WO2025020669A1 - Interactive processing method and apparatus for virtual scene, and electronic device, computer-readable storage medium and computer program product - Google Patents

Abstract

Provided in the present application are an interactive processing method and apparatus for a virtual scene, an electronic device, a computer-readable storage medium and a computer program product. The method comprises: displaying a virtual scene, wherein the virtual scene comprises a store entrance and at least one first virtual object; in response to a trigger operation for the store entrance, displaying a store control, which comprises a plurality of second virtual objects; and for the plurality of second virtual objects, displaying a first recommendation identifier on a second virtual object of a type which is the same as the type of the first virtual object, and on a second virtual object of a type which is associated with the type of the first virtual object.

Description

Interactive processing method, device, electronic device, computer-readable storage medium and computer program product for virtual scene

CROSS-REFERENCE TO RELATED APPLICATIONS

This application is based on the Chinese patent application with application number 202310927765.9 and application date July 26, 2023, and claims the priority of the Chinese patent application. The entire content of the Chinese patent application is hereby introduced into this application as a reference.

Technical Field

The present application relates to the field of computer human-computer interaction technology, and in particular to a method, device, electronic device, computer-readable storage medium and computer program product for interactive processing of a virtual scene.

Background Art

Display technology based on graphics processing hardware has expanded the channels for perceiving the environment and obtaining information, especially the display technology of virtual scenes. It can realize diversified interactions between virtual objects controlled by users or artificial intelligence according to actual application needs, and has various typical application scenarios. For example, in virtual scenes such as games, it can simulate the real battle process between virtual objects.

Take the Auto Chess game as an example. Auto Chess is an emerging multiplayer strategy game. After the player places the virtual chess pieces he already owns on the virtual chessboard, the game application will automatically control the chess pieces to fight and output the results of the battle. The player can match the chess lineup to face the opponent's lineup. The loser will lose health points and the ranking will be determined according to the elimination order.

In order to reduce the cognitive cost of players, a lineup recommendation function is commonly set up in auto chess. However, the lineup recommendation function provided by the relevant technology can only guide players to use a single lineup. When the player fails to refresh the corresponding chess pieces in the store, the corresponding lineup effect cannot be achieved. It is easy to fail because the lineup cannot be formed, and the original game experience is lost. At this time, the player needs to match the lineup by himself. This method will undoubtedly cause unnecessary waiting and resource consumption of the server, as well as delays in game processing. At the same time, the single lineup recommendation makes players lose the exploration of the core technical gameplay of changing the lineup, making it impossible for players to better cope with complex and changeable battle situations, and thus unable to gain a deep understanding of the game.

Summary of the invention

The embodiments of the present application provide a method, device, electronic device, computer-readable storage medium and computer program product for interactive processing of a virtual scene, which can significantly reduce the time for user operations and decision-making, accelerate the process of interaction in the virtual scene, and thereby reduce the waiting time and resource consumption of the server.

The technical solution of the embodiment of the present application is implemented as follows:

The embodiment of the present application provides a method for interactive processing of a virtual scene, which is executed by an electronic device and includes:

Displaying a virtual scene, wherein the virtual scene includes a store entrance and at least one first virtual object;

In response to a trigger operation on the store entrance, displaying a store control, wherein the store control includes a plurality of second virtual objects;

For the plurality of second virtual objects, a first recommendation indicator is displayed on a second virtual object of the same type as the first virtual object and a second virtual object of a type associated with the type of the first virtual object.

The embodiment of the present application provides an interactive processing device for a virtual scene, comprising:

A display module configured to display a virtual scene, wherein the virtual scene includes a store entrance and at least one first virtual object;

The display module is further configured to display a store control in response to a trigger operation on the store entrance, wherein the store control includes a plurality of second virtual objects;

The display module is further configured to display, for the plurality of second virtual objects, a first recommendation identifier on a second virtual object of the same type as the first virtual object and a second virtual object of a type associated with the type of the first virtual object.

An embodiment of the present application provides an electronic device, including:

A memory for storing executable instructions;

The processor is used to implement the interactive processing method of the virtual scene provided in the embodiment of the present application when executing the executable instructions stored in the memory.

An embodiment of the present application provides a computer-readable storage medium storing computer-executable instructions for implementing the interactive processing method of a virtual scene provided in the embodiment of the present application when executed by a processor.

An embodiment of the present application provides a computer program product, including a computer program or computer executable instructions, which are used to implement the interactive processing method of the virtual scene provided in the embodiment of the present application when executed by a processor.

The embodiments of the present application have the following beneficial effects:

The embodiment of the present application provides a lineup recommendation mechanism for real-time feedback of the current battle situation in a virtual scene. According to the first virtual object currently existing in the virtual scene, a second virtual object of the same type and a second virtual object of a type related to the type of the first virtual object are intelligently recommended to the player, thereby helping the player to flexibly match the lineup. In this way, compared with the related art in which players need to match the lineup by themselves, the user's operation and decision-making time can be significantly reduced, the interaction process in the virtual scene is accelerated, and the waiting time and resource consumption of the server are reduced.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1A is a schematic diagram of an application mode of an interactive processing method for a virtual scene provided in an embodiment of the present application;

FIG1B is a schematic diagram of an application mode of the interactive processing method of a virtual scene provided in an embodiment of the present application;

FIG. 2 is a schematic diagram of the structure of an electronic device 500 provided in an embodiment of the present application;

FIG3 is a flow chart of an interactive processing method for a virtual scene provided in an embodiment of the present application;

4A and 4B are schematic flow diagrams of a method for interactive processing of a virtual scene provided in an embodiment of the present application;

FIG5 is a schematic diagram of the structure of a machine learning model provided in an embodiment of the present application;

6A to 6G are schematic diagrams of application scenarios of the interactive processing method of a virtual scene provided in an embodiment of the present application;

7 is a schematic diagram of a flow chart of a method for interactive processing of a virtual scene provided in an embodiment of the present application;

FIG8 is a flow chart of an interactive processing method for a virtual scene provided in an embodiment of the present application.

DETAILED DESCRIPTION

In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it can be 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.

It is understandable that in the embodiments of the present application, when user information and other related data (such as data of virtual objects controlled by the user) are involved, when the embodiments of the present application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards.

In the following description, the terms "first\second\..." are used only to distinguish similar objects and do not represent Regarding the specific ordering of objects, it can be understood that "first\second\..." can be interchanged in a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

In the embodiments of the present application, the term "module" or "unit" refers to a computer program or a part of a computer program with a predetermined function, and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories) or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

Before further describing the embodiments of the present application in detail, the nouns and terms involved in the embodiments of the present application are explained. The nouns and terms involved in the embodiments of the present application are subject to the following interpretations.

1) In response to: used to indicate the conditions or states on which the executed operations depend. When the dependent conditions or states are met, one or more operations executed may be in real time or have a set delay. Unless otherwise specified, there is no restriction on the order in which the multiple operations executed may be executed.

2) Virtual scene: It is the scene displayed (or provided) when the application is running on the terminal device. The scene can be a simulation environment of the real world, a semi-simulation and semi-fictitious virtual environment, or a purely fictitious virtual environment. The virtual scene can be any one of a two-dimensional virtual scene, a 2.5-dimensional virtual scene, or a three-dimensional virtual scene. The embodiment of the present application does not limit the dimension of the virtual scene. For example, the virtual scene may include the sky, land, ocean, etc. The land may include environmental elements such as deserts and cities, and users can control virtual objects to move in the virtual scene.

3) Virtual objects: images of various people and objects that can interact in a virtual scene, or movable objects in a virtual scene. The movable objects can be virtual characters, virtual animals, cartoon characters, etc., such as characters and animals displayed in a virtual scene. The virtual object can be a virtual image in a virtual scene that represents a user, such as a virtual chess piece displayed on a virtual chessboard. A virtual scene can include multiple virtual objects, each of which has its own shape and volume in the virtual scene and occupies a part of the space in the virtual scene.

4) Scene data: characteristic data representing a virtual scene, such as the area of the construction area in the virtual scene, the current architectural style of the virtual scene, etc.; it may also include the location of the virtual building in the virtual scene, and the area occupied by the virtual building, etc.

5) Auto Chess: A new type of multiplayer strategy game. Users can build their own chess lineup and face the opponent's lineup. The loser will lose health points. When the health points are below the threshold, the player will be eliminated. The ranking is determined by the elimination order.

6) Virtual chess pieces: Various combat units in Auto Chess. Users can equip, upgrade, purchase, sell and adjust the positions of virtual chess pieces.

7) Virtual chessboard: Each user has a home chessboard and will match the lineup on the home chessboard during the preparation period. When the battle starts, the portal will teleport the user's corresponding virtual chess piece to the enemy's home chessboard (in some cases, the enemy's virtual chess piece will be teleported to the user's home chessboard) for battle.

8) Bond: refers to the relationship or connection between different virtual chess pieces. Each virtual chess piece can have at least two bonds. Bonds can provide additional strength for virtual chess pieces. To activate a bond, at least two virtual chess pieces with the bond must be on the battlefield at the same time.

9) Cloud gaming: Also known as gaming on demand, it means deploying a game program on a server and running an instance of the game program (referred to as a game instance). The game instance sends the game data output during the running process to the browser page of the user terminal. The page calls the browser's media component to decode the game data and renders the real-time game screen during the game according to the decoding result. When the page detects the user's operation in the game screen, It will be reported to the game instance running in the server. When the game data generated by the game instance in response to the operation is received, the decoding and rendering process will be repeated, so that the game screen will be presented on the page according to the changes of the user's operation.

In other words, cloud gaming is an online gaming technology based on cloud computing technology. Cloud gaming technology enables thin clients with relatively limited graphics processing and data computing capabilities to run high-quality games. In a cloud gaming scenario, the game is not run on the user terminal (such as the player's game terminal), but on the cloud server, which renders the game scene into an audio and video stream and transmits it to the user terminal over the network. In this way, the user terminal does not need to have powerful graphics computing and data processing capabilities, but only needs to have basic streaming media playback capabilities and the ability to obtain player input commands and send them to the cloud server.

Taking the auto chess game as an example, the game mode of playing by placing virtual chess pieces (referred to as chess pieces) is collectively referred to as auto chess games. The core fun of auto chess games lies in the fact that players buy chess pieces and form different lineups and combinations. In order to reduce the cognitive cost of players, auto chess games often have a lineup recommendation function, but the lineup recommendation function provided by the relevant technology can only guide players to use a single lineup. When the player does not refresh the corresponding chess pieces in the store, the corresponding lineup effect cannot be achieved, and it is easy to fail because the lineup cannot be formed, and the original game experience is lost. At the same time, the single lineup recommendation makes players lose the exploration of the core technical gameplay of changing the formation, making it impossible for players to better cope with complex and changeable battle situations, and unable to deeply understand the game. In other words, the lineup recommendation function in the auto chess game provided by the relevant technology is relatively single, and the initiative of the player is completely curbed. The starting point of the lineup recommendation only completes telling the player to use this lineup, but does not tell the player how to form a complete lineup structure through various lineup combinations. For the construction and understanding of different lineups, the solutions provided by the relevant technology are missing.

In view of this, the embodiments of the present application provide an interactive processing method, device, electronic device, computer-readable storage medium and computer program product for a virtual scene, which can intelligently recommend similar virtual objects and virtual objects of related types to players according to the current battle situation, and help players flexibly match the lineup, so as to help players to have a deeper understanding of the game content, improve the game level, and thus obtain a better game experience. At the same time, it can also significantly reduce the user's operation and decision-making time, speed up the process of interaction in the virtual scene, and thus reduce the waiting time and resource consumption of the server. In order to facilitate easier understanding of the interactive processing method of the virtual scene provided by the embodiment of the present application, the exemplary implementation scenario of the interactive processing method of the virtual scene provided by the embodiment of the present application is first described. The virtual scene in the interactive processing method of the virtual scene provided by the embodiment of the present application can be completely based on the output of the terminal device, or based on the collaborative output of the terminal device and the server.

In some embodiments, the virtual scene can be an environment for game characters to interact. For example, it can be an environment for game characters to fight in the virtual scene. By controlling the actions of the game characters, both parties can interact in the virtual scene, allowing users to relieve life stress during the game.

In one implementation scenario, referring to FIG1A , FIG1A is a schematic diagram of an application mode of an interactive processing method for a virtual scene provided in an embodiment of the present application, which is applicable to some application modes that completely rely on the computing power of the graphics processing hardware of a terminal device 400 to complete the relevant data calculation of a virtual scene 100, such as stand-alone/offline mode games, and output of virtual scenes through various types of terminal devices 400 such as smart phones, tablet computers, and virtual reality/augmented reality devices.

As an example, types of graphics processing hardware include central processing unit (CPU) and graphics processing unit (GPU).

When forming a visual perception of the virtual scene 100, the terminal device 400 calculates the data required for display through the graphics computing hardware, and completes the loading, parsing and rendering of the display data, and outputs video frames that can form a visual perception of the virtual scene through the graphics output hardware, for example, presenting two-dimensional video frames on the display screen of a smartphone, or projecting video frames to achieve a three-dimensional display effect on the lenses of augmented reality/virtual reality glasses; in addition, in order to enrich the perception effect, the terminal device 400 can also use different hardware to form one or more of auditory perception, tactile perception, motion perception and taste perception.

As an example, a client 410 (e.g., a stand-alone game application) is running on the terminal device 400. During the operation of the client 410, a virtual scene including role-playing is output. The virtual scene can be an environment for game characters to interact, such as a plain, street, valley, chessboard, etc. for game characters to fight against each other. Taking the virtual scene 100 as a virtual chessboard as an example, a store entrance 101 and at least one first virtual object (i.e., a virtual object already owned by the user) are displayed in the virtual scene 100. For example, the at least one first virtual object can be a virtual chess piece 102 (e.g., chess piece A) and a virtual chess piece 103 (e.g., chess piece B) that the user (or player) has purchased. When a click operation of the user on the store entrance 101 is received, a store control 104 can be displayed in the virtual scene 100, wherein the store control 104 can include multiple second virtual objects (i.e., virtual objects that the user does not yet own). For example, multiple virtual chess pieces can be displayed in the store control 104. Subsequently, for multiple second virtual objects, a first recommendation mark can be displayed on a second virtual object of the same type as the first virtual object, and on a second virtual object of a type associated with the type of the first virtual object. For example, when it is recognized that there is currently a chess piece B in the virtual chessboard, for multiple virtual chess pieces displayed in the store control 104, a first recommendation mark 105 can be displayed on the same type of chess piece B and the chess piece C that has a bond (i.e., an associated type) with chess piece B, so as to make recommendations to the user, thereby helping to flexibly match the lineup, which is conducive to the user's deeper understanding of the game content, improving the game level, and thus obtaining a better game experience. In addition, the technical solution provided in the embodiment of the present application can also significantly reduce the user's operation and decision-making time compared to the user's own lineup matching, accelerate the process of interaction in the virtual scene, and thus reduce the waiting time and resource consumption of the server.

In another implementation scenario, referring to FIG. 1B , FIG. 1B is a schematic diagram of an application mode of an interactive processing method for a virtual scene provided in an embodiment of the present application, which is applied to a terminal device 400 and a server 200, and is suitable for an application mode that relies on the computing power of the server 200 to complete virtual scene calculations and output virtual scenes on the terminal device 400.

Taking the visual perception of the virtual scene 100 as an example, the server 200 calculates the virtual scene related display data (such as scene data) and sends it to the terminal device 400 through the network 300. The terminal device 400 relies on the graphics computing hardware to complete the loading, parsing and rendering of the display data, and relies on the graphics output hardware to output the virtual scene to form a visual perception. For example, a two-dimensional video frame can be presented on the display screen of a smartphone, or a video frame with a three-dimensional display effect can be projected on the lenses of augmented reality/virtual reality glasses. As for the perception of the form of the virtual scene, it can be understood that the corresponding hardware output of the terminal device 400 can be used, such as using a microphone to form auditory perception, using a vibrator to form tactile perception, and so on.

As an example, a client 410 (e.g., a network version of a game application) is running on the terminal device 400, and the terminal device 400 interacts with other users in a game by connecting to the server 200 (e.g., a game server). The terminal device 400 outputs a virtual scene 100 (e.g., a virtual chessboard) of the client 410, and a store entrance 101 and at least one first virtual object (i.e., a virtual object already owned by the user) are displayed in the virtual scene 100. For example, the at least one first virtual object may be a virtual chess piece 102 (e.g., chess piece A) and a virtual chess piece 103 (e.g., chess piece B) that the user (or player) has purchased. When a click operation of the user on the store entrance 101 is received, a store control 104 may be displayed in the virtual scene 100, wherein the store control 104 may include multiple second virtual objects (i.e., virtual objects that the user does not yet own). For example, multiple virtual chess pieces may be displayed in the store control 104. Subsequently, for multiple second virtual objects, a first recommendation mark can be displayed on a second virtual object of the same type as the first virtual object, and on a second virtual object of a type associated with the type of the first virtual object. For example, when it is recognized that there is currently a chess piece B in the virtual chessboard, for multiple virtual chess pieces displayed in the store control 104, a first recommendation mark 105 can be displayed on the same type of chess piece B and the chess piece C that has a fetter (i.e., an associated type) with chess piece B, so as to make recommendations to the user, thereby helping the user to flexibly match the lineup, which is conducive to the user to have a deeper understanding of the game content, improve the game level, and thus obtain a better game experience. In addition, the technical solution provided in the embodiment of the present application can also significantly reduce the user's operation and decision-making time compared to the user's own lineup matching, accelerate the process of interaction in the virtual scene, and thus reduce the waiting time and resource consumption of the server.

It should be noted that the solution for the coordinated implementation of terminal devices and servers mainly involves two game modes: They are local game mode and cloud game mode. Local game mode means that the terminal device and the server work together to run the game processing logic. The operation instructions entered by the player in the terminal device are partly processed by the terminal device running the game logic, and the other part is processed by the server running the game logic. In addition, the game logic processing run by the server is often more complex and requires more computing power. Cloud game mode means that the game logic processing is completely run by the server (such as a cloud server), and the cloud server renders the game scene data into an audio and video stream, which is then transmitted to the terminal device through the network for display. In other words, the terminal device only needs to have basic streaming media playback capabilities and the ability to obtain the player's operation instructions and send them to the server.

In some embodiments, the terminal device 400 can implement the interactive processing method of the virtual scene provided in the embodiment of the present application by running various computer executable instructions or computer programs. 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, APPlication), that is, a program that needs to be installed in the operating system to run, such as a multiplayer strategy game APP (i.e., the above-mentioned client 410); it can also be a small program, that is, a program that can be run only by downloading it to a browser environment; it can also be a game applet that can be embedded in any APP. In short, the above-mentioned computer program can be an application, module or plug-in in any form.

Taking a computer program as an application program as an example, in actual implementation, the terminal device 400 installs and runs an application program that supports virtual scenes. The application program can be any one of a multiplayer strategy game, a virtual reality application program, a three-dimensional map program, or a multiplayer gunfight survival game. The user uses the terminal device 400 to operate a virtual object in the virtual scene to perform an activity, which includes but is not limited to: adjusting body posture, crawling, walking, running, riding, jumping, driving, picking up, shooting, attacking, throwing, and building virtual buildings. Indicatively, the virtual object can be a virtual character, such as a simulated character or an anime character.

In other embodiments, the embodiments of the present application can also be implemented with the aid of cloud technology. Cloud technology refers to a hosting technology that unifies a series of resources such as hardware, software, and network in a wide area network or a local area network to achieve data calculation, storage, processing, and sharing.

Cloud technology is a general term for network technology, information technology, integration technology, management platform technology, and application technology based on the cloud computing business model. It can form a resource pool that can be used on demand and is flexible and convenient. Cloud computing technology will become an important support. The background services of the technical network system require a large amount of computing and storage resources.

For example, the server 200 in FIG. 1 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks (CDN, Content Delivery Network), and big data and artificial intelligence platforms. The terminal device 400 may be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, a car terminal, etc., but is not limited thereto. The terminal device 400 and the server 200 may be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiments of the present application.

The structure of the electronic device provided by the embodiment of the present application will be described below. Taking the electronic device as a terminal device as an example, referring to FIG. 2, FIG. 2 is a schematic diagram of the structure of the electronic device 500 provided by the embodiment of the present application, and the electronic device 500 shown in FIG. 2 includes: at least one processor 510, a memory 550, at least one network interface 520 and a user interface 530. The various components in the electronic device 500 are coupled together through a bus system 540. It is understandable that the bus system 540 is used to realize the connection communication between these components. In addition to the data bus, the bus system 540 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, various buses are marked as bus systems 540 in FIG.

The processor 510 may be an integrated circuit chip with signal processing capability, 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., wherein the general-purpose processor may be a microprocessor or any conventional Processor, etc.

The user interface 530 includes one or more output devices 531 that enable presentation of media content, including one or more speakers and/or one or more visual display screens. The user interface 530 also includes one or more input devices 532, including user interface components that facilitate user input, such as a keyboard, mouse, microphone, touch screen display, camera, other input buttons and controls.

The memory 550 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state memory, hard drives, optical drives, etc. The memory 550 may optionally include one or more storage devices that are physically remote from the processor 510.

The memory 550 includes a volatile memory or a non-volatile memory, and may also include both volatile and non-volatile memories. The non-volatile memory may be a read-only memory (ROM), and the volatile memory may be a random access memory (RAM). The memory 550 described in the embodiments of the present application is intended to include any suitable type of memory.

In some embodiments, the memory 550 can store data to support various operations, examples of which include programs, modules, and data structures, or a subset or superset thereof, as exemplarily described below.

Operating system 551, including system programs for processing various basic system services and performing hardware-related tasks, such as framework layer, core library layer, driver layer, etc., for implementing various basic services and processing hardware-based tasks;

A network communication module 552, for reaching other computing devices via one or more (wired or wireless) network interfaces 520, exemplary network interfaces 520 include: Bluetooth, Wireless Compatibility Certification (WiFi), and Universal Serial Bus (USB), etc.;

a presentation module 553 for enabling presentation of information via one or more output devices 531 (e.g., display screen, speaker, etc.) associated with the user interface 530 (e.g., a user interface for operating peripherals and displaying content and information);

The input processing module 554 is used to detect one or more user inputs or interactions from one of the one or more input devices 532 and translate the detected inputs or interactions.

In some embodiments, the device provided in the embodiments of the present application can be implemented in software. FIG. 2 shows an interactive processing device 555 of a virtual scene stored in a memory 550, which can be software in the form of programs and plug-ins, including the following software modules: a display module 5551, a moving module 5552, a shielding module 5553, an acquisition module 5554, a deduplication module 5555, a sorting module 5556, a selection module 5557, an update module 5558, a prediction module 5559, a training module 55510, and an enhancement module 55511. These modules are logical, so they can be arbitrarily combined or further split according to the functions implemented. It should be pointed out that in FIG. 2, for the convenience of expression, all the above modules are shown at one time, but it should not be regarded as excluding the implementation of only including the display module 5551 in the interactive processing device 555 of the virtual scene. The functions of each module will be explained below.

The interactive processing method of the virtual scene provided in the embodiment of the present application will be specifically described below in combination with the exemplary application and implementation of the terminal device provided in the embodiment of the present application.

For example, see FIG3 , which is a flow chart of the interactive processing method of the virtual scene provided in an embodiment of the present application, which will be described in conjunction with the steps shown in FIG3 .

It should be noted that the method shown in FIG3 can be executed by various forms of computer programs running on the terminal device, and is not limited to the client. For example, it can also be the operating system, software module, script, and applet described above, so the example of the client in the following should not be regarded as a limitation on the embodiments of the present application. In addition, for the sake of convenience, the following does not specifically distinguish between the terminal device and the client running on the terminal device.

In step 101, a virtual scene is displayed.

Here, the virtual scene may include a store entrance and at least one first virtual object.

In some embodiments, taking the client as a multiplayer strategy game APP as an example, a multiplayer strategy game APP (such as an auto chess game APP) can be run on the terminal device associated with the user. When the icon of a multiplayer strategy game APP is clicked, a game login interface may be displayed. The user may enter a pre-registered game account and password in the game login interface. When the game account and password entered by the user are verified, a virtual scene (such as a virtual chessboard) may be displayed, and a store entrance and at least one virtual chess piece that the user has purchased and played may be displayed on the virtual chessboard.

It should be noted that the first virtual object in the embodiment of the present application does not specifically refer to a certain virtual object, but is a general term for virtual objects that the user already owns. In other words, virtual objects that the user already owns can be collectively referred to as first virtual objects. For example, taking the auto chess game as an example, the first virtual object can refer to the virtual chess piece that the user has purchased. Similarly, the second virtual object in the following text does not specifically refer to a certain virtual object, but is a general term for virtual objects that the user does not yet own. For example, still taking the auto chess game as an example, the second virtual object can refer to the virtual chess piece that the user has not yet purchased in the store control.

In some embodiments, the virtual scene may be displayed from a first-person perspective in the human-computer interaction interface of the client (for example, the user plays the virtual object in the game from his own perspective); or from a third-person perspective (for example, the user chases the virtual object in the game to play the game); or from a bird's-eye view; wherein the above-mentioned different perspectives may be switched arbitrarily.

As an example, the first virtual object may be an object controlled by the current user in the game. Of course, the virtual scene may also include other virtual objects, such as virtual objects that may be controlled by other users or by a robot program. The first virtual object may be divided into any one of a plurality of teams. The teams may be in an adversarial relationship or a cooperative relationship. The teams in the virtual scene may include one or all of the above relationships.

Taking the first-person perspective display of a virtual scene as an example, the virtual scene displayed in the human-computer interaction interface may include: determining the field of view area of the first virtual object according to the viewing position and field of view angle of the first virtual object in the complete virtual scene, and presenting a portion of the virtual scene in the field of view area in the complete virtual scene, that is, the displayed virtual scene may be a portion of the virtual scene relative to the panoramic virtual scene. Because the first-person perspective is the most impactful viewing perspective for users, it can achieve immersive perception of users during the operation process.

Taking the display of a virtual scene from a bird's eye view as an example, the virtual scene displayed in the human-computer interaction interface may include: in response to a zoom operation on a panoramic virtual scene, a portion of the virtual scene corresponding to the zoom operation is presented in the human-computer interaction interface, that is, the displayed virtual scene may be a portion of the virtual scene relative to the panoramic virtual scene. In this way, the operability of the user during the operation can be improved, thereby improving the efficiency of human-computer interaction.

In some other embodiments, the following processing can also be performed: in response to a trigger operation on any first virtual object, a pop-up window corresponding to the triggered first virtual object is displayed, wherein the pop-up window may include at least one of the following information: a type associated with the type of the triggered first virtual object (such as the bond of a virtual chess piece), attribute information of the triggered first virtual object, skill information of the triggered first virtual object, and equipment information of the triggered first virtual object.

For example, taking at least one first virtual object as a virtual chess piece A and a virtual chess piece B that the user has purchased as an example, when a user clicks on the virtual chess piece A displayed on the virtual chessboard, a pop-up window corresponding to the virtual chess piece A can be displayed on the virtual chessboard, and the virtual chess pieces (such as virtual chess piece B and virtual chess piece C) that are bound to the virtual chess piece A, the attribute information of the virtual chess piece A, the skill information of the virtual chess piece A, and the equipment information of the virtual chess piece A (such as the virtual equipment that the virtual chess piece A currently has) are displayed in the pop-up window, so that the user can view the detailed information of the chess pieces that have been put on the field by clicking, which is convenient for the user to make subsequent decisions. Of course, the type of bond that exists in the virtual chess piece A can also be displayed in the pop-up window, such as bond 1 (i.e., the bond between the virtual chess piece A and the virtual chess piece B) and bond 2 (i.e., the bond between the virtual chess piece A and the virtual chess piece C), and the embodiments of the present application do not specifically limit this.

In step 102, in response to a trigger operation for a store entrance, a store control is displayed.

Here, the store control may include multiple second virtual objects. For example, taking an auto chess game as an example, cards corresponding to multiple virtual chess pieces may be displayed in the store control.

In some embodiments, taking the client as an auto chess game APP as an example, when a user clicks on a store entrance displayed in a virtual chessboard, a store control can be displayed in the virtual chessboard, wherein the store control can include multiple cards corresponding to multiple virtual chess pieces.

In step 103 , for the plurality of second virtual objects, a first recommendation identifier is displayed on a second virtual object of the same type as the first virtual object and a second virtual object of a type associated with the type of the first virtual object.

In some embodiments, taking the client as an auto chess game APP as an example, when a chess piece B (i.e., a first virtual object) that has been put on the virtual chessboard is identified, a first recommendation logo can be displayed on the card of the same type of chess piece B and on the card of the chess piece C that has a bond (i.e., an associated type) with chess piece B for the cards corresponding to the multiple virtual chess pieces displayed in the store control, so as to make a recommendation to the user, thereby helping the user to match a complete lineup structure.

It should be noted that the type of the above-mentioned association can be a bond, wherein the type of bond can include lineup bond, that is, when two game characters (such as virtual chess pieces) of the same lineup appear in the same team, there will be additional attribute bonuses (for example, the health, attack power, defense value, etc. of the two game characters will be additionally increased); couple bond, that is, when two game characters with a couple relationship in the game background appear in the same team at the same time, there will be additional attribute bonuses (for example, the health of the two game characters will be additionally increased or the skill damage of the game characters will be enhanced, etc.); blood bond, that is, when two game characters with a blood relationship in the game background appear in the same team at the same time, there will be attribute bonuses (for example, the health or attack power of the two game characters will be additionally increased).

In other embodiments, a first account may be logged in to the virtual scene, and the number of virtual resources owned by the first account (for example, the number of virtual gold coins currently owned by the first account) may be displayed at the store entrance. After executing step 103 shown in FIG. 3 , steps 104 and 105 shown in FIG. 4A may also be executed, which will be explained in conjunction with the steps shown in FIG. 4A .

In step 104, in response to a triggering operation on any second virtual object, after deducting a corresponding amount of virtual resources owned by the first account, the triggered second virtual object is moved from the store control to the virtual scene.

In some embodiments, taking game account 1 registered by user A as an example, after user A uses game account 1 to log in to an auto chess game APP, the number of virtual gold coins currently owned by user A can be displayed in the store entrance (for example, assuming it is 5), and user A can purchase the virtual chess pieces he needs (for example, virtual chess pieces displayed with a first recommendation mark) in the store control. For example, when user A clicks on the card corresponding to chess piece C displayed in the store control (the card displays a first recommendation mark), after successfully deducting the corresponding number of virtual gold coins owned by user A (for example, 2 virtual gold coins), the virtual chess piece C can be moved from the store control to the preparation area of the virtual chessboard.

It should be noted that the amount of virtual resources that needs to be deducted when a user purchases different types of virtual objects can be the same or different, and the embodiments of the present application do not specifically limit this.

In step 105, the amount of virtual resources owned by the first account is updated and displayed in the store portal.

In some embodiments, taking the game account 1 registered by user A as an example, assuming that the number of virtual gold coins currently owned by user A is 5, the number "5" can be displayed in the store entrance, indicating that user A currently has 5 virtual gold coins. Subsequently, assuming that user A consumes 2 virtual gold coins to purchase chess piece C in the store control, the number displayed in the store entrance can be updated from "5" to "3" to indicate that user A currently has only 3 virtual gold coins left. In this way, the user can intuitively understand the number of virtual gold coins he currently has, which is convenient for the user to make subsequent decisions and operations.

In some other embodiments, the virtual scene may further include a refresh control, and if the type of the triggered second virtual object is different from the type of the first virtual object, the following processing may be performed: in response to the triggering operation on the refresh control, updating and displaying other types of second virtual objects in the store control, wherein the other types of second virtual objects are different from the types of at least some of the multiple second virtual objects; for the other types of second virtual objects, displaying the same type of the second virtual object as the triggered second virtual object and the same type of the second virtual object as the triggered second virtual object The first recommendation mark is displayed on the second virtual object of the associated type.

For example, taking at least one first virtual object as chess piece A and chess piece B that the user has purchased, and the triggered second virtual object as chess piece C as an example, after purchasing chess piece C, the user can also refresh the virtual chess piece displayed in the store control through the refresh button displayed in the virtual chessboard to purchase other types of chess pieces. For example, when a user clicks on the refresh button displayed in the virtual chessboard, other types of virtual chess pieces can be updated and displayed in the store control. In addition, for other types of virtual chess pieces, a first recommendation mark can also be displayed on the card corresponding to the same type of chess piece C and the card corresponding to the chess piece (such as chess piece G) that has a fetter with chess piece C, so as to recommend it to the user. In other words, the technical solution provided in the embodiment of the present application provides a lineup fetter recommendation mechanism for real-time feedback of the current battle situation. By recommending the same type of fetters and branch fetters, players can activate lineup fetters more flexibly, thereby better coping with the battle situation and improving the user's gaming experience.

In some embodiments, a refresh control (e.g., a refresh button) may include a first quantity, wherein the first quantity is the quantity of virtual resources that needs to be deducted each time the store control is updated. The above-mentioned updating and displaying of other types of second virtual objects in the store control in response to a trigger operation on the refresh control may be implemented in the following manner: in response to a trigger operation on the refresh control, after deducting the first quantity of virtual resources owned by the first account, updating and displaying other types of second virtual objects in the store control, and updating and displaying the quantity of virtual resources owned by the first account in the store entrance.

For example, taking the client as an auto chess game APP, assuming that each time the user refreshes the virtual chess pieces displayed in the store control, 2 virtual gold coins are consumed, the number "2" can be displayed in the refresh button. When the user clicks the refresh button, it is first determined whether the number of virtual gold coins currently owned by the user is greater than 2. For example, assuming that the user currently has 5 virtual gold coins, after successfully deducting the 2 virtual gold coins owned by the user, other types of virtual chess pieces can be updated and displayed in the store control. At the same time, the number of virtual gold coins owned by the user can also be updated in the store entrance. For example, the number displayed in the store entrance is updated from "5" to "3" to indicate that the user currently has only 3 virtual gold coins left.

In other embodiments, the following processing can also be performed: in response to the number of virtual resources owned by the first account being less than the first number, shielding a response to a trigger operation for a refresh control, and displaying a prompt message, wherein the prompt message is used to prompt that the second virtual object displayed in the store control cannot be updated because the current number of virtual resources owned is less than the first number.

For example, following the above example, when the number of virtual gold coins currently owned by the user is less than 2, the refresh button can be switched to a gray state, that is, the user cannot currently refresh the virtual chess pieces displayed in the store control by clicking the refresh button. At the same time, a prompt message can also be displayed in the virtual chessboard to prompt the user that the virtual chess pieces displayed in the store control cannot be refreshed because the number of virtual gold coins currently owned is less than 2.

In some embodiments, the following processing may also be performed: obtaining a type associated with the type of each first virtual object; performing deduplication processing on multiple associated types, and displaying the deduplicated multiple associated types in the virtual scene.

For example, taking at least one first virtual object as chess piece A and chess piece B that the user has purchased, the fetters of chess piece A and chess piece B can be obtained first, for example, assuming that the chess pieces that have a fetter with chess piece A are chess piece B and chess piece C, and the chess pieces that have a fetter with chess piece B are chess piece D and chess piece C, the following four fetters can be displayed on the virtual chessboard: fetter 1 (for example, the fetter between chess piece A and chess piece B), fetter 2 (for example, the fetter between chess piece A and chess piece C), fetter 3 (for example, the fetter between chess piece B and chess piece C), and fetter 4 (for example, the fetter between chess piece B and chess piece D). In addition, the display methods for activated fetter 1 (because chess piece A and chess piece B are both on the field) and unactivated fetters 2 to 4 can be different. For example, the activated fetter 1 can be highlighted to prompt the user of the fetter that has been activated on the field.

In some other embodiments, following the above example, the following processing may be performed: in response to a trigger operation on any second virtual object in the store control, the triggered second virtual object is moved from the store control to the virtual scene, and the type associated with the type of the triggered second virtual object is updated and displayed in the virtual scene, wherein the triggered second virtual object is The type of the triggered second virtual object is different from the type of the first virtual object.

For example, following the above, taking the triggered second virtual object as chess piece C, after the user purchases chess piece C from the store control, assuming that the chess pieces that are bound to chess piece C are chess piece B and chess piece E, that is, after the user purchases chess piece C, bond 3 (i.e., the bond between chess piece B and chess piece C) is activated, and at the same time, there is an unactivated bond 5 (i.e., the bond between chess piece C and chess piece E) on the field, then bond 3 displayed in the virtual chessboard can be highlighted to indicate that bond 3 is activated, and the unactivated bond 5 can also be updated and displayed in the virtual chessboard, so that the user can understand the current situation in a timely manner.

In some embodiments, referring to FIG. 4B , FIG. 4B is a flow chart of an interactive processing method for a virtual scene provided in an embodiment of the present application. As shown in FIG. 4B , after executing step 103 shown in FIG. 3 , steps 106 to 108 shown in FIG. 4B may also be executed, which will be explained in conjunction with the steps shown in FIG. 4B .

In step 106, the type associated with the type of each first virtual object and the type associated with the type of the second virtual object that has appeared in the store control are obtained.

In some embodiments, taking at least one first virtual object as chess piece A and chess piece B that the user has purchased, and multiple second virtual objects that have appeared in the store control as two chess pieces B, one chess piece C, one chess piece D, and one chess piece F as an example, assuming that the chess pieces that are bound to chess piece A are chess piece B and chess piece C, the chess pieces that are bound to chess piece B are chess piece A and chess piece D, the chess pieces that are bound to chess piece C are chess piece B and chess piece F, the chess pieces that are bound to chess piece D are chess piece A and chess piece C, and the chess pieces that are bound to chess piece F are chess piece C and chess piece D. That is to say, there are currently a total of 8 types of bonds, namely: bond 1 (for example, between chess piece A and chess piece B); The number of bonds is 3, 1, 3, 4, 5, 6, 7, and 8. The number of bonds 1 is 3, 1, 2, 3, 4, 5, 6, 7, and 8 is the number of bonds.

In step 107, the multiple associated types are sorted in order from large to small, and the top N associated types are selected.

Here, N is a positive integer greater than 1.

In some embodiments, following the above example, the above 8 bond types can be sorted in order from large to small to obtain a sorting result. Then, the top N bond types can be selected from the sorting result. For example, the top 5 bond types can be selected from the sorting result, assuming that they are: bond 1, bond 3, bond 4, bond 7, and bond 2.

In step 108 , an N-dimensional graph corresponding to the N associated types is displayed in the virtual scene.

Here, each dimension of the N-dimensional graph corresponds to an associated type, and the display proportion of each dimension is positively correlated with the number of corresponding associated types.

In some embodiments, following the above example, after selecting the top five bond types from the sorting results, a five-dimensional graph corresponding to the five bond types can be displayed in a virtual chessboard, wherein each dimension in the five-dimensional graph corresponds to a bond type, and the display ratio of each dimension can be positively correlated with the number of corresponding bond types. In other words, the more bond types there are, the greater the display ratio of the corresponding dimension. For example, since the number of bonds 1 is 3 and the number of bonds 2 is 1, the display ratio of the dimension corresponding to bond 1 in the five-dimensional graph is greater than the display ratio of the dimension corresponding to bond 2. In this way, the user can intuitively understand the number of each bond type through the five-dimensional graph, which is convenient for the user to make subsequent decisions and operations.

In some other embodiments, the following processing may also be performed: in response to an update of the type of the second virtual object included in the store control, the quantities corresponding to the N associated types are updated; based on the updated quantities corresponding to the N associated types, the N-dimensional graph is updated, wherein the display of each dimension in the updated N-dimensional graph is The percentage is positively correlated with the updated number of corresponding associated types.

For example, following the above, when the user clicks on the refresh button, the virtual chess pieces displayed in the store control can be updated. For example, if two bond types, bond 1 and bond 3, appear, the display proportion of the dimensions corresponding to bond 1 and bond 3 in the five-dimensional diagram will increase, while the display proportion of other dimensions will decrease accordingly, thereby reflecting the current number of each bond type in real time.

In some embodiments, after executing step 103 shown in Figure 3, the following processing can also be performed: obtain the type associated with the type of each first virtual object, and the type associated with the type of the second virtual object that has appeared in the store control; sort the multiple associated types in order from most to least, and select the top N associated types, where N is a positive integer greater than 1; display N indicator controls (such as indicator bar controls or indicator ring controls) corresponding to the N associated types in the virtual scene, where each indicator control corresponds to an associated type, and the progress of the indicator control is positively correlated with the number of corresponding associated types. In this way, the user can intuitively understand the number of each existing bond type through the indicator control, which is convenient for the user to make subsequent decisions and operations, and improves the user's gaming experience. At the same time, it can also speed up the game's interactive process and reduce the server's waiting time and resource consumption.

It should be noted that in addition to displaying in the form of an N-dimensional graph or N indicator controls, other display methods can also be used. For example, the quantities corresponding to N associated types can be directly displayed in the virtual scene. The embodiments of the present application do not make specific limitations on this.

In some embodiments, the interactive processing method of the virtual scene provided in the embodiments of the present application can also be implemented in combination with artificial intelligence (AI) technology, and the following processing can also be performed: obtaining the type associated with the type of each first virtual object; based on the type of the first virtual object and each associated type, calling the machine learning model for prediction processing to obtain the winning probability corresponding to each associated type; for multiple second virtual objects included in the store control, displaying a second recommendation logo on the second virtual object of the associated type whose winning probability is greater than the probability threshold.

For example, taking at least one first virtual object as chess piece A and chess piece B that the user has purchased as an example, assuming that the chess pieces bound to chess piece A are chess piece B and chess piece C, and the chess pieces bound to chess piece B are chess piece A and chess piece D, the machine learning model can be called for prediction processing based on the types of chess piece A and chess piece B, and each type of bond, to obtain the acquisition probability corresponding to each type of bond. Then, for the multiple virtual chess pieces displayed in the store control, a second recommendation logo can be displayed on the chess piece of the bond type corresponding to the maximum winning probability (for example, assuming it is chess piece D). In this way, by intelligently recommending the bond type with the highest winning rate to the user, the player's winning probability can be improved, and a better gaming experience can be obtained.

In other embodiments, the virtual scene may also include an N-dimensional graph corresponding to N types of associations whose number is greater than a quantity threshold, wherein N is a positive integer greater than 1, and the display method of the dimensions in the N-dimensional graph corresponding to the types of associations whose acquisition probability is greater than a probability threshold is different from the display method of other dimensions.

For example, taking the client as an auto chess game APP, assuming that after calling the machine learning model for prediction processing, the bond types with a winning probability greater than the probability threshold are bond 1 and bond 2, then for the five-dimensional graph displayed on the virtual chessboard, the dimensions corresponding to bond 1 and bond 2 in the five-dimensional graph can be displayed differently. For example, the dimensions corresponding to bond 1 and bond 2 can be highlighted to prompt the user that bond 1 and bond 2 are the bond types with a higher winning probability. In this way, recommendations can be made to users from multiple dimensions to increase the user's winning probability.

In some other embodiments, following the above example, before calling the machine learning model for prediction processing, the following processing may also be performed: obtaining interaction data of the sample winner account and the sample loser account, wherein the interaction data includes the type of virtual object controlled by the sample loser account and the type associated with the type of virtual object, and the type of virtual object controlled by the sample winner account and the type associated with the type of virtual object; based on the interaction data, calling the initialized machine learning model for prediction processing to obtain a prediction result; determining the difference between the prediction result and the labeled data, and performing back propagation based on the difference, and updating the parameters of the machine learning model layer by layer during the back propagation process, wherein, The identification data includes the type of virtual object controlled by the sample winner account and the type associated with the type of virtual object.

For example, see Figure 5, which is a schematic diagram of the structure of the machine learning model provided by the embodiment of the present application. As shown in Figure 5, the exemplary structure of the machine learning model provided by the embodiment of the present application may include: an input layer (i.e., an embedding layer), an encoding layer (e.g., it may be composed of multiple cascaded convolutional layers), a fully connected layer, and an output layer (including an activation function, such as a Softmax function). After obtaining the interactive data of the sample winner account and the sample loser account, the interactive data may first be input into the input layer for embedding processing, and then the embedded feature vector output by the input layer may be encoded by the encoding layer to obtain the hidden layer feature vector, and then the hidden layer feature vector may be fully connected by the fully connected layer, and finally the fully connected result output by the fully connected layer may be input into the output layer to activate the output layer, thereby obtaining the prediction result. After obtaining the prediction result, the prediction result and the labeled data may be substituted into the loss function to obtain the corresponding difference, and back propagation may be performed based on the difference, so that the parameters of the machine learning model may be updated layer by layer during the back propagation process to obtain the trained machine learning model.

It should be noted that the above-mentioned machine learning model can be a neural network model (such as a convolutional neural network, a deep convolutional neural network, or a fully connected neural network), a decision tree model, a gradient boosting tree, a multilayer perceptron, and a support vector machine, etc. The embodiments of the present application do not specifically limit the type of machine learning model.

In some embodiments, a first account can be logged in to the virtual scene, and the number of virtual objects that the first account can control is positively correlated with the account level. The following processing can also be performed: an experience purchase control (such as an experience purchase button) is displayed in the virtual scene; in response to a trigger operation on the experience purchase control, the account level of the first account is increased after deducting the corresponding number of virtual resources owned by the first account.

For example, taking the game account 1 registered by user A as the first account, the number of virtual chess pieces that user A can control may be positively correlated with the account level of game account 1, that is, the higher the account level, the more virtual chess pieces that user A can control. An experience purchase button may be displayed on the virtual chessboard, and user A can increase the account level of game account 1 by clicking the experience purchase button. For example, each time user A clicks the experience purchase button, 2 virtual gold coins owned by user A will be consumed, and the account level of game account 1 will be increased by 1 level. In this way, the user can make a decision between the account level and the purchase of virtual chess pieces. For example, the user can determine to consume a certain amount of virtual gold coins to purchase experience to increase the account level according to the current battle situation, so as to increase the upper limit of the number of virtual chess pieces that can be controlled, or a certain amount of virtual gold coins can be consumed to purchase virtual chess pieces, thereby increasing the fun of the game.

The interactive processing method of the virtual scene provided in the embodiment of the present application provides a lineup recommendation mechanism for real-time feedback of the current battle situation. According to the first virtual object currently existing in the virtual scene, the second virtual object of the same type and the second virtual object of the type associated with the type of the first virtual object are intelligently recommended to the player to help the user quickly match a complete lineup structure, thereby helping the user to have a deeper understanding of the game content, improve the game level, and thus obtain a better game experience. In addition, the technical solution provided in the embodiment of the present application can also significantly reduce the user's operation and decision-making time compared to the user's own lineup matching, accelerate the process of interaction in the virtual scene, and thus reduce the server's waiting time and resource consumption.

Below, taking the auto chess game as an example, an exemplary application of the embodiment of the present application in an actual application scenario is explained.

The embodiment of the present application provides an interactive processing method for a virtual scene, which collects lineup information through a big data background, and collects the chess pieces that appear in the store control (referred to as the store) and the lineup on the field to provide real-time feedback, helping players to better achieve lineup formation, and learning based on the winning rate of all players' lineup selections, giving players the lineup direction with the highest winning rate. Specifically, in the technical solution provided by the embodiment of the present application, learning how to achieve the cognition of fetters adopts the method of machine learning, and through analyzing and learning the fetter database, understands how to put together the fetter group; and based on the intelligent recommendation of the winning rate, the method of deep learning is applied, and the results corresponding to each game are analyzed independently and layered, and the results are output layer by layer, and finally the optimal lineup recommendation is analyzed.

That is to say, the technical solution provided in the embodiment of the present application is to help players in a fixed lineup by guiding tendencies. While making recommendations, we also increase the corresponding lineup expansion learning. When the recommended lineup cannot be achieved, we can provide a way to improve the lineup's combat effectiveness through other existing bond types, so that players can respond to the battle situation more flexibly. Through big data machine learning, we can derive a lineup recommendation direction with a higher probability of winning, thereby improving the player's winning rate.

The interactive processing method of the virtual scene provided in the embodiment of the present application is described in detail below.

For example, see FIG6A , which is a schematic diagram of an application scenario of the interactive processing method of a virtual scene provided by an embodiment of the present application. As shown in FIG6A , a chess piece 602 (e.g., chess piece A) and a chess piece 603 (e.g., chess piece B) are displayed on a virtual chessboard 601, that is, there are two types of chess pieces A and B on the current field. When a user clicks on chess piece 602, a pop-up window 604 corresponding to chess piece 602 may be displayed, and chess pieces B and C, attribute information, skill information, and equipment information, etc., which are bound to chess piece A, are displayed in pop-up window 604. When a user clicks on chess piece 603, a pop-up window 605 corresponding to chess piece 603 may be displayed, and chess pieces A and D, attribute information, skill information, and equipment information, etc., which are bound to chess piece B, are displayed in pop-up window 605. In addition, activated bonds 606 (i.e., bonds 1, such as the bonds between chess piece A and chess piece B), inactivated bonds 607 (i.e., bonds 2, such as the bonds between chess piece A and chess piece C), and bonds 608 (i.e., bonds 3, such as the bonds between chess piece B and chess piece D) may also be displayed on the virtual chessboard 601. In addition, a store entrance 609 may also be displayed on the virtual chessboard 601, and the user may enter the store and purchase chess pieces by clicking on the store entrance 609.

In some embodiments, all bond types can be input into the database, and the AI learns how to match these lineups through machine learning. After completing the learning phase, the client inputs the current player's on-field information and store information into the cloud database. The cloud database identifies the corresponding content of the store by judgment and marks the chess pieces that meet the recommendation conditions with the first recommendation mark (for example, a mark similar to a like).

For example, see FIG6B , which is a schematic diagram of an application scenario of the interactive processing method of a virtual scene provided by an embodiment of the present application. As shown in FIG6B , when a player clicks on a store entrance 609, a store control 610 may be displayed in a virtual chessboard 601, and purchase cards corresponding to multiple chess pieces are displayed in the store control 610. There are three types of bonds, namely, bond 1, bond 2, and bond 3, and two chess pieces, namely, A and B, on the current field. There are two judgment dimensions, namely, bonds and chess pieces. It is recognized that there are purchase cards for chess piece B and purchase cards for chess piece C with bond 2 in the current store control 610, so a first recommendation mark 611 may be displayed on the purchase cards for chess piece B and chess piece C. At this time, the user can purchase the corresponding chess piece by clicking on the purchase card.

For example, see FIG6C, which is a schematic diagram of an application scenario of an interactive processing method for a virtual scene provided by an embodiment of the present application. As shown in FIG6C, when a player clicks on a purchase card 612 for chess piece C shown in FIG6B, the purchase card 612 for chess piece C can be canceled in the store control 610, and chess piece C can be displayed in the battle preparation area. At the same time, the number displayed in the store entrance 609 can be updated from "5" to "3", indicating that the player spent 2 virtual gold coins when purchasing chess piece C, and only 3 virtual gold coins are currently left. After the player purchases chess piece C, chess piece C can activate bond 607 (i.e., bond 2, such as the bond between chess piece A and chess piece C), and at the same time, an unactivated bond 613 (i.e., bond 4, such as the bond between chess piece C and chess piece F) is added to the field. At this time, the client can send information to the cloud database, and the cloud database adds two judgment elements, bond 4 and chess piece C, after receiving the information.

For example, see FIG6D , which is a schematic diagram of an application scenario of the interactive processing method of a virtual scene provided by an embodiment of the present application. As shown in FIG6D , a player can refresh the store by clicking a refresh button 614. For example, when a player clicks on the refresh button 614, the purchase card of the chess piece displayed in the store control 610 can be refreshed. For example, after the refresh, a new chess piece G appears in the store control 610. At the same time, assuming that there is a bond between chess piece G and chess piece A, the first recommendation mark 611 can be displayed on the card corresponding to chess piece G. At the same time, the number displayed in the store entrance 609 can also be updated from "3" to "1", indicating that the player spent 2 virtual gold coins when refreshing the store, and currently only 1 virtual gold coin is left.

The following is an explanation of the lineup recommendation section.

In some embodiments, the cloud database will record the chess pieces that have appeared in the current store and the chess pieces that are currently on the field. Type, based on the frequency of chess piece bonds, the recommended lineup trend can be expressed in a five-dimensional graph or other forms. The bonds with a relatively high number (for example, greater than the number threshold) will be selected to be displayed externally. Among them, the number of bonds = the number of times the chess pieces of the bond type appear in the store + the number of chess pieces with the bond on the field, and the current display ratio of the bond = the number of bonds / the sum of the number of displayed bonds.

For example, see Figure 6E, which is a schematic diagram of an application scenario of the interactive processing method of a virtual scene provided by an embodiment of the present application. As shown in Figure 6E, assuming that the most common bonds at present are bond 1, bond 2, bond 3, bond 4, and bond 5, a five-dimensional graph 615 corresponding to these five bond types can be displayed in the virtual chessboard 601. Different bonds can have different display proportions according to the frequency of the number of bonds. In addition, the player's current bonds (i.e., activated bonds) can also be displayed differently. For example, assuming that "Bond 1" and "Bond 3" are currently activated, other colors can be used in the five-dimensional graph 615 to distinguish "Bond 1" and "Bond 3" to prompt the player that these two bonds have been activated.

For example, see FIG6F, which is a schematic diagram of an application scenario of the interactive processing method of a virtual scene provided by an embodiment of the present application. As shown in FIG6F, assuming that after the player purchases chess piece C, refreshes again, and two types of bonds, bond 5 and bond 3, appear in the store, that is, the proportion of bond 3 exceeds bond 1, then in the corresponding five-dimensional graph 615, the display proportion of bond 3 and bond 5 increases accordingly, and the display proportion of other bonds decreases accordingly. At the same time, assuming that "bond 4" is activated due to the addition of chess piece C, in the five-dimensional graph 615, "bond 4" can also be displayed in other colors to remind the player that "bond 4" has also been activated.

In other embodiments, it is also possible to count the win rates of various bond types of each player using this function, and add an additional optimal recommendation identifier (i.e., a second recommendation identifier) to the existing recommendation mechanism to help players better strengthen their lineups and improve their win rates.

For example, see Figure 6G, which is a schematic diagram of the application scenario of the interactive processing method of the virtual scene provided in an embodiment of the present application. As shown in Figure 6G, assuming that the type with the highest winning rate calculated by the cloud database based on the current battle situation is chess piece C, then for the purchase cards of multiple chess pieces displayed in the store control 610, an additional recommendation logo 616 can be displayed on the purchase card of chess piece C, thereby increasing the player's chance of winning.

The interactive processing method of the virtual scene provided in the embodiment of the present application is described below in conjunction with FIG. 7 .

For example, see FIG. 7 , which is a flow chart of an interactive processing method for a virtual scene provided in an embodiment of the present application, which will be described in conjunction with the steps shown in FIG. 7 .

In step 201, the bond database is imported into the cloud so that the AI can learn how to match the lineup.

In some embodiments, a cloud database of bond-related content can be created to enable AI to learn the database content, understand the bonds corresponding to different chess pieces, and how to recommend players to obtain chess pieces with similar bonds.

In step 202, the client feeds back the field information and store chess piece information to the cloud.

In some embodiments, the client can detect the type of chess pieces on the player's field as judgment element A, and detect the type of bonds on the field as judgment element B, and feed back judgment element A and judgment element B to the cloud database. The AI identifies the two judgment elements A and B, and obtains the type of chess pieces of the same type as the element as a judgment condition.

In step 203, the cloud selects the most common ties and notifies the client to display them.

In some embodiments, the client can feedback the chess pieces that have appeared currently to the cloud database, and the AI counts the frequency of occurrence of the number of fetters, and selects several fetter types with higher frequency. Subsequently, the cloud database can feedback the data to the client so that the client can display several fetter types with higher frequency. In addition, the client can also upload the existing fetters in the current battlefield to the cloud database, and the AI identifies such fetters and feedbacks them to the client so that the client can display them in a special identification style.

In step 204, it is determined whether there is an existing lineup. If not, step 205 is executed; if so, step 206 is executed.

In step 205, a normal display is adopted.

In step 206, a special style is used for highlighting.

In some embodiments, the client can upload the chess pieces currently available in the store to the cloud database. The AI selects the chess pieces that meet the corresponding conditions based on the current judgment elements and feeds them back to the client so that the client can add a recommendation mark on the purchase card of the corresponding chess piece.

In step 207, determine whether it is the best lineup in terms of winning rate. If not, execute step 208; if so, execute step 209.

In step 208, no additional recommendation logo is displayed.

In step 209, additional recommendation indicators are displayed.

The interactive processing method of the virtual scene provided in the embodiment of the present application is described below in conjunction with FIG. 8 .

For example, see FIG8 , which is a flow chart of the interactive processing method of the virtual scene provided in an embodiment of the present application, which will be described in conjunction with the steps shown in FIG8 .

In step 301, the bond database is imported into the cloud so that the AI can learn how to match the lineup.

In step 302, the client feeds back the field information and store chess piece information to the cloud.

In step 303, the cloud uses chess pieces and ties as judgment elements.

In step 304, determine whether there is a corresponding chess piece or bond in the store. If not, execute step 305; if so, execute step 306.

In step 305, the recommendation mark is not displayed.

In step 306, a recommendation mark is displayed on the corresponding chess piece.

In step 307 , determine whether it is the optimal direction for winning rate, if not, execute step 308 ; if so, execute step 309 .

In step 308, no additional recommendation logo is displayed.

In step 309, an additional recommendation mark is displayed on the corresponding chess piece.

In some embodiments, different quantity matching ratios of the same type of bonds will have different effects, and each type of main bond also has different branch bond development directions. This randomness and possibility will produce different lineup matching effects, and their winning rates will also be different. The embodiment of the present application collects the final lineup structure of the player in each game, combines it with the winning rate of the game, retrieves the winning rate corresponding to the lineup structure from the client, and uploads it to the cloud database, so that AI analyzes the database information, obtains the comprehensive winning rate corresponding to various types of bond types/development directions, and then feeds back the bond matching type with a higher winning rate to the client, so that the client can display an additional recommendation logo on the purchase card of the corresponding chess piece in the store, and display a special recommendation style in the bond recommendation dimension diagram.

In summary, the interactive processing method of the virtual scene provided in the embodiment of the present application has the following beneficial effects: it solves the problem that players are restricted by lineup pieces under a single lineup and cannot cope with flexible and changeable battle situations when they do not obtain the pieces in the lineup, and provides a lineup bond recommendation mechanism with real-time feedback on the current battle situation. By recommending similar bonds and branch bonds, players can activate lineup bonds more flexibly and better cope with the battle situation. At the same time, by collecting a large number of players' game records and deeply learning the bond matching win rate, they can intelligently recommend the bond type with the highest win rate to players, thereby increasing the player's chance of winning. The recommended learning of bond branches also cultivates the player's ability to form bonds, which is conducive to a deeper understanding of the game content, improving the game level, and thus obtaining a better game experience.

The following continues to describe the exemplary structure of the virtual scene interactive processing device 555 provided in the embodiment of the present application implemented as a software module. In some embodiments, as shown in Figure 2, the software module stored in the virtual scene interactive processing device 555 in the memory 550 may include: a display module 5551.

Display module 5551 is configured to display a virtual scene, wherein the virtual scene includes a store entrance and at least one first virtual object; display module 5551 is also configured to display a store control in response to a trigger operation on the store entrance, wherein the store control includes multiple second virtual objects; display module 5551 is also configured to display a first recommendation logo on a second virtual object of the same type as the first virtual object and on a second virtual object of a type associated with the type of the first virtual object for the multiple second virtual objects.

In some embodiments, the virtual scene is logged in with a first account, and the store entrance displays the first account's The number of virtual resources; the interactive processing device 555 of the virtual scene also includes a moving module 5552, which is configured to respond to a trigger operation on any second virtual object, and after deducting the corresponding number of virtual resources owned by the first account, move the triggered second virtual object from the store control to the virtual scene; the display module 5551 is also configured to update the display of the number of virtual resources owned by the first account in the store entrance.

In some embodiments, the virtual scene also includes a refresh control, and the type of the triggered second virtual object is different from the type of the first virtual object; the display module 5551 is also configured to update and display other types of second virtual objects in the store control in response to a trigger operation on the refresh control, wherein the other types of second virtual objects are different from the type of at least part of the multiple second virtual objects; for the other types of second virtual objects, a first recommendation logo is displayed on a second virtual object of the same type as the triggered second virtual object and on a second virtual object of a type associated with the type of the triggered second virtual object.

In some embodiments, the refresh control includes a first quantity, which is the number of virtual resources that need to be deducted each time the store control is updated; the display module 5551 is also configured to respond to a trigger operation on the refresh control, after deducting the first number of virtual resources owned by the first account, update and display other types of second virtual objects in the store control, and update and display the number of virtual resources owned by the first account in the store entrance.

In some embodiments, the interactive processing device 555 of the virtual scene also includes a shielding module 5553, which is configured to shield a response to a trigger operation for a refresh control in response to the number of virtual resources owned by the first account being less than a first number; the display module 5551 is also configured to display a prompt message, wherein the prompt message is used to prompt that the second virtual object displayed in the store control cannot be updated because the current number of virtual resources owned is less than the first number.

In some embodiments, the interactive processing device 555 of the virtual scene also includes an acquisition module 5554 and a deduplication module 5555, wherein the acquisition module 5554 is configured to acquire the type associated with the type of each first virtual object; the deduplication module 5555 is configured to perform deduplication processing on multiple associated types; and the display module 5551 is further configured to display the multiple associated types after deduplication in the virtual scene.

In some embodiments, the movement module 5552 is further configured to move the triggered second virtual object from the store control to the virtual scene in response to a trigger operation on any second virtual object; the display module 5551 is further configured to update the display in the virtual scene with a type associated with the type of the triggered second virtual object, wherein the type of the triggered second virtual object is different from the type of the first virtual object.

In some embodiments, the acquisition module 5554 is further configured to acquire the type associated with the type of each first virtual object and the type associated with the type of the second virtual object that has appeared in the store control; the interactive processing device 555 of the virtual scene also includes a sorting module 5556 and a selection module 5557, wherein the sorting module 5556 is configured to sort the multiple associated types in order from large to small; the selection module 5557 is configured to select the top N associated types, wherein N is a positive integer greater than 1; the display module 5551 is further configured to display an N-dimensional graph corresponding to the N associated types in the virtual scene, wherein each dimension of the N-dimensional graph corresponds to an associated type, and the display proportion of each dimension is positively correlated with the number of corresponding associated types.

In some embodiments, the interactive processing device 555 of the virtual scene also includes an update module 5558, which is configured to update the quantities corresponding to the N associated types in response to an update of the type of the second virtual object included in the store control; based on the updated quantities corresponding to the N associated types, the N-dimensional graph is updated, wherein the display proportion of each dimension in the updated N-dimensional graph is positively correlated with the updated quantity of the corresponding associated type.

In some embodiments, the acquisition module 5554 is further configured to acquire the type associated with the type of each first virtual object and the type associated with the type of the second virtual object that has appeared in the store control; the sorting module 5556 is further configured to sort the multiple associated types in order from most to least quantity; the selection module 5557 is further configured to select the top N associated types, wherein N is a positive integer greater than 1; the display module 5551 is further configured to display N indicator bar controls corresponding to the N associated types in the virtual scene, wherein each indicator bar control corresponds to an associated type, and the length of the indicator bar control is positively correlated with the number of corresponding associated types.

In some embodiments, the acquisition module 5554 is further configured to acquire a type associated with each first virtual object. type; the interactive processing device 555 of the virtual scene also includes a prediction module 5559, which is configured to call the machine learning model for prediction processing based on the type of the first virtual object and the type of each association, and obtain the winning probability corresponding to each associated type; the display module 5551 is also configured to display a second recommendation logo on the second virtual object of the associated type with a probability greater than a probability threshold for multiple second virtual objects.

In some embodiments, the interaction processing device 555 of the virtual scene also includes a training module 55510, which is configured to perform the following processing before the prediction module 5559 calls the machine learning model for prediction processing: obtaining the interaction data of the sample winner account and the sample loser account, wherein the interaction data includes the type of virtual object controlled by the sample loser account and the type associated with the type of virtual object, and the type of virtual object controlled by the sample winner account and the type associated with the type of virtual object; based on the interaction data, calling the initialized machine learning model for prediction processing to obtain a prediction result; determining the difference between the prediction result and the labeled data, and performing back propagation based on the difference, and updating the parameters of the machine learning model layer by layer during the back propagation process, wherein the labeled data includes the type of virtual object controlled by the sample winner account and the type associated with the type of virtual object.

In some embodiments, the virtual scene also includes an N-dimensional graph corresponding to N types of associations whose number is greater than a quantity threshold, wherein N is a positive integer greater than 1, and the display method of the dimensions in the N-dimensional graph corresponding to the types of associations whose acquisition probability is greater than a probability threshold is different from the display method of other dimensions.

In some embodiments, the display module 5551 is further configured to display a pop-up window corresponding to the triggered first virtual object in response to a trigger operation on any first virtual object, wherein the pop-up window includes at least one of the following information: a type associated with the type of the triggered first virtual object, attribute information of the triggered first virtual object, skill information of the triggered first virtual object, and equipment information of the triggered first virtual object.

In some embodiments, a first account is logged into the virtual scene, and the number of virtual objects that the first account can control is positively correlated with the account level; the display module 5551 is also configured to display experience purchase controls in the virtual scene; the interactive processing device 555 of the virtual scene also includes an enhancement module 55511, which is configured to respond to a trigger operation for the experience purchase control and enhance the account level of the first account after deducting the corresponding number of virtual resources owned by the first account.

It should be noted that the description of the device of the embodiment of the present application is similar to the description of the above-mentioned method embodiment, and has similar beneficial effects as the method embodiment, so it is not repeated. The unfinished technical details of the interactive processing device of the virtual scene provided in the embodiment of the present application can be understood according to the description of any of Figures 3, 4A, or 4B.

The embodiment of the present application provides a computer program product, which includes a computer program or a computer executable instruction, and the computer program or the computer executable instruction is stored in a computer-readable storage medium. The processor of the computer device reads the computer executable instruction from the computer-readable storage medium, and the processor executes the computer executable instruction, so that the computer device executes the interactive processing method of the virtual scene described in the embodiment of the present application.

An embodiment of the present application provides a computer-readable storage medium storing computer executable instructions, wherein computer executable instructions are stored. When the computer executable instructions are executed by a processor, the processor will execute the interactive processing method of the virtual scene provided by the embodiment of the present application, for example, the interactive processing method of the virtual scene shown in Figure 3, Figure 4A, or Figure 4B.

In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface storage, optical disk, or CD-ROM; or it may be various devices including one or any combination of the above memories.

In some embodiments, executable instructions may be in the form of a program, software, software module, script 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 a stand-alone program or as a module, component, subroutine or other unit suitable for use in a computing environment.

As an example, the executable instructions may be deployed to be executed on one electronic device, or on multiple electronic devices located in one location, or on multiple electronic devices distributed in multiple locations and interconnected by a communication network. Execute on.

The above is only an embodiment of the present application and is not intended to limit the protection scope of the present application. Any modifications, equivalent substitutions and improvements made within the spirit and scope of the present application are included in the protection scope of the present application.

Claims (20)

A method for interactive processing of a virtual scene, executed by an electronic device, comprising: Displaying a virtual scene, wherein the virtual scene includes a store entrance and at least one first virtual object; In response to a trigger operation on the store entrance, displaying a store control, wherein the store control includes a plurality of second virtual objects; For the plurality of second virtual objects, a first recommendation indicator is displayed on a second virtual object of the same type as the first virtual object and a second virtual object of a type associated with the type of the first virtual object. The method according to claim 1, wherein The virtual scene is logged with a first account, and the number of virtual resources owned by the first account is displayed in the store entrance; The method further comprises: In response to a triggering operation on any of the second virtual objects, after deducting a corresponding amount of virtual resources from the first account, moving the triggered second virtual object from the store control to the virtual scene, and The amount of virtual resources owned by the first account is updated and displayed in the store entrance. The method according to claim 2, wherein The virtual scene further includes a refresh control, and the type of the second virtual object triggered is different from the type of the first virtual object; The method further comprises: In response to a trigger operation on the refresh control, updating and displaying other types of second virtual objects in the store control, wherein the other types of second virtual objects are different from the types of at least part of the plurality of second virtual objects; For the other types of second virtual objects, the first recommendation identifier is displayed on a second virtual object of the same type as the triggered second virtual object and a second virtual object of a type associated with the type of the triggered second virtual object. The method according to claim 3, wherein The refresh control includes a first quantity, which is the quantity of virtual resources that need to be deducted each time the store control is updated; In response to the triggering operation on the refresh control, updating and displaying the other type of second virtual object in the store control includes: In response to a trigger operation on the refresh control, after deducting the first amount of virtual resources owned by the first account, updating and displaying a second virtual object of another type in the store control, and The amount of virtual resources owned by the first account is updated and displayed in the store entrance. The method according to claim 4, wherein the method further comprises: In response to the number of virtual resources owned by the first account being less than the first number, shielding a response to a triggering operation on the refresh control, and Prompt information is displayed, wherein the prompt information is used to prompt that the second virtual object displayed in the store control cannot be updated because the number of virtual resources currently available is less than the first number. The method according to any one of claims 1 to 5, wherein the plurality of second virtual objects are displayed in the store control in the form of cards; The displaying of the first recommendation mark on a second virtual object of the same type as the first virtual object and a second virtual object of a type associated with the type of the first virtual object comprises: For second virtual objects of the same type as the first virtual object and second virtual objects of a type associated with the type of the first virtual object among the plurality of second virtual objects, a first recommendation identifier is displayed on a card corresponding to the second virtual object. The method according to any one of claims 1 to 5, wherein the method further comprises: Obtaining a type associated with the type of each of the first virtual objects; Deduplication processing is performed on the multiple associated types, and the multiple associated types after deduplication are displayed in the virtual scene. The method according to claim 7, wherein the method further comprises: In response to a triggering operation on any of the second virtual objects, moving the triggered second virtual object from the store control to the virtual scene, and The type associated with the type of the triggered second virtual object is updated and displayed in the virtual scene, wherein the type of the triggered second virtual object is different from the type of the first virtual object. The method according to any one of claims 1 to 5, wherein the method further comprises: Obtaining a type associated with the type of each first virtual object and a type associated with the type of a second virtual object that has appeared in the store control; Sorting the plurality of associated types in descending order of number, and selecting the top N associated types, where N is a positive integer greater than 1; An N-dimensional graph corresponding to the N associated types is displayed in the virtual scene, wherein each dimension of the N-dimensional graph corresponds to one associated type, and the display proportion of each dimension is positively correlated with the number of the corresponding associated types. The method according to claim 9, wherein the method further comprises: In response to an update of the type of the second virtual object included in the store control, updating the quantities corresponding to the N associated types respectively; The N-dimensional graph is updated based on the updated quantities corresponding to the N types of associations, wherein the display proportion of each dimension in the updated N-dimensional graph is positively correlated with the updated quantity of the corresponding type of association. The method according to any one of claims 1 to 5, wherein the method further comprises: Obtaining a type associated with the type of each first virtual object and a type associated with the type of a second virtual object that has appeared in the store control; Sorting the plurality of associated types in descending order of number, and selecting the top N associated types, where N is a positive integer greater than 1; N indicator controls corresponding to the N associated types are displayed in the virtual scene, wherein each indicator control corresponds to one associated type, and the progress of the indicator control is positively correlated with the number of the corresponding associated types. The method according to any one of claims 1 to 11, wherein the method further comprises: Obtaining a type associated with the type of each of the first virtual objects; Based on the type of the first virtual object and the type of each of the associations, calling a machine learning model to perform prediction processing to obtain a winning probability corresponding to each of the types of the associations; For the plurality of second virtual objects, a second recommendation identifier is displayed on a second virtual object of the associated type whose acquisition probability is greater than a probability threshold. The method according to claim 12, wherein, before calling the machine learning model for prediction processing, the method further comprises: Acquire interaction data of a sample winner account and a sample loser account, wherein the interaction data includes the type of a virtual object controlled by the sample loser account and the type associated with the type of the virtual object, and the type of a virtual object controlled by the sample winner account and the type associated with the type of the virtual object; Based on the interaction data, calling the initialized machine learning model to perform prediction processing to obtain a prediction result; Determine the difference between the prediction result and the labeled data, and perform back propagation based on the difference, and update the parameters of the machine learning model layer by layer during the back propagation process, wherein the labeled data includes the type of the virtual object controlled by the sample winning account and the type associated with the type of the virtual object. The method according to claim 12, wherein The virtual scene also includes an N-dimensional graph corresponding to N types of associations whose number is greater than a quantity threshold, wherein N is a positive integer greater than 1, and the display method of the dimensions in the N-dimensional graph corresponding to the types of associations whose acquisition probability is greater than a probability threshold is different from the display method of other dimensions. The method according to any one of claims 1 to 11, wherein the method further comprises: In response to a trigger operation on any of the first virtual objects, a pop-up window corresponding to the triggered first virtual object is displayed, wherein the pop-up window includes at least one of the following information: a type associated with the type of the triggered first virtual object, attribute information of the triggered first virtual object, skill information of the triggered first virtual object, and equipment information of the triggered first virtual object. The method according to any one of claims 1 to 11, wherein The virtual scene is logged with a first account, and the number of virtual objects that can be controlled by the first account is positively correlated with the account level; The method further comprises: Displaying experience purchase controls in the virtual scene; In response to the triggering operation on the experience purchase control, after deducting a corresponding amount of virtual resources owned by the first account, the account level of the first account is increased. A virtual scene interactive processing device, the device comprising: A display module configured to display a virtual scene, wherein the virtual scene includes a store entrance and at least one first virtual object; The display module is further configured to display a store control in response to a trigger operation on the store entrance, wherein the store control includes a plurality of second virtual objects; The display module is further configured to display, for the plurality of second virtual objects, a first recommendation identifier on a second virtual object of the same type as the first virtual object and a second virtual object of a type associated with the type of the first virtual object. An electronic device, comprising: A memory for storing executable instructions; A processor is used to implement the interactive processing method of the virtual scene described in any one of claims 1 to 16 when executing the executable instructions stored in the memory. A computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, implement the interactive processing method of a virtual scene as described in any one of claims 1 to 16. A computer program product comprises a computer program or a computer executable instruction, wherein when the computer program or the computer executable instruction is executed by a processor, the interactive processing method of a virtual scene as claimed in any one of claims 1 to 16 is implemented.