access example; completing local development and testing; publishing a trial version for testing; and clicking online.

[0195] In the front-end access process, by introducing an xhs-ai-chatbox component in the rendering layer, the enabling and disabling (i.e., displaying and not displaying) of the extended function control in the session page can be configured, taking the extended function control including a deep thinking control and a network search control as an example, and the example code of the xhs-ai-chatbox component is as follows:

[0196]

[0197] As shown in Figure 10 , in addition to the front-end access, the intelligent agent can also involve back-end access, and the back-end access refers to the connection between the intelligent agent (including the intelligent agent corresponding sub-application or the intelligent agent corresponding intelligent agent instance) and the intelligent agent corresponding session model. For the case that the intelligent agent corresponding session model is deployed in the sub-application server, the connection refers to deploying the intelligent agent corresponding session model in the sub-application server. For the case that the intelligent agent corresponding session model is deployed in the business server, the connection refers to defining the calling interface between the sub-application server and the intelligent agent corresponding session model, and the calling interface can be, for example, SPI (Serial Peripheral Interface), which is not limited in the embodiments of the present application.

[0198] For the case that the session model corresponding to the agent is deployed on the service provider server, the sub-application server can request the session model corresponding to the agent to generate reply information corresponding to the dialogue information in the form of a request, and the session model corresponding to the agent can return the reply information corresponding to the dialogue information in the form of a response. The definition of the calling interface can include the definition of the request parameter and the definition of the response parameter. Table 1 below shows an example of the definition of the request parameter:

[0199] Table 1

[0200]

[0201] It is worth noting that in the request parameters shown in Table 1 above, the field value of the deep_thinking field is used to indicate whether the use object triggers the deep thinking control. The field value of the enable_search field can be used to indicate whether the use object triggers the network search control. The field value of the generate_type field can be the answer mode mentioned above, through which the field can require the assistant (the session model corresponding to the agent) to output the reply information as required as much as possible; for example, the answer mode can include the chat mode (CHAT) and the related word mode (RELATED_WORD). The field value of the stream field can be used to indicate the return form of the reply information by the session model corresponding to the agent, and the return form can include stream return and non-stream return; wherein the stream return means that the reply information can be returned while being generated without waiting for the complete generation of the reply information, and the non-stream return means that the complete generation of the reply information is required, and all the reply information is returned at one time.

[0202] The following code shows an example of a request of a sub-application program (specifically, a sub-application server) to a session model corresponding to an agent:

[0203]

[0204] Table 2 below shows an example of the definition of the response parameter:

[0205] Table 2

[0206]

[0207]

[0208] The following code shows an example of a response of a session model corresponding to an agent to a sub-application program (specifically, a sub-application server) (corresponding to the case of successful response (stream)):

[0209] data:

[0210] {"id":"12345","model":"deepseek","created":1741619203,"choices":[{"index":0,"delta":{"role":"assistant","content": movie},"finish_reason":null}],"usage":{"prompt_tokens":10,"completion_tokens":20,"total_tokens":30},"search_web_pages":35}

[0211] data:

[0212] {"id":"12345","model":"deepseek","created":1741619203,"choices":[{"index":0,"delta":{"role":"assistant

[0213] ","content":"A"},"finish_reason":"stop"}],"usage":{"prompt_tokens":10,"completion_tokens":20,"total_tokens":30},"search_web_pages":35}

[0214] The following code shows an example of the response of the agent corresponding to the conversation model to the sub-application (specifically, the sub-application server) (corresponding to the case of responding successfully (non-streaming)):

[0215]

[0216] The following code shows an example of the response of the agent corresponding to the conversation model to the sub-application (specifically, the sub-application server) (corresponding to the case of responding successfully (non-streaming)):

[0217]

[0218] S902, at least one agent is uniformly managed according to a unified standard; wherein the unified standard includes a rendering standard and a conversation standard, and the uniform management includes rendering management corresponding to the rendering standard and conversation management corresponding to the conversation standard.

[0219] In step S902, for the case that the at least one agent accesses the parent application in the form of a sub-application, the sub-application corresponding to the at least one agent can be uniformly managed according to a uniform standard. Alternatively, for the case that the at least one agent accesses the same sub-application of the parent application, the agent instance corresponding to the at least one agent can be uniformly managed according to a uniform standard.

[0220] The uniform standard means that the standard for managing the accessed at least one agent is uniform, which is beneficial to improving the management efficiency of the agent when the number of the accessed agents is large. The uniform standard can include a rendering standard and a session standard.

[0221] The rendering standard can be used to define a uniform rendering mode of the at least one agent, and the rendering management means rendering according to the rendering mode defined by the rendering standard, which can specifically include a page rendering standard for a session page and a rendering standard for session data in the session page. The page rendering standard can be used to define a uniform page template data, i.e., a uniform session page style, and the rendering standard for the session data can be used to define a corresponding relationship between the content type of the session data and a rendering service. Figure 11 and Figure 12 is an exemplary uniform rendering standard: in the basic area of the session page, the identifier of the agent (for example, in Figure 11 , the icon of the target agent and the name of the target agent) and the control for triggering the global class function (for example, setting, complaint and report, and restarting the session, etc.) can be included; in the session information area of the session page, the operation function (for example, copying and sharing) for the session data can be included, and the reply information can also be rendered according to the uniform rendering standard for the session data; in the input area of the session page, the function for session manipulation (for example, new conversation function, deep thinking function and network search function) can be set, and the function for external sending (for example, photo album and photographing, etc.) can also be set. Figure 13 is an exemplary session page rendered according to the uniform rendering standard for different agents, it can be seen that through the uniform rendering standard, the overall form of the session page of different agents is uniform, which can improve the use experience of the user.

[0222] The conversation standard can be used to define a unified conversation manner of the at least one agent, and the conversation management refers to the conversation with the agent according to the conversation manner defined by the conversation standard. The conversation management can include: historical conversation management, reference information injection management, request management with the agent, and response management with the agent. The historical conversation management can be used to uniformly manage historical conversation data with each agent. The reference information injection management can be used to manage the types of reference information to be injected in the triggering scenarios of different conversation requests. The request management with the agent can be used to manage the request parameters requested by the sub-application server from the conversation model corresponding to the agent. The response management with the agent can be used to manage the response parameters responded by the conversation model corresponding to the agent to the sub-application server.

[0223] In the embodiments of the present application, for the business party of the agent, the ability to quickly access the application program ecology that is common to different agents is provided, and the open ability can be quickly connected to interact with the use object of the application program in the application program. For the use object of the application program, more open agent capabilities can be contacted in the application program, which enriches the interaction scene between the use object and the application program.

[0224] Please refer to Figure 14 , Figure 14 is a structural schematic diagram of a data processing apparatus based on an agent provided in the embodiments of the present application. The data processing apparatus based on an agent can be arranged in a computer device provided in the embodiments of the present application. The computer device can be a terminal device running a parent application program. Figure 14 The data processing apparatus based on an agent shown in the figure can be a computer program running in the computer device. The data processing apparatus based on an agent can be used to execute part or all of the steps in the method embodiments shown in Figure 2 , Figure 4 , Figure 7 , Figure 8a or Figure 9 Please refer to Figure 14 , the data processing apparatus based on an agent can include the following units:

[0225] The processing unit 1401 is configured to, in response to a conversation request for a target agent triggered in the parent application program, acquire page template data, the page template data being used to generate a conversation page for the conversation with the at least one agent, and the target agent being any one of the at least one agent;

[0226] The display unit 1402 is configured to render the page template data to obtain the conversation page of the target agent, and display the conversation page.

[0227] The processing unit 1401 is further configured to, in response to the dialogue information input in the session page, generate reply information corresponding to the dialogue information by calling a session model corresponding to the target agent through a sub-application, the sub-application having a subordinate relationship with the parent application.

[0228] The display unit 1402 is further configured to render the reply information to the session page.

[0229] In an implementation manner, the display unit 1402 is configured to perform any one of the following when rendering the page template data to obtain the session page of the target agent:

[0230] rendering the page template data through the parent application to obtain the session page of the target agent;

[0231] rendering the page template data through a sub-application corresponding to the target agent to obtain the session page corresponding to the target agent; wherein one agent accessing the parent application corresponds to one sub-application;

[0232] rendering the page data through an agent instance corresponding to the target agent in the sub-application to obtain the session page of the target agent; wherein at least one agent accesses the parent application by accessing the sub-application, and one agent accessing the sub-application corresponds to one agent instance.

[0233] In an implementation manner, the display unit 1402 is further configured to perform any one of the following:

[0234] displaying a personal page of the target agent through the parent application, and generating a session request in response to a session triggering operation on the personal page;

[0235] displaying a publishing content page through the parent application, the publishing content page including a session entry of the target agent, and generating a session request in response to a session triggering operation on the session entry;

[0236] displaying a message page through the parent application, the message page including session messages of at least one object, and the at least one object including the target agent, and generating a session request in response to a session triggering operation on the target agent in the message page;

[0237] displaying a search page through the parent application, the search page including a session entry of the target agent, and generating a session request in response to a session triggering operation on the session entry;

[0238] displaying a comment page through the parent application, the comment page including comment content of the target agent, and generating a session request in response to a session triggering operation on the target agent in the comment page.

[0239] In an implementation manner, the display unit 1402 is further configured to display, by the sub-application, a conversation page of the target agent, the conversation page comprising conversation data between the target agent and the user, the conversation data comprising dialogue information and reply information;

[0240] The processing unit 1401 is further configured to receive the conversation data sent by the sub-application in response to the publishing operation on the conversation data.

[0241] The processing unit 1401 is further configured to perform conversion processing on the conversation data by the parent application, to obtain a plurality of to-be-published images, to determine target publishing content comprising the plurality of to-be-published images, and to publish the target publishing content; wherein the parent application and the sub-application have a master-slave relationship.

[0242] In an implementation manner, the processing unit 1401 is further configured to perform the following steps:

[0243] In response to the dialogue information input in the conversation page, the processing unit 1401 is configured to generate, by the sub-application, reply information corresponding to the dialogue information by calling a conversation model corresponding to the target agent.

[0244] The processing unit 1401 is configured to render the reply information to the conversation page.

[0245] In an implementation manner, when the processing unit 1401 is configured to generate, by the sub-application, reply information corresponding to the dialogue information by calling a conversation model corresponding to the target agent, the processing unit 1401 is configured to perform any one of the following:

[0246] The processing unit 1401 is configured to generate, by the sub-application, reply information corresponding to the dialogue information by calling a conversation model corresponding to the target agent; wherein one agent accessing the parent application corresponds to one sub-application.

[0247] The processing unit 1401 is configured to generate, by the sub-application, reply information corresponding to the dialogue information by calling a conversation model corresponding to the target agent through an agent instance corresponding to the target agent in the sub-application; wherein at least one agent accesses the parent application by accessing the sub-application, and one agent accessing the sub-application corresponds to one agent instance.

[0248] In an implementation manner, the processing unit 1401 is further configured to perform any one of the following:

[0249] The processing unit 1401 is configured to perform preprocessing on the dialogue information by the sub-application to obtain preprocessed dialogue information.

[0250] In an implementation manner, when the processing unit 1401 is configured to generate, by the sub-application, reply information corresponding to the dialogue information by calling a conversation model corresponding to the target agent, the processing unit 1401 is configured to perform the following steps:

[0251] The target intelligent agent corresponding to the conversation model is called by the sub-application to generate reply information corresponding to the pre-processed dialogue information.

[0252] In an implementation manner, the processing unit 1401 is specifically configured to perform the following steps when pre-processing the dialogue information through the sub-application to obtain the pre-processed dialogue information:

[0253] The reference information is obtained through the sub-application, and the reference information matches the trigger scene corresponding to the conversation request;

[0254] The reference information and the dialogue information are assembled and processed through the sub-application to obtain the pre-processed dialogue information.

[0255] The conversation model corresponding to the target intelligent agent generates the reply information corresponding to the dialogue information according to the reference information and the dialogue information.

[0256] In an implementation manner, the processing unit 1401 is specifically configured to perform the following steps when pre-processing the dialogue information through the sub-application to obtain the pre-processed dialogue information:

[0257] The answer mode is obtained through the sub-application, and the answer mode matches the conversation scene corresponding to the conversation page;

[0258] The answer mode and the dialogue information are assembled and processed through the sub-application to obtain the pre-processed dialogue information.

[0259] The conversation model corresponding to the target intelligent agent generates the reply information corresponding to the dialogue information according to the answer mode.

[0260] In an implementation manner, the processing unit 1401 is specifically configured to perform the following steps when the target intelligent agent corresponding to the conversation model is called by the sub-application to generate the reply information corresponding to the dialogue information in response to the dialogue information input in the conversation page:

[0261] At least one extension function control is displayed on the conversation page, and each extension function control corresponds to one answer generation strategy;

[0262] In response to a trigger operation on a target extension function control in the at least one extension function control and the dialogue information input in the conversation page, the target intelligent agent corresponding to the conversation model is called by the sub-application to generate the reply information corresponding to the dialogue information according to the answer generation strategy corresponding to the target extension function control.

[0263] In an implementation manner, the processing unit 1401 is specifically configured to perform the following steps when rendering the reply information to the conversation page:

[0264] The content type contained in the reply information is determined.

[0265] Call the rendering service that matches the content type to render the response information and obtain the rendered response information;

[0266] The rendered reply information will be displayed on the conversation page.

[0267] In one implementation, the processing unit 1401 is further configured to perform any of the following:

[0268] Integrate at least one sub-application corresponding to an intelligent agent into the parent application, and manage the sub-application corresponding to at least one intelligent agent in a unified manner according to a unified standard;

[0269] Alternatively, at least one agent instance corresponding to an agent can be accessed in a sub-application, and the agent instances corresponding to at least one agent can be managed in a unified manner according to a unified standard.

[0270] The unified standard includes rendering standard and session standard, and the unified management includes rendering management corresponding to the rendering standard and session management corresponding to the session standard.

[0271] According to one embodiment of this application, Figure 14 The units in the agent-based data processing device shown can be individually or entirely merged into one or more other units, or some of the units can be further divided into multiple functionally smaller units. This achieves the same operation without affecting the technical effects of the embodiments of this application. The above units are based on logical function division. In practical applications, the function of one unit can be implemented by multiple units, or the function of multiple units can be implemented by one unit. In other embodiments of this application, the device may also include other units. In practical applications, these functions can also be implemented with the assistance of other units, and can be implemented collaboratively by multiple units.

[0272] According to another embodiment of this application, the following can be achieved by running on a general-purpose computing device, such as a computer, which includes processing elements and storage elements such as a central processing unit (CPU), random access memory (RAM), and read-only memory (ROM), a device capable of performing operations such as... Figure 2 , Figure 4 , Figure 7 , Figure 8a or Figure 9 Computer programs for the steps involved in some or all of the methods shown, to construct, for example... Figure 14 The diagram illustrates an agent-based data processing apparatus and an agent-based data processing method for implementing embodiments of this application. A computer program may be recorded on, for example, a computer-readable storage medium, loaded onto the aforementioned computing device via the computer-readable storage medium, and executed therein.

[0273] In the embodiment of the present application, the page template data can be obtained in response to a session request for the target intelligent agent triggered in the parent application, the page template data can be used to generate a session page for the session with the at least one intelligent agent; the session page with the target intelligent agent can be obtained by rendering the page template data, and the session page can be displayed; the reply information corresponding to the dialogue information input in the session page can be generated by calling the session model corresponding to the target intelligent agent through the sub-application in response to the dialogue information input in the session page, the sub-application and the parent application have a subordinate relationship; and the reply information can be rendered to the session page. As can be seen, the application can be used as a parent application, the intelligent agent can be accessed through the sub-application in the parent application, so that the intelligent agent can be accessed in the application; and after the intelligent agent is accessed in the application, the session page with the intelligent agent can be rendered in the application in response to the session request for the intelligent agent triggered in the application, so that the session with the intelligent agent can be performed in the application, that is, the session page with the intelligent agent can be directly displayed in the application and the session with the intelligent agent can be performed without jumping from the application to other business platforms, which can improve the session efficiency with the intelligent agent in the application; in addition, the session page with the at least one intelligent agent accessed in the parent application can be rendered based on the same page template data, so that the session page with the at least one intelligent agent accessed in the parent application has a unified style, and the standardization degree of the intelligent agent accessing the application is improved.

[0274] Based on the above method and device embodiments, the embodiment of the present application provides a computer device. Please refer to Figure 15 , Figure 15 is a structural schematic diagram of a computer device provided by the embodiment of the present application. Figure 15 The computer device shown in the figure at least includes a processor 1501, an input interface 1502, an output interface 1503 and a computer readable storage medium 1504. Wherein, the processor 1501, the input interface 1502, the output interface 1503 and the computer readable storage medium 1504 can be connected through bus or other ways.

[0275] The computer readable storage medium 1504 can be stored in the memory of the computer device, and is used to store a computer program including computer instructions. The processor 1501 is used to execute the computer program stored in the computer readable storage medium 1504. The processor 1501 (or CPU (Central Processing Unit, Central Processing Unit)) is the computing core and control core of the computer device, which is suitable for implementing the computer program, and specifically suitable for loading and executing the computer program to implement the corresponding method flow or corresponding function.

[0276] The embodiment of the present application further provides a computer readable storage medium (Memory). The computer readable storage medium is a memory device in the computer device, and is used to store programs and data. It can be understood that the computer readable storage medium herein can include an internal storage medium in the computer device, and of course can include an extended storage medium supported by the computer device. The computer readable storage medium provides a storage space, and the storage space stores an operating system of the computer device. In addition, the storage space also stores a computer program (which can include program instructions 1-program instructions n) suitable for being loaded and executed by the processor. It should be noted that the computer readable storage medium herein can be a high-speed RAM memory, or a non-volatile memory (Non-Volatile Memory), such as at least one disk memory; optionally, it can also be at least one computer readable storage medium located away from the aforementioned processor.

[0277] The computer device can be a terminal device, and the terminal device runs a parent application. In specific implementation, the computer program stored in the computer readable storage medium 1504 can be loaded and executed by the processor 1501 to implement the corresponding steps in the method shown in the above Figure 2 、 Figure 4 、 Figure 7 、 Figure 8a or Figure 9 . In specific implementation, the computer program in the computer readable storage medium 1504 is loaded and executed by the processor 1501 as follows:

[0278] In response to a session request for a target agent triggered in the parent application, page template data is obtained, the page template data is used to generate a session page for a session with at least one agent, and the target agent is any one of the at least one agent;

[0279] The page template data is rendered to obtain a session page with the target agent, and the session page is displayed;

[0280] In response to the conversation information input in the session page, the target agent corresponding to the sub-application calls a conversation model to generate reply information corresponding to the conversation information, and the sub-application has a subordinate relationship with the parent application.

[0281] The reply information is rendered to the session page.

[0282] In an implementation, the computer program in the computer readable storage medium 1504 is loaded and executed by the processor 1501 to render the page template data to obtain the session page of the target agent, and specifically used to perform any one of the following:

[0283] The page template data is rendered by the parent application to obtain the session page of the target agent;

[0284] The page template data is rendered by the sub-application corresponding to the target agent to obtain the session page corresponding to the target agent; wherein one agent accessing the parent application corresponds to one sub-application;

[0285] The page data is rendered by the agent instance corresponding to the target agent in the sub-application to obtain the session page of the target agent; wherein at least one agent accesses the parent application by accessing the sub-application, and one agent accessing the sub-application corresponds to one agent instance.

[0286] In an implementation, the computer program in the computer readable storage medium 1504 is loaded and executed by the processor 1501 to render the page template data to obtain the session page of the target agent, and specifically used to perform any one of the following:

[0287] The personal page of the target agent is displayed by the parent application, and a conversation request is generated in response to a conversation triggering operation on the personal page;

[0288] The publication content page is displayed by the parent application, and the publication content page includes a conversation entry of the target agent, and a conversation request is generated in response to a conversation triggering operation on the conversation entry;

[0289] The message page is displayed by the parent application, and the message page includes conversation messages of at least one object, and the at least one object includes the target agent; and a conversation request is generated in response to a conversation triggering operation on the target agent in the message page;

[0290] The search page is displayed by the parent application, and the search page includes a conversation entry of the target agent, and a conversation request is generated in response to a conversation triggering operation on the conversation entry;

[0291] The comment page is displayed through the parent application, and the comment page includes comment content of the target intelligent agent; in response to a conversation triggering operation on the target intelligent agent in the comment page, a conversation request is generated.

[0292] In an implementation manner, the computer program in the computer readable storage medium 1504 is loaded by the processor 1501 and performs the following steps:

[0293] The conversation page with the target intelligent agent is displayed through the sub-application, and the conversation page includes conversation data between the target intelligent agent, and the conversation data includes dialogue information and reply information;

[0294] In response to a publishing operation on the conversation data, the conversation data sent by the sub-application is received;

[0295] The conversation data is processed through the parent application to obtain a plurality of to-be-published images, and target publishing content including the plurality of to-be-published images is determined, and the target publishing content is published; wherein the parent application and the sub-application have a subordinate relationship.

[0296] In an implementation manner, the computer program in the computer readable storage medium 1504 is loaded by the processor 1501 and is further used to perform any one of the following:

[0297] In response to the dialogue information input in the conversation page, the reply information corresponding to the dialogue information is generated by calling the conversation model corresponding to the target intelligent agent through the sub-application;

[0298] The reply information is rendered to the conversation page.

[0299] In an implementation manner, when the computer program in the computer readable storage medium 1504 is loaded by the processor 1501 and is used to generate the reply information corresponding to the dialogue information by calling the conversation model corresponding to the target intelligent agent through the sub-application, it is specifically used to perform any one of the following:

[0300] The reply information corresponding to the dialogue information is generated by calling the conversation model corresponding to the target intelligent agent through the sub-application corresponding to the target intelligent agent; wherein one intelligent agent accessing the parent application corresponds to one sub-application;

[0301] The reply information corresponding to the dialogue information is generated by calling the conversation model corresponding to the target intelligent agent through the intelligent agent instance corresponding to the target intelligent agent in the sub-application; wherein at least one intelligent agent accesses the parent application by accessing the sub-application, and one intelligent agent accessing the sub-application corresponds to one intelligent agent instance.

[0302] In an implementation manner, the computer program in the computer readable storage medium 1504 is loaded by the processor 1501 and is further used to perform any one of the following:

[0303] The dialogue information is preprocessed by the sub-application to obtain preprocessed dialogue information.

[0304] The computer program in the computer readable storage medium 1504 is loaded and executed by the processor 1501 to generate reply information corresponding to the dialogue information by calling the conversation model corresponding to the target intelligent agent through the sub-application, and specifically used to perform the following steps:

[0305] The preprocessed dialogue information is generated by calling the conversation model corresponding to the target intelligent agent through the sub-application.

[0306] In an implementation manner, the computer program in the computer readable storage medium 1504 is loaded and executed by the processor 1501 to preprocess the dialogue information through the sub-application to obtain preprocessed dialogue information, and specifically used to perform the following steps:

[0307] The reference information is obtained through the sub-application, and the reference information matches the trigger scene corresponding to the conversation request;

[0308] The reference information and the dialogue information are assembled and processed through the sub-application to obtain the preprocessed dialogue information;

[0309] The conversation model corresponding to the target intelligent agent generates the reply information corresponding to the dialogue information according to the reference information and the dialogue information.

[0310] In an implementation manner, the computer program in the computer readable storage medium 1504 is loaded and executed by the processor 1501 to preprocess the dialogue information through the sub-application to obtain preprocessed dialogue information, and specifically used to perform the following steps:

[0311] The answer mode is obtained through the sub-application, and the answer mode matches the conversation scene corresponding to the conversation page;

[0312] The answer mode and the dialogue information are assembled and processed through the sub-application to obtain the preprocessed dialogue information;

[0313] The conversation model corresponding to the target intelligent agent generates the reply information corresponding to the dialogue information according to the answer mode.

[0314] In an implementation manner, the computer program in the computer readable storage medium 1504 is loaded and executed by the processor 1501 to generate the reply information corresponding to the dialogue information by calling the conversation model corresponding to the target intelligent agent through the sub-application in response to the dialogue information input in the conversation page, and specifically used to perform the following steps:

[0315] At least one extended function control is displayed on the session page, each extended function control corresponding to a respective answer generation strategy;

[0316] In response to a triggering operation on a target extended function control in the at least one extended function control, and in response to the dialogue information input in the session page, the target agent corresponding to the target extended function control is invoked by the sub-application to generate reply information corresponding to the dialogue information according to the answer generation strategy corresponding to the target extended function control.

[0317] In an implementation manner, the computer program in the computer readable storage medium 1504 is loaded and executed by the processor 1501 to render the reply information to the session page, and specifically used to perform the following steps:

[0318] Determine the content type contained in the reply information;

[0319] Call a rendering service matched with the content type to render the reply information to obtain rendered reply information;

[0320] Display the rendered reply information in the session page.

[0321] In an implementation manner, in an implementation manner, the computer program in the computer readable storage medium 1504 is loaded and executed by the processor 1501 and is further used to perform any one of the following:

[0322] Access the at least one agent corresponding sub-application in the parent application, and uniformly manage the at least one agent corresponding sub-application according to a unified standard;

[0323] Or, access the at least one agent corresponding agent instance in the sub-application, and uniformly manage the at least one agent corresponding agent instance according to a unified standard;

[0324] The unified standard includes a rendering standard and a session standard, and the unified management includes rendering management corresponding to the rendering standard and session management corresponding to the session standard.

[0325] In this embodiment, in response to a session request for a target agent triggered in the parent application, page template data can be obtained. The page template data can be used to generate a session page for engaging in a session with at least one agent. The page template data can be rendered to obtain the session page with the target agent and displayed. In response to dialogue information entered in the session page, a response message corresponding to the dialogue information can be generated by calling the session model corresponding to the target agent through a sub-application. The sub-application and the parent application have a subordinate relationship. The response message can be rendered onto the session page. As can be seen, the application can be used as the parent application, and smart agents can be accessed through sub-applications within the parent application. This allows smart agents to be integrated into the application. Furthermore, after a smart agent is integrated into the application, in response to a session request triggered within the application, a session page for the smart agent can be rendered within the application, enabling conversations with the smart agent within the application. In other words, the session page for the smart agent can be displayed directly within the application, and conversations can be conducted directly without navigating to other business platforms, thus improving the efficiency of conversations with smart agents within the application. In addition, for at least one smart agent integrated into the parent application, a session page for engaging with at least one smart agent can be rendered based on the same page template data. This ensures that the session pages for at least one smart agent integrated into the parent application have a unified style, improving the standardization of smart agent integration into the application.

[0326] Furthermore, it should be noted that this application also provides a computer-readable storage medium storing a computer program, which includes computer instructions. When a processor executes these computer instructions, it can perform the aforementioned... Figure 2 , Figure 4 , Figure 7 , Figure 8a or Figure 9 The methods described in the corresponding embodiments are therefore not repeated here.

[0327] According to one aspect of this application, a computer program product is provided, comprising a computer program stored in a computer-readable storage medium. A processor of a computer device reads the computer program from the computer-readable storage medium, and the processor executes the computer program, enabling the computer device to perform the aforementioned... Figure 2 , Figure 4 , Figure 7 , Figure 8a or Figure 9 The methods described in the corresponding embodiments are therefore not repeated here.

[0328] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer readable storage medium. When the program is executed, the processes of the above-mentioned embodiments of the methods can be included. The computer readable storage medium can be a magnetic disc, an optical disc, a read-only memory (ROM) or a random access memory (RAM), etc.

[0329] The above only discloses the preferred embodiments of the present application, and of course cannot limit the scope of the present application. Those skilled in the art can understand that all or part of the processes of the above-mentioned embodiments can be implemented, and equivalent changes made according to the claims of the present application still fall within the scope of the present application.

Claims

1. An agent-based data processing method, characterized by, The method comprises: displaying a conversation page of a target intelligent agent; the conversation page comprises conversation data of the target intelligent agent; in response to a publishing operation on the conversation data, publishing target publishing content, wherein a cover image of the target publishing content is generated based on the conversation data, and a content page of the target publishing content comprises a conversation entry of the target intelligent agent.

2. The method of claim 1, wherein, The conversation data comprises dialogue information and reply information, and the method further comprises: generating reply information corresponding to the dialogue information in response to the dialogue information input in the conversation page; displaying the reply information corresponding to the dialogue information in the conversation page.

3. The method of claim 2, wherein, The generating of the reply information corresponding to the dialogue information in response to the dialogue information input in the conversation page comprises: displaying at least one extended function control in the conversation page, each extended function control corresponding to a respective reply generation strategy; generating the reply information corresponding to the dialogue information in response to a triggering operation on a target extended function control in the at least one extended function control and the dialogue information input in the conversation page, the reply information corresponding to the dialogue information being generated according to the reply generation strategy corresponding to the target extended function control.

4. The method of claim 1, wherein, The method further comprises: displaying a personal page of any object, the personal page comprising a conversation entry of the target intelligent agent; in response to a conversation triggering operation on the conversation entry in the personal page, displaying the conversation page; or displaying a content page comprising a conversation entry of the target intelligent agent, the content page comprising a content page of publishing content; in response to a conversation triggering operation on the conversation entry in the content page of the publishing content, displaying the conversation page; or displaying a message page, the message page comprising conversation messages of at least one object, the at least one object comprising the target intelligent agent; in response to a conversation triggering operation on the target intelligent agent in the message page, displaying the conversation page; or displaying a search page, the search page comprising a conversation entry of the target intelligent agent; in response to a conversation triggering operation on the conversation entry in the search page, displaying the conversation page; or displaying a comment page, the comment page comprising comment content of the target intelligent agent; in response to a conversation triggering operation on the target intelligent agent in the comment page, displaying the conversation page.

5. The method of claim 1, wherein, The publishing of the target publishing content in response to the publishing operation on the conversation data comprises: in response to a selection operation on target conversation data in the conversation page and a publishing operation on the target conversation data, generating the cover image based on the target conversation data and publishing target publishing content comprising the cover image.

6. The method of claim 5, wherein, The publishing of the target publishing content in response to the publishing operation on the conversation data comprises: in response to a selection operation on target conversation data in the conversation page, displaying a sharing control in the conversation page; In response to a triggering operation on the sharing control, a publishing control is displayed in the session page; In response to a triggering operation on the publishing control, the cover image is generated based on the target session data, and target publishing content containing the cover image is published.

7. The method of claim 5, wherein, The session data includes dialogue information and reply information, and the response to the selection operation on the target session data in the session page includes: In response to the selection operation on at least one dialogue information and at least one reply information in the session page, the target session data is determined, and the target session data includes at least one dialogue information and at least one reply information selected by the selection operation.

8. The method of claim 7, wherein, One dialogue information and one reply information in the session page are taken as a group of session data. The response to the selection operation on at least one dialogue information and at least one reply information in the session page to determine the target session data further includes: In response to the number of groups of session data selected by the selection operation reaching a preset group number threshold, a selection control of unselected session data in the session page is switched from a first style to a second style, or a prompt information is output, the session data in the first style is used to indicate that the corresponding session data can be selected, the session data in the second style is used to indicate that the corresponding session data cannot be selected, and the prompt information is used to prompt that the number of groups of session data selected by the selection operation has reached the preset group number threshold.

9. An agent-based data processing apparatus, characterized by, Comprise: A display unit is configured to display a session page of a target intelligent agent, wherein the session page includes session data of the target intelligent agent; A processing unit is configured to publish target publishing content in response to a publishing operation on the session data, wherein a cover image of the target publishing content is generated based on the session data, and a content page of the target publishing content includes a session entry of the target intelligent agent.

10. A computer device, comprising: Comprise: A processor is adapted to execute a computer program; A computer readable storage medium stores a computer program, and the computer program is executed by the processor to execute the intelligent agent-based data processing method according to any one of claims 1 to 8.

11. A computer readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to execute the intelligent agent-based data processing method according to any one of claims 1 to 8.

12. A computer program product, characterised in that, The computer program product comprises a computer program, and the computer program is executed by the processor to implement the intelligent agent-based data processing method according to any one of claims 1 to 8.

Images