Information content processing method and device, equipment and storage medium

Abstract

The invention discloses an information content processing method and device, equipment and a storage medium, and relates to the technical field of artificial intelligence. The method comprises the following steps: logging in the first account; obtaining recommended information content recommended for the first account by an artificial intelligence assistant, wherein the recommended information content is obtained by screening or summarizing information content in the at least one service function by the AI assistant; and displaying the recommended information content recommended for the first account by the AI assistant. The invention provides a method for quickly acquiring key contents in a large amount of information contents, so that the information density is improved, and the processing efficiency of the information contents is improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and in particular to a method, device, equipment and storage medium for processing information content. Background Art

[0002] With the continuous development of hardware, computing power, network transmission, algorithms and other technologies, more and more information is generated and transmitted. The connection between people is no longer limited by geographical location, but can be continuously extended in the virtual network space, and social accessibility is constantly strengthened; however, at the same time, too much information leads to problems such as untimely processing of information content and excessive dispersion of attention.

[0003] In the related art, when using a social client, a user needs 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.

[0004] However, the ever-increasing amount of information content on social clients has become a burden on users, and how to improve the efficiency of information content processing is a problem that needs to be solved. Summary of the invention

[0005] The embodiments of the present application provide a method, device, equipment and storage medium for processing information content, which can provide a method for using an artificial intelligence (AI) assistant to recommend information content to a first account, thereby improving the efficiency of using a social client. The technical solution is as follows:

[0006] According to one aspect of the present application, a method for processing information content is provided, the method comprising:

[0007] Log in to the first account;

[0008] 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 in the at least one business function;

[0009] Display the recommended information content recommended by the AI ​​assistant for the first account.

[0010] According to one aspect of the present application, a method for processing information content is provided, the method comprising:

[0011] Obtaining information content of the first account in at least one business function;

[0012] The information content in the at least one business function is screened or summarized by an artificial intelligence (AI) assistant to obtain recommended information content, wherein the AI ​​assistant is a recommendation service that screens or summarizes the information content based on at least an AI model;

[0013] The recommended information content is sent to the first account.

[0014] According to another aspect of the present application, a device for processing information content is provided, the device comprising:

[0015] A login module, used to log in to the first account;

[0016] 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 in the at least one business function;

[0017] The display module is used to display the recommended information content recommended by the AI ​​assistant for the first account.

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

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

[0020] A determination module, configured to filter or summarize the information content in the at least one business function through an artificial intelligence (AI) assistant to obtain recommended information content, wherein the AI ​​assistant is a recommendation service that filters or summarizes the information content based on at least an AI model;

[0021] A sending module is used to send the recommended information content to the first account.

[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 method for processing information content as described above.

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

[0025] The beneficial effects brought by the technical solution provided by the embodiment 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 the important content from the large amount of information on the social client without viewing all the original information content, and can grasp the key information in the fastest time, saving time and improving information processing efficiency; and the user does not need to switch back and forth between the interfaces of various business functions, but integrates and displays the information from multiple scattered business functions, which improves the synergy of business functions and information density, saves operating costs and information acquisition time, and greatly improves the efficiency of users using social clients. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0028] Figure 1 It is a schematic diagram of an interface of a method for processing information content provided by an exemplary embodiment of the present application;

[0029] Figure 2 It is a schematic diagram of an interface of a method for processing information content provided by an exemplary embodiment of the present application;

[0030] Figure 3 It is a schematic diagram of an interface of a method for processing information content provided by an exemplary embodiment of the present application;

[0031] Figure 4 It is a schematic diagram of an interface of a method for processing information content provided by an exemplary embodiment of the present application;

[0032] Figure 5 is a structural block diagram of a computer system provided by an exemplary embodiment of the present application;

[0033] Figure 6 is a flow chart of a method for processing information content provided by an exemplary embodiment of the present application;

[0034] Figure 7is a flow chart of a method for processing information content provided by an exemplary embodiment of the present application;

[0035] Figure 8 is a data processing flow chart of a method for processing information content provided by an exemplary embodiment of the present application;

[0036] Fig. 9 is a timing diagram of a method for processing information content provided by an exemplary embodiment of the present application;

[0037] Fig.10 is a flow chart of a method for processing information content provided by an exemplary embodiment of the present application;

[0038] Fig.11 is a structural block diagram of an information content processing device provided by an exemplary embodiment of the present application;

[0039] Fig.12 is a structural block diagram of an information content processing device provided by an exemplary embodiment of the present application;

[0040] Fig.13 is a block diagram of a computer device provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0041] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0042] First, the terms that may appear in this application are explained.

[0043] ChatGPT: Chat Generative Pre-trained Transformer is an artificial intelligence chatbot program developed by OpenAI and launched in November 2022. The program uses a large language model based on the GPT-3.5 and GPT-4 architectures and is trained with reinforcement learning. ChatGPT currently still interacts in text, but in addition to interacting in a natural human conversation way, it can also be used for complex language work, including automatic text generation, automatic question and answer, automatic summarization and other tasks.

[0044] AIO: The full name is All In One, which refers to 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. In order to provide users with a unified interactive experience, the application provides a chat window component shared by different sessions. The user's input, click operation and other behavioral habits in the component can be regarded as consistent.

[0045] Figures 1 to 4A schematic diagram of an interface showing a method for processing information content in the present application.

[0046] like Figure 1 As shown, when a user uses a social client, a function entry 13 of 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 on or off the AI ​​assistant function by triggering the function entry 13. After the user clicks the function entry 13 to turn on the AI ​​assistant function, the user interface jumps to the full-screen recommended information content interface 11, which displays the 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.

[0047] The recommended information content 15 is obtained by the AI ​​assistant after screening or summarizing the information content in multiple social functions, that is, the information content that users are most concerned about is extracted through the analysis and processing capabilities of the AI ​​language model. For example, the recommended information content 15 is the unread messages of the current user account within a certain period of time, including the summary of unread messages in single chat and group chat; for another example, the 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, the 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 contact recently, etc.; for another example, the recommended information content 15 is a recommendation of social content related to the interest tags that the current user account may follow, such as short videos, interest groups, games, etc. Optionally, the recommended information content interface 11 also displays an introduction guide 14 of the AI ​​assistant.

[0048] 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 of the new version of the data card" to achieve a quick reply to the message. Optionally, the natural language-based quick reply supports text interaction and / or voice interaction, and the user can choose freely.

[0049] The recommended information content 15 mentioned above is displayed on the user interface in the form of cards, wherein the cards support being displayed in a tiled or stacked manner. Figure 1A schematic diagram of an interface showing multiple cards displayed in a tiled manner is shown. Figure 2 A schematic diagram of an interface showing multiple cards displayed in a stacked manner is shown.

[0050] like Figure 2 As shown, when the current user account is using a social client, the user interface displays an AI assistant interface 20, on which recommended information content is displayed in a stacked manner. The recommended information content defaults to an intelligent summary of unread group chat messages during the time when the current user account is not using the social client, so as to improve the user's processing efficiency of information content. Among them, the AI ​​assistant also supports semantic understanding, and intelligently recommends the next task to be performed by the current user account based on semantic understanding, or recommends functions in the social client that match the recommended information content. 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 matching the message to be replied that is suitable for the work scenario 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.

[0051] Optionally, the AI ​​assistant can also support processing such as Figure 2 In addition to the text messages shown, it also supports processing richer intelligent combinations of rich media information (such as pictures, videos, 3D scenes, small games, etc.).

[0052] Optionally, similar to processing text messages, when processing rich media information, the AI ​​assistant can also match appropriate recommended content or related functions to the card inside or below 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.

[0053] Optionally, the arrangement order of the cards of 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 the cards of recommended information content displayed can be based on the default recommendation logic in the early stage. Later, as the user interacts with the AI ​​assistant and the user tags are gradually enriched, the relevant search and recommendation logic is continuously strengthened, so that the arrangement order of the cards of 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, and improve the user's efficiency in processing information.

[0054] Optionally, in addition to the related content or related functions in the social client, the recommended information content may also be related content or related functions from a third party, so as to more intelligently adapt to the user's social needs; for example, the recommended information content includes food delivery software, taxi-hailing software, third-party short / long video software, etc. Figure 3 The schematic diagram of the interface showing that the recommended information content includes related content or related functions from a third party. For example, based on the recent game activities of the current user account, the AI ​​assistant interface 30 displays game videos 31 recommended to be posted by the current user account to a third-party platform, and other users 32 involved in the game activities recommended to the current user account; for another example, if the interest tag of the current user account is cat, the AI ​​assistant interface 30 displays user accounts 33 from third-party platforms related to cats that the current user account follows, and group chats 34 recommended to the current user account; for another example, if the interest tag of the current user account is AI content creation, the AI ​​assistant interface 30 displays channels 35 from third-party platforms related to AI content creation that the current user account follows, and user accounts 36 with the same interest tags recommended to the current user account; for another example, based on the social relationship of the current user account in the social client, the AI ​​assistant interface 30 displays links 37 of third-party platforms recommended to be shared by the current user account to its friends.

[0055] Optionally, in addition to viewing 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. Figure 4 As shown, the AI ​​assistant interface 50 displays recommended information content, including 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 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, and 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.

[0056] Figure 5 The following is a block diagram of a computer system according to an exemplary embodiment of the present application. The computer system 100 includes: a first terminal 110 , a server 120 , and a second terminal 130 .

[0057] The first terminal 110 is installed and runs a first client 111 that supports social functions. The first client 111 can be an application or a web client with social functions. When the first terminal 110 runs the first client 111, the user interface of the first client 111 is displayed on the screen of the first terminal 110. The application can be any one 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 110 is a terminal used by the first user 112, and the first account of the first user 112 is logged in to the first client 111.

[0058] The second terminal 130 is installed and runs a second client 131 that supports social functions. The second client 131 can be an application or a web client with social functions. When the second terminal 130 runs the second client 131, the user interface of the second client 131 is displayed on the screen of the second terminal 130. The application can be any one 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 second terminal 130 is a terminal used by the second user 132, and the second user account of the second user 132 is logged in to the second client 131.

[0059] Optionally, the applications installed on the first terminal 110 and the second terminal 130 are the same, or the applications installed on the two terminals are the same type of applications on different operating system platforms (Android or IOS). The first terminal 110 may refer to one of a plurality of terminals, and the second terminal 130 may refer to another of a plurality of terminals. This embodiment is only illustrated by taking the first terminal 110 and the second terminal 130 as examples. The device types of the first terminal 110 and the second terminal 130 are the same or different, and the device type includes at least one of a smart phone, a tablet computer, an e-book reader, an MP3 player, an MP4 player, a laptop portable computer, and a desktop computer.

[0060] Figure 5Only two terminals are shown, but in different embodiments, there are multiple other terminals 140 that can access the server 120. Optionally, there are one or more terminals 140 corresponding to the developer, and a development and editing platform of a client supporting social functions is installed on the terminal 140. The developer can edit and update the client on the terminal 140, and transmit the updated application installation package to the server 120 through a wired or wireless network. The first terminal 110 and the second terminal 130 can download the application installation package from the server 120 to update the client.

[0061] The first terminal 110 , the second terminal 130 , and other terminals 140 are connected to the server 120 via a wireless network or a wired network.

[0062] The server 120 includes at least one of a single server, multiple servers, a cloud computing platform, and a virtualization center. The server 120 is used to provide background services for clients supporting social functions. Optionally, the server 120 undertakes the main computing work and the terminal undertakes the secondary computing work; or, the server 120 undertakes the secondary computing work and the terminal undertakes the main computing work; or, the server 120 and the terminal adopt a distributed computing architecture for collaborative computing.

[0063] In an illustrative example, 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 data of user accounts used by the first terminal 110, the second terminal 130, and other terminals 140, such as the user account's avatar, the user account's nickname, the group to which the user account belongs, etc.; the social service module 124 is used to provide multiple chat rooms (two-person chat or multi-person chat) for users to chat, post emoticons, send red envelopes, etc. for instant messaging, or post and browse social circle messages; the user-oriented I / O interface 125 is used to establish communication and exchange data with the first terminal 110 and / or the second terminal 130 through a wireless network or a wired network.

[0064] Combined with the above implementation environment description, the information content processing method provided by the embodiment of the present application is described, and the execution subject of the method is Figure 5The terminal 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; or the AI ​​model used by the AI ​​assistant can also be set in Figure 5 On the server in the process, 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.

[0065] Figure 6 A flowchart of a method for processing information content provided by an exemplary embodiment of the present application is shown. Figure 5 The method is performed by a social client on the terminal, and the social client includes at least one business function. The method includes:

[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] AI assistant refers to an AI service provided in a social client that is at least based on an AI model to improve the user's efficiency in processing information content; taking the AI ​​service as an example of processing information content, an AI assistant is a recommendation service that screens or summarizes information content based at least on an AI model.

[0071] The AI ​​model used by the AI ​​assistant can be a language model, such as a large language model (LLM) and 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 hundreds of billions of numerical values. Optionally, 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, tracing back 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 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 a traditional recommendation algorithm. 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. Among them, business function refers to a function designed to achieve the purpose of online social networking, including at least one of the following: communication function (including one-on-one chat, group chat, etc.), contact function, social circle function, short video function. The recommended information content is obtained by the AI ​​assistant after screening or summarizing the information content in the at least one business function. Among them, screening refers to extracting from the information content in 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.

[0074] Taking the at least one business function as a communication function as an example, 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 is the summary of the key information content of unread social messages by the AI ​​assistant; another example is the screening of historical social messages of the chat object specified by the first account by the AI ​​assistant; another example is the list of to-do items of the first account in the communication function by the AI ​​assistant, and so on.

[0075] Optionally, the business functions of the social client also include business functions of third-party applications, which may be third-party applications within the social client or third-party applications outside the social client. The business functions of third-party applications are business functions of third-party applications that are authorized for use or synchronization by the social client, i.e., the social client has the authority to obtain information content in the business functions of the authorized third-party applications and / or the authority to call function functions. For example, the social client obtains information content of a third-party application for shopping within the social client; for another example, the social client calls a function function of a third-party application for clearing memory outside the social client, and so on.

[0076] In some embodiments, the social client may include at least two business functions at different levels; the recommended information content is obtained by the AI ​​assistant after screening or summarizing the information content in the at least two business functions. For example, the recommended information content includes the summary of the information content of unread messages in the communication function, and the dynamic screening of friends in the social circle; for another example, the recommended information content includes the summary of to-do items in the communication function, and the recommendation of friends who may be known in the contact function, etc.

[0077] Exemplarily, the social client includes multiple business functions, at least two of which are located at different human-computer interaction interface levels. 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 information content in the first business function, and the first business function is located at the first human-computer interaction interface level.

[0078] The human-computer interaction interface level is used to indicate the accessibility of the human-computer interaction interface, that is, the operation cost required to reach the human-computer interaction interface, for example, the operation steps required to reach the human-computer interaction interface from the main interface of the social client. The higher the human-computer interaction interface level, the fewer operation steps the user needs to reach the human-computer interaction interface.

[0079] Exemplarily, 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] The first recommended information content is formed after filtering or summarizing the unread social messages; for example, the unread social messages in the chat list are filtered or summarized to form the first recommended information content, and 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 / group chat designated by the first account, or unread social messages in a single chat / group chat whose number of unread social messages exceeds a threshold.

[0081] The second recommended information content is obtained by filtering or summarizing the to-do items in the group chat messages or workflows; for example, the tasks scheduled in the work group chat or the information that needs to be replied to are filtered as the second recommended information content; for another example, to-do items such as group voting, group files, group announcements, etc. are used as the second recommended information content; for another example, messages that mention the first account in the group chat or messages that mention all members in the group chat are used as the second recommended information content.

[0082] The third recommended information content after filtering or summarizing the candidate information according to the preset rules of the first account; that is, the user can customize the recommended information content. For example, the first account pre-sets the objects that need to be filtered or summarized by the AI ​​assistant, and specifies the time range for filtering or summarizing, the type of information content, etc. For example, filtering or summarizing the information content of the document type last year; for another example, filtering or summarizing the dynamic messages in the dynamic space last month.

[0083] The fourth recommended information content is obtained by screening or summarizing the dynamic information of friends in the social network;

[0084] For example, the fourth recommended information content is a dynamic update of a friend in a social circle; for another example, the fourth recommended information content is a birthday reminder of a friend, and so on.

[0085] 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 friends of the first account follow.

[0086] The fifth recommended information content is obtained by screening or summarizing the information content that may be of potential interest to the first account; for example, the interest tags of the first account are determined based on the topics that the first account follows, and the information content that may be of interest to the first account is determined based on the interest tags, and the information content is screened or summarized and recommended to the first account; for another example, the information content of the entire network platform on that day is recommended to the first account, such as in the short video function, all popular short videos of that day are screened or summarized.

[0087] The sixth recommended information content is obtained by screening or summarizing the information content with a probability of being shared by the first account; for example, the interest tags or hot information of interest of the first account are determined based on the chat content between the first account and its friends, 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 the information content with a probability of being shared and is authorized to share it with friends or group chats.

[0088] The seventh recommended information content is obtained by screening or summarizing the interest groups that may be of potential interest to the first account; for example, based on the interest tags of the first account, the candidate interest groups that may be of interest to the first account are determined, and the screened or summarized interest groups are recommended to the first account as the seventh recommended information content.

[0089] · The eighth recommended information content is obtained by screening or summarizing the Point Of Interest (POI) information corresponding to the current geographic location; POI refers to point data in an Internet electronic map, including four attributes: name, address, coordinates, and category. For example, based on the current geographic location of the first account, the business information, transportation services, etc. that the first account may be interested in near the current geographic location are screened or summarized, and recommended to the first account as the eighth recommended information content. · The ninth recommended information content is obtained by screening or summarizing unfamiliar accounts that the first account has potential interest in; for example, a candidate account with the same interest tag as the first account is determined, and the candidate account has potential interest in the first account, and the screened or summarized candidate account is recommended to the first account as the ninth recommended information content.

[0090] The tenth recommended information after screening or summarizing by AI tools that may be of potential interest to the first account

[0091] Content; AI tools are tools developed based on AI technology for solving problems. For example, based on the interest tag of the first account, candidate AI tools that the first account may be interested in are determined, and the screened or summarized AI tools are recommended to the first account as the tenth recommended information content; for another example, if the interest tag of the first account is painting, then AI painting tools are recommended to the first account and a quick entry is provided.

[0092] The eleventh recommendation information after screening or summarizing the games that the first account may be interested in

[0093] content; for example, determining candidate games that the first account may be interested in, and recommending the screened or summarized games as the eleventh recommended information content to the first account.

[0094] The twelfth recommended information content is obtained by screening or summarizing the relevant information of the third-party application bound to the first account; for example, after screening or summarizing the preferential information of the food delivery software bound to the first account, it is recommended to the first account as the twelfth recommended information content.

[0095] The types of information in the aforementioned at least one business function may include the following types:

[0096] Text messages: such as text messages, Weibo, WeChat, emails, etc.

[0097] Graphic information: such as photographs, paintings, illustrations, etc.

[0098] Video information: such as TV programs, movies, short videos, etc.

[0099] Audio information: such as songs, broadcasts, radio stations, etc.

[0100] Social network information: such as personal homepage, social circle, social platform, etc.;

[0101] Game information: such as online games, mobile games, etc.

[0102] Location information: such as Global Positioning System (GPS) positioning, map navigation, etc.

[0103] Personal information: such as basic personal information, interests, personality traits, ability level, achievements, etc.;

[0104] @Group information: such as group membership, goals and tasks, organizational structure, cultural atmosphere, behavioral norms, etc.;

[0105] Emotional information: such as the emotional state, attitude, preferences, satisfaction evaluation, etc. of individuals or groups;

[0106] Behavioral information: such as the behavior patterns, behavior results, and behavior impacts of individuals or groups;

[0107] @Environmental information: such as the physical environment, social environment, cultural environment, etc. in which an individual or group is located.

[0108] Step 240: Display the recommended information content recommended by the AI ​​assistant for the first account.

[0109] Exemplarily, the recommended information content recommended by the AI ​​assistant for the first account is displayed on the AI ​​assistant interface.

[0110] 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 in the first business function of the first human-computer interaction interface level by screening or summarizing, the recommended information content recommended by the AI ​​assistant for the first account is displayed at the 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; that is, the second human-computer interaction interface requires fewer operating 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.

[0111] Optionally, 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 content recommended by the AI ​​assistant for the first account. Among them, a group of recommended information content is derived from the same business function; or, 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 screening results of key information in a business function.

[0112] The information card includes at least one of the following information:

[0113] Account information of the second account (e.g., profile picture of the second account, nickname of the second account, and note of the first account to the second account);

[0114] The number of related messages (e.g., the number of unread messages sent from the second account to the first account);

[0115] Whether the information is filtered or summarized (for example, "a summary has been generated for you");

[0116] At least one selected message (for example, an important message selected from unread messages);

[0117] At least one summarized message (e.g., a message obtained by summarizing unread messages);

[0118] Whether it is an indicator of information content processed by an AI model (for example, displaying “AI intelligent message”).

[0119] 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 tiled manner from top to bottom without overlapping (a plurality of information cards may be displayed simultaneously on the user interface, such as Figure 1As shown), the user can view different information cards by sliding up and down; or, at least two information cards are displayed in a stacked manner by partially or completely overlapping (only one information card is displayed on the user interface, such as Figure 2 As shown in the figure), users can switch between different information cards by sliding.

[0120] In a possible implementation, the at least two information cards are displayed in a tiled manner at the second human-computer interaction interface level; wherein the tiled order of the at least two information cards is determined based on the recommendation priority of the at least two information cards.

[0121] In another possible implementation, 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.

[0122] 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 come from the user account's use of 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 interest tags of the first account, and sorts the different recommended information content based on the weight of the interest tags as a priority.

[0123] 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 by 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 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 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 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 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 the stacking order.

[0124] Optionally, in response to different sliding directions on the first information card of at least two information cards, different second information cards are displayed. For example, sliding up / down displays the previous / next card of the same type of card (such as the same business function), and sliding left / right displays the previous / next card of different types of cards.

[0125] Optionally, 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, and 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 make important information content accessible to users earlier.

[0126] Optionally, the first account first turns on 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.

[0127] Exemplarily, the function entry of the AI ​​assistant function is displayed; in response to the trigger operation on the function entry, the recommended information content recommended by the AI ​​assistant for the first account is displayed. Figure 1 In the mode switching interface 10, a function entry 13 of the AI ​​assistant function "exploration mode" is displayed; 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 of the AI ​​assistant function can be displayed on the main interface of opening 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.

[0128] Optionally, when the first account turns on the AI ​​assistant, the AI ​​assistant can be turned on for all business functions, or for business functions specified by the first account; for business functions that turn on the AI ​​assistant, the first account can specify a partial range of the AI ​​assistant. That is, the range granularity specified by the first account to turn on the AI ​​assistant can be the granularity of social functions, group chats, contacts, etc. For example, the first account can specify to turn on the AI ​​assistant function for work groups that need to quickly grasp information and group chats with a large number of messages.

[0129] Optionally, in the process of 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.

[0130] When the user interface of the first account displays the recommended information content recommended by the AI ​​assistant for the first account, a quick operation entry associated with the recommended information content is displayed, and the type of the quick operation entry and the user's operation on the quick operation entry include at least one of the following:

[0131] @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:

[0132] In response to the first operation on the quick operation entry, a function user interface of the function to which the recommended information content belongs is displayed, and the function user interface includes the original information content corresponding to the recommended information content. For example, if the recommended information content is a summary of unread social messages from account A, the user can jump to the chat dialogue interface between the first account and account A by clicking on the quick operation entry to view the complete chat content.

[0133] The quick operation entry is the reply entry for replying to the second account:

[0134] In the case where the recommended information content originates from a social message of the second account, in response to the second operation on the quick operation entry, the reply content of the first account in reply to the recommended information content is obtained; a reply message is sent to the second account, and the reply message carries the reply content. For example, if 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. Figure 1 As shown, the information card displays a summary of group chat messages related to the first account, and 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, and the first account can reply to the group chat message in the information card summary by entering natural language in the dialog box. For example, the first account enters the content of the reply message 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, but can directly reply to the message in the AI ​​assistant interface, realizing a quick reply to social messages.

[0135] Optionally, 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.

[0136] The quick operation entry is a reply entry for replying to a third account using the quick reply content generated for the recommended information content:

[0137] In the case where the recommended information content originates from a social message of a third account, in 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 portal, a reply message is sent to the third account, and the reply message carries the quick reply content. For example, if the recommended information content is a social message originating from a third account, and the recommended information content is a summary of a work task that the third account requires the first account to complete, while displaying the recommended information content, quick reply content for the recommended information content is displayed, such as "OK, got it", "Will be there on time tomorrow", and "Expected to be completed before the end of get off work". For another example Figure 2 As shown, 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, the identification of the current message as the 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, and 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 social messages.

[0138] The quick operation entry is a jump entry for jumping to the task processing interface of the to-do items:

[0139] In the case where the recommended information content originates from a social message of a fourth account and the social message is associated with a to-do item, a quick operation portal (i.e., an access portal for the to-do items) is displayed during the display of the recommended information content; in response to the fourth operation of the quick operation portal, an item processing interface for the to-do items is displayed; wherein the to-do items include at least one of an electronic document, a group vote, and a third-party application. For example, the recommended information content originates from a social message of a fourth account and is related to the to-do items. For example, if the to-do items are group votes, a jump portal for the group vote is displayed while displaying the recommended information content. The first account can jump to the item processing interface for the group vote by triggering the jump portal. For another example Figure 2 As shown, 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, the identifier that the current message is the summarized or filtered message content, etc.; wherein, the social message from the group chat is associated with a to-do item, and 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, and 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 entry to quickly process the to-do item while obtaining the content of the to-do item, thereby improving the processing efficiency of the information content.

[0140] The quick operation portal is an access portal for accessing multimedia content:

[0141] In the case where the recommended information content is associated with multimedia content, a quick operation entry (i.e., an access entry for multimedia content) is displayed during the display of the recommended information content; in response to the fifth operation of the quick operation entry, a multimedia content interface of the multimedia content is displayed; wherein the multimedia content includes at least one of pictures, audio, video, and games. For example, the recommended information content is a recommendation for a game, and while displaying the recommended information content, the access entry for the game is displayed. The first account can jump to the content interface of the game by triggering the access entry. In this way, the first account can quickly jump to the multimedia content interface associated with the recommended information content, thereby improving the processing efficiency of the information content.

[0142] The quick operation entrance is a sharing entrance for sharing recommended information content to a fifth account or group:

[0143] In the process of displaying the 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; Figure 2 As shown, 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, the identification of the current message as the 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 to the fifth account or group by triggering the sharing entry 26 (for example, clicking 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 with the same interest tag as the first account among the friends of the first account is selected as the fifth account; or, the first account customizes the fifth account or group that it wants to share.

[0144] The quick operation entry is to add the sixth account or group associated with the recommended information content:

[0145] 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. The sixth account or group associated with the recommended information content may 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. Figure 3 As shown, the recommended information 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 adding entry 32 for the sixth account that plays the game with the first account is displayed. The user can quickly add the sixth account as a friend by triggering the adding entry 32 (for example, clicking the adding control).

[0146] Optionally, the first account can also obtain a solution to the problem through direct interaction with the AI ​​assistant. That is, receive the command message sent by the first account to the AI ​​assistant; display the reply content generated by the AI ​​assistant for the command message, and 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. For example, the first account sends a command message to the AI ​​assistant to summarize the information about the 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 for the command message.

[0147] In some embodiments, the interest tags of the first account are obtained based on the operation records of the first account on the social client or the analysis of user information. 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 relevant laws, regulations and standards of 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.

[0148] 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.

[0149] It should be noted that the analysis and processing functions of the AI ​​assistant in this application (such as the AI ​​model) 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.

[0150] It should be noted that in the present application, when user information and data on the client are sent to the server for analysis or processing, the client can send them anonymously, that is, the server analyzes, processes or trains AI models on them without knowing the source of the information and data, so as to protect user privacy.

[0151] To sum up, the method provided in the embodiment of the present application enables users to quickly obtain key information on the social client by acquiring 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.

[0152] Figure 7 A flowchart of a method for processing information content provided by an exemplary embodiment of the present application is shown. Figure 5 The method is performed by a social client on the terminal, and the social client includes at least one social function. The method includes:

[0153] Step 310: Log in to the first account;

[0154] The first account is the user account currently logged in on the social client.

[0155] 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.

[0156] Step 330: Obtain the recommended information content recommended by the AI ​​assistant for the first account;

[0157] AI assistant refers to an AI service provided in a social client that is at least based on an AI model to improve the user's efficiency in processing information content; taking the AI ​​service as an example of processing information content, an AI assistant is a recommendation service that screens or summarizes information content based at least on an AI model.

[0158] The AI ​​model used by the AI ​​assistant can be a language model, such as a large language model (LLM) and 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 hundreds of billions of numerical values. Optionally, 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, tracing back historical social messages, answering questions, recommending functions, emotional companionship, etc. This application is not limited to this.

[0159] Exemplarily, the 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. Obtain 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 the information content in the first business function, and the first business function is located at the first human-computer interaction interface level.

[0160] Optionally, the business functions of the social client also include business functions of third-party applications, which may be third-party applications within the social client or third-party applications outside the social client. The business functions of third-party applications are business functions of third-party applications that are authorized for use or synchronization by the social client, i.e., the social client has the authority to obtain information content in the business functions of the authorized third-party applications and / or the authority to call function functions. For example, the social client obtains information content of a third-party application for shopping within the social client; for another example, the social client calls a function function of a third-party application for clearing memory outside the social client, and so on.

[0161] The human-computer interaction interface level is used to indicate the accessibility of the human-computer interaction interface, that is, the operation cost required to reach the human-computer interaction interface, for example, the operation steps required to reach the human-computer interaction interface from the main interface of the social client. The higher the human-computer interaction interface level, the fewer operation steps the user needs to reach the human-computer interaction interface.

[0162] 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.

[0163] Exemplarily, 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:

[0164] The first recommended information content after filtering or summarizing the unread social messages;

[0165] Second recommended information content after filtering or summarizing group chat messages or to-do items in the workflow;

[0166] · The third recommended information content after screening or summarizing the candidate information according to the preset rules of the first account;

[0167] The fourth recommended information content is obtained by screening or summarizing the dynamic information of friends in the social network;

[0168] The fifth recommended information content randomly recommended for the first account;

[0169] · fifth recommended information content after screening or summarizing the information content that may be of potential interest to the first account;

[0170] · Sixth recommended information content after screening or summarizing the information content that has a probability of being shared by the first account;

[0171] · The seventh recommended information content is obtained by screening or summarizing the interest groups that may be of potential interest to the first account;

[0172] · Eighth recommended information content after filtering or summarizing the point of interest (POI) information corresponding to the current geographical location;

[0173] The tenth recommended information content after screening or summarizing by the AI ​​tool that the first account may be interested in;

[0174] · The eleventh recommended information content is obtained by screening or summarizing the games that the first account may be interested in;

[0175] @The twelfth recommended information content after screening or summarizing the relevant information of the third-party application bound to the first account;

[0176] The types of information in the aforementioned at least one business function may include the following types:

[0177] Text messages: such as text messages, Weibo, WeChat, emails, etc.

[0178] Graphic information: such as photographs, paintings, illustrations, etc.

[0179] Video information: such as TV programs, movies, short videos, etc.

[0180] Audio information: such as songs, broadcasts, radio stations, etc.

[0181] Social network information: such as personal homepage, social circle, social platform, etc.;

[0182] @Game information: such as online games, mobile games, etc.;

[0183] Location information: such as Global Positioning System (GPS) positioning, map navigation, etc.

[0184] Personal information: such as basic personal information, interests, personality traits, ability level, achievements, etc.;

[0185] Group information: such as group membership, goals and tasks, organizational structure, cultural atmosphere, behavioral norms, etc.

[0186] Emotional information: such as the emotional state, attitude, preferences, satisfaction evaluation, etc. of individuals or groups;

[0187] Behavioral information: such as the behavior patterns, behavior results, and behavior impacts of individuals or groups;

[0188] Environmental information: such as the physical, social, and cultural environment of an individual or group.

[0189] Exemplarily, in response to a trigger 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.

[0190] 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.

[0191] Optionally, 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.

[0192] Optionally, an interest tag library is constructed for each user account, and the interest tags in the interest tag library are derived from the use process of the user account in the social client. When the AI ​​assistant determines the recommended information content of the first account, the recommended information content is screened or summarized based on the interest tags of the first account.

[0193] Step 340: Displaying the recommended information content recommended by the AI ​​assistant for the first account at the second human-computer interaction interface level;

[0194] 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 in the first business function of the first human-computer interaction interface level by screening or summarizing, the recommended information content recommended by the AI ​​assistant for the first account is displayed at the 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; that is, the second human-computer interaction interface requires fewer operating 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.

[0195] Exemplarily, 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 content recommended by the AI ​​assistant for the first account. Among them, a group of recommended information content is derived from the same business function; or, 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 screening results of key information in a business function.

[0196] The information card includes at least one of the following information:

[0197] Account information of the second account (e.g., profile picture of the second account, nickname of the second account, and note of the first account to the second account);

[0198] The number of related messages (e.g., the number of unread messages sent from the second account to the first account);

[0199] Whether the information is filtered or summarized (for example, "a summary has been generated for you");

[0200] At least one selected message (for example, an important message selected from unread messages);

[0201] At least one summarized message (e.g., a message obtained by summarizing unread messages);

[0202] Whether it is an indicator of information content processed by an AI model (for example, displaying “AI intelligent message”).

[0203] 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 tiled manner from top to bottom without overlapping (a plurality of information cards may be displayed simultaneously on the user interface, such as Figure 1As shown), the user can view different information cards by sliding up and down; or, at least two information cards are displayed in a stacked manner by partially or completely overlapping (only one information card is displayed on the user interface, such as Figure 2 As shown in the figure), users can switch between different information cards by sliding.

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

[0205] In another possible implementation, 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.

[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 come from the user account's use of 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 interest tags of the first account, 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] 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 by 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 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 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 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 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 the stacking order.

[0209] Optionally, in response to different sliding directions on the first information card of at least two information cards, different second information cards are displayed. For example, sliding up / down displays the previous / next card of the same type of card (such as the same business function), and sliding left / right displays the previous / next card of different types of cards.

[0210] Optionally, 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, and 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 make important information content accessible to users earlier.

[0211] 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 to obtain the information card corresponding to the recommended information content, and then display the information card on the user interface.

[0212] 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.

[0213] In some embodiments, in addition to registering a card template with the dispatch center, the business function also registers a function supported by the card template. That is, the registered social client includes a program function corresponding to the AI ​​assistant, and receives a function supported by the card template registered by at least one business function through the program function corresponding to the AI ​​assistant. The function is used to execute a response function corresponding to the recommended information content when called.

[0214] Optionally, in the process of 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, while 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 displayed, and the type of the quick operation entry and the user's operation on the quick operation entry include at least one of the following:

[0215] 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:

[0216] In response to a first operation on the quick operation entrance, a function user interface of a 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.

[0217] The quick operation entry is a reply entry for replying to the second account, and the second operation is used to reply to social messages:

[0218] 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, a reply content of the first account replying to the recommended information content is obtained; and a reply message is sent to the second account, the reply message carrying the reply content.

[0219] The quick operation entry is a reply entry for replying 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:

[0220] In the case where the recommended information content originates from a social message of a third account, in 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.

[0221] The quick operation entry is a jump entry for jumping to the task processing interface of the to-do items. The fourth operation is used to complete the to-do items:

[0222] 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.

[0223] The quick operation entry is an access entry for accessing multimedia content. The fifth operation is used to access multimedia content:

[0224] When the recommended information content is associated with multimedia content, the access portal of the multimedia content is displayed during the display of the recommended information content; in response to the fifth operation of the shortcut operation portal (the access portal of 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.

[0225] The quick operation portal is a sharing portal for sharing recommended information content to a fifth account or group.

[0226] The sixth operation is for sharing:

[0227] 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.

[0228] The quick operation entry is an entry for adding a sixth account or group associated with the recommended information content, and the seventh operation is used to add a sixth account or group chat:

[0229] During the process of displaying the recommended information content, an adding entry for a sixth account or group associated with the recommended information content is displayed; in response to a seventh operation on the quick operation entry, the sixth account is added as a friend or joins the group.

[0230] Step 360: Receive a command message sent by the first account to the AI ​​assistant;

[0231] 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.

[0232] Optionally, the first account sends a command message to the AI ​​assistant through text input or voice input.

[0233] Optionally, the 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 the information card, such as at the bottom of the information card. The first account asks questions or instructs the AI ​​assistant by entering a command message in the dialog box.

[0234] The command message sent by the first account to the AI ​​assistant may include the following types:

[0235] ·Recall the chat content in the single chat:

[0236] A first command message sent by the first account to the AI ​​assistant is received, where the first command message is used to inquire about the chat content between the first account and the seventh account. Figure 4 As shown, the AI ​​assistant interface 50 displays an information card, and the information card displays the identifier "My AI" of the information content currently processed by the AI ​​model; the first account enters a first command message in the dialog box 53 in the information card of the AI ​​assistant interface 50 to command the AI ​​assistant to trace back the chat content in the single chat, such as "What did I talk about with my friend S recently" and clicks send to send the first command message to the AI ​​assistant. Optionally, a voice input control is set on the right side of the dialog box 53, that is, the first command message can be input by voice input.

[0237] ·Recall the chat content in the group chat:

[0238] A second command message sent by the first account to the AI ​​assistant is received, where the second command message is used to inquire about the chat content of the chat group to which the first account belongs. Figure 4 As shown, the AI ​​assistant interface 50 displays an information card, on which is displayed an 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 a second command message "What was the conclusion of the last discussion of group chat X" in voice form. After the user releases the voice input control, the second command message is sent to the AI ​​assistant, so that the first account can quickly trace back the information content of the group chat.

[0239] Get friends’ updates:

[0240] A third command message sent by the first account to the AI ​​assistant is received, where the third command message is used to ask the eighth account, which is a friend of the first account, about the content of interest. Figure 4 As shown, the AI ​​assistant interface 50 displays an information card, and the information card displays the identifier "My AI" of the information content currently processed by the AI ​​model; the first account enters a third command message in the dialog box 53 in the information card of the AI ​​assistant interface 50 to command the AI ​​assistant to obtain the friend's dynamics, such as "What is friend Y paying attention to recently" and clicks send to send the third command message to the AI ​​assistant to obtain the friend's recent dynamics. Optionally, a voice input control is set on the right side of the dialog box 53, that is, the third command message can be input by voice input.

[0241] @Get keyword information:

[0242] A fourth command message sent by the first account to the AI ​​assistant is received, where the fourth command message is used to ask for network information or social link information associated with the target keyword. Figure 4 As shown, the AI ​​assistant interface 50 displays an information card, and the information card displays the identifier "My AI" of the information content currently processed by the AI ​​model; the first account enters a fourth command message in the dialog box 53 in the information card of the AI ​​assistant interface 50 to command the AI ​​assistant to obtain keyword information, such as "What are the interest groups related to beauty recently?" 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. Optionally, a voice input control is set on the right side of the dialog box 53, that is, the fourth command message can be input by voice input.

[0243] Quick use function:

[0244] Receive a fifth command message sent by the first account to the AI ​​assistant, where the fifth command message is used to use a specified function. Figure 4 As shown, the AI ​​assistant interface 50 displays an information card, and the information card displays the identification "My AI" of the information content currently 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 to command the AI ​​assistant to help the first account quickly use the function, such as "Please help me set up the youth mode" and clicks to send, and sends the fourth command message to the AI ​​assistant to obtain an interest group that matches the interests of the first account. For another example, in the dialog box 53 in the information card of the AI ​​assistant interface 50, "It's a bit slow to start the APP recently" is entered to quickly use the cache data cleaning function. After receiving the fifth command message, the AI ​​assistant will generate and display the reply content 56 and the recommended related content 56, so that the user can quickly use the cache data cleaning function by clicking the recommended related content 56. Optionally, a voice input control is set on the right side of the dialog box 53, that is, the fourth command message can be input by voice input.

[0245] Step 380: Display the response content generated by the AI ​​assistant in response to the command message.

[0246] Exemplarily, the user interface of the social client displays the reply content generated by the AI ​​assistant in response to the command message, and 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.

[0247] For different types of command messages in step 360, the AI ​​assistant generates different reply contents, as shown below:

[0248] @Generate the first reply content for the first command message:

[0249] The first reply content generated by the AI ​​assistant to the first command message is displayed. The first reply content is obtained after the AI ​​assistant summarizes the chat content between the first account and the seventh account. For example, the AI ​​assistant determines the label of the seventh account based on the first command message, matches the social message data that matches it, and summarizes the social message data based on the AI ​​model to generate the first reply content.

[0250] Generate a second reply content for the second command message:

[0251] The second reply content generated by the AI ​​assistant to the second command message is displayed, and the second reply content is obtained after the AI ​​assistant summarizes the chat content of the chat group to which the first account belongs. For example, the AI ​​assistant matches the social message data in the group chat that matches it based on the group chat tag and content tag in the second command message, and summarizes the social message data based on the AI ​​model to generate the second reply content.

[0252] Generate a third reply content for the third command message:

[0253] The third reply content generated by the AI ​​assistant to the third command message is displayed. The third reply content is obtained after the AI ​​assistant summarizes the dynamic information of the friends 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 content after screening and summarizing based on the AI ​​model.

[0254] Generate a fourth reply content for the fourth command message:

[0255] The fourth reply content generated by the AI ​​assistant to the fourth command message is displayed. The fourth reply content is the search result after the AI ​​assistant searches the network information or social chain information associated with the target keyword. For example, based on the target keyword in the fourth command message, the AI ​​assistant matches the network information or social chain information (such as interest groups, etc.) associated with it, and generates the fourth reply content after screening and summarizing.

[0256] Generate a fifth reply content for the fifth command message:

[0257] The fifth reply content generated by the AI ​​assistant for the fifth command message is displayed. The fifth reply content is the function entry of the specified function fed back by the AI ​​assistant, or the call result after the AI ​​assistant calls the specified function. For example, the AI ​​assistant determines the function related to the keyword in the fifth command message, feeds back the function entry of the function to the first account as a shortcut path, or directly calls the function and feeds back the call result to the first account as the fifth reply content.

[0258] In some embodiments, the interest tags of the first account are obtained based on the operation records of the first account on the social client or the analysis of user information. 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 relevant laws, regulations and standards of 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.

[0259] 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.

[0260] 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.

[0261] It should be noted that in the present application, when user information and data on the client are sent to the server for analysis or processing, the client can send them anonymously, that is, the server analyzes, processes or trains AI models on them without knowing the source of the information and data.

[0262] To sum up, 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, extract effective content from a large amount of information, and improve the user's information content processing efficiency on the social client.

[0263] 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.

[0264] 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.

[0265] The social client (i.e., front end) involved in this application can be implemented using the user interface (UI) components of the client native system and / or the fifth revision of the Hypertext Markup Language (HTML5) web front end, collectively referred to as the front end. The software architecture of the front end is shown in the following table:

[0266] Table 1

[0267]

[0268]

[0269] 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.

[0270] Based on the architecture shown in the table above, the frontend can implement at least one of the following capabilities:

[0271] Implement a card interface containing recommended information content:

[0272] The card content is a mixed layout of rich text, which not only presents information but also provides quick operations. The information forms include text, pictures, voice, video, etc.; the operation forms include basic elements or element combinations such as button controls, hyperlinks, and input boxes that can respond to user touch / click or keyboard input to perform operations.

[0273] Implement diverse dynamic cards containing recommended information content:

[0274] Card types are rich and varied, with differences in information, functions and styles. Different social function modules (businesses) extend the blank card to implement their own card templates, presenting the information and optional operations unique to the sub-function module.

[0275] Implement unified structured text instructions:

[0276] Different social function modules (businesses) display the functional operations that can be performed by the module 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 to the functional operation of the module.

[0277] Through card information and instruction operations, cross-business information aggregation and cross-business function mutual invocation can be achieved:

[0278] 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.

[0279] ·Realize the dispatch center to gather card data and distribute command operations:

[0280] Each sub-function module registers the cards and command 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 / layered 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-function module function for execution; related operation feedback is reflected back to the UI interface.

[0281] Figure 8 A flowchart showing data processing of a method for processing information content provided by an exemplary embodiment of the present application is shown. Figure 8 The subjects involved include users, dispatch center, business functions and background. Figure 7 The flowchart shown includes steps 401 to 416; wherein, steps 401 to 403 are initialization processes, steps 404 to 410 are information card presentation processes, and steps 411 to 416 are instruction operation processes (steps 411 and 412 are replaceable steps, i.e., one can be executed at a time).

[0282] 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.

[0283] Step 401: The user starts a social client;

[0284] The user launches the social client through a click operation or other triggering operation.

[0285] Optionally, the user logs in to the first account on the social client.

[0286] Step 402: the dispatch center initiates a registration solicitation for a card template to the business function;

[0287] 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.

[0288] Step 403: The business function registers the card template and instruction operation information with the dispatch center;

[0289] Each business function registers the card template and instruction operation information of the information card that it supports and implements with the dispatch center. For example, the business function registers the card template that it supports and the function function that the card template supports with the dispatch center.

[0290] For example, the communication function registers a card template for summarizing unread social messages in a single chat with the dispatch center. The card template includes the sender of the message, the number of messages, the summarized message content, etc. The functions supported by the card template include jumping to the single chat interface, quick reply, access to multimedia content, sharing recommended information content, etc.

[0291] For another example, the communication function registers a card template for summarizing unread social messages in a group chat with the dispatch center. The card template includes the name of the group chat, the sender of the message, the number of messages, the summarized message content, to-do items, etc. The functions supported by the card template include jumping to the group chat interface, quick reply, accessing multimedia content, sharing recommended information content, accessing group to-do items, etc.

[0292] For another example, the communication function registers a card template for retracing historical social messages in a group chat with the dispatch center. The card template includes the name of the group chat, the sender of the message, the time when the message was sent, the summarized message content, etc. The functions supported by the card template include jumping to the group chat interface, accessing multimedia content, etc.

[0293] For another example, the social circle function registers a card template for obtaining the dynamics of friends in the social circle with the dispatch center. The card template includes the publisher of the dynamic message, the summarized dynamic message content, the filtered pictures in the dynamic message, etc. The functions supported by the card template include viewing the original content of the dynamic message, quickly replying to the dynamic message, liking the dynamic message, etc.

[0294] For another example, the short video function registers a card template for recommending short videos with the dispatch center. The 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. The functions supported by the card template include accessing the short video, quickly replying to the short video, and liking the Du Jian video.

[0295] For another example, the contact function registers a card template for recommending contacts with the dispatch center, and 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 social circle of the recommended contact, a link to quickly add friends, etc.

[0296] Information card presentation process: Step 404 to step 410, including background data acquisition, data processing, mapping data to cards, and assembling and presenting cards.

[0297] Step 404: background acquisition of data;

[0298] The background obtains data, such as the unread social messages of the first account.

[0299] Optionally, after the background obtains the data, the AI ​​model is used to generate recommended information content for the AI ​​assistant function based on the data.

[0300] Step 405: The background returns the recommended information content and instruction operation generated by AI;

[0301] The backend returns AI-generated recommended information and instruction operations to the dispatch center.

[0302] The processing of the data returned by the background to the dispatch center includes the general processing of the dispatch center (step 406) and the private processing registered by the social function module (business function) (steps 407 to 408).

[0303] Step 406 and steps 407 to 408 may be performed in any order.

[0304] Step 406: The dispatch center performs data processing and matching services;

[0305] The dispatch center performs data processing and matching services on the recommended information content and instruction operations obtained from the background. That is, the dispatch center receives the recommended information content obtained from the background, matches it to various business functions according to the data type or card template of the information card; and extracts the structured instructions generated by the AI ​​model to generate the corresponding operation button / input box / hyperlink.

[0306] Optionally, the data processing performed by the dispatch center also includes removing isolated text, redundant blank characters, etc.

[0307] Step 407: The business function performs data processing;

[0308] The dispatch center sends the recommended information content obtained from the background to each business function, so that each business function performs the private processing registered by the business function. For example, isolated text and redundant blank characters are removed according to the card template registered by the business function.

[0309] Step 408: The business function returns a result;

[0310] After each business function performs private processing on the recommended information content, the processed result data is sent to the dispatch center.

[0311] Step 409: The dispatch center maps the data to the information card;

[0312] 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).

[0313] Exemplarily, the dispatch center matches the processed data of the recommended information content to the corresponding card template View, and maps the data Model to the view ViewModel.

[0314] Step 410: Presenting an information card;

[0315] 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.

[0316] Instruction operation process: Step 411 to step 416, including triggering instruction operation, matching corresponding program call, checking / correcting parameters, function call and reflecting the result feedback to the AI ​​assistant interface.

[0317] There are two ways to trigger the command operation. The first is that the program automatically executes the command operation automatically extracted from the AI ​​results returned from the background (ie, step 411), and the second is that the user actively clicks on the interactive element containing the command operation (ie, step 412).

[0318] Step 411: The dispatch center extracts the instructions contained in the recommendation information content generated by AI;

[0319] The dispatch center automatically extracts the instructions contained in the AI-generated recommendation information content.

[0320] Step 412: The user actively interacts to trigger the instruction;

[0321] The user actively triggers the interactive elements that contain command operations, such as clicking on the controls on the AI ​​assistant interface, thereby triggering the command.

[0322] Step 413: The dispatch center matches the instruction to the corresponding program call and checks / corrects the parameters;

[0323] After the instruction is triggered, the dispatch center matches the instruction to the corresponding program call and checks and / or corrects the parameters.

[0324] Exemplarily, after receiving the operation instruction triggered by the user or automatically extracted by AI, the dispatch center matches it to the function function of the corresponding business function according to the registration information of each business function, and converts the instruction into a program call. Because there are deviations or errors in the content or structured syntax generated by AI, it is necessary to check and correct the content, and initiate the call after checking / correcting the filled parameters.

[0325] Step 414: The business function initiates a function call;

[0326] The function call of the business module is derived from the fixed template of the card containing the recommended information content, or is dynamically generated by extracting structured instructions from the results returned by the background AI. The call parameters come from AI recommendation (i.e., using AI model to optimize the parameters) and / or user specification (i.e., user customization).

[0327] Exemplarily, the business function initiates a function call that it supports.

[0328] Step 415: The business function feeds back the result;

[0329] After the function is called, the business function returns its result to the dispatch center.

[0330] Step 416: Reflect to the AI ​​assistant interface.

[0331] 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.

[0332] The background involved in this application includes business logic layer, algorithm layer, and recommendation layer; the input source of the background is the group chat / contact authorized by the user.

[0333] The business logic layer is used to implement at least one of the following functions:

[0334] ·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;

[0335] 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;

[0336] Send the parsed content to the algorithm layer, which includes algorithms for generating recommended information content using AI models; the algorithm layer appropriately summarizes these messages, as well as possible responses from users, and returns the content to the business logic layer;

[0337] The content returned by the algorithm layer is pushed to the recommendation layer, which sorts and recommends the content to users. The recommended content includes but is not limited to: the priority of the recommended information content, the links that users may be interested in, the group chats that users may be interested in, etc.

[0338] The recommended information content is returned to the social client through the business logic layer.

[0339] The algorithm layer is used to summarize and predict the possible responses of users based on the content of messages sent by the business logic layer. The sources of messages include but are not limited to: contact messages, content in group chats that mention the first account (@first account), and content in group chats that mention all members (@everyone). Message forms include but are not limited to: text, pictures, voice, video, files, and links.

[0340] Among them, the recommendation layer is used to recommend the content of the algorithm layer according to the content that the user is interested in, and additionally recommend some public links, groups, functions, etc. that the user may be interested in.

[0341] Fig. 9 A timing diagram showing a method for processing information content provided by an exemplary embodiment of the present application. Fig. 9 The entities involved include users, AI assistant interface, business logic layer, algorithm layer, recommendation layer and database.

[0342] Step 501: The user inputs the message content;

[0343] The user enters the message content in the AI ​​assistant interface, such as asking the AI ​​assistant a summary of unread messages in the group chat / contacts.

[0344] Step 502: The AI ​​assistant interface requests unread messages of the authorized group and contacts;

[0345] 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.

[0346] Step 503: The business logic layer reads unread messages;

[0347] The business logic layer reads unread messages in authorized group chats / contacts from the database, including content that mentions users in group chats, contact messages, and other content.

[0348] Step 504: the database returns unread messages;

[0349] The unread messages in the authorized group chat / contact in the database are returned to the business logic layer.

[0350] Step 505: The business logic layer parses the message content;

[0351] 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.

[0352] Step 506: The algorithm layer summarizes the message and predicts the user's response;

[0353] 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.

[0354] Step 507: the algorithm layer returns a summary message and a predicted reply;

[0355] The algorithm layer returns the summarized messages and predicted replies (i.e., the output results of the AI ​​language model) to the business logic layer.

[0356] Step 508: The business logic layer sends a summary message and a predicted reply;

[0357] The business logic layer pushes the content returned by the algorithm layer to the recommendation layer, which sorts the content and recommends it to users.

[0358] Step 509: The recommendation layer recommends information content in order according to user interests;

[0359] The recommendation layer sorts the recommended information content (i.e., summary messages and predicted replies) output by the AI ​​language model. The recommended content includes but is not limited to: the return order of the recommended information content (i.e., the priority displayed on the AI ​​assistant interface), links that the user may be interested in, group chats that the user may be interested in, etc.

[0360] The sorting algorithm of the recommendation layer can be customized by the user, or optimized for the user using an AI model.

[0361] In addition, the recommendation layer recommends additional public links, groups, functions, etc. that users may be interested in based on user information.

[0362] Step 510: the recommendation layer returns the recommended information content;

[0363] The recommendation layer returns the sorted recommendation information content to the business logic layer.

[0364] Step 511: the business logic layer returns the recommended information content;

[0365] After obtaining the recommended information content returned by the recommendation layer, the business logic layer pushes it to the AI ​​assistant interface.

[0366] Step 512: The AI ​​assistant interface displays recommended information content.

[0367] The sorted recommended information content is displayed on the AI ​​assistant interface.

[0368] Fig.10 A flowchart of a method for processing information content provided by an exemplary embodiment of the present application is shown. Figure 5 The client or server shown is executed for example. The method includes:

[0369] Step 620: Obtain information content of the first account in at least one business function;

[0370] The first account is the user account currently logged in on the social client.

[0371] The social client includes at least one business function. Among them, the business function refers to the function designed to achieve the purpose of network social networking, including at least one of the following: communication function (including one-to-one chat, group chat, etc.), contact function, social circle function, short video function.

[0372] Exemplarily, the types of information in at least one business function may include the following types:

[0373] Text messages: such as text messages, Weibo, WeChat, emails, etc.

[0374] @Image information: such as photos, paintings, illustrations, etc.;

[0375] Video information: such as TV programs, movies, short videos, etc.

[0376] Audio information: such as songs, broadcasts, radio stations, etc.

[0377] Social network information: such as personal homepage, social circle, social platform, etc.;

[0378] Game information: such as online games, mobile games, etc.

[0379] Location information: such as Global Positioning System (GPS) positioning, map navigation, etc.

[0380] Personal information: such as basic personal information, interests, personality traits, ability level, achievements, etc.;

[0381] Group information: such as group membership, goals and tasks, organizational structure, cultural atmosphere, behavioral norms, etc.

[0382] Emotional information: such as the emotional state, attitude, preferences, satisfaction evaluation, etc. of individuals or groups;

[0383] Behavioral information: such as the behavior patterns, behavior results, and behavior impacts of individuals or groups;

[0384] Environmental information: such as the physical, social, and cultural environment of an individual or group.

[0385] Optionally, the information content may be unread social messages of the first account, social messages involving the first account in the group chat, social messages involving all members in the group chat, contacts of the first account, group chat 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, and the like.

[0386] Optionally, 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.

[0387] Optionally, an interest tag library is constructed for each user account, and the interest tags in the interest tag library are derived from the use process of the user account in the social client. According to the interest tag of the first account, information content related to the interest tag in at least one business function is obtained.

[0388] Step 640: Filter or summarize the information content in at least one business function through the AI ​​assistant to obtain recommended information content;

[0389] The AI ​​assistant is a recommendation service that screens or summarizes information content based on at least an AI model. The AI ​​model used by the AI ​​assistant can be a language model, such as a large language model (LLM) and 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 hundreds of billions of numerical values. Optionally, the AI ​​model used by the AI ​​assistant can 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, retracing historical social messages, answering questions, recommending functions, emotional companionship, and so on. This application is not limited to this.

[0390] The recommended information content recommended by the AI ​​assistant for the first account can be completely generated by the AI ​​model based on the AI ​​assistant; 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. This application does not completely limit all recommended information content to be generated by the AI ​​model used by the AI ​​assistant.

[0391] Recommended information content is obtained by the AI ​​assistant after screening or summarizing the information content in at least one business function. Screening refers to extracting from the information content in the at least one business function, that is, without 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.

[0392] The recommended information includes at least one of the following:

[0393] The first recommended information content is formed after filtering or summarizing the unread social messages; for example, the unread social messages in the chat list are filtered or summarized to form the first recommended information content, and 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 / group chat designated by the first account, or unread social messages in a single chat / group chat whose number of unread social messages exceeds a threshold.

[0394] The second recommended information content is obtained by filtering or summarizing the to-do items in the group chat messages or workflows; for example, the tasks scheduled in the work group chat or the information that needs to be replied to are filtered as the second recommended information content; for another example, to-do items such as group voting, group files, group announcements, etc. are used as the second recommended information content; for another example, messages that mention the first account in the group chat or messages that mention all members in the group chat are used as the second recommended information content.

[0395] The third recommended information content after filtering or summarizing the candidate information according to the preset rules of the first account; that is, the user can customize the recommended information content. For example, the first account pre-sets the objects that need to be filtered or summarized by the AI ​​assistant, and specifies the time range for filtering or summarizing, the type of information content, etc. For example, filtering or summarizing the information content of the document type last year; for another example, filtering or summarizing the dynamic messages in the dynamic space last month.

[0396] @The fourth recommended information content after screening or summarizing the dynamic information of friends in the social network;

[0397] For example, the fourth recommended information content is a dynamic update of a friend in a social circle; for another example, the fourth recommended information content is a birthday reminder of a friend, and so on.

[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 friends of the first account follow.

[0399] The fifth recommended information content is obtained by screening or summarizing the information content that may be of potential interest to the first account; for example, the interest tags of the first account are determined based on the topics that the first account follows, and the information content that may be of interest to the first account is determined based on the interest tags, and the information content is screened or summarized and recommended to the first account; for another example, the information content of the entire network platform on that day is recommended to the first account, such as in the short video function, all popular short videos of that day are screened or summarized.

[0400] The sixth recommended information content is obtained by screening or summarizing the information content with a probability of being shared by the first account; for example, the interest tags or hot information of interest of the first account are determined based on the chat content between the first account and its friends, 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 the information content with a probability of being shared and is authorized to share it with friends or group chats.

[0401] The seventh recommended information content is obtained by screening or summarizing the interest groups that may be of potential interest to the first account; for example, based on the interest tags of the first account, the candidate interest groups that may be of interest to the first account are determined, 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 screening or summarizing the Point Of Interest (POI) information corresponding to the current geographic location; POI refers to point data in an Internet electronic map, including four attributes: name, address, coordinates, and category. For example, based on the current geographic location of the first account, the business information, transportation services, etc. that the first account may be interested in near the current geographic location are screened or summarized, and recommended to the first account as the eighth recommended information content. · The ninth recommended information content is obtained by screening or summarizing unfamiliar accounts that the first account has potential interest in; for example, a candidate account with the same interest tag as the first account is determined, and the candidate account has potential interest in the first account, and the screened or summarized candidate account is recommended to the first account as the ninth recommended information content.

[0403] @ is the tenth recommended information content after screening or summarizing 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 interest tag of the first account, the candidate AI tools that the first account may be interested in are determined, and the screened or summarized AI tools are recommended to the first account as the tenth recommended information content; for another example, if the interest tag of the first account is painting, then AI painting tools are recommended to the first account and a quick entry is provided.

[0404] · The eleventh recommended information content is obtained by screening or summarizing the games that may be of potential interest to the first account; for example, candidate games that may be of potential interest to the first account are determined, and the screened or summarized games are recommended to the first account as the eleventh recommended information content.

[0405] The twelfth recommended information content is obtained by screening or summarizing the relevant information of the third-party application bound to the first account; for example, after screening or summarizing the preferential information of the food delivery software bound to the first account, it is recommended to the first account as the twelfth recommended information content.

[0406] 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.

[0407] Step 660: Send the recommended information content to the first account.

[0408] 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.

[0409] Optionally, while sending the recommended information content to the first account, a card template registered for the business function corresponding to the recommended information content is sent; after the recommended information content is filled into the card template, it is displayed on the AI ​​assistant interface of the first account.

[0410] In summary, the method provided in the embodiment 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 a social client, extract effective content from a large amount of information, and improves the user's information content processing efficiency on the social client.

[0411] 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. And these messages are likely to have low information density. For example, multiple messages can actually be summarized in one sentence; and most of the content of these messages is similar, such as querying express information, urging shipment, requesting returns, and so on. In this scenario, the information content processing method of this application will improve the processing efficiency of customer service.

[0412] Exemplarily, log in to the first account of the customer service; obtain the recommended information content recommended by the AI ​​assistant for the first account of the customer service, the recommended information content is obtained by the AI ​​assistant after screening or summarizing the information content in at least one business function in the social client; display the recommended information content recommended by the AI ​​assistant for the first account. For example, after the customer service logs in to the first account, obtain the recommended information content recommended by the AI ​​assistant for it, the recommended information content is a summary of unread messages, and display the recommended information content on the AI ​​assistant interface of the first account.

[0413] Exemplarily, at least two information cards are displayed, 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. That is, the recommended information contents are displayed on the AI ​​assistant interface in the form of information cards containing the recommended information contents; each information card displays a summary of messages from one customer, or each message card displays the same type of requests from different customers (for example, return requests from different customers, etc.).

[0414] 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.

[0415] 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.

[0416] 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.

[0417] Exemplarily, in response to a sliding operation on a first information card among at least two information cards, the first information card is canceled from display, and a 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. That is, in the case of stacked information cards, different information cards are switched to be displayed through a sliding operation.

[0418] Exemplarily, the recommendation information content of the first account recommended to the customer service includes at least one of the following:

[0419] The first recommended information content after filtering or summarizing the unread social messages;

[0420] Second recommended information content after filtering or summarizing group chat messages or to-do items in the workflow;

[0421] · The third recommended information content after screening or summarizing the candidate information according to the preset rules of the first account;

[0422] The fourth recommended information content is obtained by screening or summarizing the dynamic information of friends in the social network;

[0423] @ is the fifth recommended information content randomly recommended by the first account;

[0424] · fifth recommended information content after screening or summarizing the information content that may be of potential interest to the first account;

[0425] · Sixth recommended information content after screening or summarizing the information content that has a probability of being shared by the first account;

[0426] · The seventh recommended information content is obtained by screening or summarizing the interest groups that may be of potential interest to the first account;

[0427] · Eighth recommended information content after filtering or summarizing the POI information corresponding to the current geographical location;

[0428] · Ninth recommended information content after screening or summarizing unfamiliar accounts that may be of potential interest to the first account;

[0429] The tenth recommended information content after screening or summarizing by the AI ​​tool that the first account may be interested in;

[0430] · The eleventh recommended information content is obtained by screening or summarizing the games that the first account may be interested in;

[0431] The twelfth recommended information content is obtained by screening or summarizing the relevant information of the third-party application bound to the first account.

[0432] Exemplarily, in response to the first operation on the recommended information content, a functional user interface of the function to which the recommended information content belongs is displayed, and the functional user interface includes the original information content corresponding to the recommended information content. That is, the customer service can jump to the original interface of the recommended information content by clicking on the recommended information content, for example, by clicking on the summary of the customer's unread messages, jump to the chat interface with the customer.

[0433] For example, the recommended information content originates from the social message of the second account, and in response to the second operation on the recommended information content, the reply content of the first account to the recommended information content is obtained; and a reply message is sent to the second account, and the reply message carries the reply content. That is, the customer service can directly enter the reply message for the second account in the AI ​​assistant interface and send it.

[0434] Exemplarily, the recommended information content originates from a social message of a third account. In 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 reply content, a reply message is sent to the third account, and the reply message carries the quick reply content. That is, the AI ​​assistant interface also displays the quick reply message recommended to the customer service, and the customer service can quickly reply by clicking on the optional quick reply message on the AI ​​assistant interface.

[0435] Exemplarily, the recommended information content originates from the social message of the fourth account and the social message is associated with a to-do item. In the process of displaying the recommended information content, the access portal of the to-do item is displayed; in response to the fourth operation of the access portal, the 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. 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, so that the customer service can access it with one click.

[0436] Exemplarily, the recommended information content is associated with multimedia content, and in the process of displaying the recommended information content, an access portal to the multimedia content is displayed; in response to the fifth operation of the access portal, a multimedia content interface of the multimedia content is displayed; wherein the multimedia content includes at least one of pictures, audio, video, and games. For example, in the case where the recommended information content is associated with a display picture of a product, an access portal to the picture display page of the product is displayed on the AI ​​assistant interface.

[0437] For example, in the process of displaying the recommended information content, a sharing entrance for sharing the recommended information content with a fifth account or group is displayed, and 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 sharing entrance, the recommended information content is shared with the fifth account or group. For example, a sharing entrance for sharing products is displayed on the AI ​​assistant interface of customer service, and customer service can quickly share the products that they may buy with potential customers.

[0438] Exemplarily, a command message sent by a first account to an AI assistant is received; and a 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 filtering or summarizing the information content in at least one business function based on the command message. For example, a customer service representative can ask the AI ​​assistant a chat summary with a customer, and the AI ​​assistant will generate a reply content and display it on the AI ​​assistant interface.

[0439] Optionally, the command message sent by the first account to the AI ​​assistant may include the following types:

[0440] ·Recall the chat content in the single chat:

[0441] Receive a first command message sent by the first account to the AI ​​assistant, where the first command message is used to ask questions 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.

[0442] ·Recall the chat content in the group chat:

[0443] 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.

[0444] @Get friends’ updates:

[0445] 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 that is a friend of the first account; display a 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.

[0446] @Get keyword information:

[0447] 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 target keyword; display a 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 target keyword.

[0448] Quick use function:

[0449] Receive a fifth command message sent by the first account to the AI ​​assistant, where the fifth command message is used to use a specified function; display a fifth reply content generated by the AI ​​assistant for the fifth command message, where the fifth reply content is the function entrance of the specified function fed back by the AI ​​assistant, or the call result after the AI ​​assistant calls the specified function.

[0450] Exemplarily, the function entrance of the AI ​​assistant function is displayed; in response to the trigger operation on the function entrance, the recommended information content recommended by the AI ​​assistant for the first account is displayed. That is, the customer service opens the AI ​​assistant function by clicking on the function entrance of the AI ​​assistant function.

[0451] Exemplarily, each information card corresponds to a business function; obtain a card template registered for the business function corresponding to the recommended information content; fill the recommended information content into the card template to obtain an information card corresponding to the recommended information content. For example, after-sales requests, group chat messages, and customer social circles correspond to different card templates, and the recommended information content belonging to different business functions is filled into the corresponding card templates to obtain information cards corresponding to the recommended information content.

[0452] 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.

[0453] 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.

[0454] 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.

[0455] 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, where 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 first account.

[0456] Fig.11 The following is a block diagram of a device for processing information content provided by an exemplary embodiment of the present application. The device includes:

[0457] Login module 710, used to log in to the first module;

[0458] An acquisition module 720 is used to acquire 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 the information content in the at least one business function;

[0459] The display module 740 is used to display the recommended information content recommended by the AI ​​assistant for the first account.

[0460] In a possible implementation, 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 recommended information content recommended by the AI ​​assistant for the first account, 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 a first human-computer interaction interface level; the display module 740 is used to display the recommended information content recommended by the AI ​​assistant for the first account at a second human-computer interaction interface level; wherein the second human-computer interaction interface level is higher than the first human-computer interaction interface level.

[0461] In a possible implementation, 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.

[0462] In a possible implementation, 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.

[0463] In a possible implementation, 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.

[0464] In one possible implementation, the display module 740 is used to cancel display of a first information card among the at least two information cards and display a second information card in response to a sliding operation on the first information card; wherein the second information card is an information card that is arranged after the first information card in the stacking order.

[0465] In a possible implementation, the recommended information content includes at least one of the following: first recommended information content after screening or summarizing unread social messages; second recommended information content after screening or summarizing group chat messages or to-do items in a workflow; third recommended information content after screening or summarizing candidate information according to preset rules of the first account; fourth recommended information content after screening or summarizing dynamic information of friends in a social network; fifth recommended information content randomly recommended for the first account; fifth recommended information content after screening or summarizing information content that is potentially of interest to the first account; sixth recommended information content after screening or summarizing information content that is likely to be shared by the first account; seventh recommended information content after screening or summarizing interest groups that are potentially of interest to the first account; eighth recommended information content after screening or summarizing POI information corresponding to the current geographic location; ninth recommended information content after screening or summarizing unfamiliar accounts that are potentially of interest to the first account; tenth recommended information content after screening or summarizing AI tools that are potentially of interest to the first account; eleventh recommended information content after screening or summarizing games that are potentially of interest to the first account; and twelfth recommended information content after screening or summarizing relevant information of third-party applications bound to the first account.

[0466] In a possible implementation, the display module 740 is used to display a quick operation entry associated with the recommended information content during the process of displaying 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.

[0467] In a possible implementation, the quick operation entry is a jump entry for jumping to a 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.

[0468] In a possible implementation, 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, in response to a second operation on the quick operation entry, a reply content of the first account replying to the recommended information content; and send a reply message to the second account, wherein the reply message carries the reply content.

[0469] In a possible implementation, 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 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 a third operation of the quick operation entry, and the reply message carries the quick reply content.

[0470] In a possible implementation, 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.

[0471] In a possible implementation, the recommended information content is associated with multimedia content, and the quick operation entry is an access entry for accessing the multimedia content; the display module 740 is used to display a multimedia content interface of the multimedia content in response to a fifth operation of the quick operation entry; wherein the multimedia content includes at least one of pictures, audio, video, and games.

[0472] In one possible implementation, the quick operation entry is a sharing entry 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 a sixth operation of the quick operation entry, and the fifth account or group is recommended by the AI ​​assistant in the social relationship chain of the first account.

[0473] In a possible implementation, 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.

[0474] In one possible implementation, the display module 740 is used to receive a command message sent by the first account to the AI ​​assistant; and display reply content generated by the AI ​​assistant in response to the command message, wherein the reply content is obtained by the AI ​​assistant after screening or summarizing the information content in the at least one social function based on the command message.

[0475] In a possible implementation, 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 questions 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 summarizes the chat content between the first account and the seventh account.

[0476] In a possible implementation, 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 in response 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.

[0477] In a possible implementation, 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 after the AI ​​assistant summarizes the friend dynamic information of the eighth account.

[0478] In a possible implementation, the display module 740 is used to receive a fourth command message sent by the first account to the AI ​​assistant, wherein the fourth command message is used to ask questions about network information or social chain information associated with the target keyword; and display a fourth reply content generated by the AI ​​assistant in response to the fourth command message, wherein the fourth reply content is the search result of the AI ​​assistant searching for network information or social chain information associated with the target keyword.

[0479] In a possible implementation, 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 a designated function; and display a fifth reply content generated by the AI ​​assistant in response to the fifth command message, where the fifth reply content is the function entry of the designated function fed back by the AI ​​assistant, or the call result after the AI ​​assistant calls the designated function.

[0480] In a possible implementation, the display module 740 is used to display a function entry of the AI ​​assistant function; and in response to a trigger operation on the function entry, display the recommended information content recommended by the AI ​​assistant for the first account.

[0481] In a possible implementation, each of the information cards corresponds to a business function; the acquisition module 720 is used to obtain a 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.

[0482] In a possible implementation, 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.

[0483] In one possible implementation, the social client includes a program function corresponding to the AI ​​assistant, and the acquisition module 720 is used to receive, through the program function corresponding to the AI ​​assistant, a function function supported by the card template registered with at least one business function, and the function function is used to execute a response function corresponding to the recommended information content when called.

[0484] Fig.12 The following is a block diagram of a device for processing information content provided by an exemplary embodiment of the present application. The device includes:

[0485] An acquisition module 820 is used to acquire information content of the first account in at least one business function;

[0486] A determination module 840 is configured to filter or summarize the information content in the at least one business function through an artificial intelligence (AI) assistant to obtain recommended information content, wherein the AI ​​assistant is a recommendation service that filters or summarizes the information content based on at least an AI model;

[0487] The sending module 860 is used to send the recommended information content to the first account.

[0488] Fig.131 is a schematic diagram of a computer device according to an exemplary embodiment. The computer device may include a terminal 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 central processing unit 1301. In some embodiments, the computer device 1300 may also include a basic input / output system (I / O system) 1306 that helps transmit information between various devices in the computer device, and a large-capacity storage device 1307 for storing an operating system 1313, an application program 1314, and other program modules 1315.

[0489] The basic input / output system 1306 includes a display 1308 for displaying information and an input device 1309 such as a mouse and a keyboard for user inputting information. The display 1308 and the input device 1309 are connected to the central processing unit 1301 through 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 inputs from a plurality of other devices such as a keyboard, a mouse, or an electronic stylus. Similarly, the input / output controller 1310 also provides output to a display screen, a printer, or other types of output devices.

[0490] The mass storage device 1307 is connected to the central processing unit 1301 through a mass storage controller (not shown) connected to the system bus 1305. The mass storage device 1307 and its associated computer device readable medium provide non-volatile storage for the computer device 1300. That is, the mass storage device 1307 may include a computer device readable medium (not shown) such as a hard disk or a compact disc read-only memory (CD-ROM) drive.

[0491] 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, cassette, tape, disk storage or other magnetic storage devices. Of course, those skilled in the art will know that the computer device storage medium is not limited to the above. The above-mentioned system memory 1304 and mass storage device 1307 can be collectively referred to as memory.

[0492] According to various embodiments of the present disclosure, the computer device 1300 can also be connected to a remote computer device on a network through a network such as the Internet. That is, the computer device 1300 can be connected to the network 1311 through the network interface unit 1312 connected to the system bus 1305, or the network interface unit 1312 can be used to connect to other types of networks or remote computer device systems (not shown).

[0493] The memory also 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.

[0494] 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.

[0495] 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.

[0496] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0497] A person 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 instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0498] The above description is only an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for processing information content, It is characterized in that The method is executed by a social client logged in with a first account, the social client includes at least one business function, and the method includes: Log in to the first account; 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 in the at least one business function; Display the recommended information content recommended by the AI ​​assistant for the first account.

2. The method according to claim 1, It is characterized in that 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 comprising information content obtained by the AI ​​assistant after screening or summarizing information content in a first business function, the first business function being located at a first human-computer interaction interface level; The displaying of the recommended information content recommended by the AI ​​assistant for the first account includes: Displaying, at a second human-computer interaction interface level, recommended information content recommended by the AI ​​assistant for the first account; 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, It is characterized in that The displaying, at the second human-computer interaction interface level, of the recommended information content recommended by the AI ​​assistant for the first account 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, It is characterized in that 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, It is characterized in that 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 claim 5, It is characterized in that 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 the stacking order.

7. The method according to any one of claims 1 to 6, It is characterized in that The recommended information content includes at least one of the following: The first recommended information content after filtering or summarizing the unread social messages; Second recommended information content after filtering or summarizing group chat messages or to-do items in the workflow; third recommended information content after screening or summarizing the candidate information according to the preset rules of the first account; The fourth recommended information content is obtained by screening or summarizing the dynamic information of friends in the social network; The fifth recommended information content randomly recommended for the first account; fifth recommended information content obtained by screening or summarizing 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 be of potential interest to the first account; The eighth recommended information content is obtained by filtering or summarizing the POI information corresponding to the current geographical location; ninth recommended information content after screening or summarizing unfamiliar accounts that may be of potential interest to the first account; a tenth recommended information content after screening or summarizing by the AI ​​tool that may be of potential interest to the first account; an eleventh recommended information content after screening or summarizing 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 6, It is characterized in that The method further comprises: During the process of displaying the recommended information content, 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 5, It is characterized in that 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 in the at least one business function based on the command message.

10. The method according to claim 9, It is characterized in that 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 summarizing the chat content between the first account and the seventh account.

11. The method according to claim 9, It is characterized in that 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 after the AI ​​assistant summarizes the chat content of the chat group to which the first account belongs.

12. The method according to claim 9, It is characterized in that 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 summarizes the friend dynamic information of the eighth account.

13. The method according to claim 9, It is characterized in that 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 chain information associated with a target 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 after the AI ​​assistant searches the network information or social chain information associated with the target keyword.

14. The method according to claim 9, It is characterized in that 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 specified 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 specified function fed back by the AI ​​assistant, or the calling result after the AI ​​assistant calls the specified function.

15. The method according to claim 1, It is characterized in that 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, It is characterized in that 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, It is characterized in that The social client includes a program function corresponding to the AI ​​assistant, and the method further includes: The card template registered for the at least one business function is received through a program function corresponding to the AI ​​assistant.

18. The method according to claim 16, It is characterized in that 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 registered with the at least one business function 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, It is characterized in that 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, It is characterized in that The method comprises: Obtaining information content of the first account in at least one business function; The information content in the at least one business function is screened or summarized by an artificial intelligence (AI) assistant to obtain recommended information content, wherein the AI ​​assistant is a recommendation service that screens or summarizes the information content based on at least an AI model; The recommended information content is sent to the first account.

21. An information content processing device, It is characterized in that The device comprises: A login module, used to log in to the first account; 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 in the at least one business function; The display module is used to display the recommended information content recommended by the AI ​​assistant for the first account.

22. An information content processing device, It is characterized in that The device comprises: An acquisition module, used to acquire information content of the first account in at least one business function; A determination module, configured to filter or summarize the information content in the at least one business function through an artificial intelligence (AI) assistant to obtain recommended information content, wherein the AI ​​assistant is a recommendation service that filters or summarizes the information content based on at least an AI model; A sending module is used to send the recommended information content to the first account.

23. A computer device, It is characterized in that The computer device includes 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, It is characterized in that The readable storage medium 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.

25. A computer program product, It is characterized in that The computer program product stores at least one program, 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