Information processing method and apparatus, electronic device, computer-readable storage medium, and computer program product

Abstract

The present application provides an information processing method and apparatus, an electronic device, a computer-readable storage medium, and a computer program product. The method comprises: displaying first recommendation information on a human-computer interaction interface on which a first account has been logged in, wherein the first recommendation information is displayed when a second account triggers a positive feedback operation on the first recommendation information, and the first account has a social relationship with the second account; displaying a first interaction control in the human-computer interaction interface, wherein the first interaction control is in a first state, and the first state indicates that the first account has not interacted with the second account with respect to the first recommendation information; and in response to a triggering operation on the first interaction control, sending first interaction information to the second account, and switching the first interaction control from the first state to a second state, wherein the second state indicates that the first account has interacted with the second account with respect to the first recommendation information.

Description

Information processing method and device, electronic equipment, computer readable storage medium and computer program product

[0001] Cross-reference of related applications

[0002] The present application is based on and claims priority to Chinese Patent Application No. 2025104906028, filed on April 17, 2025, the entire contents of which are incorporated herein by reference. TECHNICAL FIELD

[0003] The present application relates to the technical field of data processing, and in particular to an information processing method and device, electronic equipment, computer readable storage medium and computer program product. BACKGROUND

[0004] In the current flourishing development of Internet technology, social interaction has become one of the core functions of various information platforms. Users not only hope to obtain rich information on information platforms, but also expect to establish and strengthen social relationships through interaction with others. In an information recommendation system, information is recommended to users in combination with the social relationships or behavior data of the users (i.e., a first account).

[0005] In the related technical information interaction platform, when information is recommended, only information that has been interacted with by other users (i.e., a second account) having a social relationship with the user is pushed to the user in a single direction. The information is unidirectionally transmitted from the other user to the user. This unidirectional information transmission mechanism only establishes a single data push link and lacks a reverse fast feedback mechanism, thereby hindering the formation of an interaction closed loop between the first account and the second account, restricting the transmission and processing of interactive information, and also limiting further interaction with the recommended information, which in turn leads to low information interaction rates between different users and reduces the information interaction efficiency between different accounts. SUMMARY

[0006] Therefore, the embodiments of the present application provide an information processing method and device, electronic equipment, computer readable storage medium and computer program product, which can improve the information interaction efficiency between different accounts.

[0007] The technical solutions of the embodiments of the present application are implemented as follows:

[0008] The embodiments of the present application provide an information processing method, which is executed by an electronic device, and the method comprises the following steps:

[0009] display first recommendation information in a man-machine interactive interface based on a first account, wherein the first recommendation information is displayed in a case where a second account triggers a positive feedback operation for the first recommendation information, and the first account has a social relationship with the second account;

[0010] display a first interaction control in the man-machine interactive interface, wherein the first interaction control is in a first state, and the first state represents that the first account has not interacted with the second account for the first recommendation information;

[0011] in response to a trigger operation for the first interaction control, send first interaction information to the second account, and

[0012] switch the first interaction control from the first state to a second state, wherein the second state represents that the first account has interacted with the second account for the first recommendation information.

[0013] Embodiments of the present application provide an information processing device, the device comprising:

[0014] an information display module configured to display first recommendation information in a man-machine interactive interface based on a first account, wherein the first recommendation information is displayed in a case where a second account triggers a positive feedback operation for the first recommendation information, and the first account has a social relationship with the second account;

[0015] a control display module configured to display a first interaction control in the man-machine interactive interface, wherein the first interaction control is in a first state, and the first state represents that the first account has not interacted with the second account for the first recommendation information;

[0016] an information sending module configured to, in response to a trigger operation for the first interaction control, send first interaction information to the second account, and switch the first interaction control from the first state to a second state, wherein the second state represents that the first account has interacted with the second account for the first recommendation information.

[0017] Embodiments of the present application provide an electronic device, the electronic device comprising:

[0018] a memory configured to store computer executable instructions or computer programs;

[0019] a processor configured to execute the computer executable instructions or computer programs stored in the memory to implement the information processing method provided by embodiments of the present application.

[0020] This application provides a computer-readable storage medium storing a computer program or computer-executable instructions, which, when executed by a processor, implements the information processing method provided in this application.

[0021] This application provides a computer program product, including a computer program or computer executable instructions. When the computer program or computer executable instructions are executed by a processor, they implement the information processing method provided in this application.

[0022] The embodiments of this application have the following beneficial effects:

[0023] On the one hand, on the human-computer interaction interface based on the first account login, the first recommended information is displayed, which has been positively recommended by the second account that has a social relationship with the first account. The positive feedback operation reflects the second account's preference for the first recommended information (positive sentiment) and reflects the correlation between the first recommended information, the second account, and the first account. The data association between the first account, the second account, and the first recommended information is constructed by using social relationship data and positive feedback operation data. Based on this data association, the human-computer interaction interface is driven to display information, thereby improving the relevance and targeting of information recommendations.

[0024] On the other hand, by triggering the first interactive control to send the first interactive information to the second account, the first recommendation information is recommended by the second account to the first account, and then the feedback (first interactive information) from the first account to the first recommendation information is returned to the second account. This process opens up the reverse data transmission link for the first recommendation information, transforms the one-way data transmission into two-way data communication, and visually displays the interaction process between the first account and the second account, realizing the closed loop of interaction between the first account and the second account, improving the information interaction rate for the first recommendation information. At the same time, the quick feedback through the interactive control simplifies the operation process of sending interactive information and also improves the interaction efficiency between different accounts.

[0025] Furthermore, in response to a trigger operation on the first interactive control, the first interactive control is switched from a first state representing no interaction to a second state representing interaction. This state switching process records and clearly displays the historical state of the interaction on the human-computer interaction interface, which can effectively avoid repeated trigger operations on the first interactive control by the user, thereby reducing the overhead of invalid repeated interactive data transmission and processing, and thus improving information processing efficiency and operating performance. Attached Figure Description

[0026] Figure 1 is a schematic diagram of the architecture of the information processing system 100 provided in an embodiment of this application;

[0027] Figure 2 is a structural schematic diagram of the terminal 400-1 provided in an embodiment of this application;

[0028] Figure 3A is a first flowchart of the information processing method provided in an embodiment of this application;

[0029] Figure 3B is a second flowchart of the information processing method provided in an embodiment of this application;

[0030] Figure 3C is a schematic diagram of the third process of the information processing method provided in the embodiments of this application;

[0031] Figure 3D is a schematic diagram of the fourth process of the information processing method provided in the embodiments of this application;

[0032] Figure 3E is a fifth flowchart of the information processing method provided in the embodiments of this application;

[0033] Figure 3F is a schematic diagram of the sixth flow of the information processing method provided in the embodiments of this application;

[0034] Figure 3G is a schematic diagram of the seventh process of the information processing method provided in the embodiments of this application;

[0035] Figure 3H is a schematic diagram of the eighth process of the information processing method provided in the embodiment of this application;

[0036] Figure 3I is a ninth flowchart illustrating the information processing method provided in an embodiment of this application;

[0037] Figure 4A is a first schematic diagram of information processing in an information recommendation interface provided in an embodiment of this application;

[0038] Figure 4B is a second schematic diagram of information processing in the information recommendation interface provided in an embodiment of this application;

[0039] Figure 4C is a third schematic diagram of information processing in the information recommendation interface provided in an embodiment of this application;

[0040] Figure 5A is a first schematic diagram of information processing in an interactive notification interface provided by an embodiment of this application;

[0041] Figure 5B is a second schematic diagram of information processing in an interactive notification interface provided in an embodiment of this application;

[0042] Figure 6A is a first schematic diagram of information processing in the contact interface provided in an embodiment of this application;

[0043] Figure 6B is a second schematic diagram of information processing in the contact interface provided in an embodiment of this application;

[0044] Figure 7 is a schematic diagram of mutual feedback between different accounts provided in an embodiment of this application;

[0045] Figure 8A is a first schematic diagram of information processing through a floating contact interface provided in an embodiment of this application;

[0046] Figure 8B is a second schematic diagram of information processing through a floating contact interface provided in an embodiment of this application;

[0047] Figure 8C is a schematic diagram illustrating the application of the switching recommendation information provided in an embodiment of this application;

[0048] Figure 8D is a schematic diagram showing the reasons for recommendation and statistical data provided in an embodiment of this application;

[0049] Figure 9A is a schematic diagram of the deletion of the recommendation information display position provided in an embodiment of this application;

[0050] Figure 9B is a schematic diagram of the interactive notification function for disabling recommendation information provided in an embodiment of this application;

[0051] Figure 10 is a schematic diagram of the editing interaction information provided in an embodiment of this application;

[0052] Figure 11 is a schematic diagram of generating first interactive information through artificial intelligence according to an embodiment of this application;

[0053] Figure 12 is a schematic diagram of the interaction between the first account and the second account provided in an embodiment of this application;

[0054] Figure 13 is a schematic diagram of providing feedback to recommenders via the "thank you" button according to an embodiment of this application;

[0055] Figure 14 is a schematic diagram of expressing gratitude to recommenders through a friend list according to an embodiment of this application;

[0056] Figure 15 is a schematic diagram of receiving a thank-you feedback provided in an embodiment of this application.

[0057] It should be noted that the terms "first" and "second" mentioned above are only used to distinguish between different options and do not represent the degree of superiority or inferiority of the options or their priority in the implementation process. Detailed Implementation

[0058] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0059] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0060] In the following description, the terms "first / second / third" are used merely to distinguish similar objects and do not represent a specific ordering of objects. It is understood that "first / second / third" may be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0061] In this application embodiment, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0062] Unless otherwise specified, "at least one" as used below refers to one or more cases, and "multiple" can refer to two or more cases.

[0063] Unless otherwise defined, all technical and scientific terms used in the embodiments of this application have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in the embodiments of this application is for the purpose of describing the embodiments of this application only and is not intended to limit this application.

[0064] In the implementation of this application, the collection and processing of relevant data should strictly comply with the requirements of relevant laws and regulations, obtain the informed consent or separate consent of the personal information subject, and carry out subsequent data use and processing within the scope of laws and regulations and the authorization of the personal information subject.

[0065] Before providing a further detailed description of the embodiments of this application, the nouns and terms involved in the embodiments of this application will be explained, and the nouns and terms involved in the embodiments of this application shall be interpreted as follows.

[0066] 1) Responding to: used to indicate the conditions or states on which the operation is performed depends. When the conditions or states on which it depends are met, one or more operations can be performed in real time or with a set delay. Unless otherwise specified, there is no restriction on the order in which the multiple operations are performed.

[0067] 2) Human-computer interaction interface, which is used to provide human-computer interaction functions / interface to display recommended information and interactive information.

[0068] For example, graphical user interfaces (GUIs) include augmented reality (AR) interfaces, virtual reality (VR) interfaces, voice user interfaces (VUIs), interactive projection interfaces (using projection technology to display information on a flat surface), eye-tracking interfaces (interfaces controlled by detecting the user's gaze), holographic interfaces (three-dimensional holograms formed by projecting images using holographic projection technology, allowing users to see stereoscopic images without wearing special glasses), multimodal interfaces (interfaces that combine multiple interaction methods, such as tactile, visual, and auditory interaction), and brain-machine interfaces (BMIs).

[0069] 3) Recommended information refers to information displayed to users (first or second account) based on certain rules, algorithms, or behavioral data. Recommended information can include products, services, news, events, games, etc., with the aim of arousing user interest and encouraging further interaction with the recommended content. The generation of recommended information is often related to the behavior of the second account; when the second account performs specific actions on certain content, it will display that content as recommended information to the first account with which it has a social relationship.

[0070] 4) Positive feedback refers to actions taken by the second account that express a positive attitude or approval towards the recommended information. This can take many forms, such as liking, saving, commenting (positive comments), or making purchases. By recognizing the positive feedback actions of the second account, the recommended information is displayed to the first account that has a social relationship with the second account.

[0071] 5) Interactive controls are actionable elements displayed in the human-computer interaction interface, used to trigger interactive behaviors related to the recommended information. They are presented to the user in an intuitive graphical, button, or other form for easy operation. Interactive controls provide users with a way to interact with recommended information and secondary accounts; users can trigger specific interactive processes through clicks, swipes, and other actions.

[0072] 6) Interactive messages refer to content sent by the first account to the second account after triggering an interactive control, used to express a certain intention or to communicate. The content and form of interactive messages can be determined according to the specific business scenario and interactive purpose, and may include simple words of thanks, inquiries, or expressions of opinions. The aim is to promote communication and exchange between the first and second accounts regarding recommended information, thereby enhancing social interactivity.

[0073] 7) The first state is the state of the interactive control when it has not been triggered. In this state, the interactive control typically uses a specific appearance, text, or logo to indicate that the first account has not yet interacted with the second account regarding the recommendation information. It conveys a prompt to the user that an interactive action is currently possible, guiding the user to click or operate the interactive control.

[0074] 8) The second state is the state of the interactive control after it is triggered. When the first account triggers the interactive control and sends interactive information to the second account, the interactive control will switch from the first state to the second state. The second state clearly indicates to the user that the first account has interacted with the second account regarding the recommendation information by changing the appearance, text, or logo, avoiding duplicate operations by the user, and also recording the historical state of the interaction.

[0075] 9) Interest level is a quantitative or qualitative indicator used to measure the first account's attention, liking and willingness to further explore specific first recommended information. The interest level is based on a comprehensive evaluation of multiple factors, including the first account's historical interaction behavior with the first recommended information (such as browsing, liking, commenting, collecting, sharing, etc.), the first account's historical preference data (including but not limited to the types of content viewed in the past, the topics of information interacted with, etc.), and the first account's basic characteristics (such as age, gender, interest tags, etc.).

[0076] In information interaction platforms using related technologies, when recommending information, information that has been interacted with by other users with social relationships (i.e., second accounts) is pushed to the user in a one-way manner. Information is passed from other users to the user in a one-way manner. This one-way information transmission mechanism only establishes a single data push link and lacks a reverse rapid feedback mechanism, thereby hindering the formation of an interactive closed loop between the first account and the second account, restricting the transmission and processing of interactive information, and limiting further interaction with recommended information. As a result, the information interaction rate between different users is low, and the information interaction efficiency between different accounts is reduced.

[0077] Based on the above analysis, the applicant found that the information processing methods of related technologies cannot provide rapid feedback on information recommended by a second account. In response to the above problem, this application provides an information processing method that can improve the efficiency of information interaction between different accounts.

[0078] The following describes exemplary applications of the electronic devices provided in the embodiments of this application. These electronic devices can be implemented as various types of terminals such as laptops, tablets, desktop computers, set-top boxes, smartphones, smart speakers, smartwatches, smart TVs, and in-vehicle terminals, or as servers. The following will describe exemplary applications when the electronic device is implemented as a terminal.

[0079] Referring to Figure 1, which is a schematic diagram of the architecture of the information processing system 100 provided in the embodiment of this application, in order to support an information processing application, the terminal (terminal 400-1 and terminal 400-2 are shown as examples) connects to the server 200 through the network 300. The network 300 can be a wide area network or a local area network, or a combination of the two.

[0080] The human-computer interaction interface 410-1 of terminal 400-1 is logged in with a first account, and the human-computer interaction interface 410-2 of terminal 400-2 is logged in with a second account. Terminal 400-1 is used to display the first recommendation information and the first interactive control on the human-computer interaction interface 410-1. In response to the trigger operation of the first interactive control, the first interactive information is sent to the second account logged in on terminal 400-2 through network 300 and server 200.

[0081] Taking a video scenario as an example, terminal 400-1 displays the video that terminal 400-2 has performed a positive feedback operation on (such as liking, collecting, or commenting positively) and the corresponding interactive control (such as a thank you button) for the video. In response to the trigger operation of the thank you button, a thank you message is sent to terminal 400-2.

[0082] Taking the Moments feature in an instant messaging client as an example, terminal 400-1 displays Moments posts that terminal 400-2 has liked or commented on, as well as the corresponding interactive controls (such as a thank you button). In response to the triggering operation of the thank you button, a thank you message is sent to terminal 400-2.

[0083] Taking a social media scenario as an example, terminal 400-1 displays information (such as articles, music, pictures, news, etc.) commented on by terminal 400-2 and corresponding interactive controls (such as a thank you button). In response to the triggering operation of the thank you button, a thank you message is sent to terminal 400-2.

[0084] In some embodiments, server 200 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. Terminals and servers can be connected directly or indirectly via wired or wireless communication, which is not limited in this embodiment.

[0085] Referring to Figure 2, which is a schematic diagram of the structure of a terminal 400-1 provided in an embodiment of this application, the terminal 400-1 shown in Figure 2 includes: at least one processor 410, a memory 450, at least one network interface 420, and a user interface 430. The various components in the terminal 400-1 are coupled together through a bus system 440. It is understood that the bus system 440 is used to implement communication between these components. In addition to a data bus, the bus system 440 also includes a power bus, a control bus, and a status signal bus. However, for clarity, all buses are labeled as bus system 440 in Figure 2.

[0086] The processor 410 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0087] User interface 430 includes one or more output devices 431 that enable the presentation of media content, including one or more speakers and / or one or more visual displays. User interface 430 also includes one or more input devices 432, including user interface components that facilitate user input, such as a keyboard, mouse, microphone, touch screen display, camera, other input buttons and controls.

[0088] The memory 450 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state storage, hard disk drives, optical disk drives, etc. The memory 450 may optionally include one or more storage devices physically located away from the processor 410.

[0089] The memory 450 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), and the volatile memory may be random access memory (RAM). The memory 450 described in this application embodiment is intended to include any suitable type of memory.

[0090] In some embodiments, memory 450 is capable of storing data to support various operations, examples of which include programs, modules, and data structures or subsets or supersets thereof, as illustrated below.

[0091] Operating system 451 includes system programs for handling various basic system services and performing hardware-related tasks, such as the framework layer, core library layer, driver layer, etc., for implementing various basic business functions and handling hardware-based tasks;

[0092] The network communication module 452 is used to reach other electronic devices via one or more (wired or wireless) network interfaces 420, exemplary network interfaces 420 including: Bluetooth, WiFi, and Universal Serial Bus (USB), etc.

[0093] Presentation module 453 is configured to enable the presentation of information (e.g., a user interface for operating peripheral devices and displaying content and information) via one or more output devices 431 (e.g., a display screen, a speaker, etc.) associated with user interface 430;

[0094] The input processing module 454 is used to detect and translate one or more user inputs or interactions from one or more input devices 432.

[0095] In some embodiments, the apparatus provided in this application can be implemented in software. FIG2 shows an information processing apparatus 455 stored in memory 450, which can be software in the form of programs and plug-ins, including the following software modules: information display module 4551, control display module 4552, and information sending module 4553. These modules are logically related, and therefore can be arbitrarily combined or further divided according to the functions they implement. The functions of each module will be described below.

[0096] In some embodiments, the terminal or server can implement the information processing method provided in this application by running various computer-executable instructions or computer programs. For example, computer-executable instructions can be microprogram-level commands, machine instructions, or software instructions. Computer programs can be native programs or software modules in an operating system; they can be native applications (APPs), i.e., programs that need to be installed in the operating system to run, such as short video APPs or instant messaging APPs; or they can be applets that can be embedded in any APP, i.e., programs that only need to be downloaded to a browser environment to run. In summary, the aforementioned computer-executable instructions can be any form of instruction, and the aforementioned computer programs can be any form of application, module, or plugin.

[0097] The information processing method provided in this application will be described in conjunction with exemplary applications and implementations of the terminals provided in the embodiments of this application.

[0098] Referring to Figure 3A, which is a first flowchart of the information processing method provided in the embodiment of this application, the steps shown in Figure 3A will be described with the terminal as the main focus.

[0099] In step 101, the first recommendation information is displayed on the human-computer interaction interface based on the first account login. The first recommendation information is displayed when the second account triggers a positive feedback operation on the first recommendation information. The first account and the second account have a social relationship.

[0100] In some embodiments, the identity document (ID), avatar, or nickname of the second account can also be displayed in the information display area. Alternatively, only the number of second accounts that have provided positive feedback to the first recommendation information can be displayed, without showing the specific second accounts. The second accounts or the number of second accounts can be displayed anywhere on the human-computer interaction interface without obscuring the first recommendation information, or they can be displayed as cards on the human-computer interaction interface. The display position and format of the second accounts are not limited here. Positive feedback indicators, such as likes, favorites, and positive comments, can also be displayed for the second accounts that have provided positive feedback to the first recommendation information. In response to a trigger operation on the second account, the system redirects to display the information details interface of the second account.

[0101] For example, the first recommended information can be at least one of the following: videos, music, advertisements, games, articles, etc. If the first recommended information is a video, the video can be a selfie video, a movie, a TV series, etc. Positive feedback actions include, but are not limited to, at least one of the following: liking, saving, positive comments, and recommending. Social relationships include, but are not limited to, at least one of the following: one-way or two-way friendships, non-friendships but interactions in the comment area of ​​recommended information (e.g., replying to comments, following, liking, etc.), non-friendships but interactions through a chat window (e.g., one-on-one chat, or participating in the same group chat), and non-friendships but having mutual friends.

[0102] In some embodiments, when the human-computer interaction interface is an information recommendation interface, step 101 "displaying the first recommended information in the human-computer interaction interface based on the first account login" can be achieved by performing the following process: displaying the first recommended information in the information display area of ​​the information recommendation interface based on the first account login.

[0103] For example, the information recommendation interface is a dedicated interface for information recommendation, and can be an interface within an instant messaging client or a video platform client. The information recommendation interface also includes areas other than the information display area. These other areas can display the ID or avatar of the fourth account that posted the first recommendation, and can also display at least one of the following: the sending time of the first recommendation, a brief description of the first recommendation, and related topics or tags.

[0104] In some embodiments, when the human-computer interaction interface is a contact interface, step 101 "displaying the first recommendation information in the human-computer interaction interface based on the first account login" can be achieved by performing the following process: displaying the first recommendation information in the contact interface based on the first account login.

[0105] For example, the contact interface displays the contact objects, such as contacts or groups. The contact interface includes a contact area. In the contact interface based on the first account login, the first recommended information is displayed in the area outside the contact area. The outer area can be a pre-defined proportion of the contact interface starting from the top, or an area that adaptively changes according to the size of the contact area. For example, if the contact area occupies 60% of the contact interface, then the outer area will adaptively update to 40% of the contact interface size.

[0106] In some embodiments, when the human-computer interaction interface is an interactive notification interface, step 101 "displaying first recommendation information on the human-computer interaction interface based on the first account login" can be achieved by performing the following process: displaying at least one second account and the first recommendation information of the second account performing a positive feedback operation in the interactive notification interface.

[0107] For example, the interactive notification interface can be an interface used to display interactive notifications in an instant messaging client, an interface used to display interactive notifications in a video app, or an interface used to display interactive notifications in any information interaction platform. The interactive notification interface includes multiple interactive notifications, and each interactive notification includes a second account and a first recommendation message from the second account that has provided positive feedback. The interactive notification interface can display the second account's avatar, name, or nickname, etc. The first recommendation message included in different interactive notifications can be the same or different. The first recommendation message can be displayed as a thumbnail or a link.

[0108] Referring again to Figure 3A, in step 102, a first interactive control is displayed in the human-computer interaction interface. The first interactive control is in a first state, which indicates that the first account has not yet interacted with the second account regarding the first recommendation information.

[0109] For example, the first interactive control can be used to send a thank-you message to the second account, or to send a message to the second account indicating that it is not interested in the first recommended information. The form of the message includes, but is not limited to, at least one of the following: text, image, voice, emoticon, etc.

[0110] In some embodiments, when the human-computer interaction interface is an information recommendation interface, step 102 "displaying the first interactive control in the human-computer interaction interface" can be achieved by performing the following process: displaying the first interactive control in the information display area.

[0111] For example, the first interactive control can be displayed in the form of a card in the information display area, or it can be displayed floating above the first recommended information. It can also be displayed in an area outside the information display area in the information recommendation interface. Taking a video scenario as an example, the information display area is used to display the video (first recommended information), and the first interactive control is displayed in an area outside the information display area, such as below the video playback page.

[0112] In some embodiments, when the number of second accounts triggering the positive feedback operation is at least one, the above-mentioned "displaying the first interactive control in the information display area" can be achieved by performing at least one of the following processes:

[0113] Process 1: Display each second account and its corresponding first interactive control in the information display area. When any first interactive control receives a trigger operation, it will trigger the execution of sending first interactive information to the second account corresponding to that first interactive control.

[0114] For example, each secondary account can be identified by its name, icon, or other identifier. A threshold can be set for the number of secondary accounts that can be displayed. If the number of secondary accounts exceeds the threshold, multiple secondary accounts will be collapsed, and the corresponding primary interactive controls will also be collapsed. If the number of secondary accounts exceeds the threshold, an expand icon can be displayed within a preset range of secondary accounts, such as below or to the right. In response to a trigger action on the expand icon, all secondary accounts will be fully displayed. Multiple secondary accounts can be displayed in a list or scrolling format. When any primary interactive control receives a trigger action, it will send a first interactive message to the secondary account corresponding to that primary interactive control as a positive feedback action. For example, upon receiving a trigger action on any primary interactive control, a thank-you message can be sent to the secondary account corresponding to that primary interactive control, such as "Thank you for liking this video, which allows me to see such a great video!"

[0115] This application embodiment displays a first interactive control corresponding to each second account, which allows the first interactive information to be sent individually or in part by the second accounts. This improves the targeting of the interaction, enhances the social connection and interaction rate between the second accounts corresponding to the triggered first interactive control, and improves the user experience.

[0116] Process 2: Display each second account and a first interactive control for batch interaction in the information display area. The first interactive control is used to trigger the execution of sending the first interactive information to each second account when a trigger operation is received.

[0117] For example, the first interactive control can be displayed in any blank area of ​​the information display area, or displayed as a card on top of the information display area. Different first recommended information corresponds to different first interactive controls.

[0118] This application embodiment uses a first interactive control to simultaneously send first interactive information to multiple second accounts, simplifying the operation process of sending first interactive information. Triggering the control once can send information to multiple second accounts simultaneously, saving the time of sending information sequentially and improving the efficiency of interaction between the first account and multiple second accounts.

[0119] In some embodiments, at least one of the following may be displayed in the information display area, or in an area outside the information display area in the information recommendation interface: introductory information of the first recommendation information, and the homepage entry of the fourth account that published the first recommendation information.

[0120] For example, if the first recommended item is a video, its description could include the video's text and tags; if it's an article, its description could include the article's summary and keywords; and if it's music, its description could include the song title and lyrics. The fourth account's homepage entry is used to display the fourth account's homepage upon being triggered, or, if the first recommended item is jointly published by multiple fourth accounts, to display a list of the fourth accounts that published the first recommended item.

[0121] In some embodiments, when there are multiple first recommended information items displayed in the information display area and multiple second accounts that trigger the first recommended information items, the above-mentioned "displaying the first interactive control in the information display area" can be achieved by performing the following process: displaying the first interactive control corresponding to each first recommended information item in the information display area.

[0122] For example, each first interactive control is used to respond to a second account that has performed a positive feedback operation on the first recommendation information corresponding to that first interactive control. Different first recommendation information can correspond to different first interactive controls, or they can correspond to the same first interactive control. A selection control corresponding to each first recommendation information can also be displayed in the information display area. In response to a trigger operation on the selection control corresponding to any first recommendation information, a list of second accounts that have performed a positive feedback operation on that first recommendation information is displayed. In response to a selection operation on a subset of second accounts, the selected subset of second accounts is set to a selected state. The selected state indicates that the selected subset of second accounts will receive the first interactive information after triggering the first interactive control. The selected state can be represented in at least one of the following ways: enlarging the name or avatar of the second account, thickening the border of the second account, flashing, setting a background color different from other second objects, or displaying a checked checkbox.

[0123] This application embodiment displays corresponding interactive controls for each recommended piece of information. Users can personalize their interactions with each recommendation based on their interests and needs, enhancing user autonomy and participation. Users can directly interact with recommended information of interest in the information display area without needing to navigate to other pages or perform complex operations, improving the efficiency and convenience of interaction. The interactive controls are closely linked to the recommended information, allowing users to more intuitively understand the relationship between interactive actions and recommended information, enhancing the relevance of information and the user experience.

[0124] In some embodiments, when the human-computer interaction interface is an interactive notification interface, the contact object interface includes a contact object area, which includes at least one second account. Step 102, "Displaying the first interactive control in the human-computer interaction interface," can be achieved by performing the following process: displaying the first interactive control corresponding to at least one second account in the contact object interface.

[0125] For example, the contact area of ​​the contact interface displays at least one secondary account and a primary interaction control. The at least one secondary account in the contact area is displayed as a list. If there are multiple secondary accounts, they are sorted according to at least one of the following criteria: sorted in descending order of the number of positive feedbacks from the secondary account; sorted in descending order of social distance from the primary account; sorted in descending order of similarity to the primary account's preferences; sorted in descending order of the frequency of receiving corresponding historical interaction information for triggered historical recommendation information; and sorted in descending order of the frequency of interaction with the primary account.

[0126] Taking the number of positive feedbacks from the second account as an example, if second account A has 6 positive feedbacks, second account B has 4, and second account C has 10, then the descending order of the multiple second accounts is: second account C, second account A, second account B. Taking social distance from the first account as an example, social distance can be determined by factors such as the number of mutual friends between the second and first accounts, the frequency of interaction, and the time of the last interaction. If second account A has 3 mutual friends with the first account, second account B has 4, and second account C has 5, then the descending order of the multiple second accounts is: second account A, second account B, second account C. Taking the similarity of preferences with the first account as an example, the first account's preferences can be determined by the types of recommendation information whose interaction frequency with the first account exceeds a frequency threshold. For example, the types of recommendation information whose interaction frequency with the first account exceeds a frequency threshold can be counted, and these types can be vectorized to obtain multiple type vectors. These multiple type vectors can be merged into a preference vector. The account information of the second account can be vectorized to obtain the second account vector. The similarity between the preference vector and the second account vector can be determined as the similarity level. The similarity can be achieved by any of the following algorithms: cosine similarity, Euclidean distance, Manhattan distance, and Pearson correlation coefficient. Taking cosine similarity as an example, the vector product of the preference vector and the second account vector can be determined; the length product of the length of the preference vector and the length product of the second account vector can be determined; and the ratio of the vector product to the length product can be determined as the similarity level. For example, if the preference vector is m and the second account vector is n, then the vector product is m*n. The length of the preference vector is |m|, and the length of the second account vector is |n|, so the length product is |m|*|n|. The ratio of the vector product to the length product is (m*n) / (|m|*|n|), which is used as the similarity. If the similarity between the preferences of second account A and first account is 45%, the similarity between the preferences of second account B and first account is 90%, and the similarity between the preferences of second account C and first account is 77%, then the descending order of the multiple second accounts is: second account B, second account C, second account A. Taking the frequency of receiving corresponding historical interaction information as an example, for the 10 triggered historical recommendation messages, within a month, the frequency of second account A receiving corresponding historical interaction information is 6, the frequency of second account B receiving corresponding historical interaction information is 8, and the frequency of second account C receiving corresponding historical interaction information is 10. Then the descending order of the multiple second accounts is: second account C, second account B, second account A. Taking the interaction frequency with the first account as an example, if the interaction frequency between the second account A and the first account is 7, the interaction frequency between the second account A and the first account is 12, and the interaction frequency between the second account A and the first account is 5 within a week, then the descending order of the multiple second accounts is: second account B, second account A, second account C.

[0127] In some embodiments, the above-mentioned "displaying a first interactive control corresponding to at least one second account in the contact object interface" can be achieved by performing the following process: displaying at least one second account and a first interactive control corresponding to each second account in the contact object area, wherein a first interactive control is used to send a first interactive message to the second account corresponding to any first interactive control when triggered.

[0128] For example, the contact area can display at least one second account and a first interactive control corresponding to each second account in the form of a list. If there are multiple second accounts, the multiple second accounts can be sorted. The sorting parameters include, but are not limited to, at least one of the following: frequency of interaction with the first account, number of positive feedbacks, social distance with the first account, and similarity of preferences with the first account.

[0129] In some embodiments, the above-mentioned "displaying a first interactive control corresponding to at least one second account in the contact object interface" can also be achieved by performing the following process: displaying at least one second account and a first interactive control for batch interaction in the contact object area, wherein the first interactive control is used to send a first interactive message to each second account when triggered.

[0130] For example, a selection control can be displayed in the contact area. In response to a trigger operation on the selection control, a list of second accounts that have performed positive feedback operations on the first recommendation information is displayed. In response to a selection operation on some second accounts, the selected second accounts are set to a selected state. The selected state indicates that the selected second accounts will receive the first interactive information after the first interactive control is triggered. The selected state can be represented in at least one of the following ways: enlarging the name or avatar of the second account, thickening the border of the second account, flashing, setting a background color that is different from other second objects, or displaying a checked checkbox.

[0131] This application embodiment displays a first interactive control corresponding to each second account in the contact area, allowing users to personalize interactions for each account, enhancing the interaction experience with specific second accounts and improving the targeted effectiveness of interactions. Displaying first interactive controls for batch interactions allows users to send interactive information to multiple second accounts at once, improving interaction efficiency, and is particularly suitable for scenarios requiring widespread notification or invitation.

[0132] In some embodiments, when the human-computer interaction interface is a contact interface, step 102, "displaying the first interactive control in the human-computer interaction interface," can be achieved by performing the following processing: displaying a first interactive control corresponding one-to-one with each second account in the display position of each first recommendation information in the interactive notification interface; or, displaying a first interactive control for batch interaction for each second account in the interactive notification interface; wherein, when there are multiple first recommendation information, the display positions of the multiple first recommendation information are sorted in a specific order, and the specific order is sorted according to at least one of the following parameters: publication time, time of receiving positive feedback operation, number of times positive feedback operation is received, and the degree of interest of the first account in the first recommendation information.

[0133] For example, the first interactive control corresponding to each second account can be displayed, or a first interactive control for batch interaction with all second accounts regarding the first recommended information can be displayed, similar to the example of the information display area above, and will not be repeated here. Second accounts, first recommended information, and first interactive controls are displayed in a feed format. One display slot is used to display one interaction record, and one interaction record includes one second account, one first recommended information, and one first interactive control. Display slots can include interaction records involving other accounts besides interaction with second accounts. Other accounts include any of the following: the publisher of the first recommended information, or an account that has viewed the same first recommended information and interacted with the first account's comments under the first recommended information. Follow controls can also be displayed in the display slots. One follow control corresponds to one unfollowed other account. In response to the triggering operation of the follow control corresponding to any other account, if any other account has not followed the first account, it becomes a one-way follower of that other account; if any other account has followed the first account, it establishes a friend relationship with that other account. The first recommended information does not refer to a specific piece of information, but rather information recommended to the first account. The first recommended information triggered by different second accounts can be the same or different. The sorting method can be descending or ascending. Taking descending sorting as an example, if the parameter is the publication time, and the publication time of the first recommended information A is August 3, the publication time of the first recommended information B is August 4, and the publication time of the first recommended information C is August 2, then the specific order is: first recommended information B, first recommended information A, first recommended information C. If the parameter is the time when positive feedback was received, and the time when positive feedback was received for the first recommended information A is October 16, the time when positive feedback was received for the first recommended information B is December 5, and the time when positive feedback was received for the first recommended information C is September 2, then the specific order is: first recommended information C, first recommended information A, first recommended information B. If the parameter is the number of times positive feedback was received, and the number of times positive feedback was received for the first recommended information A is... If the number of feedback operations is 16, the number of positive feedback operations received by the first recommendation information B is 12, and the number of positive feedback operations received by the first recommendation information C is 9, then the specific order is: first recommendation information A, first recommendation information B, first recommendation information C. If the parameter is the degree of interest of the first account towards the first recommendation information, and the first machine learning model is called based on the first account and the first recommendation information to obtain the degree of interest of the first account towards the first recommendation information, and the degree of interest of the first account towards the first recommendation information A is 0.4, the degree of interest of the first account towards the first recommendation information B is 0.6, and the degree of interest of the first account towards the first recommendation information C is 0.8, then the specific order is: first recommendation information C, first recommendation information B, first recommendation information A.

[0134] This application embodiment displays a first interactive control corresponding to each second account in the display position of each first recommended information, providing a personalized interactive experience and allowing users to interact independently with each recommended information. For each second account in the interactive notification interface, displaying a first interactive control for batch interaction improves user interaction efficiency, allowing users to interact with multiple recommended information at once. Sorting the display positions of multiple first recommended information using at least one parameter determines the display order of recommended information from multiple dimensions, helping users quickly find content of interest and enhancing user experience and engagement.

[0135] In some embodiments, the pre-trained first machine learning model described above can be trained by performing the following processes: obtaining an initialized first machine learning model; obtaining account samples, recommendation information samples, and a first real label, wherein the first real label represents the degree of genuine interest of the account samples in relation to the annotations of the recommendation information samples; calling the initialized first machine learning model based on the account samples and recommendation information samples to obtain a first predicted label; determining a first loss based on the first real label and the first predicted label; and updating the parameters of the initialized first machine learning model based on the first loss to obtain the pre-trained first machine learning model.

[0136] For example, initialization involves randomly assigning values ​​to the model's parameters, such as assigning all parameters to 0 or all to 1. Based on account samples and recommendation information samples, the convolutional and fully connected layers of the initialized first machine learning model are called to obtain the first predicted label. A first loss is calculated between the first true label and the first predicted label using a loss function, and this first loss is backpropagated to update the parameters of the initialized first machine learning model. This process of calculating the first loss and updating parameters is iterated multiple times until the loss converges, at which point the iteration process stops, forming the pre-trained first machine learning model. The loss function can be a mean squared error loss function, a cross-entropy loss function, a multi-label classification loss function, or a triplet loss function. Backpropagation is implemented using a backpropagation algorithm, calculating the gradient of each neuron from the output layer to the input layer, and updating the neuron's weights and biases based on the gradients. Gradient descent is used to continuously update the parameters, reducing the loss value. Various gradient descent algorithms can be used, such as batch gradient descent, stochastic gradient descent, adaptive gradient descent, and momentum gradient descent.

[0137] This application's embodiments, by predicting the first account's interest in recommended information, can provide more personalized recommendations, improving accuracy and satisfaction. Utilizing machine learning models to analyze large amounts of historical data enables data-driven recommendation decisions, reducing human bias and errors. Machine learning models can automatically process and analyze large amounts of data, improving the efficiency of the recommendation system. Pre-trained machine learning models can continuously learn from new data to adapt to changes in behavior, enhancing the flexibility and adaptability of the recommendation system.

[0138] In some embodiments, when the first account triggers a positive feedback operation on the third recommendation information, the interactive notification interface also includes third interactive information. The third interactive information is sent to the first account by the second account that received the third recommendation information by triggering a third interactive control. The third interactive control is used by the second account to interact with the first account on the third recommendation information.

[0139] For example, taking a video scenario, if the first account triggers a positive feedback operation on video A (the third recommended information), such as the first account liking, favorited, or commenting on video A, video A will be recommended to the second account. If the second account triggers the third interactive control corresponding to video A, the third interactive information will be sent to the first account through the server (which can be the server 200 mentioned above).

[0140] This application embodiment enhances the social interaction and connection between the first and second accounts by allowing the second account to interact with and send third interactive information to the third recommendation information, thereby increasing users' enthusiasm for participating in content interaction and sharing. Based on the positive feedback from the first account, the second account is helped to discover more content that matches its interests, while also providing the first account with more diverse interactive information. By triggering the third interactive control to receive the third interactive information sent by the second account, a two-way data feedback communication link is established between the first and second accounts, realizing the bidirectional back-and-forth transmission of interactive data between the first and second accounts. This not only breaks the traditional one-way data push limitation but also improves the data utilization rate of historical recommendation information (third recommendation information), making the flow of interactive data more efficient and forming a continuous and stable data closed loop.

[0141] In some embodiments, referring to FIG3B, FIG3B is a second flowchart of the information processing method provided in the embodiments of this application. Step 102 of FIG3A, "displaying the first interactive control in the human-computer interaction interface", can be implemented by steps 1021 to 1022 of FIG3B, which will be described in detail below.

[0142] In step 1021, a positive feedback control for the first recommendation information is displayed in the human-computer interaction interface.

[0143] In some embodiments, if the human-computer interaction interface is an information recommendation interface, then a positive feedback control for the first recommended information is displayed in an area outside the information display area of ​​the information recommendation interface.

[0144] For example, positive feedback controls include, but are not limited to, any of the following types: like, favorite, recommend, and give coins. Taking a video scenario as an example, by triggering the recommendation interface entry in the video app, a video recommendation interface (information recommendation interface) is displayed in the video app.

[0145] In step 1022, in response to a trigger operation on the positive feedback control, a first interactive control is displayed in the human-computer interaction interface.

[0146] For example, in response to a trigger action on a positive feedback control, the first interactive control is displayed in the information display area of ​​the information recommendation interface. The styles of the first interactive controls corresponding to different positive feedback controls can be the same or different. The style of the first interactive control can reuse the icon of the positive feedback control, or it can be set by the first account in the settings interface.

[0147] This application's embodiments increase user engagement by displaying and using positive feedback controls. Interactive controls are only displayed when the user provides positive feedback on the recommended information, thus improving the click-through rate and efficiency of these controls. Recommendation systems based on user feedback can more accurately predict user needs and interests, improving the precision of recommendations.

[0148] In some embodiments, step 102 of FIG3A, "displaying the first interactive control in the human-computer interaction interface", can be implemented by performing the following process: in response to the second account meeting the first preset condition, the first interactive control is displayed, wherein the first preset condition includes at least one of the following: the interaction frequency between the first account and the second account is greater than a frequency threshold, and the similarity of the information preferences of the first account and the second account is greater than a first similarity threshold.

[0149] For example, the frequency threshold is a threshold for frequency or number of interactions. Taking a frequency threshold as an example, if the frequency threshold is 5 times / week, and the interaction frequency between the first account and the second account is 6 times / week, then the first interaction control will be displayed. The types of historical recommendation information for which the first account has performed positive feedback operations can be statistically analyzed. The types of historical recommendation information can be sorted in descending order according to the number of positive feedback operations. Starting from the top of the descending sort results, a preset proportion or preset number of types can be selected as the information preference of the first account. The information preference of the second account can be obtained in the same way as the first account. The information preference of the first account can then be vectorized. The information preferences of the second account are vectorized to obtain the first vector. The information preferences of the second account are vectorized to obtain the second vector. The similarity between the first vector and the second vector can be determined by similarity calculation methods such as cosine similarity, Euclidean distance, Manhattan distance or Pearson correlation coefficient. Taking Euclidean distance as an example, the first vector is (x1, y1) and the second vector is (x2, y2). The distance between the two is calculated as (x1-x2)2+(y1-y2)2, which is used as the similarity between the first vector and the second vector. The first similarity threshold is 0.7. If the similarity between the first vector and the second vector is 0.8, the first interactive control is displayed.

[0150] In some embodiments, step 102 of FIG3A, "displaying the first interactive control in the human-computer interaction interface", can be implemented by performing the following processing: in response to the first recommendation information satisfying the second preset condition, the first interactive control is displayed, wherein the second preset condition includes at least one of the following: the first account's interest in the first recommendation information is greater than a first interest threshold; the first account's interest in the target object in the first recommendation information is greater than a second interest threshold; the similarity between the account features of the first account and the information features of the first recommendation information is greater than a second similarity threshold; the interaction probability of the first account in relation to the first recommendation information is greater than a first probability threshold, and the interaction probability is predicted based on the historical recommendation information of the first account's interaction; the dwell time of the first account in relation to the first recommendation information is greater than a duration threshold.

[0151] For example, taking the level of interest in the first recommended information as an example, the level of interest of the first account in the first recommended information can be determined by at least one of the following parameters: the frequency of interaction between the first account and the first recommended information, the similarity between the first account and the first recommended information, and the total time the first account spends in the first recommended information. Multiple parameters can be weighted and summed, and the weight of each parameter can be determined from the historical interaction data of the first account regarding historical recommended information through statistical analysis or machine learning methods (such as linear regression, decision trees, random forests). Taking linear regression as an example, historical interaction data of the first account is collected, including the frequency of interaction with historical recommended information, the similarity with historical recommended information, the total time spent in historical recommended information, and the level of interest of the first account in historical recommended information (which can be measured by indicators such as user feedback, click-through rate, and conversion rate). The interaction frequency, similarity, and similarity of the first account to historical recommended information are then combined. Similarity and total dwell time are used as variables. The formula for the linear regression model is: Y = β1·x1 + β2·x2 + β3·x3 + ε, where Y is the degree of interest, x1, x2, and x3 are the interaction frequency, similarity, and total dwell time, respectively, β1, β2, and β3 are the first weight corresponding to the interaction frequency, the second weight corresponding to the similarity, and the third weight corresponding to the total dwell time, respectively, and ε is the error term. Multiple sets of historical interaction data are substituted into the linear regression model to obtain the first weight, the second weight, and the third weight. The interaction frequency between the first account and the first recommendation information, the similarity between the first account and the first recommendation information, and the total dwell time of the first account in the first recommendation information are substituted into the linear regression model with determined weights to obtain the degree of interest. If the threshold for the first degree of interest is 0.8 and the degree of interest of the first account in the first recommendation information is 0.9, then the first interactive control is displayed.

[0152] Taking the level of interest in a target object as an example, the target object in the first recommendation information is determined by a target recognition algorithm. If the first recommendation information is text, the target object can be identified using any one of the following algorithms: keyword extraction, Named Entity Recognition (NER), topic modeling, and semantic analysis. If the first recommendation information is video, the target object can be identified using any one of the following algorithms: video metadata, computer vision technology, and video structure analysis. If the first recommendation information is audio, the target object can be identified using any one of the following algorithms: speech-to-text, audio feature extraction, and music recognition. The level of interest of the first account in the target object of the first recommendation information can be determined by at least one of the following parameters: the frequency of interaction between the first account and the target object, the similarity between the first account and the target object, the type of interaction of the first account with the target object, and the total time the first account stays with the target object. Multiple parameters can be weighted and summed. The weight of each parameter can be determined based on the historical interaction data of the first account with the target object in the historical recommendation information, using statistical analysis or machine learning methods (such as linear regression, decision tree, random forest). The determination process is similar to the linear regression process described above and will not be elaborated here. If the second interest threshold is 0.75, and the first account's interest level in the target object in the first recommendation information is 0.82, then the first interactive control will be displayed.

[0153] Taking similarity as an example, the account features of the first account are extracted, such as historical interaction behavior, preference settings, basic information (age, gender, location, etc.), and interest tags; the information features of the first recommended information are extracted, such as content type, topic tags, keywords, publisher features, and publication time. The extracted account features and information features are converted into numerical vectors, i.e., account feature vectors and information feature vectors. This conversion can be performed using any of the following algorithms: One-Hot Encoding, Bag-of-Words Model, Term Frequency-Inverse Document Frequency (TF-IDF), pre-trained word embedding models (such as Word to Vector (Word2Vec), Bidirectional Encoder Representations from Transformers (BERT), etc.). Similarity calculation methods such as cosine similarity, Euclidean distance, Manhattan distance, or Pearson correlation coefficient can be used to determine the similarity between the account feature vector and the information feature vector. If the second similarity threshold is 0.8, and the similarity between the account features of the first account and the information features of the first recommended information is 0.85, then the first interactive control is displayed.

[0154] Taking interaction probability as an example, multiple historical recommendation information and a second true label are obtained. The historical recommendation information includes recommendations that have interacted with the first account and recommendations that haven't. The second true label indicates whether the first account has interacted with the historical recommendation information; if it has, the second true label is 1, otherwise it's 0. The account features of the first account and the historical information features of the multiple historical recommendation information are extracted. Based on the account features of the first account and the historical information features of the multiple historical recommendation information, an initialized second machine learning model is called to obtain a second predicted label. A second loss is determined between the second predicted label and the second true label using a loss function. Based on the second loss, the parameters of the initialized second machine learning model are updated to obtain a pre-trained second machine learning model. Based on the account features of the first account and the information features of the first recommendation information, the pre-trained second machine learning model is called to obtain the interaction probability of the first account with respect to the first recommendation information. If the first probability threshold is 0.7 and the interaction probability of the first account with respect to the first recommendation information is 0.8, then the first interaction control is displayed.

[0155] Taking dwell time as an example, if the first account browses the first recommended information multiple times, the dwell time for each browsing session is added together to obtain the dwell time. If the dwell time threshold is 1 hour, and the first account's dwell time for the first recommended information is 2 hours, then the first interactive control is displayed.

[0156] This application's embodiments determine whether to display interactive controls based on personalized indicators such as user interest level, similarity, and interaction probability, providing a personalized user experience. Displaying interactive controls only when users have a high level of interest in the recommended information can improve the conversion rate from browsing to interaction, thereby enhancing the effectiveness of information recommendation. By selecting a portion of the recommended information to display interactive controls, resource allocation can be optimized, unnecessary displays can be reduced, and information processing efficiency can be improved.

[0157] In some embodiments, step 102 of FIG3A, "displaying the first interactive control in the human-computer interaction interface", can be implemented by performing the following processing: obtaining the historical interaction frequency and the number of mutual friends between the first account and the second account; determining the social intimacy between the first account and the second account based on the historical interaction frequency and the number of mutual friends; if the social intimacy is greater than or equal to a preset intimacy threshold, then displaying the first interactive control in the human-computer interaction interface in a first visual form; if the social intimacy is less than the intimacy threshold, then displaying the first interactive control in the human-computer interaction interface in a second visual form, wherein the salience of the first visual form is greater than the salience of the second visual form.

[0158] For example, in the underlying data calculation and acquisition stage, the server or terminal can query a relational database or graph database to count the number of likes, comments, and private messages between the first and second accounts within a preset time period (e.g., the past 30 days), using this as the historical interaction frequency. The number of mutual friends is then calculated by intersecting the friend lists of both accounts. These two parameters—historical interaction frequency and the number of mutual friends—are normalized and weighted by preset weighting coefficients to obtain a numerical social intimacy score. If the social intimacy score is greater than or equal to an intimacy threshold (e.g., 0.8), the first interactive control is rendered in the first visual form in the human-computer interaction interface; otherwise, it is rendered in the second visual form. The difference between the first and second visual forms is specifically manifested in differences in color saturation, size, dynamic effects (UI micro-animations), or rendering parameters at the display level. For example, the first visual form can be represented by a freestanding floating icon using highly saturated colors (such as bright red or gradient colors), with dynamic breathing light effects or glowing outlines, and occupying a large pixel area on the screen interface; while the second visual form is represented by an icon using low-saturation or semi-transparent colors (such as light gray), static with no animation effects, and a smaller pixel area, embedded at the bottom of the information feed alongside regular comment, share, and other controls. By calling different interface rendering scripts and Cascading Style Sheets (CSS) parameters, the prominence of the first visual form on the human-computer interaction interface is significantly greater than that of the second visual form.

[0159] This application's embodiments accurately calculate the social relevance between target objects based on underlying business data (historical interaction frequency and number of mutual friends). Only the first visual form, which requires higher graphics processing resources, is selectively assigned to target objects with a high probability of interaction (i.e., accounts with a social intimacy greater than or equal to the intimacy threshold). This data-driven UI dynamic rendering mechanism effectively reduces redundant computational overhead when rendering a large number of low-interaction-probability controls, lowers device memory usage and system power consumption, and improves the overall smoothness and rendering efficiency of the human-computer interaction interface. By enhancing the visual salience of the first interactive control corresponding to high-intimacy accounts, the focus of the first account's operation can be quickly guided to the target area most likely to trigger interaction within a limited screen display area through visually differentiated priority arrangement. This shortens the visual addressing time for the first account to retrieve target interactive controls in complex information recommendation streams, reduces the false touch rate, and improves the input accuracy and command issuance speed for operations triggered by the first interactive control. Ultimately, this enhances the overall throughput and processing efficiency of the information processing system when receiving, processing, and forwarding interactive data between different accounts.

[0160] In some embodiments, step 102 of FIG3A, "displaying the first interactive control in the human-computer interaction interface", can be achieved by performing the following processing: predicting the probability that the first account and the second account will interact with the first recommended information based on the information characteristics of the historical interaction information sent by the first account and the first recommended information; and displaying the first interactive control in response to the probability being greater than the second probability threshold.

[0161] For example, the following steps are taken: extract historical information features of the historical interaction information sent by the first account; obtain a third true label, which represents whether the first account and the second account interacted with the historical interaction information; based on the historical information features and the information features of the first recommendation information, call the initialized third machine learning model to obtain a third predicted label; determine a third loss based on the third predicted label and the third true label; update the parameters of the initialized third machine learning model based on the third loss to obtain a pre-trained third machine learning model; and based on the first feature vector of the first interaction information and the information features of the first recommendation information, call the pre-trained third machine learning model to obtain the probability that the first account and the second account interacted with the first recommendation information.

[0162] This application's embodiments utilize personalized predictions based on historical interaction information and recommendation information features to provide more targeted interaction prompts and improve user engagement. Displaying interactive controls only when the predicted probability of interaction is high reduces ineffective or uninteresting interactions, improving the quality and relevance of interactions. Utilizing historical data and machine learning models for prediction makes social recommendations more data-driven and scientific.

[0163] In some embodiments, step 102 of FIG3A, "displaying the first interactive control in the human-computer interaction interface", can be implemented by performing the following processing: determining the area ratio of the first recommendation information in the human-computer interaction interface and the dwell time of the first recommendation information; if the area ratio is greater than or equal to a preset area threshold and the dwell time reaches a preset duration threshold, then asynchronously loading the operation data of the positive feedback operation of the second account from the server, and displaying the first interactive control in the first state in the corresponding coordinate area of ​​the human-computer interaction interface.

[0164] For example, consider a user interface where a first account scrolls through multiple first-recommendation items (e.g., a long list of short video feeds) on a terminal. During the scrolling process, the terminal's underlying interface rendering engine or window cross-observer calculates in real time the proportion of each first-recommendation item's visible pixel area within the screen's visible window relative to the total area of ​​that item, and starts a timer to record its dwell time within the visible window. If the first account quickly scrolls past a first-recommendation item, even if its area proportion reaches 100%, but the dwell time is only 0.5 seconds (less than a preset duration threshold, such as 2 seconds), it will be considered an invalid exposure, and no additional data loading instructions will be triggered. When the first account stops scrolling and effectively focuses on a first-recommendation item, if it detects that the area proportion of that first-recommendation item within the screen is greater than or equal to a preset area threshold (e.g., 60%), and the dwell time reaches a preset duration threshold (e.g., 2 seconds), the terminal's underlying asynchronous network thread will then initiate a specific query for that first-recommendation item to the server as needed, asynchronously loading the specific operation data of the second account (i.e., an account with social relationships that has performed positive feedback operations such as liking). After successfully acquiring the operation data, the terminal's graphics rendering engine dynamically instantiates and renders the first interactive control in the first state (e.g., presented as an initially inactive "Thank you" button) within the corresponding coordinate area below or to the side of the first recommendation information.

[0165] This application's embodiments address the scenario of rapidly scrolling through a large amount of first recommendation information. The network request to asynchronously load second account operation data from the server is postponed until the first recommendation information is truly and effectively exposed (i.e., meeting the dual spatiotemporal parameter verification of physical area ratio and dwell time). This successfully intercepts a large number of invalid data query commands generated by the rapid scrolling of the first account, reducing the frequency of invalid network communication and downlink bandwidth consumption between the terminal and the server. Simultaneously, it reduces the concurrent read load on the server when querying underlying social relationships and historical positive feedback records during high-frequency information stream refreshes, improving the throughput and stability of the service cluster. From the perspective of terminal device memory management and graphics rendering engine efficiency, dynamic on-demand rendering of components based on precise calculations of area and duration effectively avoids excessive expansion of interface document object model nodes or underlying UI view trees caused by preloading or silent rendering of a large number of invisible and unattended controls. By eliminating redundant component instantiation logic and interface redraw instructions, the memory usage and CPU logic operation overhead during information flow scrolling are reduced, ensuring extremely high frame rates and ultimate smoothness of human-computer interaction interface sliding operations under complex long lists or infinitely scrolling information flows, thereby improving overall operating performance and device battery life.

[0166] Referring again to Figure 3A, in step 103, in response to the triggering operation of the first interactive control, the first interactive information is sent to the second account, and the first interactive control is switched from the first state to the second state, wherein the second state indicates that the first account has interacted with the second account regarding the first recommendation information.

[0167] Here, the first interactive message is used to respond to the positive feedback action of the second account on the first recommended message. The first interactive message can take many forms, such as text, pictures, videos, voice, emoticons, etc.

[0168] In some embodiments, when there are multiple first recommended information items displayed in the information display area and multiple second accounts that trigger the first recommended information items, step 103, "in response to the trigger operation of the first interactive control, send the first interactive information to the second account", can be implemented by performing the following processing: in response to the batch selection operation of multiple first recommended information items, control the batch-selected first recommended information items to be in a selected state, and in response to the trigger operation of the first interactive control corresponding to any selected first recommended information item, send the first interactive information to the second account that implements the positive feedback operation for the first recommended information item for each batch-selected first recommended information item.

[0169] For example, the information display area also shows selection controls corresponding to each first recommended item. In response to a triggering operation on the selection controls of at least some of the first recommended items, such as a checkmark operation, the selected first recommended items will be kept in a selected state. The selected state can also be manifested in any of the following ways: the border of the first recommended item is thickened, the transparency of the selected first recommended item is increased or decreased compared to the unselected first recommended item, or the first recommended item blinks. Multiple first recommended items can be sorted in a specific order, for example, sorted in descending order of the interest level of the first account; sorted according to the predicted interaction probability of the first account with the first recommended item; or sorted according to the number of second accounts that have given positive feedback to the first recommended item. Alternatively, one first recommended item can be displayed in the information display area, and multiple first recommended items can be switched on and off in a fixed order.

[0170] This application's embodiments reduce the number of times users need to repeatedly click on the first recommended information by using batch selection and interactive operations, thereby improving user interaction efficiency and saving user time. Through batch selection and interaction, users can operate on multiple recommended information items at once, simplifying the operation process and enhancing the user experience. Users can selectively interact with multiple recommended information items according to their needs, enhancing the flexibility and personalization of the interaction.

[0171] In some embodiments, referring to FIG3C, FIG3C is a third flowchart of the information processing method provided in the embodiments of this application. When the human-computer interaction interface is an interactive notification interface, step 103 of FIG3A, "in response to the trigger operation of the first interactive control, send the first interactive information to the second account", can be implemented by steps 1031 to 1032 of FIG3C, which will be described in detail below.

[0172] In step 1031, when there is a one-to-one correspondence between the first interactive control and the second account, in response to the trigger operation for any first interactive control, the first interactive information is sent to the second account corresponding to any first interactive control.

[0173] Here, in response to a trigger operation on any first interactive control, the triggered first interactive control switches from the first state to the second state.

[0174] In step 1032, if the first interactive control is a batch interactive control, in response to a trigger operation on the first interactive control, the first interactive information is sent to each second account.

[0175] Here, in response to a trigger operation on the first interactive control, the first interactive control is switched from a first state to a second state.

[0176] Here, when the first interactive control is in the second state, the time of switching to the second state can also be displayed. For example, if the first interactive control switches to the second state at 12:00, then "Click time is 12:00" will be displayed below the first interactive control.

[0177] Here, in a high-concurrency scenario of sending first interactive information to multiple second accounts in batches, to ensure system stability and optimize network transmission performance, the above step "in response to the trigger operation of the first interactive control, send the first interactive information to each second account" can be achieved by performing the following processing: In response to the trigger operation of the batch interactive control, the terminal merges the first interactive information packets for each second account to generate a batch interactive request packet containing multiple second account identifiers, and sends this batch interactive request packet to the server through a single network request. The server's microservice architecture parses the batch interactive request packet to obtain the identifiers of each second account, and based on the configured load balancer, distributes and pushes the first interactive information to the terminals logged in by each second account. By merging the data packets on the terminal side of the first account, the number of network requests initiated by the terminal is reduced, lowering the risk of client network congestion; at the same time, the combination of microservice architecture and load balancing ensures stable operation and fast response under high-concurrency batch interaction conditions, improving the data distribution efficiency of sending the first interactive information to multiple second accounts.

[0178] In this embodiment, when there is a one-to-one correspondence between the first interactive control and the second account, personalized interaction can be performed for each second account, enhancing the targeting of the interaction and the user experience. When the first interactive control is a batch interactive control, the user can send interactive messages to all second accounts at once, improving the efficiency of the interaction. Whether it's personalized or batch interaction, the use of interactive controls enhances the social connection between the first and second accounts, increasing the activity and frequency of the interaction.

[0179] In some embodiments, the first interactive control includes a first positive interactive sub-control and a second negative interactive sub-control. The first positive interactive sub-control is used to express positive emotions to the second account in response to the first recommendation information, and the second negative interactive sub-control is used to express negative emotions to the second account in response to the first recommendation information. Step 103, "sending the first interactive information to the second account", can be implemented by performing the following process: in response to the control activation operation, controlling the target sub-control to be in an active state, and sending the first interactive information corresponding to the emotion expressed by the target sub-control to the second account, wherein the target sub-control is one of the first positive interactive sub-control and the second negative interactive sub-control, and the emotion expressed by the target sub-control is consistent with the emotion expressed by the first interactive information.

[0180] For example, activation actions can be single-click, double-click, swipe, long-press, etc., and the activation state can use different display parameters, such as color or highlight. When the target sub-control is the first positive interaction sub-control, the first interaction message can be "Thank you for your like, which allows me to see such a high-quality video!" When the target sub-control is the second negative interaction sub-control, the first interaction message can be "I just saw the article you liked, but I think it is somewhat inaccurate or biased. I would like to discuss your opinion with you, or see if there are other sources that can verify this information."

[0181] This application embodiment uses different controls to express the positive and negative emotions of the first account towards the recommended information, enriching the user's emotional expression and making the interaction more realistic and natural. By providing positive and negative interaction options, users are encouraged to participate more actively in content evaluation and discussion, increasing user engagement and activity. The emotional expression of the first account can stimulate discussion and response from the second account, enhancing interaction and connection.

[0182] Here, step 103, "In response to the trigger operation for the first interactive control, send the first interactive information to the second account," can be achieved by performing the following processing: In response to the trigger operation for the first interactive control, write the generated first interactive information and the identifier of the corresponding first recommendation information into an asynchronous message queue; within the aggregation time window corresponding to the second account, intercept multiple first interactive information pointing to the second account; when the aggregation time window reaches the termination condition, merge the multiple first interactive information pointing to the second account into an aggregated interactive data packet; send the aggregated interactive data packet to the server through a single network request, so that the server can send a merge notification for the multiple first interactive information to the terminal of the second account.

[0183] This application embodiment addresses the scenario where a first account frequently triggers multiple first interactive controls within a short period. It constructs an asynchronous message queue and data packet merging mechanism based on a time window. By merging and encapsulating multiple first interactive messages from the same second account at the sending end, it reduces the number of times the terminal initiates high-frequency short connection network requests, thereby reducing the computational overhead and network bandwidth consumption of establishing and releasing network connections. At the same time, from the perspective of the server and the receiving end (the terminal of the second account), it effectively avoids high-concurrency short message writing operations and notifications, reduces input / output load and notification rendering pressure on the terminal of the second account, and improves the overall operational stability in large-scale, high-frequency interactive scenarios.

[0184] In some embodiments, step 103, "in response to a trigger operation on the first interactive control, sending the first interactive information to the second account and switching the first interactive control from the first state to the second state," can be implemented by performing the following processing: in response to a trigger operation on the first interactive control, in the main thread local to the terminal, immediately switching the rendering properties of the first interactive control from the first state to the second state. After step 103, the following processing can also be performed: in the asynchronous network thread at the terminal's underlying level, generating a data request packet carrying the first interactive information and sending the data request packet to the server; detecting the return result of the data request packet in the asynchronous network thread; if a prompt message indicating that the data request packet failed to be sent or timed out is detected, then in the main thread, rolling back the rendering properties of the first interactive control from the second state to the first state.

[0185] For example, consider the first account browsing recommended information (such as short videos) in a weak network environment like a subway. When the first account triggers the first interactive control in its first state (e.g., displaying an unclicked icon and a "thank you" message), the terminal's local UI main thread responds immediately. Without waiting for a network communication response, it instantly switches the rendering properties of the first interactive control to the second state, such as displaying a clicked icon and a "thank you" message, and locks the first interactive control in a protected state that prevents it from being triggered again. At the same time, the terminal's underlying layer starts an asynchronous network thread, encapsulates the first interactive information, including the first account identifier, the second account identifier, and the interactive action, into a data request packet, and initiates network transmission to the server. If, due to unstable subway network signals, the underlying asynchronous network thread fails to receive a successful confirmation packet from the server within a set time threshold (e.g., 3 seconds), i.e., detects a data request packet sending failure or timeout message, the underlying asynchronous network thread will throw a callback signal indicating an abnormal state to the main thread. Upon receiving this callback signal, the main thread will immediately roll back the rendering property of the first interactive control from the second state of "Thank you" to the first state of "Thank you," ensuring that the first account is aware that the interaction was not successfully sent and can choose to re-trigger it.

[0186] This application's embodiments employ a concurrent processing architecture that separates the main thread update from the asynchronous network thread, decoupling the graphical interface's state rendering logic from the underlying network data transmission and reception logic. The moment the first account triggers the first interactive control, the local main thread first completes the graphical rendering switch from the first state to the second state. This not only eliminates human-computer interaction interface blocking and thread suspension caused by network latency or fluctuations, but also effectively intercepts continuous repeated trigger commands that the first account is prone to generate due to network latency and unresponsive interface. This avoids the terminal concurrently sending a large number of redundant and invalid duplicate data request packets to the server, saving the terminal device's computational overhead, radio frequency resources, and network communication bandwidth. Through the underlying asynchronous network result detection and the main thread's rendering state rollback mechanism, a complete closed-loop fault-tolerant processing link is constructed. In the event of a network anomaly, the terminal does not need to refresh or reload the entire human-computer interaction interface, nor does it need to re-initiate a full request for the first recommendation information data stream; it only needs to perform a partial rollback operation on the rendering attributes of the single first interactive control. This lightweight state correction and synchronization mechanism not only achieves precise alignment and strong consistency between the terminal's local interactive state and the server's backend storage state with low overhead, but also improves the robustness of operation and the reliability of data processing in complex network environments (such as weak networks or network outages).

[0187] As an example of steps 101 to 103, when the human-computer interaction interface is an information recommendation interface and the number of second accounts triggering positive feedback operations is at least one, refer to Figure 4A. Figure 4A is a first schematic diagram of information processing in an information recommendation interface provided by an embodiment of this application. In the left side of Figure 4A, the first recommendation information 703 is displayed in the information display area 702 of the information recommendation interface 701 based on the first account login. The information display area 702 displays each second account and its corresponding first interactive control, such as the first interactive control 705 corresponding to second account 704 and the first interactive control 707 corresponding to second account 706. Both first interactive controls 705 and 707 are in a first state, meaning the first account has not yet interacted with second account 704 or second account 706 regarding the first recommendation information 703. When any of the first interactive controls receives a trigger operation, it triggers the execution of sending the first interactive information to the second account corresponding to that first interactive control. For example, when first interactive control 705 receives a trigger operation, it triggers the execution of sending the first interactive information to the second account 704 corresponding to first interactive control 705. In response to a trigger operation on any of the first interactive controls, such as a trigger operation on first interactive control 705, in the right-hand diagram of Figure 4A, the first interactive information is sent to second account 704, and first interactive control 705 is switched from the first state to the second state. The second state indicates that the first account has already interacted with second account 704 regarding the first recommendation information 703.

[0188] As an example of steps 101 to 103, when the human-computer interaction interface is an information recommendation interface and the number of second accounts triggering positive feedback operations is at least one, refer to Figure 4B. Figure 4B is a second schematic diagram of information processing in an information recommendation interface provided by an embodiment of this application. In the left side view of Figure 4B, first recommendation information 703 is displayed in the information display area 702 of the information recommendation interface 701 based on first account login. Each second account (e.g., second account 704 and second account 706) and a first interactive control 708 are displayed in the information display area 702. The first interactive control 708 is used to trigger the execution of sending first interactive information to each second account when a trigger operation is received. In response to the trigger operation on the first interactive control 708, in the right side view of Figure 4B, first interactive information is sent to second account 704 and second account 706, and the first interactive control 708 is switched from a first state to a second state. The second state indicates that the first account has interacted with the second account 704 and second account 706 regarding the first recommendation information 703.

[0189] As an example of steps 101 to 103, when the human-computer interaction interface is an information recommendation interface, the number of first recommended information items displayed in the information display area is multiple, and the number of second accounts triggering the first recommended information items is multiple, refer to Figure 4C. Figure 4C is a third schematic diagram of information processing in the information recommendation interface provided by an embodiment of this application. In the left side of Figure 4C, first recommended information 703 and first recommended information 709 are displayed in the information display area 702 of the information recommendation interface 701 based on first account login. The information display area 702 displays the first interactive control corresponding to each first recommended information item, such as the first interactive control 705 corresponding to the first recommended information 703 and the first interactive control 711 corresponding to the first recommended information 709. In response to a batch selection operation for multiple first recommendation information items, for example, displaying checkboxes 712 corresponding to first recommendation information 703 and 713 corresponding to first recommendation information 709 in information display area 702, in response to a trigger operation for checkboxes 712 and 713, in the right-hand view of Figure 4C, controlling the batch-selected first recommendation information 703 and 709 to be in a selected state, and in response to a trigger operation for a first interactive control corresponding to any selected first recommendation information item, for example, a trigger operation for the first interactive control 705 corresponding to first recommendation information 703, sending first interactive information to the second account 704 that triggers a positive feedback operation for first recommendation information 703 and the second account 710 that triggers a positive feedback operation for first recommendation information 709.

[0190] As an example of steps 101 to 103, when the human-computer interaction interface is an interactive notification interface, refer to FIG5A, which is a first schematic diagram of information processing in an interactive notification interface provided by an embodiment of this application. In the left side view of FIG5A, first recommendation information 703 is displayed in the contact interface 714 based on the first account login. At least one second account and a first interactive control are displayed in the contact interface 714. When the first interactive control corresponds one-to-one with the second account, for example, the second account 704 corresponds to the first interactive control 705, the second account 706 corresponds to the first interactive control 707, the second account 710 corresponds to the first interactive control 711, the second account 715 corresponds to the first interactive control 717, and the second account 716 corresponds to the first interactive control 718, in response to a trigger operation for any first interactive control, such as a trigger operation for the first interactive control 705, in the right side view of FIG5A, first interactive information is sent to the second account 704 corresponding to the first interactive control 705, and the first interactive control 705 is switched from a first state to a second state.

[0191] As an example of steps 101 to 103, when the human-computer interaction interface is an interactive notification interface, refer to FIG5B, which is a second schematic diagram of information processing in an interactive notification interface provided by an embodiment of this application. In the left side view of FIG5B, first recommendation information 703 is displayed in the contact interface 714 based on the first account login. At least one second account and a first interactive control are displayed in the contact interface 714, such as second account 704, second account 706, second account 710, second account 715, second account 716, and first interactive control 719. When the first interactive control 719 is a batch interactive control, in response to the triggering operation for the first interactive control 719, in the right side view of FIG5B, first interactive information is sent to second account 704, second account 706, second account 710, second account 715, and second account 716, and the first interactive control 719 is switched from a first state to a second state.

[0192] As an example of steps 101 to 103, when the human-computer interaction interface is a contact interface, refer to Figure 6A. Figure 6A is a first schematic diagram of information processing in a contact interface provided by an embodiment of this application. In the left side view of Figure 6A, first recommendation information 703 is displayed in the contact interface 720 based on the first account login. The contact interface includes a contact area 721, in which at least one second account and a first interactive control corresponding to each second account are displayed. For example, second account 704 corresponds to first interactive control 705, second account 706 corresponds to first interactive control 707, and second account 710 corresponds to first interactive control 711. When a first interactive control is triggered, it sends first interactive information to the second account corresponding to any first interactive control. In response to a trigger operation for any first interactive control, such as a trigger operation for first interactive control 705, in the right side view of Figure 6A, first interactive information is sent to the second account 704 corresponding to the first interactive control 705, and the first interactive control 705 is switched from a first state to a second state.

[0193] As an example of steps 101 to 103, when the human-computer interaction interface is a contact interface, refer to FIG6B, which is a second schematic diagram of information processing in a contact interface provided by an embodiment of this application. In the left side view of FIG6B, a thumbnail of the first recommendation information 703 is displayed in the contact interface 720 based on the first account login, and at least one second account and a first interactive control 722 for batch interaction are displayed in the contact area 721. The first interactive control 722 is used to send first interactive information to the second account 704, the second account 706 and the second account 710 when triggered. In response to the triggering operation of the first interactive control 722, in the right side view of FIG6B, the first interactive information is sent to the second account 704, the second account 706 and the second account 710, and the first interactive control 722 is switched from a first state to a second state.

[0194] As an example of steps 101 to 103, taking an information recommendation interface as an example, refer to Figure 7. Figure 7 is a schematic diagram of mutual feedback between different accounts provided in this application embodiment. In the left side of Figure 7, a positive feedback control 723 for the first recommendation information 703 is displayed in the information recommendation interface 701 based on the first account login. The first recommendation information 703 and the second account 704 that performed a positive feedback operation on the first recommendation information 703 are displayed in the information display area 702 of the information recommendation interface 701. In response to the trigger operation on the positive feedback control 723, a first interactive control 705 is displayed in the information recommendation interface 701 in the middle of Figure 7. In response to the trigger operation on the first interactive control 705, in the right side of Figure 7, the first interactive information is sent to the second account 704, and the first interactive control 705 is switched from a first state to a second state.

[0195] In some embodiments, referring to FIG3D, FIG3D is a fourth flowchart of the information processing method provided in the embodiments of this application. In step 101, "displaying the first recommendation information on the human-computer interaction interface based on the first account login", steps 201 to 205 of FIG3D are executed, which are described in detail below.

[0196] In step 201, in response to the triggering operation for the second account, the first recommendation information is displayed in the first area of ​​the information recommendation interface.

[0197] In some embodiments, in response to a triggering operation targeting an identifier such as the name, avatar, or nickname of a second account, first recommended information is displayed in a first area of ​​the information recommendation interface.

[0198] For example, the first area can be a fixed area with a preset proportion in the information recommendation interface, or it can be an area that dynamically changes based on the first recommended information. When the number of second accounts exceeds a threshold, only the number of second accounts can be displayed, without showing the specific second accounts. In response to a trigger operation based on the number of second accounts, the first recommended information can be displayed in the first area of ​​the information recommendation interface.

[0199] In step 202, the contact interface is displayed in a way that it floats in the second area of ​​the information recommendation interface, wherein the second area is the area in the information recommendation interface that is different from the first area.

[0200] In some embodiments, the contact interface may be an interface with preset transparency above the second area, or it may be an interface that completely covers the second area and is perfectly aligned with the information recommendation interface.

[0201] For example, the contact interface can be a floating layer or a floating window. The size of the contact interface is the same as the size of the second area. The size of the second area can be a fixed size or it can change dynamically according to the number of second accounts in the contact interface.

[0202] In step 203, at least one second account and a second interactive control are displayed in the contact interface, wherein the second interactive control is in a first state, the first state indicating that the first account has not yet interacted with the second account regarding the first recommendation information.

[0203] For example, the contact interface can display the avatar, name, nickname, and other identifiers of at least one secondary account. The contact area of ​​the contact interface displays at least one secondary account and a secondary interactive control; one secondary interactive control can correspond to one or more secondary accounts.

[0204] In step 204, in response to a triggering operation on the second interactive control, a second interactive message is sent to the second account.

[0205] Here, in response to a triggering action on the second interactive control, a second interactive message is sent to the second account to respond to the positive feedback action.

[0206] In some embodiments, referring to FIG3E, FIG3E is a fifth flowchart of the information processing method provided in the embodiments of this application. Step 204 of FIG3D, "in response to the trigger operation of the second interactive control, send the second interactive information to the second account", can be implemented by steps 2041 to 2042 of FIG3E, which will be described in detail below.

[0207] In step 2041, when there is a one-to-one correspondence between the second interactive control and the second account, in response to the trigger operation for any second interactive control, the second interactive information is sent to the second account corresponding to any second interactive control.

[0208] In some embodiments, multiple second accounts can be displayed in a list or scrolling format. Any first interactive control, upon receiving a trigger operation, is used to send a first interactive message to the second account corresponding to that first interactive control in response to a positive feedback operation.

[0209] For example, upon receiving an action triggered by any of the first interactive controls, a thank-you message is sent to the second account corresponding to that first interactive control, such as "Thank you for liking this video, which allows me to see such an excellent video!"

[0210] In step 2042, if the second interactive control is a batch interactive control, in response to a trigger operation on the second interactive control, the second interactive information is sent to each second account.

[0211] For example, the second interactive control can be displayed in any blank sub-area of ​​the contact area on the contact interface, or displayed as a card on top of the contact area. Different first recommendation messages correspond to different first interactive controls.

[0212] Referring again to Figure 3D, in step 205, the second interactive control is switched from the first state to the second state, wherein the second state indicates that the first account has interacted with the second account regarding the first recommendation information.

[0213] As an example of steps 201 to 205, in the case where the second interactive control corresponds one-to-one with the second account, refer to Figure 8A. Figure 8A is a first schematic diagram of information processing through a floating contact interface provided in this application embodiment. In the left side view of Figure 8A, the information recommendation interface 701 includes first recommendation information 703. In response to a trigger operation for the number 724 of the second accounts, in the middle view of Figure 8A, the first recommendation information 703 is displayed in the first area 725 of the information recommendation interface 701, and the contact interface 714 is displayed in a way that it floats in the second area of ​​the information recommendation interface 701, wherein the second area is the area in the information recommendation interface 701 that is different from the first area 725. At least one second account and a second interactive control are displayed in the contact interface 714. In a one-to-one correspondence between the second interactive control and the second account, for example, second account 704 corresponds to second interactive control 726, second account 706 corresponds to second interactive control 727, second account 710 corresponds to second interactive control 728, second account 715 corresponds to second interactive control 729, and second account 716 corresponds to second interactive control 730. The second interactive control is in a first state, indicating that the first account has not yet interacted with the second account regarding the first recommendation information 703. In response to a trigger operation on any second interactive control, such as a trigger operation on second interactive control 726, in the right-hand diagram of Figure 8A, a second interactive message is sent to the second account 704 corresponding to second interactive control 726, and second interactive control 726 is switched from the first state to the second state. The second state indicates that the first account has already interacted with the second account 704 regarding the first recommendation information 703.

[0214] As an example of steps 201 to 205, when the second interactive control is a batch interactive control, refer to FIG8B. FIG8B is a second schematic diagram of information processing through a floating contact interface provided in an embodiment of this application. In the left side view of FIG8B, the information recommendation interface 701 includes first recommendation information 703. In response to a trigger operation for the number of second accounts 724, in the middle view of FIG8B, the first recommendation information 703 is displayed in the first area 725 of the information recommendation interface 701, and the contact interface 714 is displayed in a manner that floats in the second area of ​​the information recommendation interface 701, wherein the second area is the area of ​​the information recommendation interface 701 that is different from the first area 725. At least one second account and a second interactive control are displayed in the contact interface 714. If the second interactive control is a batch interactive control, such as second account 704, second account 706, second account 710, second account 715, second account 716, and second interactive control 731, then the second interactive control 731 is in a first state, indicating that the first account has not yet interacted with the second account regarding the first recommendation information 703. In response to a trigger operation on the second interactive control 731, in the right-hand diagram of Figure 8B, a second interactive message is sent to each second account, and the second interactive control 731 is switched from the first state to the second state, indicating that the first account has interacted with each second account regarding the first recommendation information 703.

[0215] This application embodiment displays the contact interface in a floating manner in the second area of ​​the information recommendation interface, allowing users to easily interact with the second account while viewing recommended information, without switching between different interfaces, maintaining a clear and tidy interface and improving the user experience. The second interaction control corresponds one-to-one with the second account, allowing users to personalize interactions for each account, enhancing the targeting of interactions and the user experience. A batch interaction control is provided, enabling users to send interactive messages to multiple second accounts at once, improving interaction efficiency.

[0216] In some embodiments, referring to FIG3F, FIG3F is a sixth flowchart of the information processing method provided in the embodiments of this application. In step 201, "displaying the first recommendation information in the first area of ​​the information recommendation interface", steps 301 to 302 of FIG3F are executed, which are described in detail below.

[0217] In step 301, in response to the switching operation for the first recommendation information, the first recommendation information is switched to the second recommendation information.

[0218] In some embodiments, the logic for switching the first recommendation information can be any of the following: switching sequentially according to the descending order of the number of received positive feedback operations; switching sequentially according to the descending order of the time when the positive feedback operations were performed; or switching sequentially according to the descending order of the degree of interest of the first account.

[0219] For example, taking the number of positive feedback operations as an example, if the second recommendation information A receives 8 positive feedback operations, the second recommendation information B receives 6 positive feedback operations, and the second recommendation information C receives 4 positive feedback operations, then the descending order is: second recommendation information A, second recommendation information B, second recommendation information C. In this case, the first recommendation information is switched to the second recommendation information A first, and in response to the switching operation for the second recommendation information A, the second recommendation information A is switched to the second recommendation information B.

[0220] In step 302, at least one second account in the contact interface is updated to at least one third account that triggered a positive feedback operation on the second recommendation information.

[0221] Here, each third account can be represented by its name, icon, or other identifier. A threshold can be set for the number of third accounts to be displayed. If the number of third accounts exceeds the threshold, multiple third accounts will be collapsed, and the interactive controls corresponding to the collapsed third accounts will also be collapsed. If the number of third accounts exceeds the threshold, an expand icon can be displayed within a preset range of third accounts, such as below or to the right. In response to a trigger operation on the expand icon, all third accounts will be fully displayed. Multiple third accounts can be displayed in a list or scrolling format. When "updating at least one second account in the contact interface to at least one third account that triggered a positive feedback operation on the second recommendation information," the second interactive control corresponding to the second account is switched to the fifth interactive control corresponding to the third account, where the fifth interactive control is in a first state. In response to a trigger operation on the fifth interactive control, a fifth interactive message is sent to the third account, and the fifth interactive control is switched from the first state to the second state.

[0222] As an example of steps 301 to 302, taking the second interactive control as a batch interactive control as an example, see Figure 8C, which is an application diagram of the switching recommendation information provided in the embodiment of this application. In the left-hand view of Figure 8C, when the first recommendation information 703 is displayed in the first area 725 of the information recommendation interface 701, in response to the switching operation for the first recommendation information 703, in the middle view of Figure 8C, the first recommendation information 703 is switched to the second recommendation information 732, and at least one second account in the contact interface 714, such as second account 704, second account 706, second account 710, second account 715 and second account 716, is updated to at least one third account that triggered a positive feedback operation for the second recommendation information 732, such as third account 733, third account 734 and third account 735, and the second interactive control 731 corresponding to the second account is switched to the fifth interactive control 736 corresponding to the third account, wherein the fifth interactive control 736 is in the first state; in response to the triggering operation for the fifth interactive control 736, in the right-hand view of Figure 8C, the fifth interactive information is sent to the third account 733, third account 734 and third account 735, and the fifth interactive control 736 is switched from the first state to the second state.

[0223] Here, steps 301 and 302 above, "in response to the switching operation for the first recommendation information, switching the first recommendation information to the second recommendation information, and updating at least one second account in the contact object interface to at least one third account that triggered a positive feedback operation for the second recommendation information," can be achieved by performing the following processing: the terminal does not need to reload the entire human-computer interaction interface based on the first account login, but only sends an asynchronous data request for the area where the contact object interface is located, queries and obtains the data of the third account from the server, and then partially renders and updates it to the contact object interface. This partial asynchronous data update mechanism reduces the bandwidth pressure of full data request during interface switching, avoids redundant interface redrawing, and improves the system response speed when switching between the first and second recommendation information.

[0224] In this embodiment, as the recommended information changes, the interactive objects in the contact interface are also updated accordingly, ensuring the relevance of the interactive objects to the current recommended information and improving the targeting of the interaction. By dynamically updating the interactive objects, third-party accounts interested in the current recommended information can be found more quickly, improving the efficiency of the interaction. This allows users to see third-party accounts related to the current content in real time while browsing recommended information, enhancing the continuity and interactivity of the user experience.

[0225] In some embodiments, when step 203 "displays at least one second account and a second interactive control in the contact interface", at least one of the following is displayed: the recommendation reason of the second account for the first recommendation information, wherein the recommendation reason is edited by the second account or generated by artificial intelligence after the second account triggers a positive feedback operation; statistics of the second account's interactive operations within a preset statistical period, wherein the statistics include at least one of the following: the number of recommendation information for which the second account performs a positive feedback operation, and the number of times the second account and the first account interact with the recommendation information.

[0226] For example, the recommendation reason can be obtained by calling a pre-trained fourth machine learning model based on the second account, the first account, and the first recommendation information. The pre-trained fourth machine learning model can be trained by performing the following process: obtaining samples of the first account, the second account, the recommendation information, and the recommendation reason samples written by humans for the recommendation information samples; calling the initialized fourth machine learning model based on the first account samples, the second account samples, the recommendation information samples, and the recommendation reason samples to obtain the predicted recommendation reason; determining the fourth loss based on the predicted recommendation reason and the recommendation reason samples; updating the parameters of the initialized fourth machine learning model based on the fourth loss to obtain the pre-trained fourth machine learning model.

[0227] As an example, taking the display of statistical data as an example, refer to Figure 8D, which is a schematic diagram of displaying recommendation reasons and statistical data provided in the embodiments of this application. In the left-hand view of Figure 8D, when at least one second account and a second interactive control 731 are displayed in the contact interface 714, such as second account 704, second account 706, second account 710, second account 715 and second account 716, the statistical data of the interaction operations of the second account within a preset statistical period are displayed. The statistical data includes at least one of the following: the number of recommendation messages for which the second account performs positive feedback operations, the number of times the second account interacts with the first account regarding the recommendation information, for example, displaying statistical data 737 corresponding to second account 704, displaying statistical data 738 corresponding to second account 706, displaying statistical data 739 corresponding to second account 710, displaying statistical data 740 corresponding to second account 715, and displaying statistical data 741 corresponding to second account 716. In response to the triggering operation of the second interactive control 731, in the right-hand view of Figure 8D, second interactive information is sent to all second accounts, and the second interactive control 731 is switched from the first state to the second state.

[0228] The embodiments of this application demonstrate that the recommendation reason allows the first account to understand why the second account recommended this information, increasing the transparency and credibility of the interaction. The recommendation reason helps users judge the relevance and value of information, improving the quality and effectiveness of the interaction. Displaying statistical data on interaction operations provides data support for users and the platform, helping to understand user interaction behavior and preferences. Displaying the number of interactions can enhance social connections between users, increasing user engagement and activity.

[0229] In some embodiments, referring to FIG3G, FIG3G is a seventh flowchart of the information processing method provided in the embodiments of this application. When displaying at least one second account and first recommendation information of the second account performing positive feedback operation in the above-mentioned interactive notification interface, steps 401 to 402 of FIG3G are executed, which are described in detail below.

[0230] In step 401, in response to a deletion operation for any first recommended information, the display position of the first recommended information is removed from the interactive notification interface.

[0231] In some embodiments, a delete control corresponding to each display position of the first recommended information is displayed on the interactive notification page, and in response to a trigger operation on the delete control, the display position of the first recommended information is deleted from the interactive notification interface.

[0232] As an example of step 401, refer to Figure 9A, which is a schematic diagram of deleting the display position of recommendation information provided in an embodiment of this application. In the left side of Figure 9A, the deletion control corresponding to each display position of the first recommendation information is displayed on the interactive notification page 761. For example, the deletion control 742 corresponding to the display position of the first recommendation information 703 is displayed. In response to the triggering operation of the deletion control 742, the display position of the first recommendation information 703 is deleted from the interactive notification interface 720 in the right side of Figure 9A.

[0233] In step 402, in response to the notification closing operation for any first recommendation information, the interactive notification function of the first recommendation information is turned off.

[0234] In some embodiments, a notification close control corresponding to each first recommendation is displayed on the interactive notification page. In response to a trigger operation on the notification close control, the interactive notification function of the first recommendation is closed, and a prompt message is displayed to indicate that the interactive notification function of the first recommendation is closed.

[0235] As an example of step 402, refer to Figure 9B, which is a schematic diagram of the interactive notification function for disabling recommendation information provided in an embodiment of this application. In the left side of Figure 9B, the interactive notification page 761 displays a notification disabling control corresponding to each first recommendation information, such as the notification disabling control 743 corresponding to the first recommendation information 703. In response to a trigger operation on the notification disabling control 743, in the right side of Figure 9B, the interactive notification function of the first recommendation information 703 is disabled, and a prompt message 744 is displayed. The prompt message 744 is used to indicate that the interactive notification function of the first recommendation information 703 is in a disabled state.

[0236] This application embodiment allows users to delete or turn off uninteresting first-recommendation information based on their preferences and needs, achieving personalized content management. By allowing users to delete or turn off uninteresting information, information overload can be reduced, making the interactive notification interface more concise and easier to manage. Users deleting or turning off uninteresting information can encourage the platform to provide higher-quality and more relevant recommendation information. Responding to any deletion operation or notification closing operation for first-recommendation information, removing the display position of the first-recommendation information from the interactive notification interface or turning off the interactive notification function for the first-recommendation information can promptly release the memory and computing resources occupied by the terminal when rendering the first-recommendation information and related first interactive controls; simultaneously, stopping the reception and display of interactive data related to the first-recommendation information effectively reduces invalid network data transmission between the terminal and the server, lowers the rendering burden and data storage overhead, and improves overall operating performance and data processing efficiency.

[0237] In some embodiments, before step 103 "sending the first interactive information to the second account", the following processing may be performed: in response to the interaction mode setting operation for the first interactive control, the first interactive control is controlled to be set to a target interaction mode, wherein the target interaction mode is one of a positive interaction mode and a negative interaction mode. The positive interaction mode is used to express positive emotions to the second account in response to the first recommendation information, and the negative interaction mode is used to express negative emotions to the second account in response to the first recommendation information. The emotions expressed by the target interaction mode are consistent with the emotions expressed by the first interactive information.

[0238] For example, the first state indicates that the first account has not yet interacted with the second account and has not expressed the emotion expressed by the target interaction mode. The second state indicates that the first account has interacted with the second account and has expressed the emotion expressed by the target interaction mode. The first interaction control can be in positive interaction mode by default. The interaction mode setting can be switched in any of the following ways: long press to switch, for example, by long pressing the first interaction control, the text of the first state can be switched from "no thanks" to "no objection expressed"; the first interaction control is in the form of a switch and can be switched by single click, double click or swipe.

[0239] This application embodiment, by setting a target interaction mode, allows users to more clearly express their positive or negative feelings towards the first recommended information, avoiding ambiguity or misunderstanding. Users can choose the interaction mode based on their true feelings, making the interaction more targeted and improving its quality. The target interaction mode helps users express their emotions more quickly, improving the efficiency and convenience of the interaction.

[0240] In some embodiments, referring to FIG3H, FIG3H is an eighth flowchart of the information processing method provided in the embodiments of this application. Before step 103 "sending the first interactive information to the second account", steps 501 to 502 of FIG3H are executed, which are described in detail below.

[0241] In step 501, the information editing interface is displayed.

[0242] Here, the information editing interface can be used to edit various types of information, including but not limited to: text, images, emoticons, voice, and video.

[0243] In step 502, in response to the editing operation in the information editing interface, the first interactive information generated by the editing is displayed.

[0244] In some embodiments, in response to editing operations in the information editing area of ​​the information editing interface, such as selecting an information template, manually inputting first interactive information, or uploading existing information resources, the first interactive information formed by editing is displayed.

[0245] As an example of steps 501 to 502, refer to FIG10, which is a schematic diagram of editing interactive information provided in an embodiment of this application. In the left side view of FIG10, an information editing interface 745 is shown. In response to an editing operation in the information editing area 746 of the information editing interface, such as a selection operation for an information template 747, the right side view of FIG10 shows the first interactive information 748 recorded in the information template 747.

[0246] This application's embodiments allow users to create personalized interactive information through editing, expressing their unique perspectives and emotions, thus enhancing the personalization and realism of the interaction. It provides various editing options, such as selecting information templates, manually entering or uploading existing information resources, satisfying different user interaction needs and preferences, enriching the form and content of interactive information, and increasing the attractiveness of the interaction.

[0247] In some embodiments, referring to FIG3I, FIG3I is a ninth flowchart of the information processing method provided in the embodiments of this application. Before step 103 "sending the first interactive information to the second account", steps 601 to 602 of FIG3I are executed, which are described in detail below.

[0248] In step 601, an AI-based content generation interface is displayed.

[0249] Here, the content generation interface can display only the operation area, or it can display an interactive intelligent agent that interacts with the primary account based on artificial intelligence.

[0250] In step 602, in response to the material set in the content generation interface, first interactive information generated by artificial intelligence based on the material is displayed, wherein the material includes at least one of the following: characteristics of a first account, characteristics of a second account, and first recommendation information.

[0251] In some embodiments, features of the first account and the second account are extracted; the features of the first account are converted into a first account feature vector and the features of the second account are converted into a second account feature vector using a word embedding algorithm, and the first recommendation information is converted into a recommendation information vector; the first account feature vector, the second account feature vector, and the recommendation information vector are fused into an input vector, and a pre-trained Large Language Model (LLM) is called based on the input vector, using a self-attention mechanism to capture contextual information in the input vector; the Large Language Model predicts the next word or character based on the current contextual information, and the self-attention mechanism and feedforward neural network are repeatedly applied to combine the predicted next word or character into a coherent text sequence, i.e., the first interaction information.

[0252] As an example of steps 601 to 602, refer to Figure 11, which is a schematic diagram of generating first interactive information using artificial intelligence according to an embodiment of this application. In the left side of Figure 11, an AI-based content generation interface 749 is shown. Responding to materials set in the content generation interface, such as material 750 corresponding to the characteristics of a first account, material 751 corresponding to the characteristics of a second account, and material 752 corresponding to first recommendation information, and in response to selection operations on material 750, material 751, and material 752, and triggering operations on the generation control 753, the right side of Figure 11 shows the first interactive information 754 generated by artificial intelligence based on material 750, material 751, and material 752. The generated first interactive information 754 can be edited using the editing control 755.

[0253] This application embodiment uses multiple materials to call artificial intelligence to generate the first interactive information, generating interactive information from multiple dimensions, which improves the accuracy of the generated interactive information. By calling a pre-trained large language model, the time for manually editing interactive information is reduced, thus improving the efficiency of interactive information generation.

[0254] In some embodiments, at any time during the execution of steps 101 to 103 above, the following processing is performed: in response to a positive feedback operation on the fourth recommendation information, the fourth recommendation information is sent to the second account to perform the following processing in the human-computer interaction interface based on the second account login: displaying the fourth recommendation information and the fourth interactive control, wherein the fourth interactive control is in a first state; in response to a trigger operation on the fourth interactive control, the fourth interactive information is sent to the first account, and the fourth interactive control is switched from the first state to the second state.

[0255] As an example, refer to Figure 12, which is a schematic diagram of the interaction between a first account and a second account provided in an embodiment of this application. In the left-hand view of Figure 12, in the human-computer interaction interface 701 for logging in with the first account, in response to a positive feedback operation of the first account on the fourth recommendation information 756, such as a trigger operation on the positive feedback control 757, in the middle view of Figure 12, the fourth recommendation information 756 is sent to the second account to perform the following processing in the human-computer interaction interface 758 based on the second account login: displaying the fourth recommendation information 756, the first account 759, and the fourth interactive control 760, wherein the fourth interactive control 760 is in a first state; in response to a trigger operation on the fourth interactive control 760, in the right-hand view of Figure 12, a fourth interactive information for responding to the positive feedback operation on the fourth recommendation information is sent to the first account 759, and the fourth interactive control 760 is switched from the first state to the second state.

[0256] In this embodiment, the fourth recommendation information that the first account has performed a positive feedback operation is pushed to the second account. The second account then triggers the fourth interactive control, and the feedback fourth interactive information is returned to the first account, thus realizing a closed-loop interaction between the first and second accounts. This ensures that no matter which account performs a positive feedback operation, the other account can interact with the information recommended by the positive feedback operation, thereby improving the information interaction rate between different accounts.

[0257] In some embodiments, after step 103 "switching the first interactive control from the first state to the second state", the following processing may be performed: in response to a withdrawal operation on the first interactive control in the second state, the first interactive information that has been displayed is hidden in the interactive notification interface based on the second account login, and the first interactive control is restored from the second state to the first state.

[0258] For example, the withdrawal operation for the first interactive control in the second state can be a long press operation, a double-click operation, or a swipe operation along a preset direction performed by the first account on the first interactive control in the second state for a duration exceeding a time threshold. Taking the long press operation as an example, when the first interactive control is in the second state, for example, the text of the first interactive control is displayed as "Thank you" and is shown with a specific background color. In response to the long press operation of the first account on the first interactive control, a "Withdraw Interaction" prompt control pops up in the human-computer interaction interface logged in by the first account. In response to the trigger operation of the "Withdraw Interaction" prompt control, the terminal of the first account generates a withdrawal request data packet and sends it to the server. After receiving the withdrawal request data packet, the server locates the corresponding storage record of the first interaction information in the database and deletes or marks the storage record of the first interaction information as invalid. At the same time, the server pushes a withdrawal synchronization message to the terminal logged in by the second account through a real-time communication unit (such as WebSocket). In the interactive notification interface based on the second account login, the terminal parses the retracted synchronization message. If the first interactive information (such as a record containing the first account's avatar, nickname, and thank-you time) has already been rendered and displayed in the information list of the interactive notification interface, the display position corresponding to the first interactive information is removed from the interactive notification interface in real time through the interface's dynamic rendering mechanism, thus hiding it. If the first interactive information has not yet been viewed, the number of unread messages in the interactive notification interface is reduced simultaneously. At the same time, in the human-computer interaction interface based on the first account login, the terminal updates the appearance, text, or logo of the first interactive control from the second state in real time and restores it to the first state, for example, restoring it to the word "thank you" and the initial inactive color, clearly showing the first account that it has returned to a state where it has not yet interacted with the second account regarding the first recommended information.

[0259] This application embodiment restores the first interactive control from the second state to the first state through a withdrawal operation, and synchronously clears or invalidates the corresponding first interactive information records in the underlying database. This effectively avoids the persistent storage of invalid interactive data caused by user accidental touches on the server side, which not only optimizes the data storage space of the server database, but also ensures the accuracy and reliability of the underlying data when the system performs thank-you count statistics and data analysis. By dynamically hiding the displayed first interactive information in the interactive notification interface of the second account through cross-terminal data communication, strong consistency of the interactive state data among the first account terminal, the server, and the second account terminal is ensured. At the same time, by hiding invalid first interactive information in real time, the second account is prevented from initiating further data requests such as viewing or clicking on invalid information, thereby reducing unnecessary invalid network communication interactions between the terminal and the server, reducing the network bandwidth consumption and data processing load of the information processing system, and improving the overall operating efficiency of the system.

[0260] In some embodiments, after step 103 "switching the first interactive control from the first state to the second state", the following processing may be performed: displaying the location of the first interactive control in the human-computer interaction interface, displaying a quick conversation overlay for the first recommendation information, wherein the quick conversation overlay includes multiple quick reply options generated based on the topic tags of the first recommendation information; in response to the selection operation for any quick reply option, displaying the second interactive information, and displaying the link to the first recommendation information and the second interactive information in the instant messaging conversation window between the first account and the second account.

[0261] For example, taking a video as the first recommended information, if the first recommended information is a video about "coffee latte art," the topic tags for the first recommended information, such as "coffee," "latte art," and "daily sharing," are extracted through video metadata or semantic analysis. After the first account triggers the first interactive control (e.g., the "thank you" button) and switches it to the second state (e.g., "thanked"), the terminal does not perform a full-screen page jump. Instead, a quick chat overlay is dynamically rendered and popped up at the local coordinates of the first interactive control. This quick chat overlay includes multiple quick reply options automatically generated based on the aforementioned topic tags, such as "This latte art is so beautiful!", "Let's go for coffee next time?", or "Please recommend coffee beans." In response to the first account's selection of the quick reply option "Let's go for coffee next time?", this text is extracted as the second interactive information, and the data is automatically invoked or directly routed to the instant messaging chat window between the first and second accounts. In the information flow of this instant messaging chat window, the structured link of the "coffee latte art" video and the second interactive information "Let's go for coffee next time?" are automatically packaged and rendered.

[0262] In this embodiment, after the first interactive control switches to the second state, a shortcut session overlay is rendered locally in its original position, replacing the processing logic of full-page navigation or reloading the complete comment interface. This dynamic loading mechanism of local UI components effectively reduces the computational overhead during interface redrawing and full data loading, and lowers the interface response latency. By extracting topic tags from the first recommendation information to automatically generate quick reply options, the underlying metadata is transformed into directly clickable front-end interactive elements, reducing the time spent by the first account on touchscreen or keyboard character input, reducing input / output (I / O) resource consumption due to waiting for long text input by the user, and improving the efficiency of instruction input during the human-computer interaction stage. In response to the selection of quick reply options, the system automatically assembles the link of the first recommended message and the second interactive message into a data packet and sends it to the data link of the instant messaging session window through a single merged network request. Compared to the traditional operation logic where the user first manually shares the link (first network request) and then returns to enter text and send it (second network request), the system internally realizes automatic cross-module data flow and merging encapsulation, reduces the number of concurrent network requests between the terminal and the server, optimizes the utilization of network bandwidth, and improves the data transmission and processing efficiency in complex social interaction scenarios.

[0263] The following will describe an exemplary application of the embodiments of this application in a video mini-program application scenario of an instant messaging client.

[0264] The embodiments of this application are not limited to information processing in the context of video mini-programs in instant messaging clients; they are equally applicable in other scenarios, such as video apps or any social media platform. Furthermore, the form of information is not limited to video; it is also applicable to music, articles, and advertisements.

[0265] In related technologies, video mini-programs on instant messaging clients already possess basic like and share functions. Responding to a user's (i.e., the second account) like on a video (the first recommended information), the like triggers a recommendation mechanism within the user's friend circle. This means that contacts in the friend list will have the opportunity to see the liked video in their own feed. After liking, the friend (i.e., the first account) can see the video. However, the platform lacks a mechanism that allows friends of the recommended video to directly express their gratitude to the recommender. This lack of interaction prevents recommenders from receiving immediate feedback from friends of the recommended video, reducing their motivation to continue recommending, lowering users' enthusiasm for recommending videos, and limiting the possibility of deep interaction between friends. Furthermore, social interaction on the video platform is mainly limited to likes and comments, lacking novel and direct interaction methods, thus limiting deep emotional exchange between users.

[0266] To enhance the feedback experience for those who like videos and strengthen interaction among friends, the information processing method provided in this application introduces a "Thank You" button (i.e., an interactive control) into the video interface of the mini-program, allowing friends to express their gratitude for recommended videos. Specifically, in response to a user watching a video recommended by a friend and triggering the "Thank You" button, a thank-you message (i.e., the first interactive message) is sent to the friend who recommended the video, improving the user's interactive experience and enhancing social stickiness.

[0267] Referring to Figure 13, Figure 13 is a schematic diagram of providing feedback to the recommender via a "thank you" button according to an embodiment of this application. On the video interface (i.e., the information recommendation interface) of the video mini-program, in response to the user's "like" (positive feedback operation) on a video, the video is pushed to the user's friends. In response to the friend's viewing operation on the information stream (i.e., the first recommendation information) and their "like" or "thumbs up" operation on the video, a "thank you" button (i.e., the first interactive control) will be displayed below the video. In response to the friend's triggering operation on this button, a thank you message is sent to the recommender. Referring to Figure 14, Figure 14 is a schematic diagram of providing thanks to the recommender via a friend list according to an embodiment of this application. The friend list of the person who liked the video is displayed (i.e., the contact interface). In response to the user's triggering operation on the "thank you" button (i.e., the first interactive control) in the friend list, a thank you message is sent to the friend. Referring to Figure 15, Figure 15 is a schematic diagram of receiving thank you feedback according to an embodiment of this application. The "Interaction Notifications" section (also known as the Interaction Notifications interface) of the recommender's personal center interface displays specific records of thank-you feedback received (i.e., the first interaction information). Each record includes the thanker's avatar, name, the time of the thank-you, and a thumbnail of the video being thanked.

[0268] In response to user actions related to watching videos in the video mini-program, if a user resonates with or likes a video, the system receives a trigger action from the user's interaction with the heart icon below the video. This triggers the recommendation logic, and an event detector is designed to detect like events. Once a like is detected, all of the user's friends are identified through the user relationship graph, and the liked video information is pushed to these friends so that the video appears in their information streams. The user relationship graph is used to establish a network of friend relationships among users and is used for the logical judgment of the "thank you" button. Specifically, database technology, such as graph databases or relational databases, is used to store user identifiers (IDs) and their friend lists to ensure fast querying of any user's friend relationships.

[0269] In response to a friend's viewing action in the feed, check if the video has been liked by that friend (heart or thumbs up). If so, dynamically display a "Thank you" button below the video, indicating that the video was recommended by a user in the friend list. Add a prominent but intrusive "Thank you" button below the video playback page or on the video card. The button design should conform to User Interface Design (UI) / User Experience Design (UX) principles. The "Thank you" button can be designed with a striking color and shape to ensure that users notice it at a glance. A brief description can be added next to the button, such as "Thank you to the recommender."

[0270] The video mini-program displays a summary of each friend's recent likes and recommendations in the user's friend list. For friends who have recommended videos, a "Thank You" button should be displayed next to their information. In response to a user's click on the "Thank You" button, the system verifies whether the clicker is a friend of the recommender. This is done by comparing the clicker's ID with the ID in the recommender's friend list; only after confirmation of a match is the "Thank You" action allowed. A real-time communication service (such as WebSocket) is developed to push a notification to the recommender in real time when the "Thank You" action occurs. Simultaneously, a database table is designed to store all "Thank You" events for later statistical analysis. A front-end framework (such as React or Vue.js) is used to detect the "Thank You" button click event, triggering asynchronous JavaScript and eXtensible Markup Language (AJAX) calls or WebSocket messages to send the click event to the backend (i.e., the server, such as server 200 mentioned above) for processing.

[0271] A "Discussion Notifications" section (i.e., the interaction notification interface) will be set up in the user center to display received thank-you feedback. Responding to the recommender's viewing of interaction records with others in the user center, the "Discussion Notifications" section will display the name or nickname of the person expressing gratitude, the time of the gratitude, and the video information of the video being thanked, providing detailed thank-you feedback details. Below the section, data analysis (i.e., statistical data) such as the number of thanks and the distribution of those expressing gratitude can be provided in the form of charts or lists to help users understand the impact of their recommendation behavior.

[0272] Simultaneously, sensitive data such as user friend lists and like records can be encrypted and stored to ensure that even if the data is accessed illegally, the specific content cannot be deciphered. Strict user authentication and permission checks, such as OAuth 2.0 authentication, are implemented to control access to the "thank you" function, ensuring that only the recommender's friends can see and click the "thank you" button. A logging system is designed to record detailed information for each "thank you" operation, including operation time, user ID, video ID, etc., for subsequent analysis and auditing. Caching technologies (such as Redis) are used to store frequently accessed data, reducing the number of direct database accesses, improving data retrieval speed, and ensuring rapid response to "thank you" operations even in a large-scale user environment. A microservice architecture is adopted to distribute request processing, and a load balancer (such as Nginx or HAProxy) is configured to reasonably allocate traffic, ensuring good responsiveness and stable operation even when handling high-concurrency "thank you" operations. A fault recovery mechanism is established, and a redundant architecture is designed, such as multi-datacenter deployment, to ensure that the backup system can seamlessly take over when the main system fails. At the same time, a regular data backup strategy is implemented to prevent data loss and ensure the system's continuous operation capability in the event of emergencies.

[0273] This application's implementation uses an instant feedback mechanism to increase user motivation to recommend videos, thereby improving the sharing and viewing rates of videos on the platform. The introduction of a "thank you" button enriches the platform's social interaction, promotes emotional exchange and social stickiness among users, and enhances the overall social experience of the video platform. The statistics and display of thank-you messages allow recommenders to feel that their social contributions are recognized, thus strengthening their sense of belonging and participation on the platform.

[0274] The following continues to describe an exemplary structure of the information processing device 455 provided in the embodiments of this application as a software module. In some embodiments, as shown in FIG2, the software module stored in the information processing device 455 in the memory 450 may include:

[0275] The information display module 4551 is configured to display first recommended information on the human-computer interaction interface based on the first account login. The first recommended information is displayed when the second account triggers a positive feedback operation on the first recommended information. The first account and the second account have a social relationship.

[0276] The control display module 4552 is configured to display a first interactive control in the human-computer interaction interface, wherein the first interactive control is in a first state, the first state indicating that the first account has not yet interacted with the second account regarding the first recommendation information.

[0277] The information sending module 4553 is configured to send first interactive information to the second account in response to a trigger operation on the first interactive control, and to switch the first interactive control from a first state to a second state, wherein the second state indicates that the first account has interacted with the second account regarding the first recommendation information.

[0278] In some embodiments, the information display module 4551 is further configured to display first recommended information in the information display area of ​​the information recommendation interface based on the first account login when the human-computer interaction interface is an information recommendation interface.

[0279] In some embodiments, the information display module 4551 is further configured to display at least one second account and first recommendation information of the second account performing a positive feedback operation in the interactive notification interface when the human-computer interaction interface is an interactive notification interface.

[0280] In some embodiments, the information display module 4551 is further configured to display first recommendation information in the contact interface based on the first account login when the human-computer interaction interface is a contact interface.

[0281] In some embodiments, the information display module 4551 is further configured to, in response to a trigger operation on a second account, display first recommended information in a first area of ​​the information recommendation interface; display a contact interface floating in a second area of ​​the information recommendation interface, wherein the second area is an area in the information recommendation interface distinct from the first area; display at least one second account and a second interactive control in the contact interface, wherein the second interactive control is in a first state, the first state indicating that the first account has not yet interacted with the second account regarding the first recommended information; send second interactive information to the second account in response to a trigger operation on the second interactive control; and switch the second interactive control from the first state to the second state, wherein the second state indicates that the first account has already interacted with the second account regarding the first recommended information.

[0282] In some embodiments, the information display module 4551 is further configured to, when there is a one-to-one correspondence between the second interactive control and the second account, send second interactive information to the second account corresponding to any second interactive control in response to a trigger operation for any second interactive control; and when the second interactive control is a batch interactive control, send second interactive information to each second account in response to a trigger operation for the second interactive control.

[0283] In some embodiments, the information display module 4551 is further configured to, in response to a switching operation on the first recommended information, switch the first recommended information to the second recommended information; and update at least one second account in the contact object interface to at least one third account that triggered a positive feedback operation on the second recommended information.

[0284] In some embodiments, the control display module 4552 is further configured to display a first interactive control in the information display area when the human-computer interaction interface is an information recommendation interface.

[0285] In some embodiments, the control display module 4552 is further configured to perform at least one of the following when the number of second accounts triggering positive feedback operations is at least one: displaying each second account and a first interactive control corresponding to each second account in the information display area, wherein any first interactive control is used to trigger the operation of sending first interactive information to the second account corresponding to any first interactive control when receiving a trigger operation; displaying each second account and a first interactive control for batch interaction in the information display area, wherein the first interactive control is used to trigger the operation of sending first interactive information to each second account when receiving a trigger operation.

[0286] In some embodiments, the control display module 4552 is further configured to display a first interactive control corresponding to each first recommendation in the information display area when the number of first recommendation information displayed in the information display area is multiple and the number of second accounts triggered for the first recommendation information is multiple.

[0287] In some embodiments, the contact object interface includes a contact object area, which includes at least one second account. The control display module 4552 is further configured to display a first interactive control corresponding to at least one second account in the contact object interface when the human-computer interaction interface is an interactive notification interface.

[0288] In some embodiments, the control display module 4552 is further configured to display at least one second account and a first interactive control corresponding to each second account in the contact object area, wherein a first interactive control is used to send first interactive information to the second account corresponding to any first interactive control when triggered.

[0289] In some embodiments, the control display module 4552 is further configured to display at least one second account and a first interactive control for batch interaction in the contact object area, wherein the first interactive control is used to send a first interactive message to each second account when triggered.

[0290] In some embodiments, the control display module 4552 is further configured to, when the human-computer interaction interface is a contact interface, display a first interactive control corresponding to each second account in the display position of each first recommended information in the interactive notification interface; or, display a first interactive control for batch interaction for each second account in the interactive notification interface; wherein, when there are multiple first recommended information, the display positions of the multiple first recommended information are sorted in a specific order, and the specific order is sorted according to at least one of the following parameters: publication time, time of receiving positive feedback operation, number of times positive feedback operation is received, and the degree of interest of the first account in the first recommended information.

[0291] In some embodiments, when the first account triggers a positive feedback operation on the third recommendation information, the interactive notification interface also includes third interactive information. The third interactive information is sent to the first account by the second account that received the third recommendation information by triggering a third interactive control. The third interactive control is used by the second account to interact with the first account on the third recommendation information.

[0292] In some embodiments, the control display module 4552 is further configured to display a positive feedback control for the first recommendation information in the human-computer interaction interface; and to display the first interactive control in response to a trigger operation on the positive feedback control.

[0293] In some embodiments, the control display module 4552 is further configured to display a first interactive control in response to the second account meeting a first preset condition, wherein the first preset condition includes at least one of the following: the interaction frequency between the first account and the second account is greater than a frequency threshold, and the similarity of information preferences between the first account and the second account is greater than a first similarity threshold.

[0294] In some embodiments, the control display module 4552 is further configured to display at least one of the following: the recommendation reason of the second account for the first recommendation information, wherein the recommendation reason is formed by the second account or generated by artificial intelligence after the second account triggers a positive feedback operation; and statistical data of the interaction operations of the second account within a preset statistical period, wherein the statistical data includes at least one of the following: the number of recommendation information for which the second account performs a positive feedback operation, and the number of times the second account and the first account interact with the recommendation information.

[0295] In some embodiments, the control display module 4552 is further configured to, in response to a deletion operation for any first recommended information, remove the display position of the first recommended information from the interactive notification interface; and in response to a notification closing operation for any first recommended information, close the interactive notification function of the first recommended information.

[0296] In some embodiments, the information sending module 4553 is further configured to, in the case that the number of first recommended information displayed in the information display area is multiple and the number of second accounts triggering the first recommended information is multiple, control the first recommended information to be selected in a selected state in response to the batch selection operation of multiple first recommended information, and in response to the triggering operation of the first interactive control corresponding to any selected first recommended information, send first interactive information to the second account that performs a positive feedback operation on the first recommended information for each batch selected first recommended information.

[0297] In some embodiments, the information sending module 4553 is further configured to, when there is a one-to-one correspondence between the first interactive control and the second account, send the first interactive information to the second account corresponding to any one of the first interactive controls in response to a trigger operation for any first interactive control; and when the first interactive control is a batch interactive control, send the first interactive information to each second account in response to a trigger operation for the first interactive control.

[0298] In some embodiments, the first interactive control includes a first positive interactive sub-control and a second negative interactive sub-control. The first positive interactive sub-control is used to express positive emotions to the second account in response to the first recommendation information, and the second negative interactive sub-control is used to express negative emotions to the second account in response to the first recommendation information. The information sending module 4553 is further configured to, in response to the control activation operation, control the target sub-control to be in an active state and send first interactive information corresponding to the emotions expressed by the target sub-control to the second account. The target sub-control is one of the first positive interactive sub-control and the second negative interactive sub-control, and the emotions expressed by the target sub-control are consistent with the emotions expressed by the first interactive information.

[0299] In some embodiments, the information sending module 4553 is further configured to control the first interactive control to be set to a target interactive mode in response to an interaction mode setting operation for the first interactive control. The target interactive mode is one of a positive interactive mode and a negative interactive mode. The positive interactive mode is used to express positive emotions to the second account in response to the first recommendation information, and the negative interactive mode is used to express negative emotions to the second account in response to the first recommendation information. The emotions expressed in the target interactive mode are consistent with the emotions expressed in the first interactive information.

[0300] In some embodiments, the information sending module 4553 is further configured to display an information editing interface; in response to an editing operation in the information editing interface, it displays the first interactive information generated by the editing.

[0301] In some embodiments, the information sending module 4553 is further configured to display an AI-based content generation interface; in response to materials set in the content generation interface, to display first interactive information generated by AI based on the materials, wherein the materials include at least one of the following: characteristics of a first account, characteristics of a second account, and first recommendation information.

[0302] In some embodiments, the information sending module 4553 is further configured to send the fourth recommendation information to the second account in response to a positive feedback operation on the fourth recommendation information, so as to perform the following processing in the human-computer interaction interface based on the second account login: displaying the fourth recommendation information and the fourth interactive control, wherein the fourth interactive control is in a first state; and sending the fourth interactive information to the first account in response to a trigger operation on the fourth interactive control, and switching the fourth interactive control from the first state to the second state.

[0303] This application provides a computer program product, which includes a computer program or computer-executable instructions stored in a computer-readable storage medium. The processor of an electronic device reads the computer-executable instructions from the computer-readable storage medium and executes the computer-executable instructions, causing the electronic device to perform the information processing method described in this application.

[0304] This application provides a computer-readable storage medium storing computer-executable instructions or a computer program. When the computer-executable instructions or the computer program are executed by a processor, the processor will execute the information processing method provided in this application, such as the information processing method shown in FIG3A.

[0305] In some embodiments, the computer-readable storage medium may be a memory such as RAM, ROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or it may be a variety of devices including one or any combination of the above-mentioned memories.

[0306] In some embodiments, computer-executable instructions may take the form of programs, software, software modules, scripts, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as stand-alone programs or as modules, components, subroutines, or other units suitable for use in a computing environment.

[0307] As an example, computer-executable instructions may, but do not necessarily, correspond to files in a file system. They may be stored as part of a file that holds other programs or data, for example, in one or more scripts in a Hyper Text Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple co-located files (e.g., files that store one or more modules, subroutines, or code sections).

[0308] As an example, computer-executable instructions can be deployed to execute on a single electronic device, or on multiple electronic devices located at one location, or on multiple electronic devices distributed across multiple locations and interconnected via a communication network.

[0309] In summary, through the embodiments of this application, on the one hand, the human-computer interaction interface based on the login of the first account displays the first recommendation information that has been positively recommended by the second account with a social relationship with the first account. The positive feedback operation reflects the second account's preference (positive sentiment) for the first recommendation information and reflects the correlation between the first recommendation information, the second account, and the first account. The data association between the first account, the second account, and the first recommendation information is constructed using social relationship data and positive feedback operation data. Based on this data association, the human-computer interaction interface is driven to display information, thereby improving the relevance and targeting of information recommendations. On the other hand, by triggering the first interactive control to send the first interactive information to the second account, the first recommendation information is recommended by the second account to the first account, and then the feedback (first interactive information) of the first account on the first recommendation information is returned to the second account. This process opens up the reverse data transmission link for the first recommendation information, transforms the one-way data transmission into two-way data communication, and visually displays the interaction process between the first account and the second account, realizing the interaction loop between the first account and the second account, improving the information interaction rate for the first recommendation information. At the same time, the quick feedback through the interactive control simplifies the operation process of sending interactive information and also improves the interaction efficiency between different accounts. Furthermore, in response to a trigger operation on the first interactive control, the first interactive control is switched from a first state representing no interaction to a second state representing interaction. This state switching process records and clearly displays the historical state of the interaction on the human-computer interaction interface, which can effectively avoid repeated trigger operations on the first interactive control by the user, thereby reducing the overhead of invalid repeated interactive data transmission and processing, and thus improving information processing efficiency and operating performance.

[0310] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, and improvements made within the spirit and scope of this application are included within the scope of protection of this application.

Claims

1. An information processing method, the method being executed by an electronic device, the method comprising: The first recommendation information is displayed on the human-computer interaction interface based on the first account login. The first recommendation information is displayed when the second account triggers a positive feedback operation on the first recommendation information. The first account and the second account have a social relationship. The human-computer interaction interface displays a first interactive control, wherein the first interactive control is in a first state, and the first state indicates that the first account has not yet interacted with the second account regarding the first recommendation information; In response to a trigger operation on the first interactive control, a first interactive message is sent to the second account, and The first interactive control is switched from the first state to the second state, wherein the second state indicates that the first account has interacted with the second account regarding the first recommendation information.

2. The method according to claim 1, wherein, When the human-computer interaction interface is an information recommendation interface, displaying the first recommended information on the human-computer interaction interface based on the first account login includes: The first recommended information is displayed in the information display area of ​​the information recommendation interface based on the first account login; The step of displaying the first interactive control in the human-computer interaction interface includes: The first interactive control is displayed in the information display area.

3. The method according to claim 2, wherein, When at least one of the second accounts triggers the positive feedback operation, displaying the first interactive control in the information display area includes: Perform at least one of the following processes: The information display area displays each second account and a first interactive control corresponding to each second account. When any of the first interactive controls receives the trigger operation, it triggers the execution of sending first interactive information to the second account corresponding to the first interactive control. The information display area displays each second account and a first interactive control for batch interaction, wherein the first interactive control is used to trigger the operation of sending the first interactive information to each second account when the trigger operation is received.

4. The method according to claim 2, wherein, When there are multiple instances of the first recommended information displayed in the information display area, and multiple instances of the second account triggering the first recommended information, displaying the first interactive control in the information display area includes: The first interactive control corresponding to each of the first recommended pieces of information is displayed in the information display area; The step of sending first interactive information to the second account in response to a trigger operation on the first interactive control includes: In response to a batch selection operation targeting multiple pieces of the first recommendation information, the selected pieces of the first recommendation information are controlled to be in a selected state, and In response to a trigger operation of the first interactive control corresponding to any selected first recommendation information, the first interactive information is sent to the second account that performs the positive feedback operation on the first recommendation information for each of the first recommendation information that is selected in batches.

5. The method according to claim 4, wherein, Before sending the first interactive information to the second account in response to a triggering operation on the first interactive control, the method further includes: The information display area displays selection controls corresponding to each of the first recommended pieces of information. In response to a trigger operation on a selection control corresponding to any of the first recommendation information, a list of the second accounts that have performed positive feedback operations on the first recommendation information is displayed; In response to a selection operation on a portion of the second accounts in the list, the selected portion of the second accounts is set to a selected state, wherein the selected state indicates that the selected portion of the second accounts will receive the first interactive information after the first interactive control is triggered.

6. The method according to any one of claims 1 to 5, wherein, When displaying the first recommendation information on the human-computer interaction interface based on the first account login, the method further includes: In response to a triggered operation targeting the second account, the first recommended information is displayed in the first area of ​​the information recommendation interface, and The contact interface is displayed in a way that it floats in the second area of ​​the information recommendation interface, wherein the second area is a region in the information recommendation interface that is different from the first area; The contact interface displays at least one second account and a second interactive control, wherein the second interactive control is in the first state, and the first state indicates that the first account has not yet interacted with the second account regarding the first recommendation information; In response to a triggering operation on the second interactive control, a second interactive message is sent to the second account, and The second interactive control is switched from the first state to the second state, wherein the second state indicates that the first account has interacted with the second account regarding the first recommendation information.

7. The method according to claim 6, wherein, The step of sending second interactive information to the second account in response to a trigger operation on the second interactive control includes: When the second interactive control corresponds one-to-one with the second account, in response to a trigger operation on any of the second interactive controls, a second interactive message is sent to the second account corresponding to any of the second interactive controls; If the second interactive control is a batch interactive control, in response to a trigger operation on the second interactive control, a second interactive message is sent to each of the second accounts.

8. The method according to claim 6, wherein, When the first recommendation information is displayed in the first area of ​​the information recommendation interface, the method further includes: In response to the switching operation on the first recommendation information, the first recommendation information is switched to the second recommendation information, and Update at least one second account in the contact interface to at least one third account that triggered a positive feedback operation on the second recommendation information.

9. The method according to claim 6, wherein, When at least one second account and a second interactive control are displayed in the contact interface, the method further includes: Show at least one of the following: The recommendation reason given by the second account for the first recommendation information is either edited by the second account or generated by artificial intelligence after the second account triggers the positive feedback operation. The statistical data of the interaction operations of the second account within a preset statistical period includes at least one of the following: the number of recommended information where the second account performs the positive feedback operation, and the number of times the second account and the first account interact with the recommended information.

10. The method according to claim 1, wherein, When there are multiple second accounts, displaying the first interactive control in the human-computer interaction interface includes: If the number of the second accounts exceeds the account number threshold, multiple second accounts will be collapsed and displayed, and the first interactive control corresponding to the collapsed second account will also be collapsed and displayed. The method further includes: Display an expand icon within a preset range of multiple second accounts; In response to a triggering operation on the expanded identifier, multiple second accounts are displayed.

11. The method according to claim 1, wherein, The step of displaying the first interactive control in the human-computer interaction interface includes: In response to the first recommendation information satisfying a second preset condition, a first interactive control is displayed, wherein the second preset condition includes at least one of the following: The first account's level of interest in the first recommended information is greater than the first interest threshold; The first account's level of interest in the target object in the first recommendation information is greater than the second interest threshold; The similarity between the account features of the first account and the information features of the first recommendation information is greater than the second similarity threshold; The first account has an interaction probability greater than a first probability threshold, and the interaction probability is predicted based on the historical recommendation information of the first account's interactions. The duration of the first account's stay on the first recommended information exceeds the duration threshold.

12. The method according to claim 1, wherein, When the human-computer interaction interface is a contact object interface, the contact object interface includes a contact object area, and the contact object area includes at least one second account; The step of displaying the first recommendation information on the human-computer interaction interface based on the first account login includes: Display the first recommended information in the contact interface based on the first account login; The step of displaying the first interactive control in the human-computer interaction interface includes: The contact interface displays a first interactive control corresponding to at least one of the second accounts.

13. The method according to claim 12, wherein, The first interactive control displayed in the contact interface corresponding to at least one of the second accounts includes: Perform at least one of the following processes: The contact object area displays at least one second account and a first interactive control corresponding to each second account, wherein when a first interactive control is triggered, it executes the sending of the first interactive information to the second account corresponding to any first interactive control; At least one second account and a first interactive control for batch interaction are displayed in the contact object area, wherein the first interactive control is used to send the first interactive information to each second account when triggered.

14. The method according to claim 1, wherein, When the human-computer interaction interface is an interactive notification interface, displaying the first recommendation information on the human-computer interaction interface based on the first account login includes: The interactive notification interface displays at least one second account and first recommendation information of the second account performing the positive feedback operation; The step of displaying the first interactive control in the human-computer interaction interface includes: For each display position of the first recommendation information in the interactive notification interface, display a first interactive control corresponding to each second account; or For each of the second accounts in the interactive notification interface, a first interactive control for batch interaction is displayed; In cases where there are multiple pieces of the first recommended information, the display positions of the multiple pieces of the first recommended information are sorted in a specific order. The specific order is sorted according to at least one of the following parameters: publication time, time of receiving the positive feedback operation, number of times the positive feedback operation is received, and the degree of interest of the first account in the first recommended information.

15. The method according to claim 14, wherein, The step of sending the first interactive information to the second account in response to a trigger operation on the first interactive control includes: When there is a one-to-one correspondence between the first interactive control and the second account, in response to the trigger operation for any of the first interactive controls, the first interactive information is sent to the second account corresponding to any of the first interactive controls; If the first interactive control is a batch interactive control, in response to a trigger operation on the first interactive control, the first interactive information is sent to each of the second accounts.

16. The method of claim 14, wherein, When displaying at least one second account and first recommendation information of the second account performing the positive feedback operation in the interactive notification interface, the method further includes: In response to a deletion operation on any of the first recommended information, the display position of the first recommended information is removed from the interactive notification interface; In response to a notification-off operation for any of the first recommendation information, the interactive notification function of the first recommendation information is turned off.

17. The method according to claim 14, wherein, When the first account triggers the positive feedback operation for the third recommendation information, the interactive notification interface also includes third interactive information. The third interactive information is sent to the first account by the second account that received the third recommendation information through the triggering third interactive control. The third interactive control is used by the second account to interact with the first account regarding the third recommendation information.

18. The method according to any one of claims 1 to 17, wherein, The method further includes: In response to a positive feedback action on the fourth recommendation information, the fourth recommendation information is sent to the second account to perform the following processing in the human-computer interaction interface based on the second account login: The fourth recommendation information and the fourth interactive control are displayed, wherein the fourth interactive control is in the first state; In response to a trigger operation on the fourth interactive control, a fourth interactive message is sent to the first account, and the fourth interactive control is switched from the first state to the second state.

19. The method according to claim 1, wherein, The step of displaying the first interactive control in the human-computer interaction interface includes: The human-computer interaction interface displays a positive feedback control for the first recommendation information; In response to a trigger operation on the positive feedback control, a first interactive control is displayed in the human-computer interaction interface.

20. The method according to claim 1, wherein, The step of displaying the first interactive control in the human-computer interaction interface includes: In response to the second account meeting a first preset condition, a first interactive control is displayed, wherein the first preset condition includes at least one of the following: the interaction frequency between the first account and the second account is greater than a frequency threshold, and the similarity of the information preferences of the first account and the second account is greater than a first similarity threshold.

21. The method according to any one of claims 1 to 20, wherein, Before sending the first interactive information to the second account, the method further includes: In response to the interaction mode setting operation for the first interactive control, the first interactive control is controlled to be set to a target interaction mode, wherein the target interaction mode is one of a positive interaction mode and a negative interaction mode. The positive interaction mode is used to express positive emotions to the second account in response to the first recommendation information, and the negative interaction mode is used to express negative emotions to the second account in response to the first recommendation information. The emotions expressed by the target interaction mode are consistent with the emotions expressed by the first interactive information.

22. The method according to any one of claims 1 to 21, wherein, The first interactive control includes a first positive interactive sub-control and a second negative interactive sub-control. The first positive interactive sub-control is used to express positive emotions to the second account in response to the first recommendation information, and the second negative interactive sub-control is used to express negative emotions to the second account in response to the first recommendation information. Sending the first interactive message to the second account includes: In response to a control activation operation, the target sub-control is controlled to be in an active state, and a first interactive message corresponding to the emotion expressed by the target sub-control is sent to the second account, wherein the target sub-control is one of the first positive interactive sub-control and the second negative interactive sub-control, and the emotion expressed by the target sub-control is consistent with the emotion expressed by the first interactive message.

23. The method according to any one of claims 1 to 22, wherein, Before sending the first interactive information to the second account, the method further includes: Display information editing interface; In response to the editing operation in the information editing interface, the first interactive information generated by the editing is displayed.

24. The method according to any one of claims 1 to 23, wherein, Before sending the first interactive information to the second account, the method further includes: Displays an AI-based content generation interface; In response to the material set in the content generation interface, the first interactive information generated by the artificial intelligence based on the material is displayed, wherein the material includes at least one of the following: characteristics of the first account, characteristics of the second account, and the first recommendation information.

25. An information processing apparatus, the apparatus comprising: The information display module is configured to display first recommended information on the human-computer interaction interface based on the first account login, wherein the first recommended information is displayed when the second account triggers a positive feedback operation on the first recommended information, and the first account and the second account have a social relationship; The control display module is configured to display a first interactive control in the human-computer interaction interface, wherein the first interactive control is in a first state, and the first state indicates that the first account has not yet interacted with the second account regarding the first recommendation information; The information sending module is configured to, in response to a trigger operation on the first interactive control, send first interactive information to the second account and switch the first interactive control from the first state to the second state, wherein the second state indicates that the first account has interacted with the second account regarding the first recommendation information.

26. An electronic device, the electronic device comprising: Memory is used to store executable instructions or computer programs. A processor, when executing computer-executable instructions or computer programs stored in the memory, implements the information processing method according to any one of claims 1 to 24.

27. A computer-readable storage medium storing computer-executable instructions or a computer program, wherein the computer-executable instructions or the computer program, when executed by a processor, implement the information processing method according to any one of claims 1 to 24.

28. A computer program product comprising computer-executable instructions or a computer program, wherein the computer-executable instructions or the computer program, when executed by a processor, implement the information processing method according to any one of claims 1 to 24.

Images