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

Abstract

The invention provides an information interaction processing method and device, electronic equipment, a computer program product and a computer readable storage medium. The method comprises the steps of displaying recommendation information in an information display interface; a plurality of interaction options are displayed, and the interaction options are generated by calling artificial intelligence based on the recommendation information; and in response to a first trigger operation for any one of the interaction options, displaying an interaction result corresponding to the selected interaction option. According to the method and the device, the interaction efficiency between the user and the recommendation information can be improved through the interaction options.

Description

Technical Field

[0001] This application relates to computer and artificial intelligence technologies, and more particularly to an interactive information processing method, apparatus, electronic device, storage medium, and program product. Background Technology

[0002] In-feed advertising is a form of advertising integrated into the user's information flow on social media, news apps, or other content platforms. It blends promoted content with the content users typically browse. In related technologies, the interaction format for in-feed ads usually involves users triggering a landing page for interaction. This limited and simplistic interaction method affects user interest and the efficiency of user engagement with in-feed ads.

[0003] Currently, there is no good way to improve the interaction efficiency between in-feed ads and users. Summary of the Invention

[0004] This application provides an interactive information processing method, apparatus, electronic device, computer-readable storage medium, and computer program product, which can improve the efficiency of user interaction with recommended information through interactive options.

[0005] The technical solution of this application embodiment is implemented as follows:

[0006] This application provides an interactive information processing method, the method comprising:

[0007] Display recommended information on the information display interface;

[0008] Multiple interactive options are displayed, wherein the multiple interactive options are generated by artificial intelligence based on the recommendation information;

[0009] In response to a first trigger operation for any of the interactive options, the interaction result corresponding to the selected interactive option is displayed.

[0010] This application provides an interactive information processing device, including:

[0011] The display module is used to display recommended information in the information display interface;

[0012] The display module is also used to display multiple interactive options, wherein the multiple interactive options are generated by artificial intelligence based on the recommendation information;

[0013] The display module is further configured to display the interaction result corresponding to the selected interaction option in response to a first trigger operation for any one of the interaction options.

[0014] This application provides an electronic device, the electronic device comprising:

[0015] Memory is used to store executable instructions or computer programs.

[0016] The processor, when executing computer-executable instructions or computer programs stored in the memory, implements the interactive information processing method provided in the embodiments of this application.

[0017] This application provides a computer-readable storage medium storing computer-executable instructions or computer programs, which, when executed by a processor, implement the interactive information processing method provided in this application.

[0018] 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 interactive information processing method provided in this application.

[0019] The embodiments of this application have the following beneficial effects:

[0020] By displaying interactive options related to the recommended information on the information display interface, the system encourages user interaction. The system then displays the corresponding interaction results for each triggered option. These options and results can attract users to browse the recommended information for longer periods and participate in the interactive processes related to the recommended information, thus improving the recommendation effect. Furthermore, labeling the recommended information with interactive options facilitates user understanding and improves the efficiency of user interaction with the recommended information. Attached Figure Description

[0021] Figure 1 This is a schematic diagram illustrating the application mode of the interactive information processing method provided in the embodiments of this application;

[0022] Figure 2 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application;

[0023] Figure 3A This is a first flowchart illustrating the information interaction processing method provided in the embodiments of this application;

[0024] Figure 3B This is a second flowchart illustrating the interactive information processing method provided in the embodiments of this application;

[0025] Figure 4 This is a third flowchart illustrating the interactive information processing method provided in the embodiments of this application;

[0026] Figure 5A This is a first schematic diagram of the information flow interface provided in the embodiments of this application;

[0027] Figure 5B This is a second schematic diagram of the information flow interface provided in the embodiments of this application;

[0028] Figure 6A This is a third schematic diagram of the information flow interface provided in the embodiments of this application;

[0029] Figure 6B This is a fourth schematic diagram of the information flow interface provided in the embodiments of this application;

[0030] Figure 6C This is the fifth schematic diagram of the information flow interface provided in the embodiments of this application;

[0031] Figure 6D This is the sixth schematic diagram of the information flow interface provided in the embodiments of this application;

[0032] Figure 7A This is the seventh schematic diagram of the information flow interface provided in the embodiments of this application;

[0033] Figure 7B This is the eighth schematic diagram of the information flow interface provided in the embodiments of this application;

[0034] Figure 7C This is the ninth schematic diagram of the information flow interface provided in the embodiments of this application;

[0035] Figure 8 This is the tenth schematic diagram of the information flow interface provided in the embodiments of this application.

[0036] 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

[0037] 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.

[0038] 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.

[0039] 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.

[0040] It should be noted that the data collection and processing in this application 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.

[0041] 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.

[0042] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0043] 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.

[0044] 1) Responding to: used to indicate the conditions or states on which the operation is performed. When the conditions or states on which the operation is performed are met, one or more operations may 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.

[0045] 2) Human-Computer Interaction Interface: A human-computer interaction interface is an interface used to provide human-computer interaction functions and display information flow. Examples include graphical user interfaces (GUIs), 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 viewing of stereoscopic images without special glasses), multimodal interfaces (interfaces combining multiple interaction methods, such as tactile, visual, and auditory interaction), and brain-machine interfaces (BMIs).

[0046] 3) Control: A control is a triggerable piece of information displayed in the form of a region, button, icon, link, text, selection box, input box, and tab; the triggering method can be contact triggering, non-contact triggering, or instruction-based triggering, etc.; in addition, the various controls in the embodiments of this application can be a single control or a collective term for multiple controls.

[0047] 4) Operation: is a method used to trigger the device to perform processing, such as click operation, double-click operation, long press operation, swipe operation, gesture operation, received trigger command, etc.; in addition, the various operations in the embodiments of this application can be a single operation or a collective term for multiple operations; and the various operations in the embodiments of this application can be touch operation or non-touch operation.

[0048] 5) Information Display Interface (IPI): This refers to an interactive interface used to display data, content, and information to users. It can exist in various types of software applications, websites, mobile devices, and other electronic devices. The design of an IPI aims to effectively convey information and allow users to interact with it conveniently.

[0049] 6) Retrofit: A type-safe Hypertext Transfer Protocol (HTTP) client library used to simplify the writing of network requests in Java and Android applications. Developed by Square, it is built on top of the OkHttp library. Retrofit defines network requests through annotations and interfaces, automatically converts JSON to Java objects, and handles thread switching, making network communication code more concise and easier to maintain.

[0050] In related technologies, the interactive methods of information flow ads in the information flow interface include click triggering, swipe triggering, or device shake triggering. The interaction forms with users are simple and have limitations, which reduces users' interest in the recommended information and affects the recommendation efficiency and the interaction efficiency with users.

[0051] This application provides an interactive information processing method, an interactive information processing apparatus, an electronic device, a computer-readable storage medium, and a computer program product, which can improve the efficiency of user interaction with recommended information through interactive options.

[0052] The following describes exemplary applications of the electronic devices provided in the embodiments of this application. These electronic devices can be implemented as terminal devices, such as laptops, tablets, desktop computers, set-top boxes, smart TVs, in-vehicle terminals, virtual reality (VR) devices, augmented reality (AR) devices, and other various types of terminals. They can also be implemented as servers. The following will describe exemplary applications when the electronic device is implemented as a terminal device or a server.

[0053] refer to Figure 1 , Figure 1 This is a schematic diagram illustrating the application mode of the interactive information processing method provided in the embodiments of this application; for example, Figure 1 The system involves server 200, network 300, terminal device 400, and database 500. Terminal device 400 is connected to server 200 through network 300, which can be a wide area network, a local area network, or a combination of both.

[0054] Terminal device 400 is used to display the information flow interface. Terminal device 400 can be a mobile phone used by the user. Server 200 can be a server of the information recommendation platform. Database 500 is used to store recommendation information and other information. For example, server 200 is a server of a social media platform, and database 500 stores a large amount of social media information and advertising recommendation information.

[0055] In some embodiments, a user browses an information stream interface 101 through a terminal device 400. A server 200 sends an information stream and recommended information to the terminal device via a network 300. The information stream interface 101 on the terminal device 400 displays recommended information 102 and related interactive options 103. The user can select an interactive option (e.g., interactive option 1, interactive option 2, and interactive option 3). These interactive options can be generated based on the actual content of the recommended information. The interactive options trigger interactive methods. In response to the triggering of any interactive option 103, the terminal device 400 displays the interaction result of the selected interactive option, such as displaying voting results, sharing with other users, or adjusting the advertising landing page. The interactive options are related to the recommended information and can increase the efficiency of user interaction with the recommended information, enhancing the interactive experience.

[0056] In some embodiments, the interactive information processing method provided in this application can also be applied to the following applications: 1. Short video applications: Recommended information is inserted into the video stream of a short video application, and interactive options related to the recommended information are displayed. Users can trigger product landing pages, game pages, or view voting results through the interactive options. 2. Reading applications: In a reading application, when a user finishes reading a chapter of text, recommended information and interactive options are displayed. The interactive options are associated with the chapter content and the recommended information, increasing user interest in the recommended information, promoting user interaction with the recommended information, and thus improving the recommendation effect of the recommended information.

[0057] This application embodiment can be implemented using database technology. A database, simply put, can be viewed as an electronic filing cabinet storing electronic files, where users can perform operations such as adding, querying, updating, and deleting data. A "database" is a collection of data stored together in a certain way, capable of being shared by multiple users, having minimal redundancy, and being independent of application programs.

[0058] A Database Management System (DBMS) is a computer software system designed to manage databases, generally possessing basic functions such as storage, retrieval, security, and backup. DBMSs can be classified according to the database model they support, such as relational or XML (Extensible Markup Language); or according to the type of computer they support, such as server clusters or mobile devices; or according to the query language used, such as Structured Query Language (SQL) or XQuery; or according to performance priorities, such as maximum scale or maximum operating speed; or other classification methods. Regardless of the classification method used, some DBMSs can cross categories, for example, simultaneously supporting multiple query languages.

[0059] In some embodiments, the server 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, CDN, and big data and artificial intelligence platforms. Electronic devices can be smartphones, tablets, laptops, desktop computers, smart speakers, smartwatches, etc., but are not limited to these. Terminal devices and servers can be directly or indirectly connected via wired or wireless communication, which is not limited in this embodiment.

[0060] See Figure 2 , Figure 2 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may be... Figure 1 400 terminal devices Figure 2 The terminal device 400 shown 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 device 400 are coupled together via 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, ... Figure 2 The general labeled all buses as Bus System 440.

[0061] 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. Among them, the general-purpose processor can be a microprocessor or any conventional processor, etc.

[0062] 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.

[0063] 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.

[0064] 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.

[0065] 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.

[0066] 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;

[0067] 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.

[0068] 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;

[0069] 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.

[0070] In some embodiments, the apparatus provided in this application can be implemented in software. Figure 2 An interactive processing device 455 is shown, containing information stored in memory 450. This device can be software in the form of programs and plug-ins, including the following software modules: a display module 4551 and a data processing module 4552. These modules are logically linked and can therefore be arbitrarily combined or further separated according to the functions they implement. Figure 2 For ease of explanation, all the above modules are shown at once, but this should not be interpreted as excluding the implementation of the information interaction processing device 455 which may only include the display module 4551. The functions of each module will be described below.

[0071] In some embodiments, the terminal device or server can implement the interactive information processing method provided in this application embodiment by running a computer program. For example, the computer executable instructions can be microprogram-level commands, machine instructions, or software instructions. The computer program can be a native program or software module in the operating system; it can be a native application (APP), that is, a program that needs to be installed in the operating system to run, such as a social platform APP or an instant messaging APP; or it can be a mini-program that can be embedded in any APP, that is, a program that only needs to be downloaded to the browser environment to run. In summary, the above-mentioned computer executable instructions can be any form of instruction, and the above-mentioned computer program can be any form of application, module, or plugin.

[0072] The interactive information processing method provided in the embodiments of this application will be described in conjunction with exemplary applications and implementations of the terminal devices provided in the embodiments of this application.

[0073] The following describes the information interaction processing method provided in the embodiments of this application. As mentioned above, the electronic device implementing the information interaction processing method of the embodiments of this application can be a terminal device or a server, or a combination of both. Therefore, the executing entity of each step will not be described again below.

[0074] It should be noted that the interactive processing examples below are illustrated using a text-displaying information feed interface. Based on the understanding of the following text, those skilled in the art can apply the interactive processing method of the information provided in the embodiments of this application to interactive processing of information feeds including other types of media data, such as the information feeds of short video applications and music applications.

[0075] See Figure 3A , Figure 3A This is a flowchart illustrating the interactive information processing method provided in the embodiments of this application, which will be combined with... Figure 3A The steps shown are explained. Figure 3A The entity responsible for executing the steps is Figure 1 Terminal device 400.

[0076] In step 301, recommended information is displayed on the information display interface.

[0077] For example, an information display interface refers to an interactive interface used to display data, content, and information to users. The information display interface can be used to display information streams, videos, and text. In this embodiment, the information display interface is used to display an information stream as an example. Since the displayed content is an information stream, the information display interface will be referred to as an information stream interface below. Recommended information includes recommended materials, which may take the form of text, images, and videos, among other things.

[0078] In some embodiments, the information display interface includes at least one first piece of information, which is different from the recommended information; step 301 can display the recommended information in any of the following ways:

[0079] Method 1: Display recommended information above at least one primary piece of information.

[0080] For example, displaying recommended information above the first piece of information means that the recommended information layer is above the layer corresponding to the first piece of information, creating a scene where the first piece of information is obscured by the recommended information. Alternatively, recommended information can be displayed above the first piece of information using a floating window, which can be semi-transparent or opaque.

[0081] Method 2: Embedded display of recommended information within the first piece of information.

[0082] For example, assuming the first piece of information is text, recommendation information can be embedded at the end or in the middle of the text. (See reference.) Figure 5A , Figure 5A This is a first schematic diagram of the information flow interface provided in this application embodiment. The information flow interface 501A displays an information flow, which includes non-recommended information 503A and recommended information 502A. The recommended information 502A is embedded in the non-recommended information 503A.

[0083] Method 3: Display recommended information between any two pieces of primary information.

[0084] For example, suppose the first piece of information is presented in the form of an information stream. Recommended information is interspersed among multiple pieces of first information to form a screen in which recommended information is displayed between two pieces of first information.

[0085] Method 4: Display recommended information in the first area adjacent to the first information.

[0086] For example, the primary information and the recommended information are not displayed in the same area. The recommended information is displayed in a specific primary area in the information display interface. For example, the recommended information is displayed as a banner in a specific area at the top of the information display interface.

[0087] In this embodiment, recommended information is displayed in the information display interface in a variety of different ways, which enriches the display methods of recommended information, improves the prominence of recommended information in the information display interface, makes it easier for users to observe recommended information, thereby arousing users' interest and improving the recommendation efficiency of recommended information.

[0088] In step 302, several interactive options are displayed.

[0089] Here, multiple interactive options are generated using artificial intelligence based on recommendation information.

[0090] For example, interactive options refer to a series of actionable elements provided to users in a user interface. Users can interact with the interface through these elements to influence its functionality or obtain more information. Interactive options can be buttons, links, menus, sliders, input boxes, etc., allowing users to make selections, enter data, trigger events, or perform other actions.

[0091] The display methods for interactive options include, but are not limited to: displaying content that covers the recommended information; or shrinking at least part of the original recommended information and displaying the interactive options in the resulting empty area. The content of the interactive options being related to the recommended information means that the interactive options are generated based on the recommended information, or that the interactive options represent content that is related to the recommended information. For example, the interactive options are answers to questions generated based on the recommended information.

[0092] For example, the interactive options are generated by artificial intelligence based on the recommendation information. The generation process can be performed on a server, which sends the recommendation information and the interactive options generated based on the recommendation information to the terminal device so that the human-computer interaction interface of the terminal device displays the recommendation information and the corresponding interactive options; or, the generation process can be performed online on the terminal device, which uses artificial intelligence to generate the corresponding interactive options based on the received recommendation information and displays them in the empty area adjacent to the recommendation information.

[0093] In some embodiments, reference Figure 3B , Figure 3B This is a schematic diagram of the second process of the information interaction processing method provided in the embodiments of this application. Step 302 can be achieved through... Figure 3B Steps 3021 and 3022 are implemented, and are explained in detail below.

[0094] In step 3021, the recommendation information is narrowed in response to the narrowing trigger operation for the recommendation information.

[0095] Here, methods for reducing the size of recommended information include: proportionally reducing the size of recommended information, and removing at least a portion of the recommended information from the information display interface.

[0096] For example, shrinking can be triggered by a tap or a two-finger swipe. For instance, a tap on a recommended item automatically shrinks it; or, the size of the recommended item shrinks as the distance of a two-finger swipe is traversed. Scaling down a recommended item proportionally means maintaining its aspect ratio while reducing its total area according to a pre-configured ratio. Moving at least a portion of a recommended item off the display screen can be achieved by moving the entire recommended item in one direction so that at least a portion of it extends beyond the display screen's boundaries and is thus hidden.

[0097] In step 3022, multiple interactive options are displayed in the empty area formed by the narrowed recommendation information, and the type of interactive option is displayed.

[0098] For example, the original display area of ​​the recommendation information becomes less occupied due to the reduced area of ​​the recommendations, creating a free area that is used to display multiple interactive options. (Reference) Figure 5B , Figure 5B This is a second schematic diagram of the information flow interface provided in the embodiments of this application. Continuing based on... Figure 5A The following examples will be used to explain and illustrate this. Figure 5AThe recommended information 502A is reduced to a smaller version of recommended information 501B. In the empty area created by this reduced information, an interactive card 502B is displayed. Recommended information 501B is for recommending brand A. Interactive card 502B includes the interactive topic "Why would you choose brand A for shopping during Singles' Day?" and several interactive options 503B. These options include: guaranteed authenticity, fast shipping, and significant discounts. The interactive options also provide answers to questions related to the recommended information.

[0099] For example, type indicators represent interactive options generated based on the recommended information using artificial intelligence. Type indicators can be represented as images or prompt text. At least one type indicator can be displayed in the information flow interface. (See reference) Figure 8 , Figure 8 This is the tenth schematic diagram of the information flow interface provided in the embodiments of this application. Figure 8 The image shows at least a portion of the information feed interface, which includes recommended information 801, interactive options 802, and type markers 803 and 804. Type marker 803 is represented by an icon image of "AI," and type marker 804 is a prompt text "Content generated by AI," indicating that the interactive options are content generated by artificial intelligence.

[0100] In this embodiment, since the newly added interactive options do not occupy additional display space for information other than the recommended information, they do not affect the display of other information in the information display interface, thus reducing interference. At the same time, the interactive options are related to the content of the recommended information, making it easier for users to understand the recommended information, increasing their interest in it, and consequently increasing the click-through rate of the recommended information.

[0101] In some embodiments, step 3022 can be implemented as follows: during the process of narrowing down the recommendation information, the following processing is performed: if the area occupied by the empty region formed by narrowing down the recommendation information reaches a first area threshold, then multiple first interactive options of the first level are displayed in the empty region; if the area occupied by the empty region reaches a second area threshold, then the multiple first interactive options are replaced with multiple second interactive options of the second level, wherein the second area threshold is greater than the first area threshold, the number of second interactive options is greater than the number of first interactive options, and the topic of the second interactive option is a subtopic of the first interactive option, and the topic and subtopic are extracted from the first recommendation information by calling artificial intelligence.

[0102] For example, the first and second area thresholds can be manually set according to the needs of the actual application scenario. For instance, the first area threshold can be set to the area required to fully display the first interactive option, or the area required to display a preset proportion of the first interactive option. Similarly, the second area threshold can be set to the area required to fully display the second interactive option, or the area required to display a preset proportion of the second interactive option. The fact that the theme of the second interactive option is a sub-theme of the first interactive option means that the theme of the second interactive option is more granular than that of the first interactive option; that is, the lower the level, the higher the degree of subdivision, and the more specific the theme of the interactive option. The theme of the second interactive option can also be generated by artificial intelligence based on the theme of the first interactive option and recommendation information.

[0103] For example, if the first and second interactive options are answers to the interactive topic "Which product would you buy?", and both options represent different entity names, then the entity name corresponding to the second option is more specific than the entity name corresponding to the first option. For instance, if the first option is "stationery," then the second option is the specific stationery name "pencil."

[0104] To facilitate understanding, the following explanation is provided in conjunction with the accompanying drawings. Figure 7A This is a seventh schematic diagram of the information flow interface provided in this application embodiment; the information display interface 703A displays shrinking recommendation information 701A and a correspondingly expanding free area 702A. As the area of ​​the recommendation information 701A shrinks, the information display interface 703A transforms into the information display interface 704A. In the information display interface 704A, when the area of ​​the free area 702A reaches a first area threshold, a first interactive option (e.g., first option 1, first option 2, and first option 3) is displayed in the free area 702A.

[0105] refer to Figure 7B , Figure 7B This is the eighth schematic diagram of the information flow interface provided in the embodiments of this application; when Figure 7A As the recommended information 701A continues to increase, the information display interface 704A will display the following: Figure 7B In the information display interface 705A, the first interactive option in the idle area 702A is switched to the second interactive option (e.g., second option 1 to second option 6), and the number of second interactive options is greater than that of the first interactive option.

[0106] In this embodiment, by distinguishing the interactive options into different levels, the hierarchical structure can help users understand the logical relationship between different options, making it easier for users to understand the recommended information, increasing users' interest in the recommended information, and enriching the interactive forms.

[0107] In some embodiments, continue to refer to Figure 3B After step 3022, steps 3023 to 3025 are executed, as detailed below.

[0108] In step 3023, the free area is reduced in response to the reduction trigger operation for the free area.

[0109] For example, the action of shrinking the free area is the same as the action of expanding the recommended information. The principle of shrinking the free area is the same as that of shrinking the recommended information. While shrinking the free area, the recommended information expands simultaneously, either proportionally or by gradually moving the removed parts of the recommended information into the information display interface.

[0110] In step 3024, during the process of shrinking the free area, the following processing is performed: if the occupied area of ​​the free area is less than the second area threshold, then multiple second interactive options are switched to multiple first interactive options.

[0111] For example, step 3024 is the inverse of the process of narrowing down the recommendation information in step 3022 above, and the switching principle is the same, so it will not be repeated here. Multiple second interaction options are switched to multiple first interaction options, that is, the... Figure 7B The information display interface of the 705A switches to... Figure 7A The information display interface of the 704A is shown in the image.

[0112] In step 3025, if the occupied area of ​​the free area is less than the first area threshold, then at least a portion of the displayed first interactive options are removed from the free area based on the reduced area of ​​the occupied area of ​​the free area relative to the first area threshold.

[0113] For example, step 3025 is the inverse of the process of narrowing down the recommendation information in step 3022 above, and the switching principle is the same, so it will not be repeated here.

[0114] In some embodiments, during the process of narrowing down the recommendation information, the following processes are performed: in response to a second trigger operation on the free area, the narrowing down of the recommendation information is stopped; in response to a third trigger operation on at least one interactive option already displayed in the free area, the interaction result corresponding to the selected interactive option is displayed; and in response to a fourth trigger operation on the free area, the narrowing down of the recommendation information continues.

[0115] For example, the second trigger action could be a single click or double click; the third trigger action could be a swipe, click, or long press; and the fourth trigger action could be another single click or double click. As the recommended information shrinks, the free area increases synchronously. If a second trigger action is received targeting the free area, the growth of the free area stops. If at least one interactive option is already displayed in the free area, the user can select an interactive option to interact with, thus executing the third trigger action. For example, currently only one or more options may be fully displayed, or multiple interactive options may be partially displayed, but this is sufficient for understanding the functionality of the options. The user can trigger the already displayed interactive option to perform the interactive processing.

[0116] For example, if the user only observes the interactive options without performing the third trigger action, but performs the fourth trigger action on the empty area, the recommended information will continue to shrink until the minimum area occupied by the recommended information is reached. If the fourth trigger action is a click action, the fourth trigger action is performed on the blank area outside the interactive options in the empty area, to distinguish it from the third trigger action on the interactive options.

[0117] In this embodiment, by pausing the zooming process, users can easily observe the interactive options and select them during the zooming process, which improves triggering efficiency and saves time required for human-computer interaction.

[0118] In some embodiments, displaying a plurality of first interactive options of the first level in a free area is achieved by: displaying the first interactive options one by one in the free area according to priority based on the current area of ​​the free area; removing at least some of the displayed first interactive options in the free area is achieved by: removing the displayed first interactive options one by one in the free area according to the reverse order of priority based on the current area of ​​the free area.

[0119] That is, as the area of ​​the free area gradually increases, the first interactive options appear one by one according to priority. When the area of ​​the free area decreases to below the second area threshold, as the area decreases, the area in the free area used to display the interactive options decreases, and the displayed first interactive options are hidden one by one in reverse order of priority.

[0120] In some embodiments, the priority of each first interactive option is obtained by sorting it using at least one of the following parameters:

[0121] 1. The relevance between the first interactive option and the recommended information. For example, the first interactive option is determined based on the recommended information. The relevance between the first interactive option and the recommended information can be represented by the similarity between the features of the text corresponding to the first interactive information and the features of the recommended information.

[0122] 2. The degree of relevance between the first interactive option and the characteristics of the currently logged-in account on the information display interface. For example, the currently logged-in account is the account used by the user currently using the information display interface. Account characteristics are extracted from account data, which is obtained with the account user's authorization. The degree of relevance is the similarity between the characteristics of the first interactive option and the account's interest characteristics; the higher the similarity, the higher the priority of the first interactive option.

[0123] 3. Historical frequency of the first interaction option being selected. For example, historical frequency is calculated by analyzing trigger data from all users who have interacted with the recommended information's interaction options. Alternatively, it can be calculated based on trigger data from accounts with social relationships to the current user regarding the interaction options. Historical frequency is positively correlated with priority; the higher the historical frequency, the higher the priority ranking.

[0124] In some embodiments, step 302 can be implemented by displaying an interactive card in the recommendation information, and displaying multiple interactive topic texts and multiple interactive options corresponding to the multiple interactive topic texts in the interactive card.

[0125] For example, interactive cards are a way of displaying multiple interactive options within a single card-shaped area; this is the specific form of displaying multiple interactive options as described above. (See reference) Figure 5B The recommendation information 502A is reduced to form a reduced recommendation information 501B. In the free area formed by the reduced recommendation information, the interactive card 502B is displayed. The recommendation information 501B is a recommendation information for recommending brand A. The interactive card 502B includes the text of the interactive topic "Why would you choose brand A to shop on Singles' Day?" and several interactive options 503B.

[0126] In this embodiment, interactive options are displayed in the form of interactive cards. These options are concentrated in a specific area, which standardizes the display range, saves space required for displaying information on the information display interface, and avoids interference with the user's observation of other information on the interface. Furthermore, concentrating the display in one area helps improve user efficiency, reduces the distance the user's fingers need to move during operation, enhances interaction efficiency, and improves the overall user experience.

[0127] In some embodiments, prior to step 303, the following process is performed: in response to an update trigger operation for the interactive options, artificial intelligence is invoked based on the recommendation information to generate a plurality of new interactive options to replace the initial plurality of interactive options.

[0128] For example, the new interactive options can be generated in real-time by the terminal device or the server, with the update trigger operation being different from the first trigger operation. Replacement controls can be displayed in the display area of ​​the interactive options, and in response to a trigger operation on the replacement controls, the new interactive options can be displayed. (See reference) Figure 7C , Figure 7C This is the ninth schematic diagram of the information flow interface provided in this application embodiment. The information display interface 703C displays recommended information 701C, a free area 702C, and a replacement control 705C. The free area 702C includes options 1 to 3. In response to a trigger operation on the replacement control 705C, options 1 to 3 are replaced with options 4 to 6, and the screen of the information display interface 703C switches to the screen of the information display interface 704C. Options 4 to 6 are new interactive options generated based on artificial intelligence.

[0129] Continue to refer to Figure 3A In step 303, in response to the first trigger operation for any interactive option, the interactive result corresponding to the selected interactive option is displayed.

[0130] For example, the first trigger action may take the form of, but is not limited to, clicking, double-clicking, or swiping. Interaction results may include, but are not limited to, displaying an ad landing page, displaying the answer to an interactive option, or displaying the voting results for an interactive option.

[0131] In this embodiment, interactive options related to the recommended information are displayed on the information display interface to encourage user interest in interaction. The corresponding interaction results are displayed for the triggered interactive options. The interactive options and results can attract users to browse the recommended information for a longer period of time, thereby improving the recommendation effect of the recommended information.

[0132] In some embodiments, multiple interactive options are associated with multiple recommendation pages of the objects recommended by the recommendation information. Step 303 can be implemented in the following way:

[0133] In response to the selected interactive option used to associate with the first recommended page, the first recommended page is displayed. The first recommended page is any one of multiple recommended pages and includes introductory information about the object recommended in the recommendation information.

[0134] For example, suppose the recommended information is for a shopping website, and each interactive option is associated with a different product landing page (first recommendation page). The first recommendation page of the corresponding product on that shopping website is triggered based on the first interactive option selected by the user.

[0135] In this embodiment, the recommendation page of the recommended object is triggered by the interactive options, which improves the interactivity between the recommendation information and the user. The content of the interactive options increases the user's understanding and awareness of the recommendation information, attracts the user to interact, and improves the interaction efficiency and recommendation efficiency.

[0136] In some embodiments, the following processing is performed before displaying the first recommendation interface:

[0137] Display a countdown control; in response to a close operation on the countdown control, if the countdown timer has not been reached, remove the countdown control; in response to the countdown timer reaching its target, proceed to display the first recommended screen.

[0138] For example, if the countdown timer hasn't reached its limit, the user can stop the countdown by closing it. Alternatively, if the user doesn't close the countdown timer before it expires, the information display will switch to the first recommended screen. (See reference.) Figure 6C , Figure 6C This is the fifth schematic diagram of the information flow interface provided in the embodiments of this application. (See reference) Figure 6D , Figure 6D This is the sixth schematic diagram of the information flow interface provided in the embodiments of this application. Figure 6C In the information flow interface 601A, the interactive card 602B switches to a countdown control 601D. The countdown control 604D indicates "Enter the product page in 4 seconds." Before the countdown ends, the user can click the cancellation control 602D, which is displayed as "No need." If the countdown ends and the user does not trigger the cancellation control 602D, the information flow interface switches to the product landing page.

[0139] In this embodiment of the application, by providing a countdown control, the direct jump to the recommendation interface is avoided, which would affect the user's viewing experience, and the interference of recommendation information on the user's viewing information display interface is reduced.

[0140] In some embodiments, multiple interactive options represent multiple evaluation information for the object recommended by the recommendation information. Step 303 can be implemented by displaying the evaluation information corresponding to each of the multiple interactive options, and displaying the evaluation information of the selected interactive option in a manner different from other interactive options.

[0141] For example, evaluation information such as voting results and text reviews for the recommended items can be found here. Figure 6C Suppose a user selects "self" from multiple interactive options (603B), then the following is displayed: Figure 6CThe screen displays multiple interactive options 603B, showing the corresponding percentage of selection and a graphical representation of that percentage. For example, the probability of selecting "Self" is 50%, "Family" is 20%, and "Friends" is 30%. The percentage of selected options can be calculated based on the selection results of all users who have performed the selection operation. The selected interactive option "Self" is displayed in a way that distinguishes it from other interactive options.

[0142] In some embodiments, multiple interactive options represent different interaction methods for the objects recommended by the recommendation information. Step 303 can be implemented by displaying the interactive interface corresponding to the selected interactive option, wherein the interactive interface is used to perform the interactive method corresponding to the interactive option, and the type of interactive method includes at least one of the following: collection, purchase, reservation, sharing with friends, and receiving virtual resources.

[0143] For example, different interaction methods display different functional interactive interfaces. The "Favorite" interaction method allows you to save the items recommended in the recommendation information; the "Purchase" interaction method allows you to buy the items recommended in the recommendation information; the "Pre-order" interaction method allows you to add the items recommended in the recommendation information to your shopping list, such as adding them to your online shopping cart. The "Share with Friends" interaction method allows you to share with other accounts that have a social relationship with your current account, or to social media platforms associated with your current account. The "Claim Virtual Resources" interaction method allows you to claim virtual resources related to the items recommended in the recommendation information. For example, if the recommended item is a membership, the virtual resource could be a discount coupon that can be used when purchasing the membership; or, a trial period for the membership.

[0144] In this embodiment, multiple different interactive interface entry points are integrated into the recommendation information through interactive options, which enriches the interaction between the recommendation information and the user and improves the user experience.

[0145] In some embodiments, the interactive options include consultation questions for the recommended objects in the recommendation information, and step 303 can be implemented in the following ways:

[0146] Based on the selected interactive option, construct prompt words for the consultation question; use the prompt words to call the question-answering model to generate the answer to the consultation question, where the question-answering model is trained based on a knowledge base related to the recommended object; display the answer to the consultation question corresponding to the selected interactive option.

[0147] For example, a question-answering model can be a deep learning network with question-answering capabilities. This network is trained using sample question texts and sample answer texts from a knowledge base and is used to generate answer text based on input prompts. The answer can be represented in at least one of the following forms: image, text, or video. Alternatively, the question-answering model can be used to search for answers from a knowledge base based on prompts.

[0148] In some embodiments, the interactive options include an introductory topic for the object recommended by the recommendation information. Step 303 can be implemented as follows: multiple search results are obtained based on the introductory topic of the selected interactive option; a target search result corresponding to the interactive option is selected according to the relevance between the multiple search results and the recommendation information; the target search result is used as the introductory information of the selected interactive option; and the introductory information under the introductory topic corresponding to the selected interactive option is displayed, wherein the introductory information is used to introduce the object recommended by the recommendation information.

[0149] For example, the topic of introduction is a specific attribute or function of the recommended object. The introductory information is the detailed information corresponding to the topic. For instance, if the recommended object is a book, the introductory topics for the interactive options are: author, background story, and book reviews. In response to the author being selected in the interactive options, the system searches the internet for author-related information based on the book title, extracting the information most closely related to the book title as the introductory information. This introductory information could include the author's biography containing the book title.

[0150] In some embodiments, the introductory information may also be text generated by calling a generative pre-trained model based on the introductory topic.

[0151] In this embodiment, interactive options are used to provide users with introductory information related to the recommended information. By differentiating topics, detailed information is provided to users, allowing them to select content they are interested in. The introduction of sub-topics based on user interests and preferences can meet users' personalized needs, increase user interest in the recommended information, improve user experience, and enhance the recommendation effect.

[0152] In some embodiments, before displaying multiple interactive options, in response to the information display interface meeting a first pre-configuration condition, the process of displaying multiple interactive options is initiated.

[0153] The first pre-configuration condition includes any one of the following:

[0154] Condition 1: The display duration of the currently displayed information on the information display interface reaches the first pre-configured duration. Condition 2: The display duration of the information display interface reaches the second pre-configured duration. For example, the first and second pre-configured durations are set according to the needs of the actual application scenario.

[0155] Condition 3: The information currently displayed on the information display interface is pre-configured information. For example, pre-configured information can be promotional information associated with recommended information, such as an advertisement for a certain brand of electric bicycle and a video of a blogger reviewing that electric bicycle. Pre-configured information establishes a mapping relationship between the pre-configured information and the recommended information before the recommended information is displayed.

[0156] Condition 4: The number of messages displayed on the information display interface has reached the pre-configured limit. For example, the pre-configured limit can be determined through statistical experiments based on the number of messages viewed by an account. The experiment can then determine how many messages a user will view before stopping browsing. The number of messages at which a user stops browsing is taken as the upper limit for message viewing. The pre-configured limit can then be set to a smaller value than this upper limit, depending on the application scenario requirements.

[0157] In some embodiments, before step 302, the following processes are performed: obtaining domain information data corresponding to the recommendation information; performing feature extraction on the recommendation information to obtain recommendation features, and performing feature extraction on the domain information data to obtain domain features; performing text generation processing based on the domain features and recommendation features to obtain interactive topic text; performing text generation processing based on the domain features, recommendation features, and interactive topic text to obtain multiple interactive option texts corresponding to the interactive topic text; filling the multiple interactive option texts into a pre-configured template to obtain images corresponding to the interactive options, and associating each interactive option with a pre-configured interactive result.

[0158] For example, domain information data refers to information within the domain to which the recommended information belongs. For instance, if an advertisement recommends a specific product, the domain information could be current events or hot topics within the industry (e.g., shopping festivals, traditional holidays, and trending topics) or data related to the product (e.g., e-commerce, gaming, and tourism). Domain information can be determined in the following ways: based on its similarity to the content of the advertising creative; or based on the click-through rate or interaction frequency over a preset time period. If the click-through rate or interaction frequency exceeds a pre-configured threshold, it is considered the domain information corresponding to the advertisement.

[0159] In some embodiments, obtaining domain information data corresponding to recommendation information can be achieved in the following ways: obtaining domain information data corresponding to recommendation information through at least one of the following methods; obtaining domain information data whose click rate reaches a pre-configured frequency within a pre-configured time period; extracting at least one keyword from recommendation information and searching for domain information data corresponding to recommendation information based on the keyword.

[0160] In some embodiments, feature extraction and text generation are performed by a neural network model. Before obtaining the domain information data corresponding to the recommendation information, the neural network model is trained as follows: A sample data set is obtained, comprising: sample recommendation information, sample domain data, sample interactive topic text, and corresponding multiple sample interactive option texts; a first neural network model is pre-trained based on the sample recommendation information and sample domain information data to obtain a pre-trained second neural network model, wherein the second neural network model is used for feature extraction processing of the recommendation information and domain information data; the second neural network is trained based on the sample data set for the text generation task to obtain a trained third neural network model, wherein the third neural network model is used to generate interactive option text based on the recommendation information and domain information data.

[0161] For example, the loss function used in the pre-training process can be cross-entropy loss, and the training method used in the pre-training stage can be supervised learning; the loss used in the training of the text generation task can be cross-entropy loss, and the training method used in the training of the text generation task can be self-supervised.

[0162] In this embodiment, the pre-trained neural network model is used to enhance its function of feature extraction processing of recommendation information and domain information data, and the fine-tuned training enhances its function of generating interactive option text based on recommendation information and domain information data, thereby improving the accuracy and effectiveness of model training.

[0163] In this embodiment, interactive options related to the recommended information are displayed on the information display interface to encourage user interaction. The corresponding interaction results are displayed for each triggered interactive option. The interactive options and results can attract users to browse the recommended information for a longer period of time and participate in the interactive processing related to the recommended information, thereby improving the recommendation effect. The interactive options are used to annotate the recommended information, which makes it easier for users to understand the recommended information and thus improves the efficiency of user interaction with the recommended information.

[0164] The following will describe an exemplary application of the interactive processing method for information in a real-world application scenario.

[0165] In-feed advertising is a form of advertising integrated into the user's information flow on social media, news apps, or other content platforms. It blends promoted content with the content users normally browse, making the ads appear more like part of the platform's content and providing a more natural and seamless user experience. Interaction methods for in-feed ads include click-triggered, swipe-triggered, or device-shaking-triggered modes. For example, the ad may display prompts such as "click" or "swipe" to encourage user interaction. However, current technologies often suffer from limited interaction between ads and users, with low relevance between interactive content and the ad itself. This reduces user interest in recommended information and impacts the efficiency of recommendation and user interaction.

[0166] This application provides an interactive information processing method to address the aforementioned problems in related technologies. (Refer to...) Figure 4 , Figure 4 This is a third flowchart illustrating the information interaction processing method provided in this application embodiment, in which the server and terminal device collaboratively execute the information interaction processing method of this application embodiment.

[0167] In step 401, feature extraction is performed on the recommendation information to obtain recommendation features, and interactive topics and interactive tags are generated based on the recommendation features and domain information.

[0168] For example, the interactive information processing method provided in this application embodiment is implemented through a server side and a terminal device. The server side is mainly responsible for supporting technical capabilities such as training artificial intelligence models, intelligent AI-driven ad delivery, collecting pre-set information such as ad materials and information, generating ad-related topics and interactive tags, and ad distribution. The terminal device side is mainly responsible for retrieving ads. The platform technology implementation scheme uses Java as an example; other implementation schemes can refer to the embodiments of this application.

[0169] For example, recommendation information can be advertising information, including advertising images, text, videos, and other advertising creatives. Domain information refers to information related to the domain of the advertising information. For instance, if the advertising information is used to recommend a specific product, the domain information could be current events and hot topics within the industry (e.g., shopping festivals, traditional holidays, and trending topics) or data related to the product (e.g., data from e-commerce, gaming, and tourism). Domain information can be determined in the following ways: based on the similarity to the content of the advertising creative; or based on the click-through rate or interaction frequency within the current preset time period. If the click-through rate or interaction frequency exceeds a pre-configured threshold, it is considered the domain information corresponding to the advertising information.

[0170] For example, step 401 is implemented using artificial intelligence techniques, such as processing recommendation information and domain information using a large language model to obtain interactive topics and interactive tags. A large language model (LLM) is a machine learning model designed to understand and generate human language. Trained on massive amounts of text data, they can perform a wide range of tasks, including text summarization, translation, sentiment analysis, and more. Large language models are characterized by their massive scale, containing billions of parameters, which help them learn complex patterns in language data, and are typically based on deep learning architectures.

[0171] In this embodiment, the large-scale artificial intelligence model used to generate interactive topics and interactive options includes an image processing model and a natural language processing model. The natural language processing model is used to extract text features from domain information, and the image processing model is used to extract image features and text from advertising materials. The large-scale artificial intelligence model is trained using a generative model training method to generate the corresponding text for interactive options and text for interactive topics. The text for interactive options and text for interactive topics are filled into corresponding pre-configured templates to form image representations of the interactive options.

[0172] In some embodiments, prior to step 401, the large-scale artificial intelligence model is trained. The training data includes sample advertising information, sample domain information, sample interactive topics, and sample interactive tags. The large-scale artificial intelligence model is pre-trained using the sample advertising information and sample domain information to enable the model to accurately extract features from the advertising information and domain information. The pre-trained large-scale artificial intelligence model is then fine-tuned using the overall training data to enable the model to generate interactive topics and interactive options based on the advertising information and domain information.

[0173] In step 402, recommended information is displayed in the information flow interface, along with interactive cards related to the recommended information.

[0174] For example, after step 401, when a user browses the information stream through a terminal device, the terminal device sends a request to the server to retrieve advertising information. The server uses Retrofit or other network libraries to fetch the advertisements and sends the generated advertising information to the terminal device. The corresponding media information and advertising information are displayed in the information stream interface of the terminal device. After the advertising information has been displayed for a pre-configured duration, the display area of ​​the advertising information is reduced. During the reduction process, an interactive card is displayed. The area occupied by the interactive card increases as the area occupied by the advertising information decreases. The reduction stops when the advertising information reaches the pre-configured size. The reduced advertising information and the interactive card are displayed in the area occupied by the advertising information before it is reduced. The interactive card includes multiple interactive options.

[0175] For example, reducing the size of an ad message can be achieved by: maintaining the aspect ratio of the ad message while reducing its occupied area to the pre-configured area; or by removing at least part of the ad message from the feed interface to reduce its occupied area.

[0176] For ease of explanation, the following references are provided. Figure 5A as well as Figure 5B , Figure 5A This is a first schematic diagram of the information flow interface provided in the embodiments of this application; Figure 5B This is a second schematic diagram of the information flow interface provided in this application embodiment. The information flow interface 501A displays an information flow, including non-recommended information 503A and recommended information 502A. When recommended information 502A is displayed, the terminal device checks whether recommended information 502A has associated interactive cards. If so, the recommended information 502A is minimized when its display duration reaches a pre-configured duration. (Reference) Figure 5B Recommendation Message 502A is reduced to form a smaller version of Recommendation Message 501B. In the empty area created by this reduction, Interactive Card 502B is displayed. Recommendation Message 501B is for recommending Brand A. Interactive Card 502B includes the interactive topic "Why would you choose Brand A for your Singles' Day shopping?" and several interactive options 503B. These options include: guaranteed authenticity, fast shipping, and significant discounts. The interactive options provide answers to questions related to the recommendation message.

[0177] In step 403, in response to a triggering action on an interactive option in the interactive card, the interaction result is displayed.

[0178] For example, triggering actions include, but are not limited to, clicking, double-clicking, and swiping. Interaction results include, but are not limited to, the following processing: redirecting to the product landing page; displaying the voting results or answers corresponding to the interactive options. For ease of explanation, the following description is provided in conjunction with the accompanying diagram.

[0179] refer to Figure 6A , Figure 6A This is a third schematic diagram of the information flow interface provided in this application embodiment. The information flow interface 601A displays media information 603A and recommendation information 602A. The recommendation information 602A is used to recommend "a certain product" and includes the advertising slogan "a certain product, more durable and easier to use". (Reference) Figure 6B , Figure 6B This is a fourth schematic diagram of the information flow interface provided in this application embodiment. Figure 6A When the duration of recommended information 602A reaches the pre-configured duration, the recommended information 602A is reduced in size, forming... Figure 6BThe recommendation information 601B is displayed, and simultaneously, an interactive card 602B is displayed in the empty area formed by the reduced recommendation information 602A. The interactive card 602B includes an interactive topic and multiple interactive options 603B. The content of the interactive topic is the text "Who would you like to buy this product for?", and each interactive option 603B is the corresponding answer to the interactive topic: family, yourself, or a friend. The interactive topic in the interactive card is related to the product recommended by the recommendation information 602A.

[0180] refer to Figure 6C , Figure 6C This is the fifth schematic diagram of the information flow interface provided in this application embodiment. Assume a user is targeting... Figure 6B In the multiple interactive options 603B, after selecting one option "Self", the following is displayed: Figure 6C The screen displays multiple interactive options 603B, showing the corresponding percentage of selection and a graphical representation of that percentage. For example, the probability of selecting "Self" is 50%, "Family" is 20%, and "Friends" is 30%. The percentage of selected options can be calculated based on the selection results of all users who have performed the selection operation. The selected interactive option "Self" is displayed in a way that distinguishes it from other interactive options.

[0181] In some embodiments, after the user selects an interactive option, the information feed interface switches to a product landing page. (See reference) Figure 6D , Figure 6D This is the sixth schematic diagram of the information flow interface provided in the embodiments of this application. It shows... Figure 6C After the interaction results are displayed Figure 6D On the feed interface 601A, the interactive card 602B switches to a countdown control 601D. The countdown control 604D indicates "Enter the product page in 4 seconds." Before the countdown ends, the user can click the cancellation control 602D, which displays "No need." If the countdown ends and the user does not trigger the cancellation control 602D, the feed interface switches to the product landing page.

[0182] In some embodiments, the display format of the recommendation information in this application is not limited to inserting recommendation information into the information stream. Recommendation information can also be displayed in the information stream interface or the functional interface of other applications via pop-ups or floating windows. For example, in a video application, recommendation information can be displayed as a floating window in the video playback interface when the user pauses watching the video. Alternatively, when a user browses a shopping application, recommendation information can be displayed as a pop-up window.

[0183] The interactive information processing method provided in this application has the following beneficial effects: 1. Without disturbing the user's browsing of application content, it attracts user attention by generating topics related to the advertising content using artificial intelligence, thereby increasing the user's acceptance and interest in the advertising information. 2. Through the topic interaction card component, the advertising content is parsed without interfering with the user's understanding of the advertising content, making it easier for the user to understand the advertising content, enhancing the user's attention to and willingness to participate in the advertising content, and improving interaction efficiency. 3. By enriching the advertising interaction methods, it helps to improve the recommendation effect of the advertisement and thus promote the conversion rate of the advertisement.

[0184] The following description continues to illustrate the exemplary structure of the interactive processing device 455 for information provided in the embodiments of this application as a software module. In some embodiments, such as Figure 2 As shown, the software modules in the interactive processing device 455 storing information in the memory 450 may include:

[0185] Display module 4551 is used to display recommended information in the information display interface; display module 4551 is used to display multiple interactive options, wherein the multiple interactive options are generated by calling artificial intelligence based on the recommended information; display module 4551 is used to display the interaction result corresponding to the selected interactive option in response to a first trigger operation for any one of the interactive options.

[0186] In some embodiments, the display module 4551 is configured to shrink the recommendation information in response to a shrinking trigger operation, wherein the shrinking of the recommendation information includes: shrinking the recommendation information proportionally, moving at least a portion of the recommendation information out of the information display interface; and displaying the plurality of interactive options in the free area formed by shrinking the recommendation information.

[0187] In some embodiments, the display module 4551 is configured to perform the following processing during the process of narrowing down the recommendation information:

[0188] If the area occupied by the empty region formed by the reduced recommendation information reaches a first area threshold, then multiple first interactive options of the first level are displayed in the empty region; if the area occupied by the empty region reaches a second area threshold, then the multiple first interactive options are replaced with multiple second interactive options of the second level, wherein the second area threshold is greater than the first area threshold, the number of second interactive options is greater than the number of first interactive options, and the topic of the second interactive option is a subtopic of the first interactive option, and the topic and subtopic are extracted from the first recommendation information by calling artificial intelligence.

[0189] In some embodiments, the display module 4551 is configured to, after displaying the plurality of interactive options in the empty area formed by shrinking the recommendation information, shrink the empty area in response to a shrinking trigger operation of the empty area; and in the process of shrinking the empty area, perform the following processing:

[0190] If the occupied area of ​​the free area is less than the second area threshold, the plurality of second interactive options are switched to the plurality of first interactive options; if the occupied area of ​​the free area is less than the first area threshold, at least a portion of the first interactive options that have been displayed are removed from the free area according to the reduction in the occupied area of ​​the free area relative to the first area threshold.

[0191] In some embodiments, the display module 4551 is configured to, during the process of shrinking the recommendation information, stop shrinking the recommendation information in response to a second triggering operation on the free area, and

[0192] In response to a third trigger operation for at least one interactive option already displayed in the free area, the interaction result corresponding to the selected interactive option is displayed; in response to a fourth trigger operation for the free area, the recommendation information is further narrowed down.

[0193] In some embodiments, the display module 4551 is configured to display the first interactive options one by one in the free area according to priority, based on the current area of ​​the free area; removing at least a portion of the displayed first interactive options in the free area includes:

[0194] Based on the current area of ​​the free area, the first interactive options that have been displayed are removed one by one in the free area according to the reverse order of the priority.

[0195] In some embodiments, the priority of each of the first interactive options is obtained by sorting using at least one of the following parameters:

[0196] The degree of relevance between the first interactive option and the recommended information; the degree of relevance between the first interactive option and the characteristics of the currently logged-in account on the information display interface; and the historical frequency of the first interactive option being selected.

[0197] In some embodiments, the display module 4551 is configured to display an interactive card in the recommendation information, and the interactive card displays multiple interactive topic texts and multiple interactive options corresponding to the multiple interactive topic texts respectively.

[0198] In some embodiments, the plurality of interactive options are respectively associated with a plurality of recommendation pages of the object recommended by the recommendation information. The display module 4551 is used to display the first recommendation page in response to the selected interactive option being associated with the first recommendation page. The first recommendation page is any one of the plurality of recommendation pages and includes introductory information of the object recommended by the recommendation information.

[0199] In some embodiments, the display module 4551 is configured to display a countdown control before displaying the first recommendation interface; remove the countdown control in response to a closing operation on the countdown control and if the countdown corresponding to the countdown control has not been reached; and proceed to the process of displaying the first recommendation interface in response to the countdown control reaching the countdown.

[0200] In some embodiments, the plurality of interactive options represent multiple evaluation information for the object recommended by the recommendation information. The display module 4551 is used to display the evaluation information corresponding to the plurality of interactive options respectively, and to display the evaluation information of the selected interactive option in a manner different from other interactive options.

[0201] In some embodiments, the plurality of interactive options represent different interaction methods for the objects recommended by the recommendation information. The display module 4551 is used to display the interactive interface corresponding to the selected interactive option. The interactive interface is used to execute the interactive method corresponding to the interactive option. The types of interactive methods include at least one of the following: collection, purchase, reservation, sharing with friends, and receiving virtual resources.

[0202] In some embodiments, the interactive options include a consultation question for the recommended object in the recommendation information. The display module 4551 is used to construct prompt words based on the consultation question of the selected interactive option; to call a question-answering model based on the prompt words to generate an answer to the consultation question, wherein the question-answering model is trained based on a knowledge base related to the recommended object; and to display the answer to the consultation question corresponding to the selected interactive option.

[0203] In some embodiments, the interactive options include introductory topics for the objects recommended by the recommendation information, and the display module 4551 is used to display the interactive results corresponding to the selected interactive option, including:

[0204] Multiple search results are obtained based on the topic of the selected interactive option; according to the relevance between the multiple search results and the recommendation information, a target search result corresponding to the interactive option is selected; the target search result is used as the description information of the selected interactive option; the description information under the topic of the selected interactive option is displayed, wherein the description information is used to introduce the object recommended by the recommendation information.

[0205] In some embodiments, the information display interface includes at least one first piece of information, which is different from the recommended information; the display module 4551 is configured to display the recommended information in any of the following ways:

[0206] The recommendation information is displayed above at least one piece of first information; the recommendation information is embedded within the first information; the recommendation information is displayed between any two pieces of first information; the recommendation information is displayed in a first region adjacent to the first information.

[0207] In some embodiments, the display module 4551 is configured to, before displaying multiple interactive options, proceed to the process of displaying multiple interactive options in response to the information display interface satisfying a first pre-configuration condition; wherein the first pre-configuration condition includes any one of the following:

[0208] The display duration of the information currently displayed in the information display interface reaches the first pre-configured duration; the display duration of the information display interface reaches the second pre-configured duration; the information currently displayed in the information display interface is pre-configured information; the number of information already displayed in the information display interface reaches the pre-configured number.

[0209] In some embodiments, the data processing module 4552 is configured to: acquire domain information data corresponding to the recommendation information before displaying the multiple interactive options; perform feature extraction on the recommendation information to obtain recommendation features, and perform feature extraction processing on the domain information data to obtain domain features; perform text generation processing based on the domain features and the recommendation features to obtain interactive topic text; perform text generation processing based on the domain features, the recommendation features, and the interactive topic text to obtain multiple interactive option texts corresponding to the interactive topic text; fill the multiple interactive option texts into a pre-configured template to obtain an image corresponding to the interactive option, and associate each interactive option with a pre-configured interactive result.

[0210] In some embodiments, the data processing module 4552 is configured to acquire domain information data corresponding to the recommendation information through at least one of the following methods: acquire domain information data whose click rate reaches a pre-configured frequency within a pre-configured time period; extract at least one keyword from the recommendation information; and search for domain information data corresponding to the recommendation information based on the keyword.

[0211] In some embodiments, the data processing module 4552 is configured to: execute the feature extraction processing and the text generation processing through a neural network model; acquire a sample data set before acquiring the domain information data corresponding to the recommendation information; wherein the sample data set includes: sample recommendation information, sample domain data, sample interactive topic text, and corresponding multiple sample interactive option texts; pre-train a first neural network model based on the sample recommendation information and the sample domain information data to obtain a pre-trained second neural network model; wherein the second neural network model is used to perform feature extraction processing on the recommendation information and the domain information data; and train the second neural network model for the text generation task based on the sample data set to obtain a trained third neural network model; wherein the third neural network model is used to generate interactive option text based on the recommendation information and the domain information data.

[0212] This application provides a computer program product, which includes a computer program or computer-executable instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer program or computer-executable instructions from the computer-readable storage medium and executes the computer program or computer-executable instructions, causing the electronic device to perform the information interaction processing method described in this application embodiment.

[0213] 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 interactive processing method for information provided in this application, for example, such as... Figure 3A The interactive processing method for the information shown.

[0214] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, 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.

[0215] 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.

[0216] 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 HyperText 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).

[0217] 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.

[0218] In summary, this application embodiment displays interactive options related to recommended information on the information display interface, which encourages user interaction. The interactive options and results displayed for each triggered option attract users to browse recommended information for a longer period and participate in related interactive processes, thus improving the recommendation effect. Furthermore, the annotation of recommended information through interactive options facilitates user understanding, thereby improving the efficiency of user interaction with recommended information.

[0219] 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 interactive information processing method, characterized in that, The method includes: Display recommended information on the information display interface; Multiple interactive options are displayed, wherein the multiple interactive options are generated by artificial intelligence based on the recommendation information; In response to a first trigger operation for any of the interactive options, the interaction result corresponding to the selected interactive option is displayed.

2. The method according to claim 1, characterized in that, The display of multiple interactive options includes: In response to a zoom-out trigger operation on the recommended information, the recommended information is zoomed out, wherein the zoom-out of the recommended information includes: zooming out of the recommended information proportionally, and removing at least a portion of the recommended information from the information display interface; The multiple interactive options are displayed in the empty area formed by the reduced recommendation information, and a type flag for the interactive options is displayed, wherein the type flag indicates that the interactive options are generated based on the recommendation information and artificial intelligence.

3. The method according to claim 2, characterized in that, Prior to the first trigger operation in response to any of the interactive options, the method further includes: In response to an update trigger operation for the interactive options, artificial intelligence is invoked based on the recommendation information to generate multiple new interactive options to replace the initial multiple interactive options.

4. The method according to claim 2, characterized in that, The display of the multiple interactive options in the empty area formed by shrinking the recommended information includes: During the process of narrowing down the recommended information, the following steps are performed: If the area occupied by the empty region formed by shrinking the recommended information reaches a first area threshold, then multiple first interactive options of the first level are displayed in the empty region. If the occupied area of ​​the free area reaches the second area threshold, the plurality of first interactive options are replaced with a plurality of second interactive options at the second level, wherein the second area threshold is greater than the first area threshold, the number of second interactive options is greater than the number of first interactive options, and the topic of the second interactive option is a sub-topic of the first interactive option, and the topic and the sub-topic are extracted from the first recommendation information by calling artificial intelligence.

5. The method according to claim 4, characterized in that, After displaying the plurality of interactive options in the empty area formed by shrinking the recommendation information, the method further includes: In response to a shrinking trigger operation targeting the free area, the free area is shrunk; During the process of shrinking the free area, the following steps are performed: If the occupied area of ​​the free area is less than the second area threshold, then the plurality of second interactive options are switched to the plurality of first interactive options; If the occupied area of ​​the free area is less than the first area threshold, then at least a portion of the first interactive options that have been displayed are removed from the free area based on the reduction in the occupied area of ​​the free area relative to the first area threshold.

6. The method according to claim 2, characterized in that, In the process of narrowing down the recommended information, the method further includes: In response to a second triggering operation targeting the free area, the narrowing of the recommendation information is stopped, and In response to a third trigger operation for at least one interactive option already displayed in the free area, the interaction result corresponding to the selected interactive option is displayed; In response to the fourth trigger operation targeting the idle area, the recommendation information is further narrowed down.

7. The method according to claim 5, characterized in that, The display of multiple first-level interactive options in the free area includes: Based on the current area of ​​the free area, the first interactive options are displayed one by one in the free area according to priority; Removing at least a portion of the first interactive options that have been displayed in the free area includes: Based on the current area of ​​the free area, the first interactive options that have been displayed are removed one by one in the free area according to the reverse order of the priority.

8. The method according to claim 7, characterized in that, The priority of each of the first interactive options is obtained by sorting using at least one of the following parameters: The degree of relevance between the first interactive option and the recommended information; The degree of correlation between the first interactive option and the characteristics of the currently logged-in account on the information display interface; The first interactive option is selected based on historical frequency.

9. The method according to any one of claims 1 to 8, characterized in that, The interactive options include consultation questions for the recommended objects in the recommendation information, and displaying the interaction results corresponding to the selected interactive option includes: Based on the consultation question of the selected interactive option, construct prompt words; The question-answering model is invoked based on the prompt words to generate the answer to the inquiry question, wherein the question-answering model is trained based on a knowledge base related to the recommended object; Displays the answer to the question corresponding to the selected interactive option.

10. The method according to any one of claims 1 to 8, characterized in that, The interactive options include introductory topics for the objects recommended in the recommendation information, and displaying the interactive results corresponding to the selected interactive option includes: Multiple search results are obtained based on the topic of the selected interactive option; Based on the relevance between the multiple search results and the recommended information, select the target search result corresponding to the interactive option; The target search result is used as introductory information for the selected interactive option; Display the introductory information under the topic corresponding to the selected interactive option, wherein the introductory information is used to introduce the object recommended by the recommendation information.

11. The method according to any one of claims 1 to 8, characterized in that, Before displaying multiple interactive options, the method further includes: Obtain the domain information data corresponding to the recommendation information; Feature extraction is performed on the recommendation information to obtain recommendation features, and feature extraction processing is performed on the domain information data to obtain domain features; Based on the domain features and the recommendation features, text generation processing is performed to obtain interactive topic text; Based on the domain features, the recommendation features, and the interactive topic text, text generation processing is performed to obtain multiple interactive option texts corresponding to the interactive topic text; The multiple interactive option texts are filled into a pre-configured template to obtain the images corresponding to the interactive options, and each interactive option is associated with a pre-configured interactive result.

12. The method according to claim 11, characterized in that, The step of obtaining the domain information data corresponding to the recommendation information includes: The domain information data corresponding to the recommendation information can be obtained through at least one of the following methods: Obtain domain information data where the click-through rate reaches the pre-configured frequency within a pre-configured time period; Extract at least one keyword from the recommendation information, and search for domain information data corresponding to the recommendation information based on the keyword.

13. The method according to claim 11, characterized in that, The feature extraction process and the text generation process are executed through a neural network model. Before obtaining the domain information data corresponding to the recommendation information, the method further includes: Obtain a sample data set, wherein the sample data set includes: sample recommendation information, sample domain data, sample interaction topic text, and corresponding multiple sample interaction option texts; The first neural network model is pre-trained based on the sample recommendation information and the sample domain information data to obtain a pre-trained second neural network model, wherein the second neural network model is used to perform feature extraction processing on the recommendation information and the domain information data; The second neural network is trained on the sample data set for the text generation task to obtain a trained third neural network model, wherein the third neural network model is used to generate interactive option text based on the recommendation information and the domain information data.

14. The method according to any one of claims 1 to 8, characterized in that, The display of multiple interactive options includes: The recommendation information displays interactive cards, which in turn display multiple interactive topic texts and the multiple interactive options corresponding to those interactive topic texts.

15. The method according to any one of claims 1 to 8, characterized in that, The multiple interactive options are respectively associated with multiple recommendation pages of the objects recommended by the recommendation information, and displaying the interaction result corresponding to the selected interactive option includes: In response to the selected interactive option for associating with a first recommended page, the first recommended page is displayed, wherein the first recommended page is any one of the plurality of recommended pages, and the first recommended page includes introductory information about the object recommended by the recommendation information.

16. The method according to claim 15, characterized in that, Before displaying the first recommendation interface, the method further includes: Display countdown control; In response to a close operation on the countdown control, and if the countdown corresponding to the countdown control has not been reached, the countdown control is removed; In response to the countdown corresponding to the countdown control being reached, the process of displaying the first recommendation interface is initiated.

17. The method according to any one of claims 1 to 8, characterized in that, The multiple interactive options represent multiple evaluation information for the objects recommended by the recommendation information, and displaying the interaction result corresponding to the selected interactive option includes: The evaluation information corresponding to each of the multiple interactive options is displayed, and the evaluation information of the selected interactive option is displayed in a manner different from that of other interactive options.

18. The method according to any one of claims 1 to 8, characterized in that, The multiple interactive options represent different interaction methods for the objects recommended in the recommendation information, and displaying the interaction results corresponding to the selected interactive option includes: The interactive interface corresponding to the selected interactive option is displayed. The interactive interface is used to execute the interactive method corresponding to the interactive option. The types of interactive methods include at least one of the following: collection, purchase, reservation, sharing with friends, and receiving virtual resources.

19. The method according to any one of claims 1 to 8, characterized in that, The information display interface includes at least one first piece of information, which is different from the recommended information; The process of displaying recommended information on the information display interface includes: The recommendation information can be displayed in any of the following ways: The recommendation information is displayed above at least one piece of first information; The recommendation information is embedded within the first information; The recommendation information is displayed between any two pieces of the first information; The recommendation information is displayed in a first area adjacent to the first information.

20. The method according to any one of claims 1 to 8, characterized in that, Before displaying multiple interactive options, the method further includes: In response to the information display interface meeting the first pre-configuration condition, the process proceeds to displaying multiple interactive options; wherein, The first pre-configuration condition includes any one of the following: The display duration of the information currently displayed in the information display interface has reached the first pre-configured duration; The display duration of the information display interface reaches the second pre-configured duration; The information currently displayed in the information display interface is pre-configured information; The number of information displayed in the information display interface has reached the pre-configured number.

21. An interactive information processing device, characterized in that, The device includes: The display module is used to display recommended information in the information display interface; The display module is also used to display multiple interactive options, wherein the multiple interactive options are generated by artificial intelligence based on the recommendation information; The display module is further configured to display the interaction result corresponding to the selected interaction option in response to a first trigger operation for any one of the interaction options.

22. An electronic device, characterized in that, The electronic device includes: 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 interactive information processing method according to any one of claims 1 to 20.

23. A computer-readable storage medium storing computer-executable instructions or a computer program, characterized in that, When the computer-executable instructions or computer program are executed by a processor, they implement the interactive information processing method according to any one of claims 1 to 20.

24. A computer program product comprising computer-executable instructions or a computer program, characterized in that, When the computer-executable instructions or computer program are executed by a processor, they implement the interactive information processing method according to any one of claims 1 to 20.

Images