Information content processing method and apparatus, and device and storage medium

Abstract

An information content processing method and apparatus, and a device and a storage medium, which relate to the technical field of artificial intelligence. The method comprises: acquiring recommended information content which is recommended by an artificial intelligence (AI) assistant for a first account, wherein the recommended information content is obtained after the AI assistant screens or summarizes information content of the first account in at least one service function; and displaying the recommended information content. By using the method, key content in a large amount of information content can be quickly acquired, thereby increasing information density, and improving the processing efficiency for the information content.

Description

Information content processing method, device, equipment and storage medium

[0001] This application claims priority to Chinese patent application number 202310714614.5, filed on June 15, 2023, entitled “Information content processing method, device, equipment and storage medium”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of artificial intelligence (AI), and in particular to a method, apparatus, device, and storage medium for processing information content. Background Art

[0003] With the continuous development of hardware, computing power, network transmission, and algorithmic technologies, more and more information is being generated and transmitted. Connections between people are no longer limited by geographic location, but can be continuously extended across virtual cyberspace, increasing social accessibility. However, at the same time, the overabundance of information leads to problems such as delayed processing of information content and excessive dispersion of attention.

[0004] In the related art, when using a social client, users need to switch between different contact / group chat interfaces / dynamic message spaces to read / reply to social messages, and switch between business function interfaces at different levels to use different functions.

[0005] However, the ever-increasing amount of information content on social clients has become a burden for users. How to improve the efficiency of information content processing is a problem that needs to be solved.

[0006] Summary of the Invention

[0007] The embodiments of the present application provide a method, apparatus, device, and storage medium for processing information content, which can provide a method for using an AI assistant to recommend information content to a first account, thereby improving the efficiency of using a social client. The technical solutions provided by this application are as follows:

[0008] According to one aspect of the present application, a method for processing information content is provided. The method is executed by a terminal device running a social client logged in with a first account, and the method includes:

[0009] Obtaining recommended information content recommended by the AI ​​assistant for the first account, where the recommended information content is obtained by the AI ​​assistant after screening or summarizing information content of the first account in the at least one business function;

[0010] The recommended information content is displayed.

[0011] According to one aspect of the present application, a method for processing information content is provided, the method being executed by a server and comprising:

[0012] Obtaining information content of the first account in at least one business function;

[0013] The AI ​​assistant filters or summarizes the information content of the first account in at least one business function to obtain recommended information content recommended by the AI ​​assistant for the first account, wherein the AI ​​assistant is a recommendation service based at least on the information content filtering or summarization by an AI model;

[0014] The recommended information content is sent to the social client where the first account is located.

[0015] According to another aspect of the present application, a device for processing information content is provided, the device comprising:

[0016] an acquisition module, configured to acquire recommended information content recommended by the AI ​​assistant for the first account, the recommended information content being obtained by the AI ​​assistant after screening or summarizing information content of the first account in the at least one business function;

[0017] The display module is used to display the recommended information content.

[0018] According to another aspect of the present application, a device for processing information content is provided, the device comprising:

[0019] An acquisition module, configured to acquire information content of the first account in at least one business function;

[0020] a determination module, configured to use an AI assistant to screen or summarize information content of the first account in at least one business function, and obtain recommended information content recommended by the AI ​​assistant for the first account, wherein the AI ​​assistant is a recommendation service that screens or summarizes information content based at least on an AI model;

[0021] The sending module is used to send the recommended information content to the social client where the first account is located.

[0022] According to another aspect of the present application, a computer device is provided, comprising a processor and a memory, wherein the memory stores at least one program, and the at least one program is loaded and executed by the processor to implement the information content processing method as described above.

[0023] According to another aspect of the present application, a computer-readable storage medium is provided, in which at least one program is stored. The at least one program is loaded and executed by the processor to implement the information content processing method as described above.

[0024] According to another aspect of the present application, a computer program product is provided, wherein at least one program segment is stored in the computer program product, and the at least one program segment is loaded and executed by the processor to implement the information content processing method as described above.

[0025] The beneficial effects of the technical solutions provided in the embodiments of the present application include at least:

[0026] By obtaining and displaying the recommended information content recommended by the AI ​​assistant to the user after logging into the user account, the user can quickly obtain important content from the large amount of information on the social client without having to view all the original information content, and can grasp key information in the fastest time, saving time and cost, and improving information processing efficiency; and the user does not need to switch back and forth between the interfaces of various business functions, but instead integrates and displays information from multiple scattered business functions, improving the synergy of business functions and information density, saving operating costs and information acquisition time, and improving the efficiency of users using social clients. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] FIG1 is a schematic diagram of an interface of a method for processing information content provided by an exemplary embodiment of the present application;

[0028] FIG2 is a schematic diagram of an interface of a method for processing information content provided by an exemplary embodiment of the present application;

[0029] FIG3 is a schematic diagram of an interface of a method for processing information content provided by an exemplary embodiment of the present application;

[0030] FIG4 is a schematic diagram of an interface of a method for processing information content provided by an exemplary embodiment of the present application;

[0031] FIG5 is a structural block diagram of a computer system provided by an exemplary embodiment of the present application;

[0032] FIG6 is a flowchart of a method for processing information content provided by an exemplary embodiment of the present application;

[0033] FIG7 is a flowchart of a method for processing information content provided by an exemplary embodiment of the present application;

[0034] FIG8 is a data processing flow chart of a method for processing information content provided by an exemplary embodiment of the present application;

[0035] FIG9 is a timing diagram of a method for processing information content provided by an exemplary embodiment of the present application;

[0036] FIG10 is a flowchart of a method for processing information content provided by an exemplary embodiment of the present application;

[0037] FIG11 is a structural block diagram of an information content processing device provided by an exemplary embodiment of the present application;

[0038] FIG12 is a structural block diagram of an information content processing device provided by an exemplary embodiment of the present application;

[0039] FIG13 is a block diagram of a computer device provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0040] In order to make the objectives, technical solutions and advantages of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0041] First, the terms that may appear in this application are explained.

[0042] ChatGPT (Chat Generative Pre-trained Transformer) is an AI chatbot developed by OpenAI and launched in November 2022. It uses a large language model based on the GPT-3.5 and GPT-4 architectures and is trained using reinforcement learning. ChatGPT currently interacts with text, but in addition to natural human conversation, it can also be used for complex language tasks, including automatic text generation, automatic question answering, and automatic summarization.

[0043] AIO (All In One, a common chat window component): For example, in an instant messaging application, users participate in many different types of conversations, such as friends, groups, and public accounts. To provide users with a unified interactive experience, the application provides a chat window component that is shared by different conversations. Users' input, click operations, and other behavioral habits in the component can be considered consistent.

[0044] 1 to 4 show schematic diagrams of interfaces of the method for processing information content in this application.

[0045] As shown in Figure 1, when a user is using a social client, a function entry 13 for the exploration mode (i.e., the AI ​​assistant function) is displayed in the mode switching interface 10 of the social client. The user can turn the AI ​​assistant function on or off by triggering this function entry 13. After the user clicks function entry 13 to turn on the AI ​​assistant function, the user interface jumps to a full-screen recommended information content interface 11, which displays recommended information content 15 pushed by the AI ​​assistant to the current user account. The recommended information content 15 is displayed in the form of a card on the recommended information content interface 11.

[0046] Recommended information content 15 is obtained by the AI ​​assistant after filtering or summarizing information content from multiple social functions. That is, it is the information content that the user is most concerned about, extracted through the analysis and processing capabilities of the AI ​​language model. For example, recommended information content 15 is the unread messages of the current user account within a certain period of time, including a summary of unread messages in individual chats and group chats; for another example, recommended information content 15 is a summary of the dynamics of friends that the current user account may follow, such as friend birthday reminders, friend dynamic updates, etc.; for another example, recommended information content 15 is a recommendation for social network interactions that the current user account may follow, such as friends who may know, friends who have been in contact most frequently recently, old friends who have been in contact but have not been in touch recently, etc.; for another example, recommended information content 15 is a recommendation of social content related to interest tags that the current user account may follow, such as short videos, interest groups, games, etc. In some embodiments, the recommended information content interface 11 also displays an introduction guide 14 of the AI ​​assistant.

[0047] Taking the recommended information content 15 as a summary of unread messages as an example, after the current user account obtains the recommended information content 15 on the recommended information content interface 11, it can jump to the traditional chat message list to view the complete message and then reply; it can also use shortcut commands to quickly reply to the corresponding message in natural language. For example, the AI ​​assistant interface 12 displays a summary 16 of group chat messages related to the current user account. The current user account can directly enter the object and content 17 to be replied in natural language in the dialog box of the AI ​​assistant interface 12, such as "Reply to Xiao A: Currently following up on the restoration issue of the new version of the data card" to quickly reply to the message. In some embodiments, the natural language-based quick reply supports text interaction and / or voice interaction, and the user can choose freely.

[0048] The recommended information content 15 is displayed in the form of cards on the user interface, wherein the cards can be displayed in a tiled or stacked manner. FIG1 shows a schematic diagram of an interface in which multiple cards are displayed in a tiled manner, and FIG2 shows a schematic diagram of an interface in which multiple cards are displayed in a stacked manner.

[0049] As shown in Figure 2, when the current user account is using a social client, the user interface displays an AI assistant interface 20. This AI assistant interface 20 displays recommended information in a layered manner. The recommended information defaults to an intelligent summary of unread group chat messages during the time the current user account was away from the social client, thereby improving the user's efficiency in processing information content. The AI ​​assistant also supports semantic understanding, using this understanding to intelligently recommend the next task for the current user account or recommend features in the social client that match the recommended information. For example, the recommended information content 21 displayed on the AI ​​assistant interface 20 includes the task "Update work schedule" posted in the group. After analyzing the semantics, the AI ​​assistant recommends the work scheduling file related to the task to the current user account, and displays the work scheduling file 22 related to the task on the AI ​​assistant interface 20, so that the user can directly use the file to complete the task; for another example, the recommended information content 23 displayed on the AI ​​assistant interface 20 includes work-related messages to be replied to. After analyzing the semantics, the AI ​​assistant recommends reply content that matches the message to be replied and is suitable for work scenarios to the current user account, and displays at least one quick reply content 24 on the AI ​​assistant interface 20, so that the user can reply quickly; for another example, the recommended information content 25 displayed on the AI ​​assistant interface 20 includes entertainment-related messages to be replied to. After analyzing the semantics, the AI ​​assistant recommends reply content to the current user account based on the interest tags of the current user account, and displays at least one reply content 26 on the AI ​​assistant interface 20, so that the user can reply or share quickly.

[0050] In some embodiments, in addition to supporting the processing of text messages as shown in FIG. 2 , the AI ​​assistant also supports processing richer intelligent combinations of rich media information (e.g., pictures, videos, 3D (three dimensional) scenes, mini-games, etc.).

[0051] In some embodiments, similar to processing text messages, when processing rich media information, the AI ​​assistant can also match appropriate recommended content or related functions to the inside or below the card of the recommended information content through a shortcut entrance based on the usage habits and user tags of the current user account, thereby further improving the user's information processing efficiency in the social client.

[0052] In some embodiments, the order of cards for recommended information content can be a default order, a user-defined order, or an order optimized based on user usage habits. For example, the order of cards for displayed recommended information content can be based on default recommendation logic in the early stages. Subsequently, as the user interacts with the AI ​​assistant and user tags are gradually enriched, the relevant search and recommendation logic is continuously strengthened, so that the order of cards for recommended information content is more in line with the user's habits, and the recommended information content is more in line with the user's interests, so that the AI ​​assistant and the user can efficiently collaborate to process information and related tasks in the social client, thereby improving the user's efficiency in processing information.

[0053] In some embodiments, recommended information content may include not only related content or related functions within the social client, but also related content or related functions from third parties, to more intelligently adapt to the user's social needs; for example, recommended information content may include food delivery apps, taxi-hailing apps, and third-party short / long video apps. Figure 3 shows a schematic diagram of an interface that includes related content or related functions from third parties in recommended information content. For example, based on the current user account's recent gaming activities, the AI ​​assistant interface 30 displays recommendations for gaming videos 31 posted by the current user account to a third-party platform, and recommendations for other users 32 involved in the gaming activities of the current user account; for another example, if the current user account's interest tag is cat, the AI ​​assistant interface 30 displays recommendations for user accounts 33 from third-party platforms related to cats that the current user account follows, and recommendations for group chats 34 that are recommended to the current user account; for another example, if the current user account's interest tag is AI content creation, the AI ​​assistant interface 30 displays recommendations for channels 35 from third-party platforms related to AI content creation that the current user account follows, and recommendations for user accounts 36 with the same interest tags that are recommended to the current user account; for another example, based on the current user account's social relationships in the social client, the AI ​​assistant interface 30 displays recommendations for links 37 from third-party platforms that the current user account shares with its friends.

[0054] In some embodiments, in addition to being able to view the cards of recommended information content generated by the AI ​​assistant, the current user account can also obtain information content by interacting with the AI ​​assistant. As shown in Figure 4, the AI ​​assistant interface 50 displays recommended information content, including a group chat information summary 51 and related files 52; the user can interact with the AI ​​assistant through text input or voice input in the input box area 53 at the bottom of the AI ​​assistant interface 50. For example, enter "It's been a bit slow to start the APP recently" in the input box area 53; after sending the message, the message is displayed in the card 54 for interacting with the AI ​​assistant. The AI ​​assistant performs semantic analysis on the message and displays the reply content 55 and recommended related functions 56 on the AI ​​assistant interface 50.

[0055] 5 shows a block diagram of a computer system according to an exemplary embodiment of the present application. The computer system 100 includes a first terminal device 110 , a server 120 , and a second terminal device 130 .

[0056] The first terminal device 110 has a first client 111 installed and running that supports social functions. This first client 111 can be an application with social functions or a web client. When the first terminal device 110 runs the first client 111, the user interface of the first client 111 is displayed on the screen of the first terminal device 110. The application can be any of an instant messaging program, a microblog program, an online community program, a payment program, a shopping program, a dating program, and a dating program. In this embodiment, the instant messaging program is used as an example. The first terminal device 110 is the terminal device used by the first user 112, and the first account of the first user 112 is logged into the first client 111.

[0057] The second terminal device 130 has a second client 131 installed and running that supports social functions. This second client 131 can be an application with social functions or a web client. When the second terminal device 130 runs the second client 131, the user interface of the second client 131 is displayed on the screen of the second terminal device 130. The application can be any of an instant messaging program, a microblog program, an online community program, a payment program, a shopping program, a dating program, and a dating program. In this embodiment, the instant messaging application is used as an example. The second terminal device 130 is used by the second user 132, and the second user account of the second user 132 is logged into the second client 131.

[0058] In some embodiments, the applications installed on the first terminal device 110 and the second terminal device 130 are the same, or the applications installed on the two terminal devices are the same type of applications on different operating system platforms (Android or iOS). The first terminal device 110 can generally refer to one of multiple terminal devices, and the second terminal device 130 can generally refer to another of the multiple terminal devices. This embodiment only uses the first terminal device 110 and the second terminal device 130 as examples. The first terminal device 110 and the second terminal device 130 can be of the same or different device types, which include at least one of a smartphone, a tablet computer, an e-book reader, an MP3 player, an MP4 player, a laptop computer, and a desktop computer.

[0059] FIG5 shows only two terminal devices, but in different embodiments, multiple other terminal devices 140 may be connected to the server 120. In some embodiments, one or more terminal devices 140 are terminal devices corresponding to developers, and a development and editing platform for a client supporting social functions is installed on the terminal device 140. The developer can edit and update the client on the terminal device 140 and transmit the updated application installation package to the server 120 via a wired or wireless network. The first terminal device 110 and the second terminal device 130 can download the application installation package from the server 120 to update the client.

[0060] The first terminal device 110 , the second terminal device 130 and other terminal devices 140 are connected to the server 120 via a wireless network or a wired network.

[0061] Server 120 includes at least one of a single server, multiple servers, a cloud computing platform, and a virtualization center. Server 120 is used to provide backend services for clients supporting social functions. In some embodiments, server 120 performs primary computing tasks, while terminal devices perform secondary computing tasks; alternatively, server 120 performs secondary computing tasks, while terminal devices perform primary computing tasks; alternatively, server 120 and terminal devices utilize a distributed computing architecture for collaborative computing.

[0062] In some embodiments, the server 120 includes a processor 122, a user account database 123, a social service module 124, and a user-oriented input / output interface (I / O interface) 125. The processor 122 is used to load instructions stored in the server 120 and process data in the user account database 123 and the social service module 124. The user account database 123 is used to store user account data used by the first terminal device 110, the second terminal device 130, and other terminal devices 140, such as user account avatars, user account nicknames, and groups to which the user accounts belong. The social service module 124 is used to provide multiple chat rooms (two-person chat or multi-person chat) for users to chat, send emoticons, send red envelopes, etc., or publish and browse social circle messages. The user-oriented I / O interface 125 is used to establish communication and exchange data with the first terminal device 110 and / or the second terminal device 130 via a wireless network or a wired network.

[0063] In conjunction with the above description of the implementation environment, the information content processing method provided in the embodiment of the present application is described, and an example is given in which the execution subject of the method is a client running on the terminal device shown in Figure 5. The terminal device runs a client, which is an application that supports social functions. The client is also provided with an AI model, which is an AI model used by an AI assistant and is used to obtain recommended information content based on the information content on the client and support other AI services; alternatively, the AI ​​model used by the AI ​​assistant can also be set on the server in Figure 5, and the client sends the information content to the server, and the server then returns the recommended information content generated by the AI ​​model to the client.

[0064] Figure 6 shows a flowchart of a method for processing information content provided by an exemplary embodiment of the present application. This embodiment illustrates the method by executing it on the terminal device shown in Figure 5 or a client running on the terminal device. For example, the terminal device runs a social client logged in with a first account, and the social client includes at least one business function. The method includes at least one of the following steps 210 to 240.

[0065] In some embodiments, the following step 210 may be implemented as a pre-execution step. For example, after the social client on the terminal device is logged in with the first account, the terminal device may only execute the following steps 220 to 240.

[0066] Step 210: Log in to the first account;

[0067] The first account is the user account currently logged in on the social client.

[0068] Exemplarily, the user enters the user name and password on the login interface and clicks the login control to log in to the first account; or, if the user sets automatic login, the user is automatically logged in to the first account when the user opens the social client.

[0069] Step 220: Obtain the recommended information content recommended by the AI ​​assistant for the first account;

[0070] An AI assistant refers to an AI service provided in a social client that is at least based on an AI model to improve the efficiency of users' processing of information content. Taking the processing of information content by AI services as an example, an AI assistant is a recommendation service that screens or summarizes information content based at least on an AI model.

[0071] The AI ​​model adopted by the AI ​​assistant can be a language model, such as a large language model (LLM) or a generative language model (GLM), which is trained on a large amount of text data to understand and generate human language, and can perform a variety of tasks such as text summarization, translation, and sentiment analysis. Among them, LLM refers to a language model whose model parameters exceed the first threshold, or the training data exceeds the second threshold, or the amount of calculation exceeds the third threshold, wherein the first threshold, the second threshold, and the third threshold are all values ​​in the hundreds of billions. In some embodiments, the AI ​​model adopted by the AI ​​assistant can also be a model for text-to-image, image-to-text, text-to-video, etc. Taking the AI ​​assistant using a large language model as an example, the AI ​​services it provides include summarizing unread social messages, optimizing social networks, reviewing historical social messages, answering questions, recommending functions, emotional companionship, etc. This application is not limited to this.

[0072] The name "AI Assistant" may be displayed on the AI ​​Assistant user interface; or, the name "AI Assistant" may not be displayed, but the content displayed on the interface is recommended information content generated in part or in full by the AI ​​model; or, functions of the same type or names of the same type may be displayed, such as "Intelligent Service", "AI Butler", "Exploration Mode", and so on. The recommended information content recommended by the AI ​​Assistant for the first account may be completely generated by the AI ​​model on which the AI ​​Assistant is based; or, it may be a combination of recommended information content generated by the AI ​​model and recommended information content generated by traditional recommendation algorithms. This application does not restrict the names of the AI ​​Assistant functions, nor does it completely limit all recommended information content to being generated by the AI ​​model used by the AI ​​Assistant.

[0073] The social client includes at least one business function. A business function refers to a function designed to achieve online social purposes, including at least one of the following: a communication function (including one-on-one chat, group chat, etc.), a contact function, a social circle function, and a short video function. Recommended information content is obtained by the AI ​​assistant after screening or summarizing the information content in the at least one business function. Screening refers to extracting information from the at least one business function, i.e., without secondary processing; summarizing refers to not directly selecting parts of the original information content, but forming summarized information content through secondary processing, such as an abstract or summary.

[0074] For example, if the at least one service function is a communication function, the recommended information content is the content obtained by the AI ​​assistant after screening or summarizing the information content in the communication function. For example, the recommended information content may be a summary of key information in unread social messages by the AI ​​assistant; another example is the AI ​​assistant screening historical social messages of a chat partner specified by the first account; another example is the AI ​​assistant listing the to-do items for the first account in the communication function, and so on.

[0075] In some embodiments, the business functions of a social client also include business functions of third-party applications. These third-party applications can be internal or external to the social client. A third-party application's business functions are those authorized for use or synchronization by the social client. This means the social client has permission to access information and / or invoke functions within the authorized third-party application's business functions. For example, a social client might access information from a third-party application used for shopping within the social client; or, in another example, a social client might invoke functions of a third-party application used to clear memory outside the social client. This includes, for example,

[0076] In some embodiments, a social client may include at least two business functions at different levels; recommended information content is obtained by the AI ​​assistant by filtering or summarizing the information content in the at least two business functions. For example, recommended information content may include a summary of unread messages in the communication function and a selection of friends' dynamics in the social circle; another example may include a summary of to-do items in the communication function and recommendations of possible friends in the contacts function, etc.

[0077] Exemplarily, a social client includes multiple business functions, at least two of which are located at different human-computer interaction interface levels. Recommended information content recommended by an AI assistant for a first account is obtained, where the recommended information content includes information content obtained by the AI ​​assistant after filtering or summarizing information content in the first business function located at the first human-computer interaction interface level.

[0078] The HMI level indicates the accessibility of the HMI, i.e., the operational cost required to reach it. For example, the number of steps required to access the HMI from the main interface of a social client. The higher the HMI level, the fewer steps a user needs to take to reach it.

[0079] For example, the recommended information content is obtained by the AI ​​assistant after screening or summarizing the information content in at least one business function. The recommended information content includes at least one of the following:

[0080] First recommended information content is generated by filtering or summarizing the unread social messages of the first account; for example, the unread social messages in the chat list are filtered or summarized to form the first recommended information content. The unread social messages may be unread social messages in a single chat, or unread social messages in a group chat, or unread social messages in a single chat or group chat designated by the first account, or unread social messages in a single chat or group chat where the number of unread social messages exceeds a threshold.

[0081] The second recommended information content is obtained by filtering or summarizing the group chat messages or to-do items in the workflow of the first account; for example, the second recommended information content includes tasks scheduled in the work group chat or messages that need to be replied to; for another example, the second recommended information content includes to-do items such as group polls, group files, and group announcements; for another example, the second recommended information content includes messages in the group chat that mention the first account or messages in the group chat that mention all members.

[0082] Third-party recommended information content, after filtering or summarizing candidate information according to the first account's preset rules; that is, users can customize recommended information content. For example, the first account can pre-set the objects for the AI ​​assistant to filter or summarize, as well as the time range and information type. For example, filtering or summarizing document-type information from last year; or filtering or summarizing dynamic messages from last month's dynamic space.

[0083] The fourth recommended information content is obtained by filtering or summarizing the dynamic information of friends in the social network of the first account; for example, the fourth recommended information content is the dynamic updates of friends in the social circle; for another example, the fourth recommended information content is a friend's birthday reminder, etc.

[0084] The fifth recommended information content is randomly recommended by the first account; for example, the fifth recommended information content is hot news recommended by the first account; for another example, the fifth recommended information content is information content that the friends of the first account follow.

[0085] Fifth recommended information content that is filtered or summarized based on information content that may be of potential interest to the first account; for example, interest tags of the first account are determined based on topics that the first account follows, and information content that may be of interest to the first account is determined based on the interest tags, and is filtered or summarized and recommended to the first account after being recommended to the first account; for another example, information content of the entire online platform on that day is recommended to the first account, such as filtering or summarizing all popular short videos of that day in the short video function.

[0086] · Sixth recommended information content after screening or summarizing information content with a high probability of being shared by the first account; for example, based on the chat content between the first account and its friends, the first account's interest tags or hot information of interest are determined, and the information content related to the interest tags or hot information of interest is screened or summarized and recommended to the first account; for another example, the first account is supported to customize information content with a high probability of being shared and authorized to share it with friends or group chats.

[0087] The seventh recommended information content is obtained by screening or summarizing interest groups that may be of potential interest to the first account; for example, candidate interest groups that may be of interest to the first account are determined based on the interest tags of the first account, and the screened or summarized interest groups are recommended to the first account as the seventh recommended information content.

[0088] The eighth recommended information content is obtained by filtering or summarizing Point of Interest (POI) information corresponding to the first account's current geographic location. POI refers to point data on an internet electronic map, including four attributes: name, address, coordinates, and category. For example, based on the first account's current geographic location, information about businesses and transportation services near the current location that may be of interest to the first account is filtered or summarized and recommended to the first account as the eighth recommended information content.

[0089] Ninth recommended information content after screening or summarizing unfamiliar accounts that may have potential interest in the first account; for example, candidate accounts with the same interest tags as the first account are identified, and the candidate accounts may have potential interest in the first account, and the screened or summarized candidate accounts may be recommended to the first account as the ninth recommended information content.

[0090] The tenth recommended information content is selected or summarized from AI tools that the first account may be interested in. AI tools are tools developed based on AI technology to solve problems. For example, based on the first account's interest tags, candidate AI tools that the first account may be interested in are identified and recommended to the first account as the tenth recommended information content. For another example, if the first account's interest tag is painting, an AI painting tool is recommended to the first account and a quick access is provided.

[0091] · An eleventh recommended information content after screening or summarizing games that may be of potential interest to the first account; for example, determining candidate games that may be of potential interest to the first account, and recommending the screened or summarized games as the eleventh recommended information content to the first account.

[0092] The twelfth recommended information content is obtained by filtering or summarizing relevant information of third-party applications bound to the first account; for example, the preferential information of a food delivery app bound to the first account is filtered or summarized and recommended to the first account as the twelfth recommended information content.

[0093] The type of information in the aforementioned at least one business function may include at least one of the following types:

[0094] Text messages: such as text messages, blogs, emails, etc.

[0095] Graphic information: such as photographs, paintings, illustrations, etc.

[0096] Video information: such as TV shows, movies, short videos, etc.

[0097] Audio information: such as songs, broadcasts, radio stations, etc.

[0098] Social network information: such as personal homepage, social circles, social platforms, etc.;

[0099] Game information: such as online games, mobile games, etc.

[0100] Location information: such as Global Positioning System (GPS) positioning, map navigation, etc.

[0101] Personal information: such as basic personal information, interests, personality traits, ability levels, achievements, etc.

[0102] Group information: such as group membership, goals and tasks, organizational structure, cultural atmosphere, and behavioral norms;

[0103] Emotional information: such as the emotional state, attitude, preferences, and satisfaction ratings of individuals or groups;

[0104] Behavioral information: such as individual or group behavior patterns, behavioral outcomes, and behavioral impacts;

[0105] Environmental information: such as the physical, social, and cultural environment of an individual or group.

[0106] Step 240: Display the recommended information content.

[0107] Exemplarily, the recommended information content recommended by the AI ​​assistant for the first account is displayed on the AI ​​assistant interface.

[0108] Exemplarily, the social client includes multiple business functions, and at least two of the multiple business functions are located at different human-computer interaction interface levels. After obtaining the recommended information content obtained by the AI ​​assistant based on the information content screening or summarizing in the first business function of the first human-computer interaction interface level, the recommended information content recommended by the AI ​​assistant for the first account is displayed at the second human-computer interaction interface level. The second human-computer interaction interface level is higher than the first human-computer interaction interface level; that is, the second human-computer interaction interface requires fewer operation steps to reach than the first human-computer interaction interface; that is, after summarizing or screening the information content of the first human-computer interaction interface at a lower level, it is displayed on the second human-computer interaction interface at a higher level, so that the cost of obtaining the information content is lower and efficiency is improved.

[0109] In some embodiments, at least two information cards are displayed at the second human-computer interaction interface level, and each of the at least two information cards is used to display one or a group of recommended information contents recommended by the AI ​​assistant for the first account. Among them, a group of recommended information contents originates from the same business function; or, originates from the same group chat / contact; or, belongs to the same topic. For example, each information card displays an information summary of unread social messages of a group chat / contact; for another example, each information card displays the filtered results of key information in a business function. The area of ​​the information card is less than or equal to the area of ​​the user interface, and the information card is displayed on the upper layer of the user interface. Displaying the recommended information content in the form of information cards can distribute different recommended information contents on different information cards, enrich the display form of the recommended information content, and improve the display flexibility of the recommended information content.

[0110] The information card includes at least one of the following information:

[0111] Account information of the second account (e.g., profile picture of the second account, nickname of the second account, and the first account's reference to the second account);

[0112] The number of related messages (e.g., the number of unread messages sent from the second account to the first account);

[0113] Whether the information is filtered or summarized (for example, "A summary has been generated for you");

[0114] At least one selected message (for example, an important message selected from unread messages);

[0115] At least one summarized message (e.g., a message obtained by summarizing unread messages);

[0116] Whether it is an indicator of information content processed by an AI model (for example, displaying “AI intelligent message”).

[0117] The at least two information cards may be displayed in a tiled manner or in a stacked manner. That is, the at least two information cards may be displayed in a non-overlapping manner from top to bottom (multiple information cards may be displayed simultaneously on the user interface, as shown in FIG1 ), and the user may view different information cards by sliding up and down; or the at least two information cards may be displayed in a stacked manner with partial or full overlap (only one information card may be displayed on the user interface, as shown in FIG2 ), and the user may switch between different information cards by sliding.

[0118] In some embodiments, the at least two information cards are displayed in a tiled manner at the second human-computer interaction interface level; wherein the tile order of the at least two information cards is determined based on the recommendation priority of the at least two information cards.

[0119] In other embodiments, the at least two information cards are displayed in a stacked manner at the second human-computer interaction interface level; wherein the stacking order of the at least two information cards is determined based on the recommendation priority of the at least two information cards.

[0120] Among them, the recommendation priority can be the default priority of the social client; or it can be a user-defined priority; or it can be a priority optimized by machine learning based on the way the user uses the social client. For example, an interest tag library is built for each user account, and the interest tags in the interest tag library are derived from the user account's use process on the social client; the weight of each interest tag is adjusted based on factors such as the user account's usage frequency and interaction frequency. When the AI ​​assistant determines the recommended information content of the first account, it filters or summarizes the recommended information content based on the first account's interest tags, and sorts the different recommended information content based on the weight of the interest tags as a priority.

[0121] In a stacked display mode, the user needs to switch between different information cards, and switching between different information cards can be achieved through sliding operations. That is, in response to a sliding operation on the first information card among at least two information cards, the first information card is canceled from display, and the second information card is displayed; wherein the second information card is the information card that follows the first information card in the stacking order. Alternatively, in response to an upward sliding operation on the first information card among at least two information cards, the first information card is canceled from display, and the second information card is displayed; and / or, in response to a downward sliding operation on the second information card among at least two information cards, the second information card is canceled from display, and the first information card is displayed. wherein the second information card is the information card that follows the first information card in the stacking order.

[0122] In some embodiments, in response to different swiping directions on a first information card among at least two information cards, a different second information card is displayed. For example, swiping up / down displays the previous / next card of the same type (e.g., the same business function), while swiping left / right displays the previous / next card of a different type of card.

[0123] In some embodiments, the display level of the recommended information content recommended by the AI ​​assistant to the first account is higher than the level of the original function corresponding to the recommended information content. For example, the original function level is at the third level, while the display interface of the AI ​​assistant is at the first level to ensure that users can access important information more promptly. Taking the recommended information content as a summary of unread social messages as an example, the recommended information content on the AI ​​assistant interface is displayed when the social client is opened, while the original unread social messages need to jump through the main interface, contact interface, and chat interface in sequence before they can be displayed. Therefore, the AI ​​assistant can enable important information content to be accessed by users earlier.

[0124] In some embodiments, the first account first activates the AI ​​assistant, and then displays the recommended information content recommended by the AI ​​assistant to the first account on the user interface. That is, before jumping to the interface of the AI ​​assistant function, a function entrance to the AI ​​assistant function is set.

[0125] Exemplarily, a function entry for the AI ​​assistant function is displayed; in response to a trigger operation on the function entry, the recommended information content recommended by the AI ​​assistant for the first account is displayed. For example, in FIG1 , a function entry 13 for the AI ​​assistant function "exploration mode" is displayed in the mode switching interface 10; after the user triggers the function entry 13 to turn on the AI ​​assistant function, the recommended information content recommended by the AI ​​assistant for the first account is displayed, such as the recommended information content 15 displayed on the recommended information content interface 11. The entry to the AI ​​assistant function can be displayed on the main interface of the social client, or on the setting interface of the business function, or on the setting interface of the group chat / contact, etc. This application is not limited to this.

[0126] The technical solution provided by the embodiments of this application displays recommended information content in response to triggering operations on function portals to meet the needs of different users. When the user does not want to activate the function of the recommended information content, the function portal can be deactivated. When the user does want to activate the function of the recommended information content, the function portal can be activated, thus realizing flexible settings of the AI ​​assistant.

[0127] In some embodiments, when a first account activates the AI ​​assistant, the AI ​​assistant can be enabled for all business functions or for business functions specified by the first account. For business functions for which the AI ​​assistant is enabled, the first account can specify a specific scope for enabling the AI ​​assistant. That is, the scope granularity for enabling the AI ​​assistant by the first account can be social function granularity, group chat granularity, contact granularity, etc. For example, the first account can specify that the AI ​​assistant function be enabled for work groups that need to quickly obtain information and group chats with a large number of messages.

[0128] In some embodiments, during the process of displaying the recommended information content, before or after displaying the recommended information content, a quick operation entry associated with the recommended information content is displayed; in response to the operation on the quick operation entry, the quick processing function corresponding to the quick operation entry is executed.

[0129] The user interface of the first account displays the recommended information content recommended by the AI ​​assistant for the first account, and displays a quick operation entry associated with the recommended information content. The type of the quick operation entry and the user's operation on the quick operation entry include at least one of the following:

[0130] The quick operation entry is a jump entry for jumping to the function user interface of the function to which the recommended information content belongs:

[0131] In response to a first action on the quick action entry, a user interface for the function to which the recommended information belongs is displayed, including the original information corresponding to the recommended information. For example, if the recommended information is a summary of unread social messages from account A, clicking the quick action entry will redirect the user to the chat interface between the first account and account A, allowing the user to view the complete chat content.

[0132] The quick operation entry is for replying to the second account:

[0133] In the case where the recommended information content originates from a social message of the second account, in response to a second operation on the quick operation entry, the reply content of the first account in reply to the recommended information content is obtained; and a reply message carrying the reply content is sent to the second account. For example, the recommended information content is a summary of the social message originating from the second account. The first account can directly enter the reply content to the social message in the quick operation entry on the interface displaying the recommended information content (i.e., the AI ​​assistant interface), and the reply message carrying the reply content will be sent to the second account. As shown in Figure 1, a summary of group chat messages related to the first account is displayed in the information card. Each group chat message includes the group chat name, the name of the group member who mentioned the first account, and the message content that mentioned the first account; a dialog box for input is displayed below the information card. The first account can reply to the group chat message summarized in the information card by entering natural language in the dialog box. For example, the first account enters the reply message content 17 in the dialog box, and the content will be replied to the group chat member Xiao A. In this way, the first account avoids the multiple steps of jumping to the original chat dialogue interface with the second account and then replying to the message. Instead, it can reply to the message directly in the AI ​​assistant interface, realizing a quick reply to social messages.

[0134] In some embodiments, the quick operation entrance can be set inside the information card, for example, below the recommended information content or at the bottom of the information card; or, the quick operation entrance can be set at the bottom of the AI ​​assistant interface, that is, below the information card; or, the first account first clicks on the recommended information content to jump to the interface of the original information content corresponding to the recommended information content (that is, the first operation), and then enters the reply information in the dialog box in the interface of the original information content.

[0135] The quick operation entry is used to reply to a third account using the quick reply content generated for the recommended information content:

[0136] If the recommended content originates from a social message from a third account, a quick reply generated for the recommended content will be displayed during the display of the recommended content. In response to a third action in the quick action portal, a reply message is sent to the third account, carrying the quick reply content. For example, if the recommended content is a social message from a third account and the recommended content is a summary of a work task requested by the third account for the first account, the quick reply content for the recommended content will be displayed simultaneously with the recommended content, such as "OK, got it," "I'll be there on time tomorrow," or "Expected to be completed before the end of the get off work day." As another example, as shown in Figure 2, the recommended information content 23 displayed on the information card on the AI ​​assistant interface 20 includes the contact nickname or note name, the contact avatar, the number of unread messages from the contact, the summarized or filtered message content, an indicator that the current message is a summarized or filtered message content, etc.; the bottom of the AI ​​assistant interface 20 also displays quick reply content 24, which can be one or more candidate quick reply contents. The multiple candidate quick reply contents are arranged in sequence on the left and right sides of the bottom of the AI ​​assistant interface 20. The first account can select a suitable reply message from the quick reply content by sliding left and right, and send the reply message to the third account through a third operation. In this way, the first account avoids manually entering a reply message, but can directly select from the recommended candidate reply messages, thereby realizing a quick reply to a social message.

[0137] The quick operation entry is used to jump to the to-do item processing interface:

[0138] If the recommended information originates from a social message from a fourth account and is associated with a to-do item, a quick access entry (i.e., an access entry for the to-do item) is displayed during the display of the recommended information. In response to a fourth operation on the quick access entry, a task processing interface for the to-do item is displayed. The to-do item includes at least one of an electronic document, a group vote, and a third-party application. For example, if the recommended information originates from a social message from a fourth account and is related to a to-do item, and the to-do item is a group vote, a jump entry for the group vote is displayed simultaneously with the display of the recommended information. The first account can trigger the jump entry to jump to the task processing interface for the group vote. As another example, as shown in FIG2 , the recommended information content 21 displayed on the information card on the AI ​​assistant interface 20 includes the group chat name or note name, the group chat avatar, the number of unread messages from the group chat, the summarized or filtered message content, an indicator that the current message is a summarized or filtered message content, and so on; wherein, the social message from the group chat is associated with a to-do item. While displaying the recommended information content 21, the electronic document 22 corresponding to the to-do item is displayed at the bottom of the AI ​​assistant interface 20. The first account can open the electronic document 22 and directly complete the to-do item by clicking on the electronic document 22. In this way, the first account can obtain the content of the to-do item while obtaining the entry to quickly process the to-do item, thereby improving the efficiency of information content processing.

[0139] The quick operation portal is used to access multimedia content:

[0140] When the recommended information is associated with multimedia content, a quick operation portal (i.e., an access portal for the multimedia content) is displayed during the display of the recommended information; in response to a fifth operation of the quick operation portal, a multimedia content interface for the multimedia content is displayed; wherein the multimedia content includes at least one of images, audio, video, and games. For example, if the recommended information is a recommendation for a game, the access portal for the game is displayed simultaneously with the display of the recommended information. The first account can jump to the content interface of the game by triggering the access portal. In this way, the first account can quickly jump to the multimedia content interface associated with the recommended information, thereby improving the processing efficiency of the information content.

[0141] The quick operation portal is used to share recommended information content with a fifth account or group:

[0142] During the display of recommended information content, a quick operation entry for sharing the recommended information content with a fifth account or group is displayed, wherein the fifth account or group is recommended by the AI ​​assistant in the social relationship chain of the first account; in response to the sixth operation of the quick operation entry, the recommended information content is shared with the fifth account or group. For example, if the recommended information content is a recommendation for a movie, while displaying the recommended information content, a sharing entry for sharing the movie with the fifth account or group is displayed, and the first account can quickly share the movie by triggering the sharing entry; as shown in Figure 2, the recommended information content 25 displayed on the information card on the AI ​​assistant interface 20 includes the group chat name or note name, the group chat avatar, the number of unread messages from the group chat, the summarized or filtered message content, an indicator that the current message is a summarized or filtered message content, etc.; while displaying the recommended information content 25, a sharing entry 26 for sharing the recommended information content is displayed at the bottom of the AI ​​assistant interface 20, and the user can quickly share the recommended information content with the fifth account or group by triggering the sharing entry 26 (for example, clicking on the sharing control). Among them, the fifth account or group is an account or group that has a social relationship with the first account; for example, a user account among the friends of the first account with the same interest tag as the first account is selected as the fifth account; or, the first account customizes the fifth account or group that it wants to share.

[0143] The quick operation entry is to add the sixth account or group associated with the recommended information content:

[0144] In the process of displaying the recommended information content, an entry for adding the sixth account or group associated with the recommended information content is displayed; in response to the seventh operation on the shortcut operation entry, the sixth account is added as a friend or joins the group. Among them, the sixth account or group associated with the recommended information content can be the sender of the recommended information content, the participant of the recommended information content, the account or group chat mentioned in the recommended information content, the account or group chat that may be interested in the recommended information content, the account or group chat whose interest tag matches the content contained in the recommended information content, and so on. As shown in Figure 3, the recommended information content displayed on the AI ​​assistant interface 30 is a game video 31 recommended for the current user account to be published on a third-party platform, and at the same time, an entry for adding the sixth account that plays the game together with the first account is displayed. The user can quickly add the sixth account as a friend by triggering the addition entry 32 (for example, clicking on the add control).

[0145] In some embodiments, the first account can also obtain solutions to the problem through direct interaction with the AI ​​assistant. That is, the first account receives a command message sent to the AI ​​assistant by the first account; and displays the reply content generated by the AI ​​assistant in response to the command message. The reply content is obtained by the AI ​​assistant after filtering or summarizing the information content in at least one social function based on the command message. For example, the first account sends a command message to the AI ​​assistant to summarize information about TV series in group chat A. After the AI ​​assistant obtains and summarizes the relevant information about the TV series involved in group chat A, it displays the reply content generated in response to the command message.

[0146] In some embodiments, the interest tags of the first account are obtained based on the operation records or user information analysis of the first account on the social client. However, it should be noted that the user information (including but not limited to personal information, social platform information, location information, social relationship information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions. For example, the social platform information and other information involved in this application are all obtained with full authorization. For another example, the information content and other information involved in this application are all obtained after the user's authorization and permission, and the user can customize the authorized single chat / group chat and change the settings at any time.

[0147] It should be noted that the user information and data involved in this application will undergo sensitive information detection before analysis; when sensitive information (such as sensitive keywords, etc.) is detected, desensitization operations will be performed before usage analysis. It should be noted that the analysis and processing functions of the AI ​​assistant in this application (such as AI models) are all deployed on the client, and the server uses federated learning to train the AI ​​model and update the model parameters, that is, the server does not retain user information and data, and is only used to train the AI ​​model. It should be noted that in this application, when the user information and data on the client are sent to the server for analysis or processing, the client can send it to the server anonymously, that is, the server analyzes, processes or trains the AI ​​model without knowing the source of the information and data to protect user privacy.

[0148] In summary, the method provided in the embodiment of the present application enables users to quickly obtain key information on the social client by obtaining and displaying the recommended information content recommended by the AI ​​assistant on the user interface, extract effective content from a large amount of information, and improve the user's information content processing efficiency on the social client.

[0149] Figure 7 shows a flowchart of a method for processing information content provided by an exemplary embodiment of the present application. This embodiment illustrates the method by executing it on the terminal device shown in Figure 5 or a client running on the terminal device. For example, the terminal device runs a social client logged in with a first account, and the social client includes at least one social function. The method includes at least one of the following steps 310 to 380.

[0150] In some embodiments, the following step 310 may be implemented as a pre-execution step. For example, after the social client on the terminal device is logged into the first account, the terminal device may only execute the following steps 330 to 380.

[0151] Step 310: Log in to the first account;

[0152] The first account is the user account currently logged in on the social client.

[0153] Exemplarily, the user enters the user name and password on the login interface and clicks the login control to log in to the first account; or, if the user sets automatic login, the user is automatically logged in to the first account when the user opens the social client.

[0154] Step 330: Obtain the recommended information content recommended by the AI ​​assistant for the first account;

[0155] An AI assistant refers to an AI service provided in a social client that is at least based on an AI model to improve the efficiency of users' processing of information content. Taking the processing of information content by AI services as an example, an AI assistant is a recommendation service that screens or summarizes information content based at least on an AI model.

[0156] The AI ​​model used by the AI ​​assistant can be a language model, such as LLM, GLM, which is trained on a large amount of text data, aims to understand and generate human language, and can perform a variety of tasks such as text summarization, translation, and sentiment analysis. Among them, LLM refers to a language model whose model parameters exceed the first threshold, or the training data exceeds the second threshold, or the amount of calculation exceeds the third threshold, wherein the first threshold, the second threshold, and the third threshold are all values ​​in the hundreds of billions. In some embodiments, the AI ​​model used by the AI ​​assistant can also be a model for text-to-image, image-to-text, text-to-video, etc. Taking the AI ​​assistant using a large language model as an example, the AI ​​services it provides include summarizing unread social messages, optimizing social networks, reviewing historical social messages, answering questions, recommending functions, emotional companionship, etc. This application is not limited to this.

[0157] Exemplarily, a social client includes multiple business functions, at least two of which are located at different human-computer interaction interface levels. Business functions refer to functions designed to achieve online social purposes, including at least one of the following: communication functions (including one-on-one chat, group chat, etc.), contact functions, social circle functions, and short video functions. The recommended information content recommended by the AI ​​assistant for the first account is obtained, and the recommended information content includes information content obtained by the AI ​​assistant after screening or summarizing the information content in the first business function, and the first business function is located at the first human-computer interaction interface level.

[0158] In some embodiments, the social client's service functions also include service functions of third-party applications. These third-party applications can be internal or external to the social client. A third-party application's service functions are those authorized for use or synchronization by the social client. This means the social client has permission to access information and / or invoke functions within the authorized third-party application's service functions. For example, a social client might access information from a third-party application used for shopping within the social client; or invoke functions from a third-party application external to the social client used to clear memory. This can occur, for example, when a social client accesses information from a third-party application used for shopping within the social client.

[0159] The HMI level indicates the accessibility of the HMI, i.e., the operational cost required to reach it. For example, the number of steps required to access the HMI from the main interface of a social client. The higher the HMI level, the fewer steps a user needs to take to reach it.

[0160] Among them, screening refers to extracting from the information content of the at least one business function, that is, there is no secondary processing; summarizing means not directly selecting part of the original information content, but forming generalized information content through secondary processing, such as an abstract or summary.

[0161] For example, the recommended information content is obtained by the AI ​​assistant after screening or summarizing the information content in at least one business function. The recommended information content includes at least one of the following:

[0162] The first recommended information content after filtering or summarizing the unread social messages of the first account;

[0163] Second recommended information content that is filtered or summarized from the group chat messages or to-do items in the workflow of the first account;

[0164] The third recommended information content is obtained by screening or summarizing the candidate information according to the preset rules of the first account;

[0165] Fourth recommended information content that is obtained by screening or summarizing dynamic information of friends in the social network of the first account;

[0166] The fifth recommended information content randomly recommended for the first account;

[0167] Fifth recommended information content after screening or summarizing information content that may be of potential interest to the first account;

[0168] The sixth recommended information content is obtained by screening or summarizing the information content that is likely to be shared by the first account;

[0169] The seventh recommended information content is obtained by screening or summarizing interest groups that may be potentially interested in the first account;

[0170] Eighth recommended information content obtained by filtering or summarizing POI information corresponding to the current geographic location of the first account;

[0171] The tenth recommended information content selected or summarized by the AI ​​tool that may be of potential interest to the first account;

[0172] · Eleventh recommended information content after screening or summarizing games that the first account may be interested in;

[0173] a twelfth recommended information content obtained by screening or summarizing relevant information of third-party applications bound to the first account;

[0174] The types of information in the aforementioned at least one business function may include the following types:

[0175] Text messages: such as text messages, blogs, emails, etc.

[0176] Graphic information: such as photographs, paintings, illustrations, etc.

[0177] Video information: such as TV shows, movies, short videos, etc.

[0178] Audio information: such as songs, broadcasts, radio stations, etc.

[0179] Social network information: such as personal homepage, social circles, social platforms, etc.;

[0180] Game information: such as online games, mobile games, etc.

[0181] Location information: such as GPS positioning, map navigation, etc.

[0182] Personal information: such as basic personal information, interests, personality traits, ability levels, achievements, etc.

[0183] Group information: such as group membership, goals and tasks, organizational structure, cultural atmosphere, and behavioral norms;

[0184] Emotional information: such as the emotional state, attitude, preferences, and satisfaction ratings of individuals or groups;

[0185] Behavioral information: such as individual or group behavior patterns, behavioral outcomes, and behavioral impacts;

[0186] Environmental information: such as the physical, social, and cultural environment of an individual or group.

[0187] Exemplarily, in response to a triggering operation on a function entry of an AI function, the recommended information content recommended by the AI ​​assistant for the first account is obtained; that is, after the first account chooses to use the AI ​​assistant, the recommended information content summarized or filtered by the AI ​​assistant is obtained.

[0188] Exemplarily, information content in at least one business function in the social client is obtained, and an AI model (such as a large language model) based on the AI ​​assistant is used to summarize the information content and predict the reply of the first account.

[0189] In some embodiments, the recommended information content recommended by the AI ​​assistant for the first account can be completely generated by the AI ​​model on which the AI ​​assistant is based; or, it can be a combination of recommended information content generated by the AI ​​model and recommended information content generated by a traditional recommendation algorithm.

[0190] In some embodiments, an interest tag library is constructed for each user account, and the interest tags in the interest tag library are derived from the user account's usage of the social client. When the AI ​​assistant determines recommended information content for a first account, the recommended information content is filtered or summarized based on the first account's interest tags.

[0191] The technical solution provided in the embodiment of the present application obtains recommended information content by screening or summarizing the different information content of the first account under different social functions. In other words, the recommended information content can cover different aspects of different business functions of the social application. Therefore, the technical solution provided in the embodiment of the present application reflects the diversity of recommended information content.

[0192] Step 340: Display the recommended information content at the second human-computer interaction interface level;

[0193] Exemplarily, the social client includes multiple business functions, and at least two of the multiple business functions are located at different human-computer interaction interface levels. After obtaining the recommended information content obtained by the AI ​​assistant based on the information content screening or summarizing in the first business function of the first human-computer interaction interface level, the recommended information content recommended by the AI ​​assistant for the first account is displayed at the second human-computer interaction interface level. The second human-computer interaction interface level is higher than the first human-computer interaction interface level; that is, the second human-computer interaction interface requires fewer operation steps to reach than the first human-computer interaction interface; that is, after summarizing or screening the information content of the first human-computer interaction interface at a lower level, it is displayed on the second human-computer interaction interface at a higher level, so that the cost of obtaining the information content is lower and efficiency is improved.

[0194] Exemplarily, at least two information cards are displayed at the second human-computer interaction interface level, each of which is used to display one or a group of recommended information content recommended by the AI ​​assistant for the first account. A group of recommended information content may originate from the same business function, or from the same group chat / contact, or from the same topic. For example, each information card may display a summary of unread social messages from a group chat / contact; or, for another example, each information card may display a filtered result of key information from a business function.

[0195] The information card includes at least one of the following information:

[0196] Account information of the second account (e.g., profile picture of the second account, nickname of the second account, and the first account's reference to the second account);

[0197] The number of related messages (e.g., the number of unread messages sent from the second account to the first account);

[0198] Whether the information is filtered or summarized (for example, "A summary has been generated for you");

[0199] At least one selected message (for example, an important message selected from unread messages);

[0200] At least one summarized message (e.g., a message obtained by summarizing unread messages);

[0201] Whether it is an indicator of information content processed by an AI model (for example, displaying “AI intelligent message”).

[0202] The at least two information cards may be displayed in a tiled manner or in a stacked manner. That is, the at least two information cards may be displayed in a non-overlapping manner from top to bottom (multiple information cards may be displayed simultaneously on the user interface, as shown in FIG1 ), and the user may view different information cards by sliding up and down; or the at least two information cards may be displayed in a stacked manner with partial or full overlap (only one information card may be displayed on the user interface, as shown in FIG2 ), and the user may switch between different information cards by sliding.

[0203] In some embodiments, the at least two information cards are displayed in a tiled manner at the second human-computer interaction interface level; wherein the tile order of the at least two information cards is determined based on the recommendation priority of the at least two information cards.

[0204] In other embodiments, the at least two information cards are displayed in a stacked manner at the second human-computer interaction interface level; wherein the stacking order of the at least two information cards is determined based on the recommendation priority of the at least two information cards.

[0205] The technical solution provided by the embodiments of this application provides two ways to display information cards. The information cards can be displayed flatly or stacked. When the information cards are displayed flatly, the recommended information content indicated by multiple information cards can be obtained at once. When the information cards are stacked, the display area of ​​the information cards can be reduced, thereby reducing the display cost of the information cards to a certain extent.

[0206] Among them, the recommendation priority can be the default priority of the social client; or it can be a user-defined priority; or it can be a priority optimized by machine learning based on the way the user uses the social client. For example, an interest tag library is built for each user account, and the interest tags in the interest tag library are derived from the user account's use process on the social client; the weight of each interest tag is adjusted based on factors such as the user account's usage frequency and interaction frequency. When the AI ​​assistant determines the recommended information content of the first account, it filters or summarizes the recommended information content based on the first account's interest tags, and sorts the different recommended information content based on the weight of the interest tags as a priority.

[0207] That is, obtain the interest tags and weights of the interest tags of the first account; determine the recommendation priority of at least two information cards based on the target interest tags matching the recommended information content and the weights of the target interest tags; and determine the sorting order of at least two information cards based on the priorities of at least two information cards.

[0208] The technical solution provided in the embodiment of the present application determines the recommendation priority of information cards based on the interest tags of the first account and the weights of the interest tags, so that the information cards displayed according to the recommendation priority are in line with the user's interests and are more likely to meet the user's needs, which is conducive to improving the display effect of the information cards.

[0209] In the stacked display mode, the user needs to switch to display different information cards, and the switching between different information cards can be achieved through sliding operations. That is, in response to the sliding operation on the first information card among at least two information cards, the first information card is canceled and the second information card is displayed; wherein the second information card is an information card that is arranged after the first information card in a stacking order or a tiled order. Alternatively, in response to the upward sliding operation on the first information card among at least two information cards, the first information card is canceled and the second information card is displayed; and / or, in response to the downward sliding operation on the second information card among at least two information cards, the second information card is canceled and the first information card is displayed. wherein the second information card is an information card that is arranged after the first information card in a stacking order or a tiled order. This method realizes the switching display between information cards through sliding operations, which is conducive to improving switching efficiency and switching flexibility.

[0210] In some embodiments, in response to different swiping directions on a first information card among at least two information cards, a different second information card is displayed. For example, swiping up / down displays the previous / next card of the same type (e.g., the same business function), while swiping left / right displays the previous / next card of a different type of card.

[0211] In some embodiments, the display level of the recommended information content recommended by the AI ​​assistant to the first account is higher than the level of the original function corresponding to the recommended information content. For example, the original function level is at the third level, while the display interface of the AI ​​assistant is at the first level to ensure that users can access important information more promptly. Taking the recommended information content as a summary of unread social messages as an example, the recommended information content on the AI ​​assistant interface is displayed when the social client is opened, while the original unread social messages need to jump through the main interface, contact interface, and chat interface in sequence before they can be displayed. Therefore, the AI ​​assistant can enable important information content to be accessed by users earlier.

[0212] In some embodiments, each information card corresponds to a business function; each business function registers the card template it uses with the dispatch center, fills the recommended information content into the card template, and obtains a card containing the recommended information content; that is, obtain the card template registered by the business function corresponding to the recommended information content; fill the recommended information content into the card template, obtain the information card corresponding to the recommended information content, and then display the information card on the user interface.

[0213] In some embodiments, the social client includes a program function corresponding to the AI ​​assistant, and receives a card template registered for at least one business function through the program function corresponding to the AI ​​assistant. The card template is used to combine with the recommended information content belonging to the business function to generate and display an information card containing the recommended information content.

[0214] In some embodiments, in addition to registering card templates with the dispatch center, the business function also registers the functional functions supported by the card templates. Specifically, the registered social client includes a program function corresponding to the AI ​​assistant, and the program function corresponding to the AI ​​assistant receives at least one functional function supported by the card template registered by the business function through the program function corresponding to the AI ​​assistant. The functional function is used to execute a response function corresponding to the recommended information content when called.

[0215] The technical solution provided in the embodiment of the present application introduces a card template registered with a business function and fills the recommended information content into the card template to obtain an information card, which is conducive to standardizing the generation of information cards and improving the generation efficiency of information cards.

[0216] In addition, the program function provided by the program in the AI ​​assistant is used to receive a card template registered separately by at least one business function to generate recommended information content. When the requirements for the AI ​​assistant are different, the program function provided by the AI ​​assistant can be changed, which is conducive to improving the diversity and flexibility of the program function provided by the AI ​​assistant. In addition, receiving a card template registered separately by at least one business function through a program function to generate recommended information content generally does not make mistakes, which is conducive to improving the accuracy of the generated recommended information content. Furthermore, through the program function corresponding to the AI ​​assistant, the function function supported by the card template registered separately by at least one business function is received, and the function function is used to execute the response function corresponding to the recommended information content when called. That is, by registering the function function and utilizing its corresponding response function, the rapid generation of different recommended information content is achieved, which is conducive to improving the generation efficiency of the recommended information content.

[0217] In some embodiments, during, before, or after displaying the recommended information content, a quick operation entry associated with the recommended information content is displayed; in response to an operation on the quick operation entry, a quick processing function corresponding to the quick operation entry is executed. That is, when the user interface of the first account displays the recommended information content recommended by the AI ​​assistant for the first account, the quick operation entry associated with the recommended information content is also displayed. The type of quick operation entry and the user's operation on the quick operation entry include at least one of the following:

[0218] The quick operation entry is a jump entry for jumping to the function user interface of the function to which the recommended information content belongs. The first operation is used to obtain the original information content corresponding to the recommended information content:

[0219] In response to a first operation on the quick operation entrance, a function user interface of the function to which the recommended information content belongs is displayed, and the function user interface includes original information content corresponding to the recommended information content.

[0220] The quick operation entry is used to reply to the second account. The second operation is used to reply to social messages:

[0221] In the case where the recommended information content originates from a social message of the second account, in response to a second operation on the quick operation entrance, the reply content of the first account in reply to the recommended information content is obtained; and a reply message carrying the reply content is sent to the second account.

[0222] The quick operation entry is used to reply to a third account using the quick reply content generated for the recommended information content. The third operation is used to quickly reply to social messages:

[0223] In the case where the recommended information content originates from a social message of a third account, during the process of displaying the recommended information content, the quick reply content generated for the recommended information content is displayed; in response to the third operation of the quick operation entrance, a reply message is sent to the third account, and the reply message carries the quick reply content.

[0224] The quick operation entry is used to jump to the to-do item processing interface. The fourth operation is used to complete the to-do item:

[0225] When the recommended information content originates from a social message of a fourth account and the social message is associated with a to-do item, an access entrance to the to-do item is displayed during the display of the recommended information content; in response to a fourth operation of the quick operation entrance (the access entrance to the to-do item), an item processing interface of the to-do item is displayed; wherein the to-do item includes at least one of an electronic document, a group vote, and a third-party application.

[0226] The quick operation entry is an access entry for accessing multimedia content. The fifth operation is used to access multimedia content:

[0227] When the recommended information content is associated with multimedia content, the access entrance to the multimedia content is displayed during the display of the recommended information content; in response to the fifth operation of the shortcut operation entrance (access entrance to the multimedia content), the multimedia content interface of the multimedia content is displayed; wherein the multimedia content includes at least one of pictures, audio, video, and games.

[0228] The quick operation entry is used to share recommended information content to the fifth account or group. The sixth operation is used to share:

[0229] During the process of displaying recommended information content, a sharing entrance for sharing the recommended information content with a fifth account or group is displayed, wherein the fifth account or group is recommended by the AI ​​assistant in the social relationship chain of the first account; in response to the sixth operation of the quick operation entrance (sharing entrance), the recommended information content is shared with the fifth account or group.

[0230] The quick operation entry is for adding a sixth account or group associated with the recommended information content, and the seventh operation is for adding a sixth account or group chat:

[0231] During the display of the recommended information content, an entry for adding a sixth account or group associated with the recommended information content is displayed; in response to a seventh operation on the shortcut operation entry, the sixth account is added as a friend or joins the group.

[0232] The technical solution provided by the embodiments of this application displays a quick operation entry associated with the recommended information content; in response to different operations on the quick operation entry, different quick processing functions corresponding to the quick operation entry are executed. Therefore, by providing the aforementioned several forms of quick processing functions, this application meets the different needs of users, enriches the human-computer interaction form, reduces the number of operation steps, and further reduces device processing overhead.

[0233] Step 360: Receive a command message sent by the first account to the AI ​​assistant;

[0234] The first account can obtain solutions to the problem or relevant recommendations through natural language by interacting with the AI ​​assistant; that is, the first account sends a command message to the AI ​​assistant, and the social client receives the command message sent by the first account to the AI ​​assistant.

[0235] In some embodiments, the first account sends a command message to the AI ​​assistant through text input or voice input.

[0236] In some embodiments, a dialog box for the first account to send a command message to the AI ​​assistant is located at the bottom of the user interface, or the dialog box for the first account to send a command message to the AI ​​assistant is located inside an information card, for example, at the bottom of the information card. The first account can ask questions or provide instructions to the AI ​​assistant by entering a command message in the dialog box.

[0237] The technical solution provided by the embodiment of this application uses a first account to send a command message to the AI ​​assistant to obtain a reply, enriching the human-computer interaction form and improving the efficiency of human-computer interaction. Users can send any command message to the AI ​​assistant to obtain a reply, improving the efficiency of information acquisition and simplifying the information acquisition process.

[0238] The command message sent by the first account to the AI ​​assistant may include the following types:

[0239] Review the chat content in the single chat:

[0240] A first command message sent by the first account to the AI ​​assistant is received, and the first command message is used to inquire about the chat content between the first account and the seventh account. For example, as shown in Figure 4, the AI ​​assistant interface 50 displays an information card, and the information card displays the identifier "My AI" of the information content currently being processed by the AI ​​model; the first account enters the first command message in the dialog box 53 in the information card in the AI ​​assistant interface 50 to command the AI ​​assistant to review the chat content in the single chat, such as "What have I talked about with my friend S recently?" and clicks send to send the first command message to the AI ​​assistant. In some embodiments, a voice input control is provided on the right side of the dialog box 53, that is, the first command message can be entered by voice input.

[0241] The embodiment of the present application receives the first reply content generated for the first command message by sending a first command message to the AI ​​assistant, which is conducive to obtaining the chat content in the retrospective single chat, improving the efficiency of obtaining the chat content in the single chat, and simplifying the steps of obtaining the chat content in the single chat.

[0242] Recall the chat content in the group chat:

[0243] Receive a second command message sent by the first account to the AI ​​assistant, the second command message being used to inquire about the chat content of the chat group to which the first account belongs. For example, as shown in Figure 4, the AI ​​assistant interface 50 displays an information card, which displays the identifier "My AI" indicating the information content currently being processed by the AI ​​model. The first account can click the voice input control in the dialog box 53 and simultaneously input the second command message "What was the conclusion of the last discussion in group chat X" in voice form. After the user releases the voice input control, the second command message is sent to the AI ​​assistant, allowing the first account to quickly review the information content of the group chat.

[0244] The embodiment of the present application receives the second reply content generated for the second command message by sending a second command message to the AI ​​assistant, which is conducive to obtaining the chat content in the retrospective group chat, improving the efficiency of obtaining the chat content in the group chat, and simplifying the steps of obtaining the chat content in the group chat.

[0245] Get friends’ updates:

[0246] Receive a third command message sent by the first account to the AI ​​assistant, the third command message is used to ask the eighth account, which is a friend of the first account, what content they are following. For example, as shown in Figure 4, the AI ​​assistant interface 50 displays an information card, and the information card displays the identifier "My AI" of the information content currently being processed by the AI ​​model; the first account enters a third command message in the dialog box 53 of the information card in the AI ​​assistant interface 50, commanding the AI ​​assistant to obtain friend dynamics, such as "What is friend Y following recently" and clicks send, sending the third command message to the AI ​​assistant to obtain the friend's recent dynamics. In some embodiments, a voice input control is provided on the right side of the dialog box 53, that is, the third command message can be entered by voice input.

[0247] The embodiment of the present application receives the third reply content generated for the third command message by sending a third command message to the AI ​​assistant, which is conducive to obtaining friend dynamics, improving the efficiency of obtaining friend dynamics, and simplifying the steps of obtaining friend dynamics.

[0248] Get keyword information:

[0249] Receive a fourth command message sent by the first account to the AI ​​assistant, where the fourth command message is used to ask questions about network information or social chain information associated with the first keyword. Exemplarily, the first keyword is a keyword extracted from the fourth command message. For example, as shown in Figure 4, the AI ​​assistant interface 50 displays an information card, and the information card displays the identifier "My AI" of the information content currently being processed by the AI ​​model; the first account enters the fourth command message in the dialog box 53 in the information card of the AI ​​assistant interface 50, commanding the AI ​​assistant to obtain keyword information, such as "What are the recent interest groups related to beauty?" and clicks send to send the fourth command message to the AI ​​assistant to obtain interest groups that match the interests of the first account. In some embodiments, a voice input control is provided on the right side of the dialog box 53, that is, the fourth command message can be input by voice input.

[0250] The embodiment of the present application receives the fourth reply content generated for the fourth command message by sending a fourth command message to the AI ​​assistant, which is conducive to obtaining network information or social chain information based on keywords, improving the efficiency of obtaining network information or social chain information, and simplifying the steps of obtaining network information or social chain information.

[0251] Quick use function:

[0252] A fifth command message is received from a first account to the AI ​​assistant, the fifth command message being used to activate a first function. Exemplarily, the first function is a function identified from the fifth command message. For example, as shown in FIG4 , the AI ​​assistant interface 50 displays an information card, which displays an identifier "My AI" indicating the information content currently being processed by the AI ​​model. The first account enters a fourth command message in a dialog box 53 within the information card within the AI ​​assistant interface 50, requesting the AI ​​assistant to help the first account quickly access a function, such as "Please help me set up Teen Mode," and clicks "Send." This sends a fifth command message to the AI ​​assistant to retrieve interest groups that match the first account's interests. For another example, a user enters "App launches have been slow lately" in a dialog box 53 within the information card within the AI ​​assistant interface 50 to quickly activate the cache data clearing function. Upon receiving the fifth command message, the AI ​​assistant generates and displays a reply 56 and recommended related content 56, allowing the user to quickly activate the cache data clearing function by clicking on the recommended related content 56. In some embodiments, a voice input control is provided on the right side of the dialog box 53, allowing the user to enter the fifth command message via voice input.

[0253] The embodiment of the present application sends a fifth command message to the AI ​​assistant and receives the fifth reply content generated for the fifth command message, which is conducive to quickly using the first function, simplifying the implementation steps of the first function, and improving the processing efficiency of the device.

[0254] Step 380: Display the response content generated by the AI ​​assistant in response to the command message.

[0255] Exemplarily, the user interface of the social client displays the reply content generated by the AI ​​assistant in response to the command message. The reply content is obtained by the AI ​​assistant after screening or summarizing the information content in at least one social function based on the command message.

[0256] For different types of command messages in step 360, the AI ​​assistant generates different reply contents, as shown below:

[0257] Generate a first reply content for the first command message:

[0258] The first reply generated by the AI ​​assistant to the first command message is displayed. The first reply is obtained by the AI ​​assistant summarizing the chat content between the first account and the seventh account. For example, the AI ​​assistant determines the tag of the seventh account based on the first command message, matches it with social message data that matches it, and summarizes the social message data based on the AI ​​model to generate the first reply.

[0259] Generate a second reply content for the second command message:

[0260] The second reply generated by the AI ​​assistant in response to the second command message is displayed. The second reply is generated by the AI ​​assistant summarizing the chat content of the chat group to which the first account belongs. For example, based on the group chat tag and content tags in the second command message, the AI ​​assistant matches the social message data in the group chat that matches them, and summarizes the social message data based on the AI ​​model to generate the second reply.

[0261] Generating a third reply content for the third command message:

[0262] The third reply generated by the AI ​​assistant to the third command message is displayed. The third reply is obtained by the AI ​​assistant summarizing the friend dynamic information of the eighth account. For example, the AI ​​assistant matches the dynamic information that matches the friend tag in the third command message and generates the third reply after filtering and summarizing it based on the AI ​​model.

[0263] Generate a fourth reply content for the fourth command message:

[0264] The fourth reply content generated by the AI ​​assistant in response to the fourth command message is displayed. The fourth reply content is the search result of the AI ​​assistant searching for network information or social link information associated with the first keyword. For example, based on the first keyword in the fourth command message, the AI ​​assistant matches the network information or social link information associated with it (such as interest groups, etc.), and generates the fourth reply content after screening and summarizing.

[0265] Generate a fifth reply content for the fifth command message:

[0266] The fifth reply generated by the AI ​​assistant in response to the fifth command message is displayed. The fifth reply is the function entry of the first function reported by the AI ​​assistant, or the call result after the AI ​​assistant calls the first function. For example, based on the keywords in the fifth command message, the AI ​​assistant determines the relevant function and returns the function entry of the function to the first account as a shortcut, or directly calls the function and returns the call result as the fifth reply to the first account.

[0267] In some embodiments, the interest tags of the first account are obtained based on the operation records or user information analysis of the first account on the social client. However, it should be noted that the user information (including but not limited to personal information, social platform information, location information, social relationship information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions. For example, the social platform information and other information involved in this application are all obtained with full authorization. For another example, the information content and other information involved in this application are all obtained after the user's authorization and permission, and the user can customize the authorized single chat / group chat and change the settings at any time.

[0268] It should be noted that the user information and data involved in this application will undergo sensitive information detection before analysis; when sensitive information (such as sensitive keywords, etc.) is detected, desensitization operations will be performed before usage analysis. It should be noted that the social application in this application is completely deployed on the client, and the server uses federated learning to train the AI ​​model and update the model parameters, that is, the server does not retain user information and data, and is only used to train the AI ​​model. It should be noted that in this application, when the user information and data on the client are sent to the server for analysis or processing, the client can send it anonymously to the server, that is, the server analyzes, processes or trains the AI ​​model without knowing the source of the information and data. In summary, the method provided in the embodiment of the present application enables users to quickly obtain key information on the social client by displaying the recommended information content recommended by the AI ​​assistant on the user interface, extracting effective content from a large amount of information, and improving the user's information content processing efficiency on the social client. In addition, the method provided in the embodiment of the present application supports various types of information, supports the access of third-party platforms, expands the form of information content, and further improves the processing efficiency of information content. In addition, according to the method provided in the embodiment of the present application, users can also quickly obtain information summaries or solutions to problems by directly interacting with the AI ​​assistant, thereby improving the efficiency of using the social client.

[0269] The social client (i.e., frontend) involved in this application can be implemented using the client's native system user interface (UI) components and / or a Hypertext Markup Language 5 (HTML5) web frontend, collectively referred to as the frontend. The frontend's software architecture is shown in Table 1 below:

[0270] Table 1: Front-end software architecture

[0271] Among them, the UI layer (View layer) is used to implement the UI presentation of the user interface and the interaction logic of user operations (such as interaction with the AI ​​assistant); the business logic layer (Logic layer) is used to implement instruction operation distribution (such as the distribution of structured operation instructions generated by the AI ​​assistant) and data conversion mapping (such as operation mapping to UI); the data layer (Data layer) is used to implement persistent data access (such as unread social messages of the first account, etc.) and network protocol sending and receiving.

[0272] Based on the architecture shown in the preceding table, the frontend can implement at least one of the following capabilities:

[0273] Implement a card interface containing recommended information content:

[0274] Card content is a mix of rich text, presenting both information and quick actions. Information can be in the form of text, images, audio, and video; actions can be in the form of buttons, hyperlinks, input boxes, and other basic elements or combinations of elements that respond to user touches / clicks or keyboard input to execute actions.

[0275] Implement diverse dynamic cards containing recommended information content:

[0276] Card types are rich and diverse, with differences in information, functions, and styles. Different social function modules (businesses) expand on the blank card to implement their own card templates, presenting information and optional operations unique to that sub-function module.

[0277] Implement unified structured text instructions:

[0278] Different social function modules (businesses) display the functional operations that the module can perform in the form of structured text with unified specifications, including operation name, program function, parameter list, optional parameter values, operation and parameter meanings and other information, so that AI and / or programs can generate structured text based on this as an instruction to express the call of the module's functional operations.

[0279] Through card information and instruction operations, cross-business information aggregation and cross-business function mutual calling can be achieved:

[0280] The dynamic information, possible operations and interface styles that need to be presented in the card are agreed upon in advance between the background and the front-end, and between the front-end functional modules. Variable fields are reserved and encapsulated as data structures. During runtime, data from the background is filled in and presented to the interface. At the same time, instructions from the background data are converted and responded to.

[0281] Implement the dispatch center to gather card data and distribute command operations:

[0282] Each sub-functional module registers the cards and supported instruction operations that it supports and implements with the dispatch center (business logic layer); the dispatch center matches the corresponding cards based on the data received from the background, fills the dynamic data and operation parameters into the business card template, and presents it to the interface; UI cards for different businesses are tiled / stacked on the same page; when the dispatch center generates structured operation instructions based on AI, the user triggers the instruction operation and distributes it to the corresponding sub-functional module function for execution; relevant operation feedback is reflected back to the UI interface.

[0283] FIG8 shows a flowchart of data processing of a method for processing information content provided by an exemplary embodiment of the present application. The subjects involved in FIG8 include users, a dispatch center, business functions, and a backend. The flowchart shown in FIG7 includes steps 401 to 416; wherein, steps 401 to 403 are an initialization process, steps 404 to 410 are an information card presentation process, and steps 411 to 416 are an instruction operation process (steps 411 and 412 are interchangeable steps, i.e., one can be executed at a time).

[0284] Initialization process: From step 401 to step 403, the social function module (business function) registers the card template of the information card and the functional functions supported by the card template to the scheduling center.

[0285] Step 401: The user starts a social client;

[0286] The user launches the social client through a click operation or other triggering operation.

[0287] In some embodiments, the user logs into a first account on the social client.

[0288] Step 402: The dispatch center initiates a registration solicitation for card templates to the business function;

[0289] The dispatch center initiates a registration solicitation for the card template of the information card and the functional functions supported by the card template to each business function.

[0290] Step 403: The business function registers the card template and instruction operation information with the dispatch center;

[0291] Each business function registers the card templates and instruction operation information of the information cards that it supports and implements with the dispatch center. For example, the business function registers the card templates it supports and the functions supported by the card templates with the dispatch center.

[0292] For example, the communication function registers a card template with the dispatch center to summarize unread social messages in a one-on-one chat. This card template includes the sender, number of messages, and summarized message content. Functions supported by this card template include redirecting to the one-on-one chat interface, quick replies, accessing multimedia content, and sharing recommended information.

[0293] For example, the communication function registers a card template with the dispatch center to summarize unread social messages in a group chat. This card template includes the group chat name, sender, number of messages, summarized message content, and to-do items. Functions supported by this card template include jumping to the group chat interface, quick replies, accessing multimedia content, sharing recommended information content, and accessing group to-do items.

[0294] For example, the communication function registers a card template with the dispatch center for reviewing historical social messages in a group chat. The card template includes the name of the group chat, the sender of the message, the time the message was sent, and a summary of the message content. Functions supported by the card template include jumping to the group chat interface and accessing multimedia content.

[0295] For example, the social circle function registers a card template with the dispatch center for obtaining dynamic messages from friends in the social circle. This card template includes the publisher of the dynamic message, the summarized dynamic message content, and the filtered images in the dynamic message. Functions supported by this card template include viewing the original content of the dynamic message, quick replying to the dynamic message, and liking the dynamic message.

[0296] For example, the short video function registers a card template for recommending short videos with the dispatch center. This card template includes the publisher of the short video, the release time of the short video, the title of the short video, and the access link of the short video. Functions supported by this card template include accessing the short video, quickly replying to the short video, and liking the short video.

[0297] For example, the contact function registers a card template for recommending contacts with the dispatch center. The card template includes the account name of the recommended contact and the relationship between the first account and the recommended contact. Functions supported by the card template include accessing the recommended contact's social circle and a link to quickly add friends.

[0298] Information card presentation process: Steps 404 to 410 include backend data acquisition, data processing, mapping data to cards, and assembling and presenting cards.

[0299] Step 404: backend obtains data;

[0300] The background obtains data, such as the unread social messages of the first account.

[0301] In some embodiments, after the background obtains data, the AI ​​model generates recommended information content for the AI ​​assistant function based on the data.

[0302] Step 405: The backend returns the recommended information and instruction operations generated by AI;

[0303] The backend returns AI-generated recommended information and instruction operations to the dispatch center.

[0304] The processing of the data returned by the backend to the dispatch center includes general processing by the dispatch center (step 406) and private processing registered by the social function module (business function) (steps 407 to 408). Step 406 and steps 407 to 408 are executed in no particular order.

[0305] Step 406: The dispatch center performs data processing and service matching;

[0306] The dispatch center processes and matches the recommended information and instruction operations obtained from the backend. Specifically, the dispatch center receives recommended information from the backend and matches it to various business functions based on the data type or card template of the information card. It also extracts the structured instructions generated by the AI ​​model and generates corresponding action buttons / input boxes / hyperlinks.

[0307] In some embodiments, the data processing performed by the dispatch center also includes removing isolated text, redundant blank characters, etc.

[0308] Step 407: The business function performs data processing;

[0309] The dispatch center sends the recommended information obtained from the backend to each business function, allowing each business function to perform the private processing registered by the business function. For example, it removes isolated text and redundant whitespace characters based on the card template registered by the business function.

[0310] Step 408: The business function returns a result;

[0311] After each business function privately processes the recommended information content, it sends the processed result data to the dispatch center.

[0312] Step 409: The dispatch center maps the data to the information card;

[0313] The dispatch center maps the processed data of the recommended information content to the information card, that is, the dispatch center instantiates the UI (including the information card and the operation button).

[0314] Exemplarily, the dispatch center matches the processed recommended information content data to the corresponding card template View, and maps the data Model to the view ViewModel.

[0315] Step 410: Presenting an information card;

[0316] After mapping the data of the recommended information content to the information card, the dispatch center presents the information card to the user, that is, the information card including the recommended information content is displayed on the AI ​​assistant interface.

[0317] Instruction operation process: Steps 411 to 416, including triggering instruction operation, matching corresponding program calls, verifying / correcting parameters, function calls, and reflecting the result feedback to the AI ​​assistant interface.

[0318] There are two ways to trigger the instruction operation. The first is that the program automatically executes the instruction operation automatically extracted from the AI ​​results returned from the background (i.e., step 411), and the second is that the user actively clicks on the interactive element containing the instruction operation (i.e., step 412).

[0319] Step 411: The dispatch center extracts the instructions contained in the recommendation information generated by the AI;

[0320] The dispatch center automatically extracts the instructions contained in the recommended information content generated by AI.

[0321] Step 412: User actively interacts to trigger the instruction;

[0322] The user actively triggers the interactive elements that contain command operations, such as clicking the controls on the AI ​​assistant interface to trigger the command.

[0323] Step 413: The dispatch center matches the instruction to the corresponding program call and checks / corrects the parameters;

[0324] After the instruction is triggered, the dispatch center matches the instruction to the corresponding program call and verifies and / or corrects the parameters.

[0325] For example, after receiving an operation instruction triggered by a user or automatically extracted by AI, the dispatch center matches it to the corresponding business function based on the registration information of each business function and converts the instruction into a program call. Due to deviations or errors in the AI-generated content or structured syntax, the content needs to be verified and corrected, and the call is initiated after the filled parameters are verified / corrected.

[0326] Step 414: The business function initiates a function call;

[0327] Function calls in business modules are derived from fixed templates of cards containing recommended information, or dynamically generated by extracting structured instructions from the results returned by the backend AI. Call parameters are derived from AI recommendations (i.e., using AI models to optimize parameters) and / or user-specified (i.e., user-defined).

[0328] Illustratively, the business function initiates a function call that it supports.

[0329] Step 415: The business function feeds back the result;

[0330] After the function is called, the business function returns its result to the dispatch center.

[0331] Step 416: Reflect to the AI ​​assistant interface.

[0332] The dispatch center reflects the function call results of the received business functions to the AI ​​assistant interface, that is, displays the recommended information content of the AI ​​assistant on the AI ​​assistant interface.

[0333] The background involved in this application includes the business logic layer, algorithm layer, and recommendation layer; the input source of the background is the group chat / contact authorized by the user.

[0334] The business logic layer is used to implement at least one of the following functions:

[0335] Based on the group chat / contact selected by the user, read the user's unread group chat messages, content mentioning the user in the group chat, contact messages, dynamic messages, etc. in the database;

[0336] Asynchronously parse the message content of each group chat / contact, including the sender, sending time, and content (including text, pictures, voice, video, files, and links) of each message;

[0337] The parsed content is sent to the algorithm layer, which includes algorithms that use AI models to generate recommended information content. The algorithm layer appropriately summarizes these messages and possible user responses and returns the content to the business logic layer.

[0338] The content returned by the algorithm layer is pushed to the recommendation layer, which then ranks and recommends it to users. Recommendations include, but are not limited to, the priority of recommended information, links that users may be interested in, and group chats that users may be interested in.

[0339] The recommended information content is returned to the social client through the business logic layer.

[0340] The algorithm layer is used to summarize and predict likely user responses based on the content of messages sent by the business logic layer. Message sources include, but are not limited to, contact messages, group chat content mentioning the primary account (@firstaccount), and group chat content mentioning all members (@all). Message formats include, but are not limited to, text, images, voice, video, files, and links.

[0341] Among them, the recommendation layer is used to recommend the content of the algorithm layer based on the content that the user is interested in, and additionally recommend some public links, groups, functions, etc. that the user may be interested in.

[0342] Figure 9 shows a timing diagram of a method for processing information content provided by an exemplary embodiment of the present application. The entities involved in Figure 9 include users, AI assistant interface, business logic layer, algorithm layer, recommendation layer, and database.

[0343] Step 501: The user enters the message content;

[0344] The user enters the message content in the AI ​​assistant interface, such as asking the AI ​​assistant to summarize the unread messages in the group chat / contacts.

[0345] Step 502: The AI ​​assistant interface requests authorization of unread messages for groups and contacts;

[0346] After receiving the user's input message, the AI ​​assistant interface needs to request authorization from the business logic layer to obtain the unread messages in the corresponding group chat / contact.

[0347] Step 503: The business logic layer reads unread messages;

[0348] The business logic layer reads unread messages in authorized group chats / contacts from the database, including content mentioning users in group chats, contact messages, and other content.

[0349] Step 504: the database returns unread messages;

[0350] The unread messages in the authorized group chat / contact in the database are returned to the business logic layer.

[0351] Step 505: The business logic layer parses the message content;

[0352] The business logic layer asynchronously parses the message content of each group chat / contact obtained in step 504, including the sender, sending time, and sending content (including text, pictures, voice, video, files and links) of each message; and then sends the parsed content to the algorithm layer.

[0353] Step 506: The algorithm layer summarizes the message and predicts the user's response;

[0354] The algorithm layer analyzes the message content based on the business logic layer, summarizes it according to the AI ​​language model, and predicts the responses that users may adopt.

[0355] Step 507: The algorithm layer returns a summary message and a predicted response;

[0356] The algorithm layer returns the summarized messages and predicted responses (i.e., the output results of the AI ​​language model) to the business logic layer.

[0357] Step 508: The business logic layer sends a summary message and a predicted reply;

[0358] The business logic layer pushes the content returned by the algorithm layer to the recommendation layer, which then sorts and recommends the content to users.

[0359] Step 509: The recommendation layer recommends information content in order based on user interests;

[0360] The recommendation layer ranks the recommended information content (i.e., summary messages and predicted replies) output by the AI ​​language model. Recommendations include, but are not limited to, the order in which recommended information is returned (i.e., the priority displayed on the AI ​​assistant interface), links that may be of interest to the user, and group chats that may be of interest to the user.

[0361] The sorting algorithm of the recommendation layer can be customized by the user, or optimized for the user using an AI model.

[0362] In addition, the recommendation layer recommends additional public links, groups, functions, etc. that users may be interested in based on user information.

[0363] Step 510: The recommendation layer returns the recommended information content;

[0364] The recommendation layer returns the sorted recommendation information content to the business logic layer.

[0365] Step 511: The business logic layer returns the recommended information content;

[0366] After obtaining the recommended information content returned by the recommendation layer, the business logic layer pushes it to the AI ​​assistant interface.

[0367] Step 512: The AI ​​assistant interface displays the recommended information content.

[0368] The sorted recommended information content is displayed on the AI ​​assistant interface.

[0369] Figure 10 shows a flowchart of a method for processing information content provided by an exemplary embodiment of the present application. This embodiment illustrates the method by executing the terminal device shown in Figure 5, or a client or server running on the terminal device. For example, the terminal device runs a social client logged in with a first account. The method includes at least one of the following steps 620 to 660.

[0370] Step 620: Obtain information content of the first account in at least one business function;

[0371] The first account is the user account currently logged in on the social client.

[0372] The social client includes at least one business function. Among them, business functions refer to functions designed to achieve online social purposes, including at least one of the following: communication function (including one-on-one chat, group chat, etc.), contact function, social circle function, and short video function.

[0373] For example, the types of information in at least one business function may include the following types:

[0374] Text messages: such as text messages, blogs, emails, etc.

[0375] Graphic information: such as photographs, paintings, illustrations, etc.

[0376] Video information: such as TV shows, movies, short videos, etc.

[0377] Audio information: such as songs, broadcasts, radio stations, etc.

[0378] Social network information: such as personal homepage, social circles, social platforms, etc.;

[0379] Game information: such as online games, mobile games, etc.

[0380] Location information: such as GPS positioning, map navigation, etc.

[0381] Personal information: such as basic personal information, interests, personality traits, ability levels, achievements, etc.

[0382] Group information: such as group membership, goals and tasks, organizational structure, cultural atmosphere, and behavioral norms;

[0383] Emotional information: such as the emotional state, attitude, preferences, and satisfaction ratings of individuals or groups;

[0384] Behavioral information: such as individual or group behavior patterns, behavioral outcomes, and behavioral impacts;

[0385] Environmental information: such as the physical, social, and cultural environment of an individual or group.

[0386] In some embodiments, the information content may be unread social messages of the first account, social messages involving the first account in a group chat, social messages involving all members in a group chat, contacts of the first account, group chats of the first account, social dynamics of the first account and user accounts on its social chain, short videos posted by the first account and user accounts on its social chain, interest tags of the first account and user accounts on its social chain, etc.

[0387] In some embodiments, information content of the first account in at least one business function is obtained from a database, for example, unread social messages of the first account are obtained from a database.

[0388] In some embodiments, an interest tag library is constructed for each user account, wherein the interest tags in the interest tag library are derived from the user account's use of the social client. Based on the interest tags of the first account, information content related to the interest tags in at least one business function is obtained.

[0389] Step 640: Using the AI ​​assistant, filter or summarize the information content of the first account in at least one business function to obtain recommended information content;

[0390] An AI assistant is a recommendation service that filters or summarizes information content based at least on an AI model. The AI ​​model used by the AI ​​assistant may be a language model, such as LLM or GLM, which is trained on a large amount of text data and is intended to understand and generate human language. It can perform a variety of tasks such as text summarization, translation, and sentiment analysis. Among them, LLM refers to a language model whose model parameters exceed a first threshold, or whose training data exceeds a second threshold, or whose computational amount exceeds a third threshold, wherein the first threshold, the second threshold, and the third threshold are all values ​​in the hundreds of billions. In some embodiments, the AI ​​model used by the AI ​​assistant may be a model for text-to-image, image-to-text, text-to-video, and the like. Taking the AI ​​assistant using a large language model as an example, the AI ​​services it provides include summarizing unread social messages, optimizing social networks, reviewing historical social messages, answering questions, recommending functions, emotional companionship, and so on. This application is not limited to this.

[0391] The recommended information content recommended by the AI ​​assistant for the first account can be generated entirely by the AI ​​model on which the AI ​​assistant is based; or it can be a combination of recommended information content generated by the AI ​​model and recommended information content generated by traditional recommendation algorithms. This application does not limit all recommended information content to being generated by the AI ​​model used by the AI ​​assistant.

[0392] Recommended information is obtained by the AI ​​assistant through screening or summarizing information from at least one business function. Screening refers to extracting information from the at least one business function without secondary processing; summarizing refers to not directly selecting parts of the original information, but rather forming summarized information through secondary processing, such as an abstract or summary.

[0393] The recommended information includes at least one of the following:

[0394] First recommended information content is generated by filtering or summarizing the unread social messages of the first account; for example, the unread social messages in the chat list are filtered or summarized to form the first recommended information content. The unread social messages may be unread social messages in a single chat, or unread social messages in a group chat, or unread social messages in a single chat or group chat designated by the first account, or unread social messages in a single chat or group chat where the number of unread social messages exceeds a threshold.

[0395] The second recommended information content is obtained by filtering or summarizing the group chat messages or to-do items in the workflow of the first account; for example, the second recommended information content includes tasks scheduled in the work group chat or messages that need to be replied to; for another example, the second recommended information content includes to-do items such as group polls, group files, and group announcements; for another example, the second recommended information content includes messages in the group chat that mention the first account or messages in the group chat that mention all members.

[0396] Third-party recommended information content, after filtering or summarizing candidate information according to the first account's preset rules; that is, users can customize recommended information content. For example, the first account can pre-set the objects for the AI ​​assistant to filter or summarize, as well as the time range and information type. For example, filtering or summarizing document-type information from last year; or filtering or summarizing dynamic messages from last month's dynamic space.

[0397] The fourth recommended information content is obtained by filtering or summarizing the dynamic information of friends in the social network of the first account; for example, the fourth recommended information content is the dynamic updates of friends in the social circle; for another example, the fourth recommended information content is a friend's birthday reminder, etc.

[0398] The fifth recommended information content is randomly recommended by the first account; for example, the fifth recommended information content is hot news recommended by the first account; for another example, the fifth recommended information content is information content that the friends of the first account follow.

[0399] Fifth recommended information content that is filtered or summarized based on information content that may be of potential interest to the first account; for example, interest tags of the first account are determined based on topics that the first account follows, and information content that may be of interest to the first account is determined based on the interest tags, and is filtered or summarized and recommended to the first account after being recommended to the first account; for another example, information content of the entire online platform on that day is recommended to the first account, such as filtering or summarizing all popular short videos of that day in the short video function.

[0400] · Sixth recommended information content after screening or summarizing information content with a high probability of being shared by the first account; for example, based on the chat content between the first account and its friends, the first account's interest tags or hot information of interest are determined, and the information content related to the interest tags or hot information of interest is screened or summarized and recommended to the first account; for another example, the first account is supported to customize information content with a high probability of being shared and authorized to share it with friends or group chats.

[0401] The seventh recommended information content is obtained by screening or summarizing interest groups that may be of potential interest to the first account; for example, candidate interest groups that may be of interest to the first account are determined based on the interest tags of the first account, and the screened or summarized interest groups are recommended to the first account as the seventh recommended information content.

[0402] The eighth recommended information content is obtained by filtering or summarizing POI information corresponding to the first account's current geographic location. POI refers to point data on an internet electronic map, including four attributes: name, address, coordinates, and category. For example, based on the first account's current geographic location, information about businesses and transportation services near the current location that may be of interest to the first account is filtered or summarized and recommended to the first account as the eighth recommended information content.

[0403] Ninth recommended information content after screening or summarizing unfamiliar accounts that may have potential interest in the first account; for example, candidate accounts with the same interest tags as the first account are identified, and the candidate accounts may have potential interest in the first account, and the screened or summarized candidate accounts may be recommended to the first account as the ninth recommended information content.

[0404] The tenth recommended information content is selected or summarized from AI tools that the first account may be interested in. AI tools are tools developed based on AI technology to solve problems. For example, based on the first account's interest tags, candidate AI tools that the first account may be interested in are identified and recommended to the first account as the tenth recommended information content. For another example, if the first account's interest tag is painting, an AI painting tool is recommended to the first account and a quick access is provided.

[0405] · An eleventh recommended information content after screening or summarizing games that may be of potential interest to the first account; for example, determining candidate games that may be of potential interest to the first account, and recommending the screened or summarized games as the eleventh recommended information content to the first account.

[0406] The twelfth recommended information content is obtained by filtering or summarizing relevant information of third-party applications bound to the first account; for example, the preferential information of a food delivery app bound to the first account is filtered or summarized and recommended to the first account as the twelfth recommended information content.

[0407] Exemplarily, the AI ​​model based on the AI ​​assistant is called to filter or summarize the information content in at least one business function to obtain recommended information content.

[0408] Step 660: Send the recommended information content to the social client where the first account is located.

[0409] Exemplarily, after obtaining the recommended information content generated by the AI ​​model based on which the AI ​​assistant is based, the recommended information content is sent to the first account, and the recommended information content is displayed on the AI ​​assistant interface of the first account.

[0410] In some embodiments, while sending the recommended information content to the first account, the card template registered for the business function corresponding to the recommended information content is also sent; after the recommended information content is filled into the card template, it is displayed on the AI ​​assistant interface of the first account.

[0411] In summary, the method provided in the embodiments of the present application, by obtaining information content from a social client and determining recommended information content based thereon, enables users to quickly obtain key information on the social client, extract effective content from a large amount of information, and improve the efficiency of users in processing information content on the social client.

[0412] The information content processing method involved in this application has a wide range of applications in various scenarios. Take the customer service scenario of the e-commerce industry as an example. Since it connects and communicates with a large number of customers every day, its social client will receive a large number of messages. However, the information density of these messages is likely not large. For example, many messages can actually be summarized in one sentence; and most of the content of these messages is similar, such as querying express information, urging delivery, requesting returns, etc. In this scenario, the information content processing method of this application will improve the processing efficiency of customer service.

[0413] Exemplarily, the system logs in to a customer service representative's first account; obtains recommended information content recommended by the AI ​​assistant for the customer service representative's first account, where the recommended information content is obtained by the AI ​​assistant after filtering or summarizing information content related to at least one business function of the first account in the social client; and displays the recommended information content. For example, after the customer service representative logs in to the first account, the system obtains recommended information content recommended by the AI ​​assistant for the customer service representative, where the recommended information content is a summary of unread messages, and displays the recommended information content on the AI ​​assistant interface of the first account.

[0414] Exemplarily, at least two information cards are displayed, each of which is used to display one or a group of recommended information content recommended by the AI ​​assistant for the first account. That is, the recommended information content is displayed on the AI ​​assistant interface in the form of information cards containing the recommended information content; each information card displays a summary of messages from a customer, or each message card displays the same type of requests from different customers (for example, return requests from different customers, etc.).

[0415] Exemplarily, the at least two information cards are displayed in a tiled manner; wherein the tile order of the at least two information cards is determined based on the recommendation priorities of the at least two information cards.

[0416] Exemplarily, the at least two information cards are displayed in a stacked manner; wherein the stacking order of the at least two information cards is determined based on the recommendation priorities of the at least two information cards.

[0417] That is, multiple information cards can be displayed in a tiled (non-overlapping) or stacked (partially or fully overlapping) manner; the display order is determined based on the recommendation priority, and the recommendation priority is user-defined or AI-optimized.

[0418] Exemplarily, in response to a swipe operation on a first information card among at least two information cards, the first information card is canceled and a second information card is displayed; wherein the second information card is an information card that follows the first information card in a stacking order or a tiled order. That is, when the information cards are displayed in a stacked or tiled manner, a swipe operation switches to displaying a different information card.

[0419] Illustratively, the recommendation information content of the first account recommended to the customer service includes at least one of the following:

[0420] The first recommended information content after filtering or summarizing the unread social messages of the first account;

[0421] Second recommended information content that is filtered or summarized from the group chat messages or to-do items in the workflow of the first account;

[0422] The third recommended information content is obtained by screening or summarizing the candidate information according to the preset rules of the first account;

[0423] Fourth recommended information content that is obtained by screening or summarizing dynamic information of friends in the social network of the first account;

[0424] The fifth recommended information content randomly recommended for the first account;

[0425] Fifth recommended information content after screening or summarizing information content that may be of potential interest to the first account;

[0426] The sixth recommended information content is obtained by screening or summarizing the information content that is likely to be shared by the first account;

[0427] The seventh recommended information content is obtained by screening or summarizing interest groups that may be potentially interested in the first account;

[0428] Eighth recommended information content obtained by filtering or summarizing POI information corresponding to the current geographic location of the first account;

[0429] The ninth recommended information content is obtained by screening or summarizing unfamiliar accounts that may be potentially interested in the first account;

[0430] The tenth recommended information content selected or summarized by the AI ​​tool that may be of potential interest to the first account;

[0431] · Eleventh recommended information content after screening or summarizing games that the first account may be interested in;

[0432] The twelfth recommended information content is obtained by filtering or summarizing relevant information of the third-party application bound to the first account.

[0433] For example, in response to a first action on a recommended message, a user interface for the function to which the recommended message belongs is displayed, the user interface including the original message content corresponding to the recommended message. That is, a customer service representative can click on a recommended message to be redirected to the original interface of the recommended message. For example, by clicking on a summary of a customer's unread messages, the customer service representative can be redirected to a chat interface with the customer.

[0434] For example, the recommended information is derived from a social message from a second account. In response to a second action on the recommended information, the first account's reply to the recommended information is retrieved, and a reply message containing the reply is sent to the second account. In other words, the customer service representative can directly enter and send a reply message to the second account on the AI ​​assistant interface.

[0435] For example, the recommended information content originates from a social message of a third account. During the display of the recommended information content, a quick reply content generated for the recommended information content is displayed. In response to a third action on the quick reply content, a reply message is sent to the third account, carrying the quick reply content. That is, the AI ​​assistant interface also displays the quick reply message recommended to the customer service representative, who can, in some embodiments, quickly reply by clicking on the quick reply message on the AI ​​assistant interface.

[0436] For example, if the recommended information comes from a social message from a fourth account and the social message is associated with a to-do item, during the display of the recommended information, an access portal for the to-do item is displayed; in response to a fourth operation on the access portal, an interface for processing the to-do item is displayed; the to-do item includes at least one of an electronic document, a group poll, and a third-party application. For example, for a to-do item (such as filling out a return form), a link to the return form is displayed on the AI ​​assistant interface, allowing customer service to access it with one click.

[0437] For example, if the recommended information is associated with multimedia content, an access portal to the multimedia content is displayed during the display of the recommended information. In response to a fifth operation on the access portal, a multimedia content interface for the multimedia content is displayed. The multimedia content includes at least one of images, audio, video, and games. For example, if the recommended information is associated with a product display image, an access portal to the product's image display page is displayed on the AI ​​assistant interface.

[0438] For example, during the display of recommended information, a sharing entry is displayed for sharing the recommended information with a fifth account or group, where the fifth account or group was recommended by the AI ​​assistant in the social relationship chain of the first account; in response to a sixth operation on the sharing entry, the recommended information is shared with the fifth account or group. For example, a customer service AI assistant interface displays a sharing entry for sharing products, allowing the customer service representative to quickly share products they may purchase with potential customers.

[0439] Exemplarily, a command message sent from a first account to an AI assistant is received; and a response generated by the AI ​​assistant in response to the command message is displayed. The response is obtained by the AI ​​assistant filtering or summarizing information from at least one business function based on the command message. For example, a customer service representative can ask the AI ​​assistant a summary of a conversation with a customer, and the AI ​​assistant will generate a response and display it on the AI ​​assistant interface.

[0440] In some embodiments, the command message sent by the first account to the AI ​​assistant may include the following types:

[0441] Review the chat content in the single chat:

[0442] Receive a first command message sent by a first account to the AI ​​assistant, where the first command message is used to inquire about the chat content between the first account and the seventh account; display a first reply content generated by the AI ​​assistant to the first command message, where the first reply content is obtained after the AI ​​assistant summarizes the chat content between the first account and the seventh account.

[0443] Recall the chat content in the group chat:

[0444] Receive a second command message sent by the first account to the AI ​​assistant, where the second command message is used to ask questions about the chat content of the chat group to which the first account belongs; display a second reply content generated by the AI ​​assistant to the second command message, where the second reply content is obtained after the AI ​​assistant summarizes the chat content of the chat group to which the first account belongs.

[0445] Get friends’ updates:

[0446] Receive a third command message sent by the first account to the AI ​​assistant, where the third command message is used to ask questions about the content of interest of the eighth account, which is a friend of the first account; display the third reply content generated by the AI ​​assistant to the third command message, where the third reply content is obtained after the AI ​​assistant summarizes the friend dynamic information of the eighth account.

[0447] Get keyword information:

[0448] Receive a fourth command message sent by the first account to the AI ​​assistant, where the fourth command message is used to ask questions about network information or social chain information associated with the first keyword; display the fourth reply content generated by the AI ​​assistant to the fourth command message, where the fourth reply content is the search result after the AI ​​assistant searches for network information or social chain information associated with the first keyword.

[0449] Quick use function:

[0450] Receive the fifth command message sent by the first account to the AI ​​assistant, where the fifth command message is used to use the first function; display the fifth reply content generated by the AI ​​assistant for the fifth command message, where the fifth reply content is the function entrance of the first function fed back by the AI ​​assistant, or the call result after the AI ​​assistant calls the first function.

[0451] For example, the function entry of the AI ​​assistant function is displayed; in response to a trigger operation on the function entry, the recommended information content recommended by the AI ​​assistant for the first account is displayed. That is, the customer service activates the AI ​​assistant function by clicking on the function entry of the AI ​​assistant function.

[0452] For example, each information card corresponds to a business function; a card template registered for the business function corresponding to the recommended information content is obtained; the recommended information content is entered into the card template to obtain the information card corresponding to the recommended information content. For example, after-sales requests, group chat messages, and a customer's social circle each correspond to a different card template. The recommended information content belonging to each business function is entered into the corresponding card template to obtain the information card corresponding to the recommended information content.

[0453] Exemplarily, the social client includes a program function corresponding to the AI ​​assistant, and receives a card template registered for at least one business function through the program function corresponding to the AI ​​assistant.

[0454] Exemplarily, the social client includes a program function corresponding to the AI ​​assistant, and receives a function function supported by a card template registered with at least one business function through the program function corresponding to the AI ​​assistant, and the function function is used to execute a response function corresponding to the recommended information content when called.

[0455] Exemplarily, the interest tags and weights of the interest tags of the first account are obtained; based on the target interest tags matching the recommended information content and the weights of the target interest tags, the recommendation priorities of at least two information cards are determined; based on the priorities of the at least two information cards, the sorting order of the at least two information cards is determined.

[0456] Exemplarily, the information content of the first account in at least one business function is obtained; the information content in the at least one business function is filtered or summarized by an AI assistant to obtain recommended information content, and the AI ​​assistant is a recommendation service that filters or summarizes information content based at least on an AI model; and the recommended information content is sent to the social client where the first account is located.

[0457] The following are device embodiments of the present application, which can be used to implement the method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.

[0458] FIG11 shows a block diagram of an information content processing device provided by an exemplary embodiment of the present application. The device may be a terminal device or may be provided in a terminal device. The device includes:

[0459] In some embodiments, the apparatus includes a login module 710. The login module 710 is used to log in to the first account;

[0460] An acquisition module 720 is configured to acquire recommended information content recommended by the AI ​​assistant for the first account, where the recommended information content is obtained by the AI ​​assistant after screening or summarizing the information content of the first account in the at least one business function;

[0461] The display module 740 is configured to display the recommended information content.

[0462] In some embodiments, a social client is logged in to the device, and the social client includes multiple business functions, at least two of the multiple business functions are located at different human-computer interaction interface levels; the acquisition module 720 is used to obtain the recommended information content recommended by the AI ​​assistant for the first account, and the recommended information content includes the information content obtained by the AI ​​assistant after screening or summarizing the information content of the first account in the first business function, and the first business function is located at the first human-computer interaction interface level; the display module 740 is used to display the recommended information content at the second human-computer interaction interface level; wherein, the second human-computer interaction interface level is higher than the first human-computer interaction interface level.

[0463] In some embodiments, the display module 740 is used to display at least two information cards at the second human-computer interaction interface level, and each of the at least two information cards is used to display one or a group of recommended information contents recommended by the AI ​​assistant for the first account.

[0464] In some embodiments, the display module 740 is used to display the at least two information cards in a tiled manner at the second human-computer interaction interface level; wherein the tile order of the at least two information cards is determined based on the recommendation priority of the at least two information cards.

[0465] In some embodiments, the display module 740 is used to display the at least two information cards in a stacked manner at the second human-computer interaction interface level; wherein the stacking order of the at least two information cards is determined based on the recommendation priority of the at least two information cards.

[0466] In some embodiments, the display module 740 is used to cancel the display of the first information card and display the second information card in response to a sliding operation on the first information card among the at least two information cards; wherein, the second information card is an information card that is arranged after the first information card in a stacking order or a tiling order.

[0467] In some embodiments, the recommended information content includes at least one of the following: first recommended information content that is filtered or summarized from unread social messages of the first account; second recommended information content that is filtered or summarized from group chat messages or to-do items in the workflow of the first account; third recommended information content that is filtered or summarized from candidate information according to preset rules of the first account; fourth recommended information content that is filtered or summarized from dynamic information of friends in the social network of the first account; fifth recommended information content that is randomly recommended for the first account; fifth recommended information content that is filtered or summarized from information content that is potentially of interest to the first account; sixth recommended information content that is filtered or summarized from information content that is likely to be shared by the first account; seventh recommended information content that is filtered or summarized from interest groups that are potentially of interest to the first account; eighth recommended information content that is filtered or summarized from POI information corresponding to the current geographic location of the first account; ninth recommended information content that is filtered or summarized from unfamiliar accounts that are potentially of interest to the first account; tenth recommended information content that is filtered or summarized from AI tools that are potentially of interest to the first account; eleventh recommended information content that is filtered or summarized from games that are potentially of interest to the first account; and twelfth recommended information content that is filtered or summarized from relevant information of third-party applications bound to the first account.

[0468] In some embodiments, the display module 740 is configured to display a quick operation entry associated with the recommended information content; and execute a quick processing function corresponding to the quick operation entry in response to an operation on the quick operation entry.

[0469] In some embodiments, the quick operation entry is a jump entry for jumping to the functional user interface of the function to which the recommended information content belongs; the display module 740 is used to display the functional user interface of the function to which the recommended information content belongs in response to a first operation on the quick operation entry, and the functional user interface includes the original information content corresponding to the recommended information content.

[0470] In some embodiments, the recommended information content originates from a social message of a second account, and the quick operation entry is a reply entry for replying to the second account; the display module 740 is used to obtain the reply content of the first account in response to a second operation on the quick operation entry to reply to the recommended information content; and send a reply message to the second account, wherein the reply message carries the reply content.

[0471] In some embodiments, the recommended information content originates from a social message of a third account, and the quick operation entry is a reply entry for replying to the third account using the quick reply content generated for the recommended information content; the display module 740 is used to send a reply message to the third account in response to the third operation of the quick operation entry, and the reply message carries the quick reply content.

[0472] In some embodiments, the recommended information content originates from a social message of a fourth account and the social message is associated with a to-do item, and the quick operation entry is a jump entry for jumping to an item processing interface of the to-do item; the display module 740 is used to display the item processing interface of the to-do item in response to a fourth operation of the quick operation entry; wherein, the to-do item includes at least one of an electronic document, a group vote, and a third-party application.

[0473] In some embodiments, the recommended information content is associated with multimedia content, and the quick operation entrance is an access entrance for accessing the multimedia content; the display module 740 is used to display the multimedia content interface of the multimedia content in response to the fifth operation of the quick operation entrance; wherein, the multimedia content includes at least one of pictures, audio, video, and games.

[0474] In some embodiments, the quick operation entrance is a sharing entrance for sharing the recommended information content to a fifth account or group; the display module 740 is used to share the recommended information content to the fifth account or group in response to the sixth operation of the quick operation entrance, and the fifth account or group is recommended by the AI ​​assistant in the social relationship chain of the first account.

[0475] In some embodiments, the quick operation entry is an entry for adding a sixth account or group associated with the recommended information content; the display module 740 is used to add the sixth account as a friend or join a group in response to a seventh operation of the quick operation entry.

[0476] In some embodiments, the display module 740 is used to receive a command message sent by the first account to the AI ​​assistant; and display the reply content generated by the AI ​​assistant in response to the command message, where the reply content is obtained by the AI ​​assistant after screening or summarizing the information content of the first account in the at least one social function based on the command message.

[0477] In some embodiments, the display module 740 is used to receive a first command message sent by the first account to the AI ​​assistant, where the first command message is used to ask about the chat content between the first account and the seventh account; and display a first reply content generated by the AI ​​assistant to the first command message, where the first reply content is obtained after the AI ​​assistant screens or summarizes the chat content between the first account and the seventh account.

[0478] In some embodiments, the display module 740 is used to receive a second command message sent by the first account to the AI ​​assistant, where the second command message is used to ask questions about the chat content of the chat group to which the first account belongs; and display a second reply content generated by the AI ​​assistant to the second command message, where the second reply content is obtained by the AI ​​assistant after screening or summarizing the chat content of the chat group to which the first account belongs.

[0479] In some embodiments, the display module 740 is used to receive a third command message sent by the first account to the AI ​​assistant, where the third command message is used to ask questions about the content of interest of an eighth account that is a friend of the first account; and display a third reply content generated by the AI ​​assistant to the third command message, where the third reply content is obtained by the AI ​​assistant after screening or summarizing the dynamic information of the friends of the eighth account.

[0480] In some embodiments, the display module 740 is used to receive a fourth command message sent by the first account to the AI ​​assistant, where the fourth command message is used to ask questions about network information or social chain information associated with the first keyword; and display a fourth reply content generated by the AI ​​assistant to the fourth command message, where the fourth reply content is the search result obtained by the AI ​​assistant after searching for network information or social chain information associated with the first keyword.

[0481] In some embodiments, the display module 740 is used to receive a fifth command message sent by the first account to the AI ​​assistant, where the fifth command message is used to use the first function; and display a fifth reply content generated by the AI ​​assistant to the fifth command message, where the fifth reply content is the function entrance of the first function fed back by the AI ​​assistant, or the call result after the AI ​​assistant calls the first function.

[0482] In some embodiments, the display module 740 is used to display the function entrance of the AI ​​assistant function; in response to a trigger operation on the function entrance, the recommended information content recommended by the AI ​​assistant for the first account is displayed.

[0483] In some embodiments, each of the information cards corresponds to a business function; the acquisition module 720 is used to obtain the card template registered for the business function corresponding to the recommended information content; fill the recommended information content into the card template to obtain the information card corresponding to the recommended information content.

[0484] In some embodiments, the social client includes a program function corresponding to the AI ​​assistant, and the acquisition module 720 is used to receive the card template registered for the at least one business function through the program function corresponding to the AI ​​assistant.

[0485] In some embodiments, the social client includes a program function corresponding to the AI ​​assistant, and the acquisition module 720 is used to receive the function function supported by the card template registered by the at least one business function through the program function corresponding to the AI ​​assistant, and the function function is used to execute a response function corresponding to the recommended information content when called.

[0486] FIG12 shows a block diagram of an information content processing device provided by an exemplary embodiment of the present application. The device may be a server or may be provided in a server. The device includes:

[0487] An acquisition module 820 is configured to acquire information content of the first account in at least one business function;

[0488] Determining module 840 is configured to use an AI assistant to screen or summarize information content of the first account in at least one business function to obtain recommended information content recommended by the AI ​​assistant for the first account, where the AI ​​assistant is a recommendation service that screens or summarizes information content based at least on an AI model;

[0489] The sending module 860 is configured to send the recommended information content to the social client where the first account is located.

[0490] FIG13 is a schematic diagram of the structure of a computer device according to an exemplary embodiment. The computer device may include a terminal device or a server. The computer device 1300 includes a central processing unit (CPU) 1301, a system memory 1304 including a random access memory (RAM) 1302 and a read-only memory (ROM) 1303, and a system bus 1305 connecting the system memory 1304 and the CPU 1301. In some embodiments, the computer device 1300 may also include a basic input / output system (I / O system) 1306 for facilitating information transmission between various components within the computer device, and a mass storage device 1307 for storing an operating system 1313, application programs 1314, and other program modules 1315.

[0491] The basic input / output system 1306 includes a display 1308 for displaying information and an input device 1309, such as a mouse or keyboard, for user input. Both the display 1308 and the input device 1309 are connected to the central processing unit 1301 via an input / output controller 1310 connected to the system bus 1305. The basic input / output system 1306 may also include an input / output controller 1310 for receiving and processing input from a variety of other devices, such as a keyboard, mouse, or electronic stylus. Similarly, the input / output controller 1310 also provides output to a display screen, printer, or other types of output devices.

[0492] The mass storage device 1307 is connected to the central processing unit 1301 via a mass storage controller (not shown) connected to the system bus 1305. The mass storage device 1307 and its associated computer-readable medium provide non-volatile storage for the computer device 1300. In other words, the mass storage device 1307 may include computer-readable media (not shown) such as a hard disk or a CD-ROM drive.

[0493] Without loss of generality, the computer device readable medium may include computer device storage media and communication media. Computer device storage media include volatile and non-volatile, removable and non-removable media implemented by any method or technology for storing information such as computer device readable instructions, data structures, program modules or other data. Computer device storage media include RAM, ROM, Erasable Programmable Read Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), CD-ROM, Digital Video Disc (DVD) or other optical storage, tape cassettes, magnetic tapes, disk storage or other magnetic storage devices. Of course, those skilled in the art will appreciate that the computer device storage media are not limited to the above-mentioned ones. The above-mentioned system memory 1304 and mass storage device 1307 can be collectively referred to as memory.

[0494] According to various embodiments of the present disclosure, the computer device 1300 may also be connected to a remote computer device on a network such as the Internet for operation. That is, the computer device 1300 may be connected to the network 1311 via the network interface unit 1312 connected to the system bus 1305, or the network interface unit 1312 may be used to connect to other types of networks or remote computer device systems (not shown).

[0495] The memory further includes one or more programs, which are stored in the memory. The central processing unit 1301 implements all or part of the steps of the above-mentioned information content processing method by executing the one or more programs.

[0496] The present application provides a computer-readable storage medium, in which at least one program is stored. The at least one program is loaded by the processor and executes the information content processing method provided by the above-mentioned various method embodiments.

[0497] The present application also provides a computer program product, in which at least one program is stored. The at least one program is loaded by the processor and executes the information content processing methods provided by the above-mentioned various method embodiments.

[0498] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0499] Those skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware, or by a program to instruct the relevant hardware, and the program may be stored in a computer-readable storage medium, which may be a read-only memory, a disk, or an optical disk, etc.

[0500] The above description is merely an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for processing information content, the method being executed by a terminal device, wherein a social client logged in with a first account is running in the terminal device, the social client including at least one business function, the method comprising: Obtaining recommended information content recommended by an artificial intelligence (AI) assistant for the first account, where the recommended information content is obtained by the AI ​​assistant after screening or summarizing information content of the first account in the at least one business function; The recommended information content is displayed.

2. The method according to claim 1, wherein: The social client includes a plurality of business functions, at least two of the plurality of business functions are located at different human-computer interaction interface levels; The obtaining of the recommended information content recommended by the AI ​​assistant for the first account includes: Obtaining recommended information content recommended by the AI ​​assistant for the first account, the recommended information content including information content obtained by the AI ​​assistant after screening or summarizing information content of the first account in a first business function, where the first business function is located at a first human-computer interaction interface level; The displaying of the recommended information content includes: Displaying the recommended information content at a second human-computer interaction interface level; Among them, the second human-computer interaction interface level is higher than the first human-computer interaction interface level.

3. The method according to claim 2, wherein: The displaying of the recommended information content at the second human-computer interaction interface level includes: At least two information cards are displayed at the second human-computer interaction interface level, and each of the at least two information cards is used to display one or a group of recommended information contents recommended by the AI ​​assistant for the first account.

4. The method according to claim 3, wherein: The displaying of at least two information cards at the second human-computer interaction interface level includes: Displaying the at least two information cards in a tiled manner at the second human-computer interaction interface level; The tiling order of the at least two information cards is determined based on the recommendation priorities of the at least two information cards.

5. The method according to claim 3, wherein: The displaying of at least two information cards at the second human-computer interaction interface level includes: Displaying the at least two information cards in a stacked manner at the second human-computer interaction interface level; The stacking order of the at least two information cards is determined based on the recommendation priorities of the at least two information cards.

6. The method according to any one of claims 3 to 5, wherein: The method further comprises: In response to a sliding operation on a first information card among the at least two information cards, canceling display of the first information card and displaying a second information card; The second information card is an information card that is arranged after the first information card in a stacking order or a tiling order.

7. The method according to any one of claims 1 to 6, wherein: The recommended information content includes at least one of the following: first recommended information content after screening or summarizing the unread social messages of the first account; second recommended information content obtained by screening or summarizing the group chat messages or to-do items in the workflow of the first account; third recommended information content after screening or summarizing the candidate information according to the preset rules of the first account; fourth recommended information content obtained by screening or summarizing dynamic information of friends in the social network of the first account; The fifth recommended information content randomly recommended for the first account; fifth recommended information content after screening or summarizing the information content that may be of potential interest to the first account; sixth recommended information content after screening or summarizing the information content that has a probability of being shared by the first account; seventh recommended information content after screening or summarizing interest groups that may have potential interest in the first account; an eighth recommended information content obtained by filtering or summarizing the POI information corresponding to the current geographical location of the first account; ninth recommended information content after screening or summarizing unfamiliar accounts that may be potentially interested in the first account; The tenth recommended information content selected or summarized by the AI ​​tool that may be of potential interest to the first account; eleventh recommended information content that is screened or summarized for games that the first account may be interested in; The twelfth recommended information content is obtained by screening or summarizing the relevant information of the third-party application bound to the first account.

8. The method according to any one of claims 1 to 7, wherein: The method further comprises: Displaying a quick operation entry associated with the recommended information content; In response to an operation on the quick operation entry, a quick processing function corresponding to the quick operation entry is executed.

9. The method according to any one of claims 1 to 8, wherein: The method further comprises: Receiving a command message sent by the first account to the AI ​​assistant; The reply content generated by the AI ​​assistant in response to the command message is displayed, where the reply content is obtained by the AI ​​assistant after screening or summarizing the information content of the first account in the at least one business function based on the command message.

10. The method according to claim 9, wherein: The receiving a command message sent by the first account to the AI ​​assistant includes: receiving a first command message sent by the first account to the AI ​​assistant, where the first command message is used to inquire about the chat content between the first account and the seventh account; The displaying of the reply content generated by the AI ​​assistant in response to the command message includes: The first reply content generated by the AI ​​assistant to the first command message is displayed, where the first reply content is obtained by the AI ​​assistant after screening or summarizing the chat content between the first account and the seventh account.

11. The method according to claim 9 or 10, wherein: The receiving a command message sent by the first account to the AI ​​assistant includes: receiving a second command message sent by the first account to the AI ​​assistant, where the second command message is used to ask a question about a chat content of a chat group to which the first account belongs; The displaying of the reply content generated by the AI ​​assistant in response to the command message includes: The second reply content generated by the AI ​​assistant to the second command message is displayed, where the second reply content is obtained by the AI ​​assistant after screening or summarizing the chat content of the chat group to which the first account belongs.

12. The method according to any one of claims 9 to 11, wherein: The receiving a command message sent by the first account to the AI ​​assistant includes: receiving a third command message sent by the first account to the AI ​​assistant, wherein the third command message is used to inquire about the content of interest of an eighth account that is a friend of the first account; The displaying of the reply content generated by the AI ​​assistant in response to the command message includes: The third reply content generated by the AI ​​assistant to the third command message is displayed, and the third reply content is obtained after the AI ​​assistant screens or summarizes the friend dynamic information of the eighth account.

13. The method according to any one of claims 9 to 12, wherein: The receiving a command message sent by the first account to the AI ​​assistant includes: receiving a fourth command message sent by the first account to the AI ​​assistant, wherein the fourth command message is used to ask for network information or social link information associated with the first keyword; The displaying of the reply content generated by the AI ​​assistant in response to the command message includes: Display the fourth reply content generated by the AI ​​assistant to the fourth command message, where the fourth reply content is the search result obtained by the AI ​​assistant after searching the network information or social chain information associated with the first keyword.

14. The method according to any one of claims 9 to 13, wherein: The receiving a command message sent by the first account to the AI ​​assistant includes: receiving a fifth command message sent by the first account to the AI ​​assistant, where the fifth command message is used to use a first function; The displaying of the reply content generated by the AI ​​assistant in response to the command message includes: The fifth reply content generated by the AI ​​assistant to the fifth command message is displayed, where the fifth reply content is the function entrance of the first function fed back by the AI ​​assistant, or the calling result after the AI ​​assistant calls the first function.

15. The method according to any one of claims 1 to 14, wherein: The method further comprises: Display the function entry of the AI ​​assistant function; The display of the recommended information content recommended by the artificial intelligence AI assistant for the first account includes: In response to a trigger operation on the function entry, the recommended information content recommended by the AI ​​assistant for the first account is displayed.

16. The method according to any one of claims 3 to 6, wherein: Each of the information cards corresponds to a business function; The method further comprises: Obtaining a card template for the business function registration corresponding to the recommended information content; The recommended information content is filled into the card template to obtain the information card corresponding to the recommended information content.

17. The method according to claim 16, wherein: The social client includes a program function corresponding to the AI ​​assistant, and the method further includes: The card templates registered respectively for the at least one business function are received through a program function corresponding to the AI ​​assistant.

18. The method according to claim 16 or 17, wherein: The social client includes a program function corresponding to the AI ​​assistant, and the method further includes: Through the program function corresponding to the AI ​​assistant, a function function supported by the card template to which the at least one business function is respectively registered is received, and the function function is used to execute a response function corresponding to the recommended information content when called.

19. The method according to any one of claims 3 to 6, wherein: The method further comprises: Obtaining interest tags of the first account and weights of the interest tags; Determining the recommendation priority of the at least two information cards based on the target interest tag matching the recommended information content and the weight of the target interest tag; Based on the priorities of the at least two information cards, a sorting order of the at least two information cards is determined.

20. A method for processing information content, the method being executed by a server, the method comprising: Obtaining information content of the first account in at least one business function; By using an artificial intelligence (AI) assistant, the information content of the first account in at least one business function is screened or summarized to obtain recommended information content recommended by the AI ​​assistant for the first account, wherein the AI ​​assistant is a recommendation service based at least on the screening or summarization of information content by an AI model; The recommended information content is sent to the social client where the first account is located.

21. An apparatus for processing information content, the apparatus comprising: an acquisition module, configured to acquire recommended information content recommended by an artificial intelligence (AI) assistant for the first account, wherein the recommended information content is obtained by the AI ​​assistant after screening or summarizing the information content of the first account in the at least one business function; The display module is used to display the recommended information content.

22. An apparatus for processing information content, the apparatus comprising: An acquisition module, used to acquire information content of the first account in at least one business function; a determination module, configured to screen or summarize the information content of the first account in at least one business function through an artificial intelligence (AI) assistant, and obtain recommended information content recommended by the AI ​​assistant for the first account, wherein the AI ​​assistant is a recommendation service that screens or summarizes the information content based on at least an AI model; The sending module is used to send the recommended information content to the social client where the first account is located.

23. A computer device, comprising a processor and a memory, wherein the memory stores at least one program, and the at least one program is loaded and executed by the processor to implement the information content processing method according to any one of claims 1 to 19 or the information content processing method according to claim 20.

24. A computer-readable storage medium, wherein at least one program is stored in the computer-readable storage medium, and the at least one program is loaded and executed by a processor to implement the information content processing method according to any one of claims 1 to 19 or the information content processing method according to claim 20.

25. A computer program product, wherein at least one program is stored in the computer program product, and the at least one program is loaded and executed by a processor to implement the information content processing method according to any one of claims 1 to 19 or the information content processing method according to claim 20.

Images