Interaction processing methods and apparatuses, electronic device, computer-readable storage medium, and computer program product

Abstract

Provided in the present application are interaction processing methods and apparatuses, an electronic device, a computer-readable storage medium, and a computer program product. A method comprises: displaying first information in an information flow interface, the first information comprising a first interaction control; in response to a first trigger operation for the first interaction control, displaying a first interaction interface, the first interaction interface being used for editing a special-effect animation; in response to a first editing operation in the first interaction interface, displaying a first special-effect animation formed by the editing; and in response to a second trigger operation for the first special-effect animation, playing back the first special-effect animation.

Description

Interactive processing methods, devices, electronic devices, computer-readable storage media, and computer program products

[0001] Cross-references to related applications

[0002] This application is based on and claims priority to Chinese Patent Application No. 2024115407461, filed on October 30, 2024, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application relates to the field of computer technology, and in particular to an interactive processing method, apparatus, electronic device, computer-readable storage medium, and computer program product. Background Technology

[0004] In related technologies, the interactive methods in information flow interfaces include, but are not limited to, liking, commenting, and forwarding. These methods are relatively limited, and information exchange in information flow interfaces is mostly confined to static content such as text and images. Some complex interactive functions require the installation of specific applications to function, resulting in limited triggering methods. Furthermore, for users unfamiliar with new or advanced technologies, complex triggering methods may create an entry barrier, impacting interaction efficiency. Simultaneously, the fixed triggering logic of interactive controls in related technologies makes it difficult to support complex interactive processes. Introducing complex dynamic content, due to the lack of a unified resource management mechanism, can lead to uneven resource load, often resulting in resource contention during playback, causing interface stuttering, large frame rate fluctuations, prolonged loading time, and increased device power consumption.

[0005] Currently, there is no good way to enrich the interactive forms in the information flow interface and improve the efficiency of interaction. Summary of the Invention

[0006] This application provides an interactive processing method, apparatus, electronic device, computer-readable storage medium, and computer program product, which can enrich the interactive forms in the information flow interface and improve the efficiency of interaction.

[0007] The technical solution of this application embodiment is implemented as follows:

[0008] This application provides an interactive processing method, which is executed by an electronic device, and the method includes:

[0009] The first information is displayed in the information flow interface, wherein the first information includes a first interactive control;

[0010] In response to a first trigger operation on the first interactive control, a first interactive interface is displayed, wherein the first interactive interface is used to edit special effects animation;

[0011] In response to a first editing operation in the first interactive interface, a first special effects animation generated by the editing is displayed;

[0012] In response to a second triggering operation on the first special effects animation, the first special effects animation is played.

[0013] This application provides an interactive processing method, which is executed by an electronic device, and the method includes:

[0014] The first information is displayed in the information flow interface, wherein the first information includes a first interactive control and a free area;

[0015] In response to a first trigger operation on the first interactive control, a first special effects animation carrying recommended material is displayed in the free area.

[0016] This application provides an interactive processing device, including:

[0017] The display module is configured to display first information in the information flow interface, wherein the first information includes a first interactive control;

[0018] The display module is further configured to display a first interactive interface in response to a first trigger operation on the first interactive control, wherein the first interactive interface is used for editing special effects animation;

[0019] The display module is further configured to display a first special effects animation generated by editing in response to a first editing operation in the first interactive interface;

[0020] The display module is further configured to play the first special effects animation in response to a second trigger operation on the first special effects animation.

[0021] This application provides an interactive processing device, the device comprising:

[0022] The display module is configured to display first information in the information flow interface, wherein the first information includes a first interactive control and a free area;

[0023] The display module is further configured to display a first special effects animation carrying recommended materials in the free area in response to a first trigger operation on the first interactive control.

[0024] This application provides an electronic device, the electronic device comprising:

[0025] Memory is used to store executable instructions or computer programs.

[0026] The processor, when executing computer-executable instructions or computer programs stored in the memory, implements the interactive processing method provided in the embodiments of this application.

[0027] This application provides a computer-readable storage medium storing computer-executable instructions or computer programs, which, when executed by a processor, implement the interactive processing method provided in this application.

[0028] 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 processing method provided in this application.

[0029] The embodiments of this application have the following beneficial effects:

[0030] The information flow interface displays first information including a first interactive control. This first interactive control triggers a first interactive interface for editing special effects animations. By embedding animation editing functionality into the information flow interface, the interactive forms of the information flow interface are enriched, allowing users to create and share dynamic content, thereby enhancing the interactivity and fun of information exchange and improving the user experience. In response to a second trigger operation on the first special effects animation, the first special effects animation is played. The first special effects animation is displayed in the first information within the information flow interface, allowing the edited special effects animation to be displayed instantly in the information flow, making information transmission more intuitive. By directly integrating editing functionality into the information flow interface, special effects animations can be edited and sent without switching to other applications or interfaces, simplifying the user's operation process, improving interaction efficiency, and avoiding process start / stop and resource reloading operations during application switching. It eliminates the need to start independent processes of external applications and release and reallocate resources of the current information flow process, reducing the overhead of process scheduling and the repeated occupation of memory resources by multiple applications. This allows system resources to be more focused on serving interactive operations within the information flow, improving resource utilization efficiency. Meanwhile, since the editing, display, and playback of special effects animations are all completed within the information flow interface, there is no need for additional data interaction with external applications or independent servers. Data flows within the information flow system, shortening the data interaction link and reducing the waiting time for data transmission, thereby reducing the system's response latency and allowing users to receive more immediate feedback. Attached Figure Description

[0031] Figure 1A is a schematic diagram of the first application mode of the interactive processing method provided in the embodiment of this application;

[0032] Figure 1B is a schematic diagram of the second application mode of the interactive processing method provided in the embodiments of this application;

[0033] Figure 2 is a schematic diagram of the structure of the electronic device provided in an embodiment of this application;

[0034] Figure 3A is a first flowchart of the interactive processing method provided in an embodiment of this application;

[0035] Figure 3B is a second flowchart of the interactive processing method provided in the embodiment of this application;

[0036] Figure 3C is a schematic diagram of the third process of the interactive processing method provided in the embodiments of this application;

[0037] Figure 3D is a schematic diagram of the fourth process of the interactive processing method provided in the embodiments of this application;

[0038] Figure 4 is a fifth flowchart of the interactive processing method provided in the embodiments of this application;

[0039] Figure 5A is a first schematic diagram of the human-computer interaction interface provided in an embodiment of this application;

[0040] Figure 5B is a second schematic diagram of the human-computer interaction interface provided in an embodiment of this application;

[0041] Figure 5C is a third schematic diagram of the human-computer interaction interface provided in an embodiment of this application;

[0042] Figure 5D is a fourth schematic diagram of the human-computer interaction interface provided in the embodiments of this application;

[0043] Figure 6A is a fifth schematic diagram of the human-computer interaction interface provided in the embodiments of this application;

[0044] Figure 6B is a sixth schematic diagram of the human-computer interaction interface provided in the embodiments of this application;

[0045] Figure 6C is a seventh schematic diagram of the human-computer interaction interface provided in the embodiments of this application.

[0046] 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

[0047] 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.

[0048] 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.

[0049] 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.

[0050] It should be noted that the data collection and processing in this application (e.g., user-related data) should strictly comply with the requirements of relevant laws and regulations, obtain the informed consent or separate consent of the personal information subject, and carry out subsequent data use and processing within the scope of laws and regulations and the authorization of the personal information subject.

[0051] 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.

[0052] 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.

[0053] 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.

[0054] 1) Responding to: used to indicate the conditions or states on which the operation is performed depends. When the conditions or states on which it depends are met, one or more operations can be performed in real time or with a set delay. Unless otherwise specified, there is no restriction on the order in which the multiple operations are performed.

[0055] 2) Human-Computer Interaction Interface: 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), etc.

[0056] 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.

[0057] 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.

[0058] 5) Special effects animation: refers to a form of animation that applies various visual effects to enhance the expressiveness of the visuals, create visual impact, or achieve specific artistic effects. In this embodiment, the special effects animation is an animation formed through pre-configured templates and editing operations.

[0059] 6) Sharing operation: An action that sends content created or acquired within an application (such as text, images, videos, links, audio, files, or location information) to one or more recipients. In this embodiment, the sharing operation is used to forward the currently shared content to the terminal devices of other users.

[0060] 7) Information refers to the content displayed in the information flow interface that can be viewed and interacted with by users. This includes basic content such as text and images, and can be associated with special effects animations (such as animations generated by user editing). The information needs to be equipped with interactive controls to trigger editing operations (such as controls to enter the animation editing interface) and sharing controls to trigger sharing operations, supporting users to perform interactive behaviors such as editing animations and sharing information based on the information. At the same time, the information can be sent to the terminal devices of other objects, allowing the receiving objects to view, edit new animations, and further share them, realizing cross-object transmission and interactive iteration of information.

[0061] 8) The information flow interface is an interactive interface used to display various types of information. The information flow interface arranges information content according to preset rules and supports users to browse, select, and trigger interactive operations. The information flow interface may include an information display area, a control area for triggering interaction, and a preview or playback area for dynamic content (such as special effects animation) associated with the information. It can also adapt to the screen size of different terminal devices to ensure that information and interactive elements are displayed completely, so that users can obtain information and perform subsequent operations.

[0062] 9) Key elements are content units extracted from selected information that reflect the core characteristics of the information. The types of key elements include keywords and key images. Keywords are words extracted from the text content of the information that reflect the theme or core semantics of the information. Key images are image fragments extracted from the image content of the information that reflect the core scene or object of the information. Key elements can be used as basic data to generate prompt words, match animation templates, or generate animation content, providing the core basis for the creation of special effects animations related to information and ensuring that the animation content is highly consistent with the characteristics of the information.

[0063] This application provides an interactive processing method, an interactive processing device, an electronic device, a computer-readable storage medium, and a computer program product, which can enrich the interactive forms in the information flow interface and improve the efficiency of interaction.

[0064] 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.

[0065] Referring to Figure 1A, which is a schematic diagram of the first application mode of the interactive processing method provided in the embodiments of this application; for example, Figure 1A involves a server 200, a network 300, a terminal device 400, and a database 500. The terminal device 400 is connected to the server 200 through the network 300, and the database 500 stores media information. The network 300 can be a wide area network or a local area network, or a combination of both.

[0066] For example, terminal device 400 has an application installed for displaying an information stream interface, and server 200 sends the screen data of the information stream to terminal device 400 via a network. Based on the above example, the terminal device 400 displays an information stream interface 101A. In response to a trigger operation on a first interactive control in the first information within the information stream interface 101A, a first interactive interface is displayed. In the first interactive interface, the user creates a first special effect animation through editing operations. In response to a second trigger operation, the first special effect animation 102A is displayed in the information stream interface. This enriches the user's interaction methods with the information in the information stream, embeds animation editing functionality into the first information, and improves interaction efficiency.

[0067] Referring to Figure 1B, which is a schematic diagram of the second application mode of the interactive processing method provided in the embodiments of this application; for example, Figure 1B involves a server 200, a network 300, a terminal device 400, a second terminal device 402, and a database 500. The terminal device 400 is connected to the server 200 through the network 300, and the database 500 stores media information. The network 300 can be a wide area network or a local area network, or a combination of both.

[0068] For example, the second user is distinct from the first user. The second terminal device 402 is the terminal device used by the second user. The first user performs a sharing operation on terminal device 400 to share the first information and the first special effect animation from the information flow interface to the second user on the second terminal device 402. The shared content is displayed on the second user's information flow interface or dialog interface on the second terminal device 402. The second user can trigger the first interactive control in the first information from the information flow interface of the second terminal device 402. The information flow interface of the second terminal device 402 displays an interactive interface for editing the special effect animation, and the second user can also edit the special effect animation.

[0069] In some embodiments, the interactive processing method of this application can also be applied in the following application scenarios:

[0070] 1. In instant messaging applications, users can trigger the animation editing function in the first message through the information flow interface of the instant messaging application, which enriches the interaction methods. The first special effect animation is displayed in the information flow interface, and other users who have a friend relationship with the first user can also observe the corresponding first special effect animation, which promotes other users to edit animations in a seamless manner and enriches the interaction forms in the information flow interface.

[0071] 2. Ad Recommendation: Assuming the first piece of information is an advertisement posted by an advertiser, an interactive control is embedded in the advertisement. This interactive control triggers the corresponding special effects animation editing function. The first special effects animation contains the advertisement material and can increase the probability of interaction between the user and the recommended content, thereby improving the recommendation effect of the advertisement.

[0072] 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.

[0073] 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.

[0074] 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.

[0075] Referring to Figure 2, which is a schematic diagram of the structure of an electronic device provided in an embodiment of this application, the electronic device may be the terminal device 400 shown in Figure 1A or Figure 1B. The terminal device 400 shown in Figure 2 includes: at least one processor 410, a memory 450, at least one network interface 420, and a user interface 430. The various components in the terminal device 400 are coupled together through a bus system 440. It is understood that the bus system 440 is used to realize the connection and communication between these components. In addition to a data bus, the bus system 440 also includes a power bus, a control bus, and a status signal bus. However, for clarity, all buses are labeled as bus system 440 in Figure 2.

[0076] The processor 410 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0077] 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.

[0078] 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.

[0079] 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.

[0080] 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.

[0081] 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;

[0082] 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.

[0083] 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;

[0084] 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.

[0085] In some embodiments, the apparatus provided in this application can be implemented in software. FIG2 shows an interactive processing device 455 stored in memory 450, which can be software in the form of programs and plug-ins, including the following software modules: display module 4551 and data processing module 4552. These modules are logically related and can therefore be arbitrarily combined or further split according to the functions they implement. For ease of explanation, all the above modules are shown at once in FIG2, but this should not be considered as excluding the implementation of the interactive processing device 455 which may only include the display module 4551. The functions of each module will be described below.

[0086] In some embodiments, the terminal device or server can implement the interactive processing method provided in this application 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.

[0087] The interactive processing method provided in this application will be described in conjunction with exemplary applications and implementations of the terminal devices provided in the embodiments of this application.

[0088] The interactive processing method provided in the embodiments of this application will be described below. As mentioned above, the electronic device implementing the interactive 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.

[0089] It should be noted that the interactive processing examples below are illustrated using an instant messaging application. Based on the understanding of the following text, those skilled in the art can apply the interactive processing methods provided in the embodiments of this application to processing in other types of applications, such as news applications, short video applications, and social media applications.

[0090] Referring to Figure 3A, which is a flowchart illustrating the interactive processing method provided in an embodiment of this application, the steps shown in Figure 3A will be explained in conjunction with the steps shown in Figure 3A. The executing entity of the steps in Figure 3A is the terminal device 400 in Figure 1A.

[0091] In step 301, the first information is displayed in the information flow interface.

[0092] Here, the first information includes the first interactive control.

[0093] In some embodiments, the first interactive control is an interactive element embedded in the first information, serving as an entry point to trigger subsequent special effects animation editing functions. Its form can be an icon, button, etc., depending on the interface design, and it is directly associated with the content area of ​​the first information. If the first information includes text or multimedia content, and the text or multimedia content exceeds the screen area when displayed at the default font size, the information flow interface will reserve vertical or horizontal space to ensure the complete display of the first information. The interactive logic of the information flow interface must match the triggering requirements of the first interactive control. For example, during the scrolling operation of the information flow interface, when the first information is within the user's field of vision, the first interactive control must remain clickable and will not temporarily become invalid due to interface scrolling, ensuring that the user can perform triggering operations on the first interactive control at any time.

[0094] For example, an Information Stream Interface (ISI) is a user interface design that displays continuous information content in chronological order or according to user-specified rules. It is commonly found in social media applications, news applications, instant messaging software, and other services that need to display dynamically updated content. The ISI displays continuous information content in chronological order or according to user-specified rules. The first piece of information displayed in the ISI can be of any type. The first piece of information can be promotional or non-promotional. Promotional information refers to related items or content provided to the user through a recommendation system, such as advertisements recommended by an advertising recommendation system. Non-promotional information can be original content posted or forwarded by the user. The first interactive control is used to trigger the playback of special effects animations or to display the first interactive interface, which is the interface used to edit special effects animations.

[0095] For ease of understanding, the following explanation is provided in conjunction with the accompanying drawings. Referring to Figure 5A, Figure 5A is a first schematic diagram of the human-computer interaction interface provided in an embodiment of this application; the information flow interface 501A includes first information 502A and a first interactive control 503A. The first interactive control 503A is embedded in the first information 502A. The first information 502A is promotional information released by a brand, used to recommend corresponding products. In response to the first interactive control 503A being triggered, the first interactive interface is displayed.

[0096] In some embodiments, step 301 can be implemented by displaying at least one parameter associated with the first interactive control in the first information:

[0097] For example, the parameters associated with the first interactive control are information related to the function of the first interactive control. Examples include: prompts representing the function of the first interactive control, parameters recording the number of times the first interactive control is interacted with (such as the number of objects interacting with it), and data generated during the interaction process performed by the interactive control.

[0098] Parameter 1: Prompt information for the function of the first interactive control.

[0099] In some embodiments, the prompt information regarding the function of the first interactive control is explanatory content embedded within the first information and directly associated with the first interactive control. Its core function is to allow users to quickly understand the core function of the first interactive control, namely, that triggering the control allows entry into the first interactive interface to edit special effects animations. The display format of this prompt information needs to be closely bound to the first interactive control; it can be directly marked next to the first interactive control (such as a text label) or presented as a hover tooltip (such as when the user hovers the cursor over the first interactive control).

[0100] For example, assuming the special effects animation is a fireworks effect animation, the prompt message could be "Light the fireworks". Referring to Figure 5A, which is a first schematic diagram of the human-computer interaction interface provided in an embodiment of this application; the prompt message "Light the fireworks" is displayed in the first interactive control 503A, indicating that the first interactive control 503A can be used to perform the function of playing fireworks effects, so as to prompt the user to interact through the first interactive control 503A.

[0101] Parameter 2: The number of objects that perform interactive processing on the first interactive control.

[0102] In some embodiments, the number of objects that perform interactive processing on the first interactive control reflects how many users have participated in special effects animation-related interactions through the first interactive control. This data is bound to the first interactive control and displayed in the first information. Interactive processing specifically refers to the user's actions of triggering the first interactive control, entering the first interactive interface to edit and generate the first special effects animation. The number of objects is updated in real time; whenever a new user completes the aforementioned interactive processing, the number of objects increases accordingly. The distance between the display position of the object count and the position of the first interactive control is less than a distance threshold.

[0103] For example, the number of objects that performed the interaction could be displayed as the number of objects in the network that performed the interaction, or the number of objects that have a friend relationship with the current user that performed the interaction; it could also be the name of each object that participated in the interaction. Referring again to Figure 5A, the prompt message 504A includes the names of multiple users who have performed the interaction. The current user can use the displayed usernames to understand the number of users and usernames who have performed the interaction with the first interactive control 503A.

[0104] Parameter 3: The text content included in the first special effects animation.

[0105] In some embodiments, the text content included in the first special effects animation refers to the text information embedded in the animation when editing the first special effects animation through the first interactive interface. This text content extracts key parts (such as core keywords or short phrases) and displays them in the current first information, associated with the first interactive control. The displayed text content needs to be selected to be representative information, and the display of the text content is distinct from the core content of the first information, so as not to interfere with the user's reading of the first information itself. It displays the text already generated in the first special effects animation and does not include temporary text content that has not yet been edited.

[0106] For example, in this embodiment of the application, the first interactive control is used to trigger the interactive processing of editing special effects animation. The data in the interactive process executed by the interactive control can be the text content in the edited special effects animation. Assuming the first information is promotional information, the text content can be advertising slogans pre-configured by the advertiser; or, assuming the first information is related to a festival, the text content can be pre-configured blessing information. Continuing to refer to Figure 5A, phrases such as "Joyful Celebration" and "May All Your Wishes Come True" are text content in the already generated special effects animation.

[0107] In this embodiment, by displaying various parameters of the first interactive control in the information flow interface, the user's interest in interacting with the first interactive control is promoted, and the probability of interaction is increased. The various parameters of the first interactive control can characterize the function of the first interactive control and play a functional guiding role for the user. At least one parameter of the first interactive control can provide the user with more content to understand the function of the interactive control, which can improve the user's interaction efficiency.

[0108] In some embodiments, prior to step 302, the following process is performed: a second special effects animation is displayed in the first information, the second special effects animation being different from the first special effects animation.

[0109] For example, the first special effect animation is the special effect animation currently edited by the user, while the second special effect animation is different from the first special effect animation in that the second special effect animation is a special effect animation that existed before the current user performed the editing operation.

[0110] Referring to Figure 5B, which is a second schematic diagram of the human-computer interaction interface provided in an embodiment of this application; assuming that after the first interactive control in the information flow interface 501A of Figure 5A is triggered, the information flow interface 501A shown in Figure 5B is displayed, and the second special effects animation 501B is displayed in the information flow interface 501A of Figure 5B. The first information may be promotional information published by an advertiser, then the second special effects animation 501B is a pre-configured special effects animation. In some embodiments, the second special effects animation 501B may also include recommended materials.

[0111] For example, the second special effects animation is any of the following types of special effects animation:

[0112] Type 1: Special effects animations pre-configured for the first piece of information.

[0113] In some embodiments, the pre-configured special effects animation for the first information is a second special effects animation that is pre-set when the first information is generated or enters the information flow interface, and can be displayed directly without editing the first object. The second special effects animation matches the content theme of the first information. For example, when the first information is a holiday greeting, the pre-configured second special effects animation may include holiday elements (such as fireworks and ribbons); when the first information is a product promotion, the pre-configured special effects animation may include product highlight display effects. The pre-configured second special effects animation will automatically loop or play once in a designated area of ​​the first information (such as the content background or next to the title), and will not affect the normal display and function triggering of the first interactive control.

[0114] For example, a pre-configured special effects animation for the first piece of information refers to a special effects animation pre-configured based on the content of the first piece of information; or associating the first piece of information with a specific special effects animation to form a pre-configured special effects animation for the first piece of information. For instance, a second special effects animation is a special effects animation associated with the content of the first piece of information. Assuming the first piece of information is promotional information, the second special effects animation could be a promotional animation used to recommend corresponding products. Alternatively, if the first piece of information is user-generated original content, the second special effects animation could be an explanatory special effects animation used to explain the principles involved in the original content. Another example: an advertiser provides the first piece of information and an advertising animation, associating the advertising animation as a second special effects animation with the first piece of information.

[0115] Type 2: Special effects animations edited by the second object, which is a different object from the first object in the browsing information flow interface.

[0116] In some embodiments, the special effects animation edited by the second object is generated by another user (the second object), different from the first object browsing the information flow interface, by triggering the first interactive control of the first information and entering the first interactive interface to edit the animation. The second special effects animation is bound to the first information and is displayed as a second special effects animation when the first object browses the first information. When there are multiple second special effects animations, at least one of the most recently edited special effects animations can be displayed first to avoid too many animations occupying the display space of the first information; and each special effects animation will be marked with the identity identifier of the editor (second object) (such as a nickname abbreviation) so that the first object knows the source of the animation.

[0117] For example, the second object can be an object that is a friend of the first object, or an object that is a friend of another friend of the first object. The first object must have the corresponding viewing permissions for the special effects animations edited by the second object. If the first object does not have the corresponding viewing permissions, the special effects animations edited by the second object will not be displayed in the information flow interface of the first object's terminal device.

[0118] In this embodiment of the application, by displaying a second special effects animation as an example before displaying the first interactive interface, a visual effect display can be provided to the user, which can arouse the user's interest in performing the interaction, thereby increasing the interaction frequency in the first interactive interface; at the same time, the second special effects animation, as a display animation displayed before the first interactive interface, can serve as a reference animation to provide functional guidance to the user, making it easier for the user to edit the special effects animation and improve the interaction efficiency.

[0119] In some embodiments, the type of the second special effects animation displayed in the first information varies depending on the type of the first information, which can be achieved in the following ways:

[0120] Method 1: When the first information is published by the second object, display the special effects animation edited by the second object in the first information.

[0121] For example, when the first information is posted by the second object, the special effects animation edited by the second object is displayed. When the second object has not edited a second special effects animation, the second special effects animation edited by the second object's friend, or edited by another object with a similarity greater than the similarity threshold to the second object, is displayed. The similarity between the second object and other objects can be determined as follows: feature extraction is performed on the data of the account used by each user to log in to the application to obtain the account features corresponding to each user. The similarity between the account features of the second object and the account features of other objects is determined, and the special effects animation edited by the account with the highest similarity is selected as the second special effects animation.

[0122] For example, "other objects" refers to any object other than the first and second objects among all objects browsing the information flow interface. Similarity can be determined using any of the following similarity algorithms: cosine similarity, Euclidean distance, Manhattan distance, and Pearson correlation coefficient. Taking cosine similarity as an example, the similarity is determined by: the vector product of the feature vector of the second object and the feature vectors of the other objects; the length product of the lengths of the feature vectors of the second object and the feature vectors of the other objects; and the ratio of the vector product to the length product. If the feature vector of the second object is m and the feature vectors of the other objects are n, then the vector product is m*n. If the length of the feature vector of the second object is |m| and the length of the feature vectors of the other objects is |n|, then the length product is |m|*|n|. The ratio of the vector product to the length product is (m*n) / (|m|*|n|), which is used as the similarity.

[0123] Method 2: When the first message is not the message published by the second object, display the pre-configured special effects animation in the first message.

[0124] In some embodiments, when the publisher of the first information is different from the second object, a pre-configured special effects animation for the first information is invoked and displayed as the second special effects animation in the first information. The pre-configured special effects animation is set in advance according to the content type of the first information (such as holiday information, product promotion, and lifestyle updates). For example, a steaming special effects animation is pre-configured for food-related first information, and a landscape gradient special effects animation is pre-configured for travel-related first information, ensuring that the animation style matches the theme of the first information. The display of the special effects animation does not rely on any user editing operations. It is automatically loaded and played when the first information enters the information flow interface, and the playback logic is stable (such as loop playback, pause after a single playback). There will be no blank situation where no animation can be displayed due to the second object not participating in the interaction, ensuring the dynamic display effect of the first information.

[0125] For example, if the first message is not published by a user's account that browses the information flow interface through a terminal device, then the first message is a promotional message placed by an advertiser, and the promotional message has pre-configured associated special effects animations.

[0126] This application embodiment, by displaying a second special effects animation before displaying the first interactive interface as an example, brings a visual impact to the user, which can stimulate the user's interactive interest and improve the user's interactive efficiency. Displaying different types of second special effects animations according to different types of first information, matching the information type and animation effect, can provide users with a more intuitive and vivid interactive experience, enhancing the user's overall experience.

[0127] In some embodiments, displaying the second special effects animation in the first information can be achieved in any of the following ways:

[0128] Method 1: Display at least one second special effects animation.

[0129] For example, when there is only one second special effect animation, it can be displayed in a portion of the first information, above the first information, or in an adjacent area surrounding the first information. The adjacent area surrounding the first information refers to an area whose distance from the first information is less than a distance threshold. When there are multiple second special effect animations, at least some of them play in an overlay format, and the key elements of each second special effect animation are visible.

[0130] For example, playing in an overlay format refers to simultaneously displaying two or more special effects animations within the same user interface, creating a visually overlapping or layered effect. Overlay special effects animations can be presented in any of the following ways: the second special effects animation in the upper layer has transparency, allowing the second special effects animation in the lower layer to be visible through the upper layer; or, a smaller portion of another second special effects animation is embedded within the frame of one second special effects animation; or, two or more second special effects animations dynamically switch or merge according to specific rules.

[0131] For example, multiple overlaid secondary special effects animations are playing simultaneously. The key element of each overlaid secondary special effects animation is visible, while other parts of the overlaid secondary special effects animations may overlap. The key element of a secondary special effects animation is the element used to distinguish it from other secondary special effects animations. Key elements can be keywords or key images.

[0132] For example, key elements can be determined in the following ways: by calling a deep learning model to perform feature extraction on the second special effects animation to obtain animation features, and then calling a deep learning model to perform image segmentation on the animation features to obtain key images in the second special effects animation; or by calling a deep learning model to perform semantic understanding on the animation features to obtain keywords in the second special effects animation.

[0133] For example, key elements can also be determined in the following ways: A deep learning model is invoked to perform feature extraction on the second special effects animation to obtain the element features of each element in the second special effects animation; and a deep learning model is invoked to extract features from the first information and the account of the first object browsing the information flow interface to obtain the information features of the first information and the account features of the first object. The similarity between the information features of the first information and each element feature is determined, as well as the similarity between the account features of the first object and each element feature. Based on at least one of the two similarities, the key elements among all elements in the second special effects animation are determined. For example: the element corresponding to the element feature with the highest similarity to the account feature is taken as the key element; the element corresponding to the element feature with the highest similarity to the information feature is taken as the key element. Alternatively, the two similarities are weighted and summed, and the element corresponding to the element feature with the highest weighted sum is taken as the key element.

[0134] For example, "calling a deep learning model to extract features from the second special effects animation to obtain the element features of each element in the second special effects animation" can be achieved by performing the following processing: convert the second special effects animation into a frame sequence with a fixed frame rate and fixed resolution to ensure that the data format input to the deep learning model is consistent; perform data augmentation on the frame sequence (such as brightness normalization and noise reduction) to eliminate the interference of image quality fluctuations during animation playback on feature extraction; segment or detect contours of the elements in the animation using pixel thresholding to separate independent elements from the background and obtain frame sequence fragments corresponding to individual elements, avoiding feature confusion between elements; input the preprocessed single-element frame sequence into the selected deep learning model, such as a 3D (3D) convolutional neural network. The Network (CNN) model uses 3D convolution kernels to perform convolution operations on consecutive frames, extracting spatial features (such as shape, color, and texture) and temporal features (such as motion direction, speed, and duration) of elements. The deep learning model then uses fully connected layers or pooling layers to reduce the dimensionality of the extracted spatial and temporal features and integrate them to obtain a high-dimensional feature vector for each element, which is the element feature of each element in the second special effects animation. "Using a deep learning model to extract features from the first piece of information and the account of the first object browsing the information feed interface, obtaining the information features of the first piece of information and the account features of the first object" can be achieved by performing the following processing: Preprocess the first piece of information, input the preprocessed first piece of information into the deep learning model. If the deep learning model is a Transformer model, capture the relationship between the text and image of the first piece of information through a self-attention mechanism, and extract the semantic features of the text (such as sentiment tendency, topic keywords) and the visual features of the image (such as scene category, object identifier). Then, fuse the semantic features and visual features through a feature fusion layer to obtain the first fused feature. Perform dimensionality reduction on the first fused feature to obtain the high-dimensional feature vector of the first piece of information, which is the information feature of the first piece of information. Obtain the basic attribute data (such as account registration time, interest tags) and historical behavior data (such as records of browsing the first piece of information in the information feed interface, records of triggering the first interactive control, records of editing the first special effect animation), convert the basic attribute data into a basic attribute vector, and convert the historical behavior data into a historical behavior sequence vector. Input the preprocessed basic attribute vector and historical behavior sequence vector into the deep learning model. If it is a Long Short-Term Memory (LSTM) network... The Short-Term Memory (LSTM) model captures long-term dependencies in behavioral sequences through a gating mechanism, while integrating basic attribute vectors into hidden layer features to obtain a second fused feature. The second fused feature is then dimensionality-reduced to obtain a high-dimensional feature vector of the first object's account, which is the account feature of the first object.

[0135] For example, referring to Figure 6B, which is a sixth schematic diagram of the human-computer interaction interface provided in this application embodiment, the information flow interface 601A displays superimposed special effects animation 601B. The superimposed special effects animation 601B is formed by superimposing multiple second special effects animations. It is assumed that the key elements in the second special effects animations are keywords, such as "enjoy the moment," "stay curious," and "be joyful" in Figure 6B. Multiple second special effects animations are played in a superimposed form, and the keywords of each second special effects animation are in a visible state.

[0136] Method 2: Display multiple second special effects animations one by one.

[0137] For example, displaying multiple second-effect animations one by one means that each second-effect animation plays at least a portion of its content, and after playback, the already played second-effect animation is hidden, and the next second-effect animation is displayed. For instance, second-effect animation 1 plays for 3 seconds before second-effect animation 2 is displayed, second-effect animation 2 plays for 3 seconds before second-effect animation 3 is displayed, and so on; or, second-effect animation 1 plays completely before second-effect animation 2 is displayed. During this sequential display, the playback duration of each second-effect animation can be set according to the application scenario's requirements. During application, the video player on the information flow interface sequentially calls the data corresponding to each second-effect animation to play, thereby achieving the sequential display of multiple second-effect animations.

[0138] For example, each secondary special effects animation has different content, and the display order of multiple secondary special effects animations is sorted according to at least one of the following factors: release time, user interest, relevance to the primary information, and interaction frequency.

[0139] For example, the release time refers to the time when the second special effects animation is publicly released on the network. User interest can be represented by the similarity between the animation features of the second special effects animation and the account features of the first object; the relevance to the first information can be represented by the similarity between the animation features of the second special effects animation and the information features of the first information. Interaction frequency can be represented by the frequency and number of interaction actions, where the types of interaction actions include: likes, shares, comments, and favorites.

[0140] Referring to Figure 5D, which is a fourth schematic diagram of the human-computer interaction interface provided in this application embodiment, a second special effects animation 501D is displayed in the information flow interface 501A. After the second special effects animation 501D has played for a pre-configured duration, it is automatically hidden, and a second special effects animation 502D is displayed in the information flow interface 501A. The content of the second special effects animation 501D and the second special effects animation 502D are different. For example, as shown in Figure 5D, the text and patterns in the second special effects animation 501D are different from those in the second special effects animation 502D.

[0141] Method 3: Display a second special effects animation and a second interactive control. In response to a trigger operation on the second interactive control, switch to displaying another second special effects animation.

[0142] In some embodiments, if there are multiple second special effects animations associated with the first information, the second interactive control is displayed and is in a triggerable state; if there is only one second special effects animation associated with the first information, the second interactive control is hidden, or the second interactive control is set to an untriggerable state (e.g., grayed out), to avoid the user having no animation to switch after triggering it and to reduce invalid operations.

[0143] For example, another secondary special effects animation refers to a special effects animation that is different from the content of an already displayed secondary special effects animation. Method 2 automatically switches between secondary special effects animations, while Method 3, compared to Method 2, switches secondary special effects animations through a triggered action.

[0144] For example, in this embodiment of the application, multiple second special effects animations are pre-configured. If a user still needs to watch after viewing the first displayed special effects animation, they can trigger a second interactive control to display other second special effects animations with different content. If the user does not need to watch more second special effects animations, they can also end the playback process of the second special effects animations by triggering an area in the human-computer interaction interface where no second special effects animation is displayed.

[0145] Referring again to Figure 5B, the information flow interface 501A also displays a second interactive control 502B. In response to a trigger operation on the second interactive control 502B, the currently displayed "Enjoy the Moment" second special effect animation is switched to display another second special effect animation. The content of this other second special effect animation is different from the content of the currently displayed "Enjoy the Moment" second special effect animation.

[0146] In this embodiment, multiple second special effects animations are displayed in different ways. These second special effects animations can serve as reference animations, providing guidance to users and facilitating their subsequent independent editing of special effects animations. Displaying different second special effects animations enriches the visual presentation of the information flow interface and provides users with a better visual experience.

[0147] In step 302, in response to a first trigger operation on the first interactive control, the first interactive interface is displayed.

[0148] Here, the first interactive interface is used to edit special effects animations.

[0149] For example, special effects animation refers to a form of animation that applies various visual effects to enhance the expressiveness of the image, create visual impact, or achieve specific artistic effects. In this embodiment, special effects animation is an animation formed through pre-configured animation templates and editing operations. The first interactive interface integrates various functions for editing special effects animation, including but not limited to: selecting a template for special effects animation, inputting content in the special effects animation (e.g., text, images, audio), and trimming the playback duration of the special effects animation. The functions of the first interactive interface will be explained in detail in the following steps.

[0150] In step 303, in response to the first editing operation in the first interactive interface, the first special effects animation formed by the editing is displayed.

[0151] For example, editing operations include, but are not limited to: entering text, selecting pre-configured effects templates, and adding background music. The first special effects animation displayed in the first interactive interface is specifically a preview of that animation. This preview information showcases the video content (i.e., the first special effects animation) and can be a scene or keyframe from the animation. The preview allows users to understand at least part of the special effects animation without playing the full animation.

[0152] For ease of understanding, refer to Figure 6A, which is a fifth schematic diagram of the human-computer interaction interface provided in this embodiment of the application. The content displayed in the first interactive interface 601A includes special effects animation templates (e.g., templates 1 to 3), preview information 603A, reference animation 604A, input controls 602A, and send controls 606A. Preview information 603A indicates that the currently selected template is template 2, and the entered text content is "Joyful". Reference animation 604A is an illustration of special effects animations that have been edited by other users, which can be used to provide a reference for the current user to edit special effects animations.

[0153] In some embodiments, the first editing operation further includes an input operation; step 303 can be implemented by displaying an input control on a first interactive interface; in response to an input operation on the input control, playing the input content corresponding to the input operation in a first special effects animation, wherein the type of input content includes: text, image, audio and video.

[0154] For example, the audio can be the user's input voice or uploaded music. Continuing to refer to FIG. 6A, in response to a trigger operation on the input control 602A, text or voice is input, and the text content "overjoyed" is formed and displayed in the preview information 603A.

[0155] Here, for text-based input content, the input control supports text input, deletion, and modification, and has built-in functions for adjusting font, color, and size; for image-based input content, the input control supports selecting from the album of the terminal device or taking a real-time photo, and provides image cropping and rotation tools; for audio-based input content, the input control supports recording, playing, and re-recording, and displays the recording duration; for video-based input content, the input control supports selecting from the album of the terminal device or real-time recording, and provides a function for截取 video segments.

[0156] In the embodiments of the present application, it supports the user to input text content and other media content, enriches the editing method, improves the freedom of interactive processing, and makes the first special effect animation obtained by editing more in line with the user's needs.

[0157] In some embodiments, the types of the first editing operation include: a selection operation; step 303 can be implemented in the following manner: display multiple first animation templates in the first interactive interface; in response to a selection operation on any one of the first animation templates, display the first special effect animation generated according to the target animation template, where the target animation template is the selected first animation template.

[0158] For example, an animation template is a pre-designed animation framework that contains the basic structure and elements of the animation. Users can add custom content on this basis to quickly generate personalized animation works. In the embodiments of the present application, the animation template can include the following content: the elements displayed in each frame of the special effect animation, the preset background sound, and the preset text content. Users can edit the preset animation template through an editing operation to form the first special effect animation. Or, without modification, directly use the content of the animation template as the first special effect animation.

[0159] For example, during the editing process, in response to a selection operation on any one of the first animation templates, the display of the first special effect animation generated according to the target animation template is achieved in the following manner: in response to a selection operation on any one of the first animation templates, highlight the selected target animation template, and in response to a generation operation, display the first special effect animation generated according to the target animation template.

[0160] Continuing to refer to FIG. 6A, the preview information 603A is a screen formed based on an editing operation. For example, if the current editing operation includes selecting Template 2 and inputting the text "extremely happy", the corresponding screen is presented in the preview information 603A. Template 2 is highlighted in a manner different from Template 1 and Template 3. In response to a confirmation operation for Template 2 (such as a click operation or a long-press operation), Template 2 and other content filled in by the user are synthesized to form a first special effect animation. In FIG. 6A, Template 2 and the filled text "extremely happy" are synthesized to obtain the first special effect animation.

[0161] In some embodiments, the first information is promotional information, and each first animation template includes recommended materials related to the promotional information; the display of the first special effect animation generated according to the target animation template can be achieved by the following method: displaying the first special effect animation including the recommended materials generated according to the target animation template.

[0162] For example, the promotional information is also advertising information, and the types of recommended materials related to the promotional information include: product introduction information of the object recommended by the advertisement, product views, logos, advertising words, and other contents. At least one of the above types of recommended materials is carried in the first animation template, and thus the recommended materials are also carried in the first special effect animation generated according to the selected first animation template. Referring to FIG. 6A, the recommended material 607A carried in Template 2 is displayed in the first interaction interface 601A, and the recommended material 607A is a brand logo (LOGO) related to the first information configured by the advertiser. In the embodiments of the present application, the recommended material 607A is only used as an example of the recommended material being a brand logo. In specific implementations, the recommended material can be any other pattern form.

[0163] In the embodiments of the present application, by providing the function of editing the special effect animation carrying the recommended materials in the promotional information, the interaction form between the user and the promotional information is enriched. Through the interaction process, the contact depth between the user and the promotional information is increased, the exposure duration of the promotional information is increased, and thus the interest and impression of the user for the promotional information can be improved, and the recommendation effect of the promotional information can be enhanced.

[0164] In some embodiments, before step 303, the first animation template is determined by at least one of the following methods:

[0165] Method 1: Using the second animation template selected by the second account as the first animation template, where the second account is an account having a social relationship with the first account browsing the information flow interface.

[0166] In some embodiments, the social relationship list of the first account is obtained in real time, and the second animation template used by the second account in the social relationship list within a preset time period is filtered out. The second animation template with the highest usage frequency is given priority as the first animation template. If multiple second accounts use different second animation templates, they are sorted according to the social intimacy between the second account and the first account (such as the number of interactions and the duration of friendship), and the second animation template used by the second account with the highest intimacy is selected.

[0167] For example, a social relationship means that there is a friend relationship between the first account and the second account, or there is a friend relationship between the second account and the first account's friends, thus forming an indirect friend relationship between the first account and the second account, and the first account has the permission to browse the templates selected by the second account.

[0168] Method 2: Use the animation template that is selected the most times as the first animation template.

[0169] For example, the number of times an animation template is selected is calculated based on a large amount of user selection data. The statistical scope can be all the friend accounts of the current account, all accounts in the region where the current account is located, or all user accounts that have performed editing operations using the interactive interface.

[0170] Method 3: Determine the first similarity between the information features of the first information and the semantic features of the candidate animation template, and take the candidate animation template with the highest first similarity as the first animation template.

[0171] For example, Method 3 and Method 4 below are implemented through a neural network model. The information features of the first information and the semantic features of the candidate animation template are extracted through the neural network model. When the information features of the first information and the semantic features of the candidate animation template are represented in vector form, the first similarity can be cosine similarity.

[0172] For example, the information features of the first information can be determined by performing the following processing: extracting the text content from the first information, performing word segmentation and stop word removal; then converting the processed text into a sequence of tokens recognizable by the neural network model, and generating text embedding vectors through the word embedding layer of the neural network model; extracting the image content from the first information, converting the image in the first information into a computer-recognizable digital format to obtain an initial image digital matrix, scaling the initial image digital matrix according to the preset resolution of the neural network model to obtain a fixed-size image digital matrix, and reorganizing the fixed-size image digital matrix in a preset order to obtain an image tensor that conforms to the model input format; and then combining the preprocessed text embedding vectors with... Image tensors are integrated according to the format required by the neural network model to form multimodal input data for the first information. Based on the integrated multimodal input data for the first information, the neural network model is invoked. The text encoder of the neural network model performs self-attention calculation on the text embedding vectors to capture the semantic relationships between texts and obtain text features. The image encoder of the neural network model performs convolution and attention operations on the image tensors to extract the visual features of the image. The multimodal fusion layer of the neural network model fuses the text features and image features into a unified multimodal feature through a cross-attention mechanism. The fused multimodal feature is then dimensionality-reduced through the fully connected layer of the model, mapping the high-dimensional features to a fixed-dimensional feature vector as the information features of the first information. The semantic features of candidate animation templates can be determined by performing the following processing: obtaining the semantic description text of each candidate animation template, performing word segmentation and stop word removal on the semantic description text; then converting the processed text into a token sequence required by the neural network model, and generating text embedding vectors through the word embedding layer of the neural network model; inputting the standardized text embedding vectors into a fine-tuned Bidirectional Encoder Representations from Transformers (BERT) model, and performing multi-layer self-attention calculation on the text embedding vectors through the BERT encoder to capture semantic associations and obtain sequence features; converting the sequence features into fixed-length text semantic feature vectors through the BERT pooling layer; and reducing the dimensionality of the pooled text semantic feature vectors to the same dimension as the information features of the first information through a fully connected layer to obtain the semantic features of the candidate animation templates.

[0173] Method 4: Determine the second similarity between the first account features of the first account and the semantic features of the candidate animation template, and take the candidate animation template with the highest second similarity as the first animation template.

[0174] For example, similar to method 3, the first account features of the first account and the semantic features of the candidate animation template can also be extracted through a neural network model. When the first account features of the first account and the semantic features of the candidate animation template are represented in vector form, the second similarity can be cosine similarity.

[0175] For example, the first account's first account features can be determined by performing the following processes: Obtain the first account's basic attribute data and historical behavior data; perform one-hot encoding on the categorical attributes (such as interest tags) in the basic attribute data, converting them into binary vectors to obtain categorical attribute vectors; normalize the numerical attributes (such as registration time) in the basic attribute data, mapping the values ​​to the 0-1 range to obtain numerical attribute vectors; concatenate the categorical attribute vectors and numerical attribute vectors to obtain the first account's basic attribute vectors; organize the behavior records in chronological order to form a behavior sequence, encode each behavior record to obtain a behavior token sequence; through the behavior embedding layer of a neural network model, convert the behavior token sequence into behavior embedding vectors, capturing the semantic information of the behavior to form the first account's historical behavior embedding sequence; combine the basic attribute vectors and historical behavior embedding sequences into fused features; reduce the dimensionality of the fused features through the pooling layer of the neural network model to obtain candidate features; map the candidate features to a fixed dimension through a fully connected layer to obtain the first account's account features.

[0176] In this embodiment, animation templates are recommended in various ways, enabling users to obtain animation templates that better meet their needs, thereby improving the efficiency and convenience of users editing special effects animations and enhancing interaction efficiency.

[0177] In some embodiments, referring to FIG3B, FIG3B is a second flowchart of the interactive processing method provided in the embodiments of this application. Before displaying the first special effects animation formed by editing, the following steps 3051 to 3053 are performed, which are described in detail below.

[0178] In step 3051, in response to an input operation on the first interactive interface, the first prompt word that was entered is displayed.

[0179] In some embodiments, the first interactive interface can provide a reference example of prompt words, which users can edit to optimize the first prompt words; if the length of the prompt words entered by the user is less than the length threshold, guidance prompts can be displayed, such as "It is recommended to supplement the scene description", to help generate a more accurate reference image and first frame image.

[0180] For example, the first interactive interface includes an input control. In response to an input operation on the input control, the first prompt word entered is displayed. The input method can be text editing using an input method or text conversion via speech. Referring to Figure 6C, Figure 6C is a seventh schematic diagram of the human-computer interaction interface provided in this embodiment. The first interactive interface 601A displays an input control 602C, through which the user inputs the text "New Year Fireworks". "New Year Fireworks" is used as the first prompt word.

[0181] In step 3052, a reference image is searched based on the first prompt word, and a pre-trained text-to-image model is called to generate multiple first frame images based on the reference image and the first prompt word.

[0182] In some embodiments, the image encoder built into the pre-trained text-based graph model extracts features from the reference image to obtain a visual feature vector of the reference image; the text encoder of the pre-trained text-based graph model performs semantic analysis on the first prompt word to obtain a text semantic vector; the visual feature vector of the reference image and the text semantic vector of the first prompt word are fused to obtain a fused vector; the pre-trained text-based graph model starts with a random noise image and gradually denoises the image through multi-step diffusion iteration to generate an initial frame image that conforms to the feature guidance; the pre-trained text-based graph model makes differentiated adjustments to the initial frame image by adjusting conditional parameters, presets a dynamic parameter sequence for the dynamic description in the first prompt word, and generates the first frame image one by one according to the dynamic parameter sequence to obtain multiple first frame images.

[0183] For example, the first-response keyword search reference images are selected based on the search results obtained through a search engine on the web using the first-response keyword, and those images that match the first-response keyword most closely are used as reference images. There can be one or more reference images.

[0184] For example, a text-to-image model is an artificial intelligence model that learns from large amounts of text and image data to understand textual descriptions and generate corresponding images. Such models are typically built using deep learning techniques, particularly architectures based on Generative Adversarial Networks (GANs) or Variational Autoencoders (VAEs). The core advantage of pre-trained text-to-image models lies in their ability to learn from large amounts of unlabeled data, enabling them to generate high-quality images even without task-specific training.

[0185] For example, for each first frame image, the i-th first frame image is generated based on the reference image, the prompt word, and the i-1 already generated first frame images. This makes the content of the first frame images related, thereby improving the smoothness of the special effects animation formed by multiple first frame images. Continuing to refer to Figure 6C, based on the prompt word "New Year fireworks," images of fireworks and images of New Year-related elements are searched online as reference images to generate multiple video frames. One of the first video frames can be presented as the video frame preview screen 601C in Figure 6C. The video frame preview screen 601C contains the text "Happy New Year" and a fireworks pattern, which meets the requirements of the first prompt word.

[0186] In step 3053, multiple first frame images are arranged according to the generation order, and a first special effects animation is generated based on the arranged multiple first frame images.

[0187] For example, using an editing application, each first frame image is arranged according to a preset time interval based on the generation order to form the first special effects animation. Continuing to refer to Figure 6C, multiple video frames 603C are sorted on the timeline 604C according to the generation order to form the data for the first special effects animation. During the editing process, the user can view the video frame preview screen 601C to understand the specific content of the first special effects animation.

[0188] In this embodiment, users can generate first special effects animations through artificial intelligence functions, which can improve the efficiency of generating first special effects animations, customize different first special effects animations for each user, increase the richness of interactive processing, and improve the user experience.

[0189] In some embodiments, referring to FIG3C, which is a schematic diagram of the third flow of the interactive processing method provided in the embodiments of this application, before displaying the first special effects animation formed by editing, the following steps 3061 to 3064 are performed, which are described in detail below.

[0190] In step 3061, in response to a selection operation on information in the information flow interface, key elements are extracted from the selected information.

[0191] For example, extracting key elements from information refers to elements that represent the key content of the information. Key elements can be keywords or key images. Key elements can be determined in the following ways: by calling a deep learning model to perform feature extraction processing on the selected information to obtain information features, and then calling a deep learning model to perform image segmentation processing on the information features to obtain key images in the selected information; or by calling a deep learning model to perform semantic understanding processing on the information features to obtain keywords in the selected information.

[0192] For example, the process involves extracting the text content from the selected information, performing word segmentation and stop word removal; converting the processed text into a token sequence recognizable by the deep learning model, and generating text embedding vectors through the word embedding layer of the deep learning model; extracting the image content from the selected information, scaling the image size to the preset resolution of the deep learning model, and performing normalization to obtain an image tensor; concatenating the preprocessed text embedding vectors and the image tensor according to the format required by the deep learning model to form multimodal input data; inputting the multimodal input data into a fine-tuned Transformer multimodal model, performing self-attention calculation on the text embedding vectors to capture semantic relationships between the text; performing convolution and attention operations on the image tensor through an image encoder to extract visual features of the image; and finally, a multimodal fusion layer fuses text and image features through a cross-attention mechanism to generate information features of the selected information. The first step involves converting image-related visual feature vectors from information features into model-recognizable image feature tensors. These tensors are then input into a fine-tuned semantic segmentation model, where convolution and pooling operations further compress the features to capture global image semantics. Based on the decoder, upsampling restores the feature map resolution, and category prediction is performed for each pixel to generate a pixel-level semantic segmentation map. According to the category labels in the semantic segmentation map, object regions with an area ratio greater than a preset threshold and a relevance to the first information topic greater than a relevance threshold are selected. These selected object regions are then cropped from the original image to form independent image fragments, serving as key images in the selected information. The second step involves converting text-related semantic feature vectors from information features into model-recognizable text feature sequences. These text feature sequences are input into a fine-tuned semantic understanding model, where a multi-layer Transformer encoder performs self-attention calculations on the feature sequences, assigning semantic weights to each token. A fully connected layer and a softmax function then output the semantic importance score for each token. Tokens with importance scores greater than a threshold are selected as keywords in the selected information.

[0193] In step 3062, a pre-trained text generation model is invoked based on the key elements to perform text generation processing and obtain the second prompt word.

[0194] For example, in this embodiment of the application, a pre-trained text generation model is used to generate text based on text or images. Text generation models are a class of artificial intelligence models that can generate text based on given input (such as text prompts, context, or instructions). These models are typically based on deep learning techniques, especially recurrent neural networks (RNNs), long short-term memory networks (LSTMs), gated recurrent units (GRUs), and more recently, transformer architectures. Text generation models are widely used in various natural language processing tasks, including machine translation, content creation, chatbots, speech recognition, and text summarization. Text generation models extract features from key elements and decode the extracted features to form the corresponding text.

[0195] In step 3063, the pre-trained text-to-image model is invoked based on the second prompt word to perform image generation processing, resulting in multiple second frame images.

[0196] In some embodiments, a reference image is searched based on a second prompt word, and a pre-trained text-based image model is invoked to generate multiple second-frame images based on the reference image and the second prompt word. The image encoder built into the pre-trained text-based image model extracts features from the reference image to obtain a visual feature vector; the text encoder of the pre-trained text-based image model performs semantic analysis on the second prompt word to obtain a text semantic vector; the visual feature vector of the reference image and the text semantic vector of the second prompt word are fused to obtain a fused vector; the pre-trained text-based image model starts with a randomly noisy image and gradually denoises the image through multi-step diffusion iterations to generate an initial frame image that conforms to feature guidance; the pre-trained text-based image model differentiates the initial frame image by adjusting conditional parameters, presets a dynamic parameter sequence for the dynamic description in the second prompt word, and generates multiple second-frame images one by one according to the dynamic parameter sequence. The second prompt word search for reference images is based on searching the network using a search engine for the second prompt word, and the images with a high degree of matching with the second prompt word in the search results are used as reference images. The number of reference images can be one or more.

[0197] For example, the principle of the text-based image model to obtain the second frame image can be referred to in step 3052 above, and will not be repeated here.

[0198] In step 3064, multiple second frame images are arranged according to the generation order, and a first special effects animation is generated based on the arranged multiple second frame images.

[0199] In some embodiments, the editing application arranges each second frame image according to a preset time interval based on the generation order to form the first special effects animation. During animation compositing, the animation compositing function is invoked to composite the frame sequence into the first special effects animation according to the frame rate selected by the user. At the same time, inter-frame transition effects adapted to the scene are automatically added to avoid inter-frame gaps. After generation, the first special effects animation automatically plays in the animation preview window of the information flow interface. The first special effects animation can be associated with the selected information by clicking the save animation button, or the second prompt word can be adjusted and composited again by clicking the regenerate button.

[0200] For example, step 3064 can refer to step 3053 above, and will not be repeated here.

[0201] In this embodiment, by having the user select information from the information flow interface, key elements are obtained to generate a first special effects animation, enhancing the efficiency and frequency of interaction between the user and the information. Supporting users in generating the first special effects animation through artificial intelligence functions improves the efficiency of generating the first special effects animation, allows for customization of different first special effects animations for each user, increases the richness of interactive processing, and enhances the user experience.

[0202] Referring again to Figure 3A, in step 304, in response to the second triggering operation for the first special effects animation, the first special effects animation is played.

[0203] For example, the second trigger operation represents the completion of editing the first special effects animation and the operation of viewing the content of the first special effects animation. Playing the first special effects animation can be a local preview on the terminal device; or playing the first special effects animation can represent publishing the first special effects animation on the network, that is, sending the first special effects animation to a social network for users of the social network (e.g., all users, or followed users; in actual scenarios, it depends on the permission settings of different users).

[0204] In some embodiments, special effects animation serves as an extension of the content displayed in the primary information, enriching its content. For example, if the primary information is promotional information, the special effects animation could be a video showcasing the recommended content; or if the primary information is an original article published by a user, the special effects animation could be an animation explaining the principles behind that original article.

[0205] In some embodiments, step 304 may play the first special effects animation in any of the following ways:

[0206] Method 1: Play the first special effects animation in a floating window above the first information.

[0207] In some embodiments, the floating window has a semi-transparent and adjustable feature, and the transparency can be set to 90% when initially displayed to ensure that the animation content is clearly visible; the size can be adjusted by dragging the edge of the floating window, or by long-pressing and dragging the floating window to other positions above the first information; during playback, a close button can be displayed in the upper right corner of the floating window to stop playback and close the floating window; if the user does not actively close it, the floating window can be automatically hidden after the animation is completed, without affecting the subsequent information flow browsing.

[0208] For example, the area of ​​the floating window can cover the entire information feed interface or only a portion of it. Referring to Figure 5B, the second special effect animation 501B is displayed in the information feed interface 501A of Figure 5B. The display principle of the second special effect animation is the same as that of the first special effect animation; the second special effect animation will be used as a reference to explain the first special effect animation. The second special effect animation 501B is displayed in a floating window with transparency, which covers the entire information feed interface, and the content of the information feed interface can be displayed through the second special effect animation 501B.

[0209] Method 2: Play the first special effects animation in the pre-configured area of ​​the first information.

[0210] In some embodiments, the pre-configured area in the first information is a region specifically designed for playing dynamic content, fixed during information generation. This area is independently separated from the text and image areas of the first information. Common locations include the dynamic display bar at the top of the first information, the animation playback bar below the image area, and the sidebar to the right of the text area. The size and proportions of the pre-configured area are determined when the first information is created. During playback, the pre-configured area can fully adapt to the size and frame rate of the animation: the pre-configured area can play at the frame rate of the first special effects animation without stretching or compression; during animation playback, the play icon in the area will change to a pause icon, which the user can click to pause playback and click again to resume playback; after playback is complete, a replay icon will be displayed in the area, which the user can click to replay, satisfying the need for multiple viewings.

[0211] For example, the pre-configured area can be inside the first piece of information or the area surrounding the first piece of information. In practice, the display position of the first special effects animation can be configured according to the needs of the user or the advertiser.

[0212] Method 3: Play the first special effects animation in an interface other than the information flow interface.

[0213] In some embodiments, in response to a playback operation triggered on the feed interface, a seamless transition is made to other interfaces (such as a fade-in transition from the feed interface to the details page interface), and the animation playback is uninterrupted during the transition. If the transition is to the details page interface, the first special effects animation must play in the core display area of ​​the details page (such as the large image area at the top of the details page). If the transition is to the full-screen playback interface, the animation must fill the entire screen and support playback in both portrait and landscape orientations. Other interfaces must provide convenient entry points to return to the feed interface (such as a back button in the upper left corner of other interfaces or a feed icon in the bottom navigation bar). In response to a trigger operation on a convenient entry point, the user can directly return to the original position of the first piece of information in the feed interface, ensuring a smooth browsing flow.

[0214] For example, Method 3 differs from Method 1 and Method 2 mentioned above. Other interfaces can be the system interface, the first interactive interface, the chat interface, any interface in the current application other than the information flow interface, or the interface of other applications, etc.

[0215] In this embodiment, the first special effects animation is played in different ways, so that the first special effects animation can be adapted to various interfaces in the application, improving the convenience of editing the first special effects animation and the convenience of viewing the first special effects animation, thereby enhancing the user experience.

[0216] In some embodiments, after step 304, a sharing control is displayed in the first information; in response to a triggering operation on the sharing control, the first information carrying the first special effects animation is sent to the terminal device of the second object, wherein the second object is an object different from the first object browsing the information flow interface.

[0217] For example, in a real-world application scenario, the second object is an object that has a friend relationship with the first object using the information flow interface. The friend relationship can be a two-way friend relationship between the first object and the second object (that is, the first object and the second object have added each other as friends) or a one-way friend relationship (that is, only the first object has added the second object as a friend, and the second object has not added the first object as a friend).

[0218] This application embodiment strongly binds the display timing of the sharing control to the animation playback state, avoiding pop-up windows interfering with viewing and ensuring that users can quickly initiate sharing when they have just finished watching the animation and are at their most interested, without needing to search for a separate sharing entry point. This makes the interaction process more seamless, reduces user interruption, and improves the overall interactive experience. Users can quickly share the first information carrying the first special effects animation through the sharing control without any learning, reducing operational complexity and thus increasing the willingness to participate in sharing. Compared to purely static first information, first information carrying the first special effects animation has a dynamic visual advantage when shared with a second object, allowing the second object to more intuitively perceive the theme of the first information through the playback of the animation, improving the transmission effect of the first information.

[0219] In some embodiments, sending the first information carrying the first special effects animation to the terminal device of the second object is achieved by: sending the first information to the terminal device of the second object in any of the following ways:

[0220] Method 1: Publish the second information in the information flow interface of the second object.

[0221] In some embodiments, the second information, as forwarded information generated based on the first information and the first special effects animation, must fully retain the core content (text, images) of the first information and all data (frame sequence, playback parameters) of the first special effects animation. The second information can be directly pushed to the information flow interface of the second object, and the push position conforms to the conventional sorting rules of the information flow (such as inserting the latest position according to the publication time), without creating a separate special section; when the second information is displayed in the information flow of the second object, it maintains the same interface style as other native information, distinguished only by the forwarding identifier, and the playback triggering method of the first special effects animation (such as clicking the play button) is also consistent with the animation playback logic of the native information, ensuring that there is no cognitive cost for operating the second object.

[0222] For example, the second information is forwarding information generated based on the first information and the first special effects animation, and the second information is used for browsing by the second object.

[0223] Method 2: Display the object name of the second object and the pointer associated with the object name in the first information.

[0224] For example, the pointer symbol indicates that a notification message for sharing the message has been sent to the terminal device of the second object. This notification message is displayed in the notification list of the information flow interface corresponding to the second object. The pointer symbol is also the email application symbol (@). The notification message corresponding to the shared content is displayed in the notification list of the second object's information flow interface. For example, the notification list may display "Who is @ing me," where "who" refers to the first object and "me" refers to the second object. When the second object triggers this notification message, the current interface switches to the information flow interface, and the screen of the switched information flow interface includes the shared first message and the first special effect animation.

[0225] Method 3: Display the shared information in the chat interface corresponding to the second person.

[0226] In some embodiments, the shared information includes a core content summary of the first information (such as a text summary or image thumbnail), a preview entry point for the first special effects animation (such as a play animation button), and a sharing identifier for the first object (such as an account avatar or nickname). The interface style must be consistent with regular messages in the chat interface (such as text messages or image messages), blending seamlessly into the chat context. The shared information can be sent directly to the chat interface between the first and second objects, with the interaction record inserted in chronological order of sending. After the second object sees the shared information in the chat interface, clicking the play animation button allows the first special effects animation to be played directly within the chat interface via a floating window or pop-up, without needing to switch to the information stream interface, ensuring convenient viewing. After playback, the shared information remains in the interaction record, and the second object can click to play again or reply to the first object.

[0227] For example, the chat interface corresponding to the second object is the chat interface between the first object's first account and the second object's second account.

[0228] This application embodiment publishes the second information (forwarded information) generated based on the first information and the first special effects animation on the second object's information flow interface; displays the second object's name and associated pointing symbol in the first information to send a prompt message to the second object's prompt message list; and displays the shared information in the chat interface corresponding to the second object. These three methods correspond to three different scenarios: information flow display, prompt message reminder, and chat interface presentation. The first object can choose according to its needs, ensuring that information can reach the second object in different forms and improving the flexibility of information delivery.

[0229] In some embodiments, when there are multiple second objects and multiple first special effects animations, before sending the first information carrying the first special effects animation to the terminal device of the second object, the target first special effects animation carried by each piece of first information is determined by at least one of the following methods:

[0230] Method 1: In response to a selection operation for any first special effect animation, the selected first special effect animation is used as the target first special effect animation, wherein each first information carries the same target first special effect animation.

[0231] Here, when multiple first-effect animations exist, all first-effect animations can be displayed together as thumbnails or preview videos. A selection button is shown next to each first-effect animation, allowing the first target to perform a selection operation. In response to a selection button action next to any first-effect animation, the selected first-effect animation is marked as the target first-effect animation, and a prompt "'XX animation' has been selected as the target animation for sharing information" is displayed on the interface.

[0232] Method 2: When the number of first special effects animations is greater than the number of second objects, determine the target first special effects animation corresponding to each piece of first information according to the mapping relationship between the editing order and the object selection order. Here, the editing order is the editing order of the first special effects animations, and the object selection order is the order in which the second objects are selected.

[0233] In some embodiments, the editing order is the chronological order in which the first object creates the first special effects animation; the object selection order is the order in which the first object selects the second object when sharing. When the number of first special effects animations is greater than the number of second objects, a mapping relationship is automatically established between the editing order and the object selection order of the same sequence. That is, the animation in the first position of the editing order corresponds to the second object in the first position of the object selection order, the animation in the second position of the editing order corresponds to the second object in the second position of the object selection order, and the remaining unmapped first special effects animations are not used for the time being.

[0234] For example, the second completed animation is sent to the terminal device of the second selected friend.

[0235] Method 3: When the number of first special effects animations is less than the number of second objects, extract the target first special effects animation carried by each first information from multiple first special effects animations.

[0236] In some embodiments, when the number of first special effects animations is less than the number of second objects, a target first special effects animation is assigned to each second object from the first information corresponding to the multiple first special effects animations using either cyclic extraction or random extraction. If cyclic extraction is selected, the first special effects animations are assigned cyclically according to their editing order; if random extraction is selected, a target first special effects animation is randomly assigned to each second object from all the first special effects animations using a random algorithm.

[0237] For example, if the number of first effect animations completed is less than the number of friends who share it, a first effect animation is randomly assigned to each friend.

[0238] This application's embodiments cover different scenarios involving combinations of multiple first special effects animations and multiple second objects, avoiding issues such as chaotic animation allocation or some objects lacking animation, ensuring that each piece of first information has a clearly defined target first special effects animation. There's no need for the first object to select a target animation individually for each second object; all allocations are completed through a single selection, automatic mapping, and automatic extraction, reducing repetitive operations. A unified selection method satisfies the first object's desire for all second objects to receive the same animation, while sequential mapping and extraction methods satisfy the desire for differentiated animation allocations. Both requirements can be achieved through corresponding methods, balancing uniformity and diversity, and improving the flexibility of sharing operations.

[0239] In some embodiments, when there are multiple second objects and multiple first special effects animations, before sending the first information carrying the first special effects animation to the terminal device of the second object, the first special effects animation corresponding to each second object is determined in the following manner:

[0240] The deep learning model is invoked to extract features from each second object, resulting in second object features. The deep learning model is trained using sample object data and sample special effects animation data. The deep learning model is then invoked to extract features from each first special effects animation, resulting in animation features. The third similarity between each second object feature and each animation feature is determined. For the first information to be sent for each second object, the first special effects animation corresponding to the maximum third similarity of the second object features is used as the target first special effects animation carried in the first information to be sent.

[0241] For example, the third similarity can be cosine similarity. During the training of a deep learning model, sample object data and sample effect animation data constitute sample pairs. Each sample pair includes sample account data of a sample object and sample animation data of a sample effect animation. The label of each sample pair is 1 or 0. A label value of 1 indicates that the similarity between the sample object and the sample effect animation included in each sample pair is greater than a threshold. Conversely, a label value of 0 indicates that the similarity between the sample object and the sample effect animation included in each sample pair is less than or equal to the threshold.

[0242] This application's embodiments allocate target animations based on a third similarity between the features of the second object and the animation features. This ensures that the animation received by each second object highly matches its own preferences. Compared to uniform or random allocation, this is more likely to attract the attention of the second object and increase its willingness to receive and watch. From feature extraction and third similarity calculation to the determination of the target first special effects animation, the entire process is automatically completed by a deep learning model. The first object does not need to manually select an animation for each second object, nor does it need to analyze object preferences; it only needs to confirm the allocation list, reducing operational steps and decision-making difficulty, and improving sharing efficiency. The deep learning model is trained through massive sample object and sample animation data, possessing the ability to accurately capture the correlation between object preferences and animation features. The calculated third similarity can truly reflect the degree of matching, avoiding the problem of animations not matching object preferences due to subjective judgment errors during manual allocation, thus improving the accuracy of target animation allocation.

[0243] In some embodiments, the shared first information is used to enable the terminal device of the second object to perform the following processes: displaying the first information, wherein the first information includes a first interactive control; displaying a third special effects animation in the first information in response to a trigger operation on the first interactive control; and sending the first information carrying the third special effects animation to the terminal device of the third object in response to a trigger operation on the sharing control in the first information, wherein the third object is a different object from the first object and the second object.

[0244] For example, the third special effect animation can be an effect animation edited by the first object or other objects, or it can be a pre-configured effect animation for promotional information. The third object can be an object that has a friend relationship with the second object. The third object and the first object may or may not have a friend relationship. When the first information is displayed on the third object's terminal device, if the first object and the third object have a friend relationship, the first special effect animation edited by the first object can be displayed in the first information on the third object's terminal device. If the first object and the third object do not have a friend relationship, the third object's terminal device does not have viewing permissions for the first special effect animation, and the first special effect animation edited by the first object will not be displayed in the first information on the third object's terminal device.

[0245] In this embodiment, users' terminal devices can share the special effects animations obtained from the interactive processing, forming an interactive chain that enhances the fun of the interactive processing and user participation.

[0246] In some embodiments, the shared first information is used to enable the terminal device of the second object to perform the following processes: displaying the first information, wherein the first information includes a first interactive control; displaying a second interactive interface in response to a trigger operation on the first interactive control; displaying a fourth special effects animation formed by editing in response to a second editing operation on the second interactive interface; and sending the first information carrying the fourth special effects animation to the terminal device of the third object in response to a trigger operation on the sharing control in the first information, wherein the third object is a different object from the first object and the second object.

[0247] For example, when the first information is displayed on the terminal device of the second object, the second object can perform corresponding editing operations based on the first information to form a customized fourth special effect animation. The second object can also send the edited fourth special effect animation to the terminal devices of other objects. That is, after the first user shares the special effect animation and the first information with other users, other users can share it again based on the received information, forming an interactive chain.

[0248] This application embodiment allows the first information and special effects animation to be continuously propagated among multiple objects, expanding the coverage. A second object can generate a personalized fourth special effects animation based on the animation shared by the first object through a second editing operation, enriching the expression of the first information. Subsequent third objects can continue to iterate and edit, continuously injecting new content into the information and animation effects as more sharing objects are added, enhancing the richness and attractiveness of the information.

[0249] In some embodiments, when the first information is promotional information, the first information is used to enable the terminal device of the second object to perform the following processes: displaying the promotional information, wherein the first information includes the first interactive control; in response to a trigger operation on the first interactive control, displaying a third special effects animation containing a first recommended material and a second interactive interface, wherein the first recommended material is related to the promotional information; in response to a second editing operation in the second interactive interface, displaying an edited fourth special effects animation containing a second recommended material, wherein the second recommended material is related to the promotional information.

[0250] For example, promotional information refers to relevant items or content provided to users through a recommendation system, such as advertising information recommended by an advertising recommendation system. The current user's account forwards the promotional information to a social media platform or sends it to another user's (second target's) chat interface. The other user receives the promotional information through a second terminal device and, after triggering interactive controls, displays a third special effect animation carrying recommended materials, a second interactive interface, and can edit a fourth special effect animation carrying recommended materials through the second interactive interface. The first and second recommended materials can be the same or different.

[0251] For example, during the editing of special effects animation, the screen displayed on the terminal device of the second object is similar to the screen displayed on the terminal device of the first object. Please refer to the explanation of steps 301 to 304 above, which will not be repeated here.

[0252] In this embodiment, by forwarding promotional information carrying recommended materials to other users, and allowing other users to edit special effects animations carrying recommended materials through the interactive interface, the dissemination methods of promotional information are enriched, as are the forms of interaction between promotional information and users. This creates an interactive chain between promotional information and users through user forwarding, improving the efficiency of promotional information dissemination. Through user interaction with promotional information, the exposure time of the promotional information is increased, enhancing user interest and thus improving the recommendation effect of the promotional information.

[0253] In some embodiments, this application also proposes an interactive processing method. Referring to FIG3D, FIG3D is a fourth flowchart of the interactive processing method provided in the embodiments of this application, and will be described in conjunction with the steps shown in FIG3D. The executing entity of the steps in FIG3A is the terminal device 400 in FIG1A.

[0254] In step 307, the first information is displayed in the information flow interface.

[0255] Here, the first information includes the first interactive control and the free area.

[0256] For example, the first piece of information is promotional information that does not display recommended content, and the empty area in the first piece of information is used to play special effects animations. The principle of displaying the first interactive control in the first piece of information in step 307 can be referred to step 301, and will not be repeated here.

[0257] In step 308, in response to a first trigger operation on the first interactive control, a first special effects animation carrying recommended material is displayed in the free area.

[0258] For example, the first special effects animation can be pre-configured based on the content of the first information and embedded in the first information for display. For instance, the first special effects animation is an advertising video placed by an advertiser, and the advertising materials carried by the first special effects animation can be generated by artificial intelligence based on the first information or manually edited and configured.

[0259] In this embodiment, a first piece of information, including a first interactive control, is displayed in the information flow interface. The first interactive control can trigger a first interactive interface for editing special effects animations. By embedding animation editing functionality into the information flow interface, the interactive forms of the information flow interface are enriched, enabling users to create and share dynamic content, thereby enhancing the interactivity and fun of information exchange and improving the user experience. In response to a second trigger operation on the first special effects animation, the first special effects animation is played. The first special effects animation is displayed in the first piece of information in the information flow interface, allowing the edited special effects animation to be displayed instantly in the information flow, making information transmission more intuitive. By directly integrating editing functionality into the information flow interface, editing and sending special effects animations can be done without jumping to other applications or interfaces, simplifying the user's operation process and improving interaction efficiency.

[0260] The following will describe an exemplary application of the interactive processing method of this application in a real-world application scenario.

[0261] An information stream interface (SMI) is a user interface design that displays continuous information content in chronological order or according to user-specified rules. It is commonly found in social media applications, news apps, instant messaging software, and other services that require dynamically updated content. With the widespread adoption of social networking platforms, the ways users interact are constantly evolving. Traditional interaction methods such as likes and comments are no longer sufficient to meet users' growing interactive needs.

[0262] Taking the information flow interface of social platforms as an example, the current interactive methods in the information flow interface have the following problems: (1) The interactive methods are monotonous. The types of interactive methods on social networking platforms include: likes, comments and forwards. Although these interactive methods are simple and easy to use, they lack novelty and appeal, and it is difficult to stimulate users' continuous interactive interest. (2) The monotonous interactive methods make it difficult to better represent users' emotions. The interactive methods of related technologies are relatively simple in terms of emotional expression. Users find it difficult to fully express their emotions and blessings through simple likes or comments, especially on some special holidays or important moments, when users hope to have richer ways to express their emotions. (3) The interactive depth is insufficient. The interactive methods of related technologies are mostly one-way interactions, and the interactive depth between users is insufficient, making it difficult to form a continuous interactive chain. (4) The visual appeal is insufficient. The interactive methods of related technologies are relatively monotonous in terms of visual effects and lack appeal, making it difficult to attract users' attention and participation. Users tend to ignore these interactive elements when browsing dynamics.

[0263] To address the aforementioned problems in related technologies, the interactive processing method provided in this application, in an information flow interface (e.g., the information flow interface of a social platform), responds to a click operation on an interactive control (i.e., the first interactive control) and displays an interactive interface (i.e., the first interactive interface). The interactive interface allows users to freely customize special effects animations (e.g., fireworks animations). The special effects animation (i.e., the first special effects animation) is displayed in the information flow interface and then shared with other users after the special effects animation is displayed, thereby enhancing the user's interactive experience and increasing the frequency and depth of interaction between users.

[0264] Referring to Figure 4, which is a fifth flowchart of the interactive processing method provided in the embodiments of this application, the interactive processing method provided in the embodiments of this application will be explained below with reference to the steps in Figure 4. Figure 4 uses the terminal device 400 in Figure 1A or Figure 1B as the execution subject.

[0265] In step 401, the first information containing the first interactive control is displayed in the information flow interface.

[0266] For example, the information feed interface displays multiple pieces of information. The type of the first piece of information includes, but is not limited to, promotional information and user-posted dynamic information. This application embodiment uses the information feed interface of a social platform as an example for illustration. The first piece of information can be promotional information provided by an advertiser. In response to the opening operation of an instant messaging application, the information feed interface is triggered, and the promotional information is displayed in the information feed interface. The promotional information displays a first interactive control. Within a preset distance of the first interactive control, the number of users who have interacted with the first interactive control, the function of the first interactive control, and the interaction results related to the function corresponding to the first interactive control can also be displayed.

[0267] Referring to Figure 5A, which is a first schematic diagram of the human-computer interaction interface provided in this embodiment of the application; the information flow interface 501A includes first information 502A, first interactive control 503A, and prompt information 504A. First information 502A is promotional information published by the advertiser. The first interactive control 503A displays the text "Light the fireworks" to prompt the user to interact. Prompt information 504A includes the name of the user who has already performed the interaction. Content such as "Joyful" and "May all your wishes come true" are from the already generated special effects animation.

[0268] In step 402, in response to a trigger operation on the first interactive control, a special effects animation is displayed in the information flow interface.

[0269] For example, the triggering operation can be a long press, a click, a double-click, etc., and this application embodiment does not limit this. When the first information is a share from the current user's friend, in response to a click on the first interactive control, a special effect animation created by the friend is displayed; if the current promotional information is not content shared by the user's friend, in response to a click on the first interactive control, the interface switches from the information flow interface to the editing interface. The location where the special effect animation is displayed can be a relevant location of the first information (e.g., displayed as a floating window above the first information, within the first information, or in an area adjacent to the first information).

[0270] In some embodiments, the special effects animation may be played continuously. Alternatively, while displaying the special effects animation, a repeating interactive control may be displayed. In response to a trigger operation on the repeating interactive control, a special effects animation that is the same as or different from the already displayed special effects animation may be displayed. Referring to FIG5B, FIG5B is a second schematic diagram of a human-computer interaction interface provided in an embodiment of this application; the information flow interface 501A displays a second special effects animation 501B. Continuing with the example above, the first information is promotional information published by an advertiser, and the second special effects animation 501B is a pre-configured special effects animation. In some embodiments, the second special effects animation 501B may also include recommended materials.

[0271] In step 403, the first interactive interface is displayed.

[0272] For example, the first interactive interface is used to edit special effects animation styles; it can also be called the editing interface. The first interactive interface includes various pre-configured special effects animation templates, input controls, and a send control. Input controls are used to input text, audio, voice, images, or video. The pre-configured special effects animation templates are for the user to select, and the user's customized content is filled into the selected template to create the edited special effects animation. The send control is used to trigger the function of publishing the special effects animation in the news feed interface, or to trigger the function of displaying the special effects animation as the first message in the news feed interface. Triggering the send control also indicates that the user has completed editing the special effects animation. The first interactive interface will be explained in detail in the following steps.

[0273] In step 404, in response to an editing operation on the first interactive interface, a preview of the special effects animation generated by the editing operation is displayed.

[0274] For example, during the editing process, the first interactive interface displays a special effect animation of fireworks as an example. Users can select the corresponding style from a variety of fireworks effect templates in this editing interface.

[0275] Exemplarily, in response to a selection operation on a template for special effect animation, content such as text and pictures can be added through an input control. Continuing with the example of the fireworks special effect mentioned above, for example: blessing text is added through the input control. The blessing text is used to be displayed in the special effect animation, and users can increase the emotional expression of interaction through the blessing text. The blessing text can be pre-set or edited by the user himself.

[0276] Referring to FIG. 6A, FIG. 6A is a fourth schematic diagram of the human-computer interaction interface provided by an embodiment of the present application; the content displayed in the first interaction interface 601A includes special effect animation templates (for example: templates 1 to 3), preview information 603A, reference animation 604A, input control 602A, and send control 606A. The input control 602A is used to input text, audio, voice, image or video. The send control 606A is used to receive a second trigger operation. The reference animation 604A is a special effect animation edited and completed by other users. The preview information 603A is a picture formed based on the editing operation. For example: the current editing operation includes: selecting template 2 and inputting the text "overjoyed", then the corresponding picture is presented in the preview information 603A.

[0277] In step 405, in response to a second trigger operation on the special effect animation, the edited special effect animation is displayed in the information flow interface.

[0278] Exemplarily, the second trigger operation refers to an operation of publishing the special effect animation to the information flow interface for the current user and other users to watch.

[0279] Continuing to refer to FIG. 5B, FIG. 5B shows the picture of the special effect animation displayed in the information flow interface. In some embodiments, in addition to the form shown in FIG. 5B, the special effect animation can also be displayed in an area inside the first information and with a distance from the first information less than the distance threshold.

[0280] In step 406, a sharing control is displayed in the first information. In response to a trigger operation on the sharing control, the first information and the edited special effect animation are sent to the terminal device of the second object.

[0281] Exemplarily, the second object refers to a friend of the current user. After the edited special effect animation is displayed in the information flow interface, the state of the first interaction control is switched to the edited state, and a sharing control is displayed in the first information. The position of the sharing control can be at the bottom, top or next to the first interaction control of the first information.

[0282] Referring to Figure 5C, which is a third schematic diagram of the human-computer interaction interface provided in this application embodiment; compared to Figure 5A, the content of the first interactive control 503A in Figure 5C is updated to "Fireworks have been set off", indicating that the user has performed the interactive process, specifically, the user has at least performed the process of triggering the first interactive control 503A. Also, compared to Figure 5A, Figure 5C displays a sharing control 501C. Since the data generated during the playback of the special effects animation has been stored in the background, sharing information can be generated based on the first information and the played special effects animation. In response to the trigger operation of the sharing control 501C, the sharing information is sent to the terminal devices of other users.

[0283] For example, during the sharing process, in response to a trigger operation on the sharing control, a friend list is displayed. In response to a selection operation on a friend in the friend list, the first information and the edited special effects animation are sent to the terminal device of the second object. That is, the user selects the friend they want to share with and clicks to send it to the corresponding friend's terminal device. In some embodiments, multiple friends can be selected during the friend selection process to send the first information and the edited special effects animation to multiple friends in batches. In a specific implementation, assuming the special effects animation is a fireworks special effects animation, the fireworks and blessing content sent to each friend can be the same, or the current user has edited multiple special effects animations, and the special effects animation sent to each friend is different, or different special effects animations are randomly selected from the fireworks and blessing messages filled in by the user and sent to different friends.

[0284] In some embodiments, after the first sharing operation is completed, the first object can continue to perform the sharing operation, or switch the current interface back to the information feed interface to continue browsing other content in the information feed interface.

[0285] In some embodiments, the terminal device stores user interaction data regarding special effects animations within the interactive interface. This interaction data includes: the user's selected special effects animation template, content entered by the user for the selected template (e.g., text, audio, images, or video), and records of the user's first messages shared with other users. Simultaneously, the terminal device also sends this interaction data to a server for storage. The server can update existing special effects animation templates or optimize the functionality of the interactive interface based on this data.

[0286] For example, the interaction process data in this application embodiment is obtained with user authorization.

[0287] In this embodiment, interaction process data is stored. This data represents the user's choices and inputs. By analyzing these choices and inputs, user preferences can be understood, leading to personalized content recommendations and improved user experience. Special effects animation templates can be optimized and improved based on the user's historical interaction data to better meet user needs.

[0288] In step 407, a prompt message for sharing information is displayed, and in response to a trigger operation on the prompt message, information containing the first interactive control is displayed in the information flow interface.

[0289] For example, step 407 can be performed by the terminal device of the second object. When the terminal device of the second object receives a prompt message from the information flow interface or the chat window, in response to the trigger operation for the raised information (i.e., the trigger operation to view), the information containing the first interactive control is displayed in the information flow interface of the terminal device of the second object. The screen presented by the information flow interface of the terminal device of the second object can be referred to Figure 5A above, and its principle is the same as that of the information flow interface presented in the terminal device of the first object. The information containing the first interactive control is also known as the first information, which is shared by other users in step 407.

[0290] In step 408, in response to a trigger operation on the first interactive control, a special effects animation indicating that the first object has been edited is displayed.

[0291] For example, the first object to be edited is the user who edited the special effects animation. The user can share the edited special effects animation with a notification message sent to a friend's device via an email identifier and user ID in the feed interface. After receiving the sharing notification, the friend's device can view the shared message in their own feed interface, edit the special effects animation again within that message, and then share the special effects animation to their own feed interface for other friends to view, forming an interactive chain. Referring to comment area 505A in Figure 5A, the comments in the comment area include "User N: @User 3, let's set off fireworks!" and "User 3: @User 4, let's set off fireworks!", representing that the sharing between users forms an interactive chain.

[0292] For example, a friend of the first person sees the shared special effects animation in their own feed. They can edit other special effects animations to create customized content special effects animations, and then share the customized content special effects animations to their own feed for other users to watch, thus forming an interactive chain.

[0293] In some embodiments, special effects animations edited by friends are displayed in the first message of the current user's feed interface. For example, a user can see a friend's blessing in the message of a shared special effects animation. User A edits a special effects animation and shares it to User B's chat interface. User B receives the sharing message and shares the special effects animation edited by User B to their own feed interface for friend User C to view. If User C is a friend of User A, then User C can see the special effects animations shared by both User A and User B in User B's shared message. If User C is not a friend of User A, then User C can only see the special effects animation shared by User B.

[0294] In some embodiments, if the first information is not information shared by other objects, after step 401, in response to a trigger operation on the first interactive control, the first interactive interface is directly displayed. Alternatively, if the first information is promotional information (e.g., information provided by an advertiser with recommended creative materials), in response to a trigger operation on the first interactive control, a pre-configured special effects animation with recommended creative materials is displayed.

[0295] The interactive processing method provided in this application has the following effects:

[0296] (1) The interactive forms are enriched. By adding the first interactive control to the information flow interface, users can select different special effects animation templates to edit and share the edited special effects animations, which increases the diversity and novelty of the interactive methods and stimulates users' interest in interaction. Users can express their emotions and blessings more fully through the edited special effects animations, which is especially suitable for special occasions such as festivals and birthdays, and enhances the user's interactive experience.

[0297] (2) Increased interaction frequency and depth: The interactive sharing function in this embodiment allows users to share edited special effects animations with friends, who can then edit the animations in their own feed, forming an interactive chain. This not only increases the frequency of interaction between users but also enhances the depth of interaction, promoting continuous interaction between users. Furthermore, through novel interactive methods and deep interactive chains, the user's interactive experience in the feed interface is improved, thereby increasing the user's interest in performing interactive processing.

[0298] (3) Enhancing the visual appeal of interactive processing: This application embodiment increases the visual appeal of interactive methods through the display of special effects animation. The fireworks effect can change according to the style selected by the user, increasing visual diversity and appeal, attracting the user's attention and interest in participation. The special effects animation not only increases visual impact, but also provides users with a better visual experience when browsing the information flow interface, improving the overall user experience.

[0299] (4) Enhancing the participation in interactive processing: Through the interactive sharing mechanism, users can share special effects animations with friends. After receiving the share, friends can edit the special effects animations in their own information flow interface, forming an interactive chain. This interactive sharing mechanism improves user participation and interaction enthusiasm. Interactive sharing between users not only increases individual participation but also expands the scope of interaction through social dissemination effects, attracting more users to participate in the interaction and improving overall user participation.

[0300] (5) By recording users' editing and sharing processes for special effects animations, the server can obtain more data records. This data can be used to analyze user interests and preferences, optimize the platform's recommendation algorithm and user experience, improve the accuracy of the recommendation algorithm, and enhance the recommendation effect.

[0301] In summary, the embodiments of this application have produced significant beneficial effects by providing novel interactive methods, enhancing emotional expression, increasing the depth and frequency of interaction, improving visual appeal, and increasing user engagement, and have broad application prospects.

[0302] The following continues to describe an exemplary structure of the interactive processing device 455 provided in the embodiments of this application as a software module. In some embodiments, as shown in FIG2, the software module stored in the interactive processing device 455 in the memory 450 may include:

[0303] Display module 4551 is configured to display first information in an information flow interface, wherein the first information includes a first interactive control; display module 4551 is further configured to display a first interactive interface in response to a first trigger operation on the first interactive control, wherein the first interactive interface is used for editing special effects animation; display module 4551 is further configured to display a first special effects animation created by editing in response to a first editing operation on the first interactive interface. Display module 4551 is further configured to play the first special effects animation in response to a second trigger operation on the first special effects animation.

[0304] In some embodiments, the display module 4551 is further configured to display a second special effects animation in the first information before displaying the first interactive interface, wherein the second special effects animation is different from the first special effects animation, and the second special effects animation is any of the following types of special effects animation: a special effects animation pre-configured for the first information, a special effects animation edited by a second object, and the second object is an object different from the first object browsing the information flow interface.

[0305] In some embodiments, the display module 4551 is further configured to display the special effects animation edited by the second object in the first information when the first information is information published by the second object; and to display the pre-configured special effects animation in the first information when the first information is not information published by the second object.

[0306] In some embodiments, the display module 4551 is further configured to display the second special effect animation in any of the following ways: displaying at least one of the second special effect animations, wherein when there are multiple second special effect animations, at least some of the second special effect animations are played in an overlay manner, and the key elements of each second special effect animation are exposed; displaying multiple second special effect animations one by one, wherein each second special effect animation has different content, wherein the order is based on at least one of the following factors: publication time, user interest level, relevance to the first information, and interaction frequency; displaying one second special effect animation and a second interactive control, and switching to displaying another second special effect animation in response to a trigger operation on the second interactive control.

[0307] In some embodiments, the display module 4551 is further configured such that at least a portion of the second special effects animation played in an overlay manner is presented in any of the following ways: the second special effects animation located in the upper layer has transparency, and the second special effects animation located in the lower layer is revealed through the upper layer; the frames of other second special effects animations are embedded in the frame of one second special effects animation, wherein the area of ​​the frames of the other second special effects animations is smaller than the area of ​​the frame of the second special effects animation; multiple second special effects animations are dynamically switched or merged according to specific rules.

[0308] In some embodiments, the type of the first editing operation includes: a selection operation; the display module 4551 is further configured to display a plurality of first animation templates in the first interactive interface; in response to a selection operation for any one of the first animation templates, displaying a first special effects animation generated according to a target animation template, wherein the target animation template is the selected first animation template.

[0309] In some embodiments, the first information is promotional information, and each first animation template includes recommended materials related to the promotional information; the display module 4551 is further configured to display a first special effects animation generated based on the target animation template and including the recommended materials.

[0310] In some embodiments, the data processing module 4551 is further configured to determine the first animation template by at least one of the following methods before the first special effects animation is formed by the display editing:

[0311] The second animation template selected by the second account is used as the first animation template, wherein the second account is an object with a social relationship with the first account browsing the information flow interface; the animation template with the most selections is used as the first animation template; a first similarity is determined between the information features of the first information and the semantic features of the candidate animation templates, and the candidate animation template with the highest first similarity is used as the first animation template; a second similarity is determined between the first account features of the first account and the semantic features of the candidate animation templates, and the candidate animation template with the highest second similarity is used as the first animation template.

[0312] In some embodiments, the display module 4551 is further configured to, in response to an input operation on the first interactive interface, display a first prompt word before the first special effects animation is formed by the display editing; search for a reference image based on the first prompt word, and generate a plurality of first frame images by calling a pre-trained text-to-image model based on the reference image and the prompt word; arrange the plurality of first frame images according to the generation order, and generate the first special effects animation based on the arranged plurality of first frame images.

[0313] In some embodiments, the display module 4551 is further configured to, before the first special effects animation formed by the display editing, extract key elements from the selected information in response to a selection operation on information in the information flow interface; perform text generation processing by calling a pre-trained text generation model based on the key elements to obtain a second prompt word; perform image generation processing by calling a pre-trained text-to-image model based on the second prompt word to obtain a plurality of second frame images; arrange the plurality of second frame images according to the generation order, and generate the first special effects animation based on the arranged plurality of second frame images.

[0314] In some embodiments, the key element includes at least one of keywords and key images. The display module 4551 is further configured to determine the key element by at least one of the following methods: calling a pre-trained deep learning model to extract features from the selected information to obtain information features; calling the deep learning model to perform image segmentation processing on the information features to obtain the key image in the selected information; and calling the deep learning model to perform semantic understanding processing on the information features to obtain the keywords in the selected information.

[0315] In some embodiments, the first editing operation further includes an input operation; the display module 4551 is further configured to display an input control on the first interactive interface; in response to an input operation on the input control, the input content corresponding to the input operation is played in the first special effects animation, wherein the type of the input content includes: text, image, audio and video.

[0316] In some embodiments, the display module 4551 is further configured to display preview information of the edited first special effects animation, wherein the preview information is information for displaying the first special effects animation, and the preview information includes at least one of the following: a scene in the first special effects animation, and keyframes in the first special effects animation.

[0317] In some embodiments, the display module 4551 is further configured to play the first special effects animation in any of the following ways:

[0318] The first special effects animation is played as a floating window above the first information; the first special effects animation is played in the pre-configured area of ​​the first information; and the first special effects animation is played in other interfaces outside the information flow interface.

[0319] In some embodiments, the display module 4551 is further configured to display a sharing control in the first information after playing the first special effects animation; and to send the first information carrying the first special effects animation to a terminal device of a second object in response to a trigger operation on the sharing control, wherein the second object is a different object from the first object browsing the information flow interface.

[0320] In some embodiments, the display module 4551 is configured to send the first information to the terminal device of the second object in any of the following ways: publishing the second information in the information flow interface of the second object, wherein the second information is forwarding information generated based on the first information and the first special effects animation; displaying the object name of the second object and a pointer symbol associated with the object name in the first information, wherein the pointer symbol represents sending a prompt message for the shared message to the terminal device of the second object, and the prompt message is used to display in the prompt message list of the information flow interface corresponding to the second object; and displaying the shared information in the chat interface corresponding to the second object.

[0321] In some embodiments, the display module 4551 is further configured to, when there are multiple second objects and multiple first special effects animations, before sending the first information carrying the first special effects animation to the terminal device of the second object, determine the target first special effects animation carried by each piece of first information in at least one of the following ways: in response to a selection operation for any one of the first special effects animations, the selected first special effects animation is taken as the target first special effects animation, wherein the target first special effects animation carried by each piece of first information is the same; when the number of first special effects animations is greater than the number of second objects, determine the target first special effects animation corresponding to each piece of first information according to the mapping relationship between the editing order and the object selection order, wherein the editing order is the editing order of the first special effects animations, and the object selection order is the order in which the second objects are selected; when the number of first special effects animations is less than the number of second objects, extract the target first special effects animation carried by each piece of first information from the multiple first special effects animations.

[0322] In some embodiments, the display module 4551 is further configured to, when there are multiple second objects and multiple first special effects animations, before sending the first information carrying the first special effects animation to the terminal device of the second object, call a deep learning model to extract features from each second object to obtain second object features, wherein the deep learning model is trained using sample object data and sample special effects animation data; call the deep learning model to extract features from each first special effects animation to obtain animation features; determine a third similarity between each second object feature and each animation feature; and for each first information to be sent of the second object, use the first special effects animation corresponding to the maximum third similarity of the second object features as the target first special effects animation carried by the first information to be sent.

[0323] In some embodiments, the first information is used to enable the terminal device of the second object to perform the following processes: displaying the first information, wherein the first information includes the first interactive control; displaying a third special effects animation in the first information in response to a trigger operation on the first interactive control; and sending the first information carrying the third special effects animation to the terminal device of the third object in response to a trigger operation on the sharing control in the first information, wherein the third object is a different object from the first object and the second object.

[0324] In some embodiments, the first information is used to enable the terminal device of the second object to perform the following processes: displaying the first information, wherein the first information includes the first interactive control; displaying a second interactive interface in response to a trigger operation on the first interactive control; displaying a fourth special effects animation formed by editing in response to a second editing operation in the second interactive interface; and sending the first information carrying the fourth special effects animation to the terminal device of a third object in response to a trigger operation on the sharing control in the first information, wherein the third object is a different object from the first object and the second object.

[0325] In some embodiments, when the first information is promotional information, the first information is used to enable the terminal device of the second object to perform the following processes: displaying the promotional information, wherein the first information includes the first interactive control; in response to a trigger operation on the first interactive control, displaying a third special effects animation containing a first recommended material and a second interactive interface, wherein the first recommended material is related to the promotional information; in response to a second editing operation in the second interactive interface, displaying an edited fourth special effects animation containing a second recommended material, wherein the second recommended material is related to the promotional information.

[0326] In some embodiments, the display module 4551 is further configured to display at least one parameter associated with the first interactive control in the first information: a prompt message for the function of the first interactive control, the number of objects performing interactive processing on the first interactive control, and the text content contained in the first special effects animation.

[0327] In some embodiments, this application also proposes an interactive processing device, including: a display module 4551, further configured to display first information in an information flow interface, wherein the first information includes a first interactive control and a free area; the display module 4551 is further configured to display a first special effects animation carrying recommended materials in the free area in response to a first trigger operation on the first interactive control.

[0328] 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 interactive processing method described above in this application.

[0329] 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 provided in this application, such as the interactive processing method shown in FIG3A.

[0330] 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.

[0331] 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.

[0332] As an example, computer-executable instructions may, but do not necessarily, correspond to files in a file system. They may be stored as part of a file that holds other programs or data, for example, in one or more scripts in a Hyper Text Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple co-located files (e.g., files that store one or more modules, subroutines, or code sections).

[0333] 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.

[0334] In summary, this application embodiment displays first information including a first interactive control in the information flow interface. The first interactive control can trigger a first interactive interface for editing special effects animations. By embedding animation editing functionality into the information flow interface, the interactive forms of the information flow interface are enriched, enabling users to create and share dynamic content, thereby enhancing the interactivity and fun of information exchange and improving the user experience. In response to a second trigger operation on the first special effects animation, the first special effects animation is played. Displaying the first special effects animation in the first information within the information flow interface allows the edited special effects animation to be displayed instantly in the information flow, making information transmission more intuitive. By directly integrating editing functionality into the information flow interface, editing and sending special effects animations can be done without jumping to other applications or interfaces, simplifying the user's operation process and improving interaction efficiency.

[0335] 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 processing method, the method being executed by an electronic device, the method comprising: The first information is displayed in the information flow interface, wherein the first information includes a first interactive control; In response to a first trigger operation on the first interactive control, a first interactive interface is displayed, wherein the first interactive interface is used to edit special effects animation; In response to a first editing operation in the first interactive interface, a first special effects animation generated by the editing is displayed; In response to a second triggering operation on the first special effects animation, the first special effects animation is played.

2. The method according to claim 1, wherein, Before displaying the first interactive interface, the method further includes: The second special effects animation is displayed in the first information, wherein the second special effects animation is different from the first special effects animation, and the second special effects animation is any of the following types of special effects animation: special effects animation pre-configured for the first information, special effects animation edited by a second object, and the second object is an object different from the first object browsing the information flow interface.

3. The method according to claim 2, wherein, The step of displaying the second special effects animation in the first information includes: When the first information is information published by the second object, the special effects animation edited by the second object is displayed in the first information; When the first information is not information published by the second object, the pre-configured special effects animation is displayed in the first information.

4. The method according to claim 2, wherein, The step of displaying the second special effects animation in the first information includes: Display the second special effects animation in any of the following ways: Display at least one of the second special effects animations, wherein when there are multiple second special effects animations, at least some of the second special effects animations are played in an overlay manner, and the key elements of each second special effects animation are in a visible state; Multiple second special effects animations are displayed one by one, wherein the content of each second special effects animation is different, and the animations are ordered according to at least one of the following factors: the order of publication, the user's interest, the relevance to the first information, and the frequency of interaction. Display one of the second special effects animations and a second interactive control, and switch to displaying another of the second special effects animations in response to a trigger operation on the second interactive control.

5. The method according to claim 4, wherein, At least a portion of the second special effects animation, played in an overlay manner, is presented in any of the following ways: The second special effect animation located in the upper layer has transparency, and the second special effect animation located in the lower layer is revealed through the upper layer; Another second special effects animation is embedded within a frame of a second special effects animation, wherein the area of ​​the other second special effects animation is smaller than the area of ​​the second special effects animation. Multiple second-level special effects animations can be dynamically switched or merged according to specific rules.

6. The method according to any one of claims 1 to 5, wherein, The first editing operation includes the following types: selection operation; The response to a first editing operation in the first interactive interface, displaying the first special effects animation formed by the editing, includes: Multiple first animation templates are displayed in the first interactive interface; In response to a selection operation for any of the first animation templates, a first special effects animation generated based on a target animation template is displayed, wherein the target animation template is the selected first animation template.

7. The method according to claim 6, wherein, The first information is promotional information, and each of the first animation templates includes recommended materials related to the promotional information; The display of the first special effects animation generated based on the target animation template includes: Displays a first special effects animation containing the recommended materials, generated based on the target animation template.

8. The method according to claim 6 or 7, wherein, Prior to the first special effects animation formed by the display editing, the method further includes: The first animation template is determined by at least one of the following methods: The second animation template selected by the second account is used as the first animation template, wherein the second account is an account that has a social relationship with the first account that browses the information flow interface; The animation template that is selected the most times will be used as the first animation template; Determine the first similarity between the information features of the first information and the semantic features of the candidate animation template, and take the candidate animation template with the highest first similarity as the first animation template; Determine the second similarity between the first account feature of the first account and the semantic feature of the candidate animation template, and use the candidate animation template with the highest second similarity as the first animation template.

9. The method according to any one of claims 1 to 8, wherein, Prior to the first special effects animation formed by the display editing, the method further includes: In response to an input operation on the first interactive interface, the first prompt word that has been entered is displayed; Based on the first prompt word, a reference image is searched, and based on the reference image and the first prompt word, a pre-trained text-to-image model is invoked to generate multiple first frame images; The plurality of first frame images are arranged according to the generation order, and the first special effects animation is generated based on the arranged plurality of first frame images.

10. The method according to any one of claims 1 to 8, wherein, Prior to the first special effects animation formed by the display editing, the method further includes: In response to a selection operation on information in the information flow interface, key elements are extracted from the selected information; Based on the aforementioned key elements, a pre-trained text generation model is invoked to perform text generation processing, thereby obtaining the second prompt word; Based on the second prompt word, a pre-trained text-to-image model is invoked to generate images, resulting in multiple second-frame images; The plurality of second frame images are arranged according to the generation order, and the first special effects animation is generated based on the arranged plurality of second frame images.

11. The method according to claim 10, wherein, The key element includes at least one of keywords and key images, and the key element is determined by at least one of the following methods: The pre-trained deep learning model is invoked to extract features from the selected information to obtain information features. The deep learning model is then invoked to perform image segmentation processing on the information features to obtain the key image in the selected information. The deep learning model is invoked to perform semantic understanding processing on the information features to obtain the keywords in the selected information.

12. The method according to any one of claims 1 to 5, wherein, The first editing operation also includes an input operation; The response to a first editing operation in the first interactive interface, displaying the first special effects animation formed by the editing, includes: The input controls are displayed on the first interactive interface; In response to an input operation on the input control, the input content corresponding to the input operation is played in the first special effects animation, wherein the type of the input content includes: text, image, audio and video.

13. The method according to any one of claims 1 to 12, wherein, Prior to the first special effects animation formed by the display editing, the method further includes: The preview information of the first special effects animation created by editing is displayed. The preview information is used to display the first special effects animation and includes at least one of the following: a scene in the first special effects animation and keyframes in the first special effects animation.

14. The method according to any one of claims 1 to 13, wherein, Playing the first special effects animation includes: Play the first special effects animation in any of the following ways: The first special effects animation is played in a floating window above the first information; Play the first special effects animation in the pre-configured area of ​​the first information; Play the first special effects animation in an interface other than the information flow interface.

15. The method according to any one of claims 1 to 14, wherein, After playing the first special effects animation, the method further includes: The sharing control is displayed in the first information; In response to a trigger operation on the sharing control, the first information carrying the first special effects animation is sent to the terminal device of the second object, wherein the second object is a different object from the first object browsing the information flow interface.

16. The method according to claim 15, wherein, The step of sending the first information carrying the first special effects animation to the terminal device of the second object includes: The first information may be sent to the terminal device of the second object in any of the following ways: The second information is published in the information flow interface of the second object, wherein the second information is forwarding information generated based on the first information and the first special effects animation; The first information displays the object name of the second object and a pointing symbol associated with the object name, wherein the pointing symbol represents sending the prompt information of the sharing message to the terminal device of the second object, and the prompt information is used to display in the prompt information list of the information flow interface corresponding to the second object; The shared information is displayed in the chat interface corresponding to the second object.

17. The method according to claim 15 or 16, wherein, When there are multiple second objects and multiple first special effects animations, before sending the first information carrying the first special effects animation to the terminal device of the second object, the method further includes: The target first special effects animation carried by each of the first information is determined by at least one of the following methods: In response to a selection operation for any one of the first special effects animations, the selected first special effects animation is taken as the target first special effects animation, wherein the target first special effects animation carried by each of the first information is the same; When the number of the first special effects animations is greater than the number of the second objects, the target first special effects animation corresponding to each piece of first information is determined according to the mapping relationship between the editing order and the object selection order, wherein the editing order is the editing order of the first special effects animations, and the object selection order is the order in which the second objects are selected; When the number of the first special effects animations is less than the number of the second objects, extract the target first special effects animation carried by each of the multiple first special effects animations.

18. The method according to claim 15 or 16, wherein, When there are multiple second objects and multiple first special effects animations, before sending the first information carrying the first special effects animation to the terminal device of the second object, the method further includes: The deep learning model is invoked to extract features from each of the second objects to obtain the features of the second objects. The deep learning model is trained using sample object data and sample special effects animation data. A deep learning model is invoked to extract features from each of the first special effects animations to obtain animation features; Determine a third similarity between each of the second object features and each of the animation features; For each piece of first information to be sent from the second object, the first special effect animation corresponding to the maximum third similarity of the features of the second object is used as the target first special effect animation carried by the first information to be sent.

19. The method according to any one of claims 12 to 18, wherein, The first information is used to enable the terminal device of the second object to perform the following processing: Display the first information, wherein the first information includes the first interactive control; In response to a trigger operation on the first interactive control, a third special effects animation is displayed; In response to a trigger operation on the sharing control in the first information, the first information carrying the third special effects animation is sent to the terminal device of a third object, wherein the third object is a different object from the first object and the second object.

20. The method according to any one of claims 12 to 18, wherein, The first information is used to enable the terminal device of the second object to perform the following processing: Display the first information, wherein the first information includes the first interactive control; In response to a trigger operation on the first interactive control, a second interactive interface is displayed; In response to the second editing operation in the second interactive interface, the fourth special effects animation generated by the editing is displayed; In response to a trigger operation on the sharing control in the first information, the first information carrying the fourth special effects animation is sent to the terminal device of a third object, wherein the third object is a different object from the first object and the second object.

21. The method according to any one of claims 12 to 18, wherein, When the first information is promotional information, the first information is used to enable the terminal device of the second object to perform the following processing: The promotional information is displayed, wherein the first information includes the first interactive control; In response to a trigger operation on the first interactive control, a third special effects animation containing the first recommended material and a second interactive interface are displayed, wherein the first recommended material is related to the promotional information; In response to a second editing operation in the second interactive interface, a fourth special effects animation containing a second recommended material is displayed, wherein the second recommended material is related to the promotional information.

22. The method according to any one of claims 1 to 21, wherein, The step of displaying the first information in the information flow interface includes: The first information displays at least one parameter associated with the first interactive control: a prompt message for the function of the first interactive control, the number of objects that perform interactive processing on the first interactive control, and the text content contained in the first special effects animation.

23. An interactive processing method, the method being performed by an electronic device, the method comprising: The first information is displayed in the information flow interface, wherein the first information includes a first interactive control and a free area; In response to a first trigger operation on the first interactive control, a first special effects animation carrying recommended material is displayed in the free area.

24. An interactive processing apparatus, the apparatus comprising: The display module is configured to display first information in the information flow interface, wherein the first information includes a first interactive control; The display module is further configured to display a first interactive interface in response to a first trigger operation on the first interactive control, wherein the first interactive interface is used for editing special effects animation; The display module is further configured to display a first special effects animation generated by editing in response to a first editing operation in the first interactive interface; The display module is further configured to play the first special effects animation in response to a second trigger operation on the first special effects animation.

25. An interactive processing apparatus, the apparatus comprising: The display module is configured to display first information in the information flow interface, wherein the first information includes a first interactive control and a free area; The display module is further configured to display a first special effects animation carrying recommended materials in the free area in response to a first trigger operation on the first interactive control.

26. An electronic device, the electronic device comprising: Memory is used to store executable instructions or computer programs. A processor, when executing computer-executable instructions or computer programs stored in the memory, implements the interactive processing method according to any one of claims 1 to 23.

27. A computer-readable storage medium storing computer-executable instructions or a computer program that, when executed by a processor, implements the interactive processing method according to any one of claims 1 to 23.

28. A computer program product comprising computer-executable instructions or a computer program that, when executed by a processor, implements the interactive processing method according to any one of claims 1 to 23.

Images