Game interaction method and apparatus, computer device, computer-readable storage medium and computer program product

Abstract

Embodiments of the present application relate to the technical field of computers, and provide a game interaction method and apparatus, a computer device, a computer-readable storage medium and a computer program product. The method comprises: displaying a game page, wherein original clothes are displayed in the game page; in response to a trigger operation of a generation function, acquiring a first keyword and original clothes information of the original clothes, wherein the original clothes information comprises at least one of a first inherent color map, a first normal map and a first material map, the first inherent color map is used for indicating the style and color of the original clothes, the first normal map is used for indicating the visual effect of the original clothes, and the first material map is used for indicating the material of the original clothes; and displaying target clothes matching the first keyword and generated on the basis of the original clothes information, and on the basis of the target clothes, carrying out game interaction. The matching degree of the clothes generated by the method and a game object is high, so that game interaction is more flexible and diversified.

Description

Game interaction method, device, computer equipment, computer-readable storage medium, and computer program product

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application is based on the Chinese patent application with application number 202311431308.7 and application date October 30, 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

[0003] The embodiments of the present application relate to the field of computer technology, and relate to, but are not limited to, a game interaction method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0004] With the continuous development of computer technology, more and more users use games as a way of entertainment. In order to increase the fun of the game, different clothes are usually provided in the game for users to change into.

[0005] In related technologies, players can only choose from the costumes provided by the game, which narrows their selection and may result in the costumes provided not being what the player wants. These game interaction methods limit the depth and efficiency of player interaction, forcing players to seek other ways to further interact during the game in order to select a costume that is highly compatible with them. This obviously results in a huge waste of computing resources.

[0006] In summary, there is no effective solution in the relevant technologies for developing in-depth and efficient interactive methods in games in a resource-intensive manner.

[0007] Summary of the Invention

[0008] The embodiments of the present application provide a game interaction method, apparatus, computer device, computer-readable storage medium, and computer program product, which can expand in-depth and efficient interaction methods in the game in a resource-intensive manner, provide players with desired clothing, and improve the matching degree between the clothing selected by the players and the players.

[0009] The technical solutions of the embodiments of this application include:

[0010] An embodiment of the present application provides a game interaction method, which is executed by a computer device and includes: displaying a game page, in which an original garment is displayed; in response to a first trigger operation for a generation function, obtaining a first keyword and original garment information of the original garment; the original garment information includes at least one of a first intrinsic color map, a first normal map, and a first material map, the first intrinsic color map being used to indicate the style and color of the original garment, the first normal map being used to indicate the visual effect of the original garment, and the first material map being used to indicate the material of the original garment; displaying a target garment matching the first keyword generated based on the original garment information; and performing game interaction based on the target garment.

[0011] An embodiment of the present application provides a game interaction device, the device comprising: a display module configured to display a game page, wherein the game page displays an original garment; an acquisition module configured to acquire a first keyword and original garment information of the original garment in response to a first trigger operation for a generation function; the original garment information comprises at least one of a first intrinsic color map, a first normal map, and a first material map, the first intrinsic color map being used to indicate the style and color of the original garment, the first normal map being used to indicate the visual effect of the original garment, and the first material map being used to indicate the material of the original garment; the display module being further configured to display a target garment matching the first keyword generated based on the original garment information; and an interaction module being configured to perform game interaction based on the target garment.

[0012] An embodiment of the present application provides a computer device, which includes a processor and a memory, wherein the memory stores at least one computer instruction, and the at least one computer instruction is loaded and executed by the processor to enable the computer device to implement the above-mentioned game interaction method.

[0013] An embodiment of the present application provides a computer-readable storage medium, in which at least one computer instruction is stored. The at least one computer instruction is loaded and executed by a processor to enable a computer device to implement the above-mentioned game interaction method.

[0014] An embodiment of the present application provides a computer program product, wherein at least one computer instruction is stored in the computer program product, and the at least one computer instruction is loaded and executed by a processor to enable a computer device to implement the above-mentioned game interaction method.

[0015] The technical solutions provided by the embodiments of the present application bring at least the following beneficial effects:

[0016] The technical solution provided in the embodiment of the present application displays a target garment that matches the first keyword, generated based on the original garment information, after obtaining the first keyword and the original garment's original garment information. This method improves the flexibility and diversity of generating target garments. Furthermore, since the first keyword can accurately express the player's preferences, and the generated target garment matches the first keyword, that is, the generated target garment is a garment that matches the player, the generated garment better meets the player's needs and has a higher degree of match with the player. Players can not only select garments provided in the game, but also generate their own garments, expanding the player's range of garment choices and thereby improving the player's gaming experience. Players can interact in the game based on the target garment, increasing the diversity and flexibility of game interactions.

[0017] In addition, players can generate new clothes by themselves, so game developers do not need to design a large number of clothes, which can save game developers' art production costs and cycles, and reduce the cost of game development; and because the clothes that match the players are generated automatically in the game, players do not need to seek other ways to further interact during the game. Therefore, it is achieved in a resource-intensive way to expand in-depth and efficient interaction methods in the game, which can greatly reduce the computing resources when generating clothes. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0019] FIG1 is a schematic diagram of an implementation environment of a game interaction method provided in an embodiment of the present application;

[0020] FIG2 is a flow chart of a game interaction method provided in an embodiment of the present application;

[0021] FIG3 is a schematic diagram showing a display of a game page provided in an embodiment of the present application;

[0022] FIG4 is a schematic diagram showing another display of a game page provided in an embodiment of the present application;

[0023] FIG5 is a schematic diagram showing another display of a game page provided in an embodiment of the present application;

[0024] FIG6 is a process diagram of obtaining an intrinsic color mapping model provided by an embodiment of the present application;

[0025] FIG7 is a diagram of a process for obtaining a first text noise feature and a first image noise feature according to an embodiment of the present application;

[0026] FIG8 is a diagram of a process for obtaining a second image feature according to an embodiment of the present application;

[0027] FIG9 is a schematic diagram showing another display of a game page provided in an embodiment of the present application;

[0028] FIG10 is a flowchart of a game interaction method provided in an embodiment of the present application;

[0029] FIG11 is a schematic structural diagram of a game interaction device provided in an embodiment of the present application;

[0030] FIG12 is a schematic structural diagram of a terminal device provided in an embodiment of the present application;

[0031] FIG13 is a schematic diagram of the structure of a server provided in an embodiment of the present application. DETAILED DESCRIPTION

[0032] In order to make the objectives, technical solutions and advantages of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0033] It should be noted that the terms "first," "second," and the like in this application are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0034] Before describing the game interaction method according to the embodiment of the present application, the abbreviations and key terms involved in the embodiment of the present application are first defined.

[0035] (1) Artificial Intelligence (AI): It is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new type of intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is also the study of the design principles and implementation methods of various intelligent machines, so that machines have the functions of perception, reasoning and decision-making. Artificial intelligence technology is an interdisciplinary subject that covers a wide range of fields, including both hardware-level technology and software-level technology. Basic artificial intelligence technologies generally include sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, pre-trained model technology, operation / interaction system, and integration of several points. Among them, pre-trained models are also called large models and basic models. After fine-tuning, they can be widely used in downstream tasks in various major directions of artificial intelligence. Artificial intelligence software technology mainly includes computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0036] (2) Natural Language Processing (NLP): It is an important direction in the fields of computer science and artificial intelligence. It studies various theories and methods that can enable effective communication between humans and computers using natural language. Natural language processing involves natural language, that is, the language people use in daily life. It is closely related to linguistic research, and also involves computer science and mathematics. It is an important technology for model training in the field of artificial intelligence. The pre-training model is developed from the large language model in the field of NLP. After fine-tuning, the large language model can be widely used in downstream tasks. Natural language processing technology usually includes text processing, semantic understanding, machine translation, robot question answering, knowledge graph and other technologies.

[0037] (3) Machine Learning (ML): It is a multi-disciplinary interdisciplinary subject involving probability theory, statistics, approximation theory, convex analysis, algorithmic complexity theory and other disciplines. It specializes in studying how computers simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their own performance. Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent. Its applications are spread across all areas of artificial intelligence. Machine learning and deep learning usually include artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and self-learning. Pre-trained models are the latest development of deep learning and integrate the above technologies.

[0038] (4) Virtual scene: refers to the scene provided (or displayed) when the application is running on the terminal device. The virtual scene refers to the scene created for virtual objects to carry out activities. The virtual scene can be a two-dimensional virtual scene, a 2.5-dimensional virtual scene, or a three-dimensional virtual scene. The virtual scene can be a simulation of the real world, a semi-simulation of the real world, or a purely fictional scene. For example, the virtual scene involved in the embodiments of the present application is a three-dimensional virtual scene.

[0039] (5) Virtual Object: refers to an object that can be moved in a virtual scene. Such an object can be a virtual person, a virtual animal, an anime character, etc. Players can manipulate virtual objects through external components or by clicking on a touch screen. Each virtual object has its own shape and volume in the virtual scene and occupies a portion of the space in the virtual scene. For example, when the virtual scene is a three-dimensional virtual scene, the virtual object is a three-dimensional model created based on animation skeletal technology.

[0040] (6) Text features: a string of digital codes. Since it is impossible for computer devices to recognize text, some model tools are needed to convert text into specific digital codes that computer devices can recognize and use for subsequent image generation.

[0041] (7) Image features: a string of digital codes. Since it is impossible for computer devices to recognize pixel images, some model tools are needed to convert images into specific digital codes that computer devices can recognize and use for subsequent image generation.

[0042] FIG1 is a schematic diagram of an implementation environment of a game interaction method provided in an embodiment of the present application. As shown in FIG1 , the implementation environment includes: terminal devices (such as terminal device 100-1 and terminal device 100-2 shown in FIG1 ) and server 102. A game client capable of providing a virtual scene is installed and running in the terminal device, and the terminal device is used to execute the game interaction method provided in an embodiment of the present application.

[0043] Exemplarily, a game client capable of providing a virtual scene may be a third-person shooter (TPS) game, a first-person shooter (FPS) game, a multiplayer online tactical competitive (MOBA) game, a multiplayer shooting survival game, a massively multiplayer online role-playing game (MMO), an action role-playing game (ARPG), a virtual reality (VR) client, an augmented reality (AR) client, a three-dimensional map program, a map simulation program, a social client, an interactive entertainment client, and the like.

[0044] Server 102 provides backend services for game clients installed on terminal devices that can create virtual environments. In one possible implementation, server 102 performs primary computing tasks, while the terminal devices perform secondary computing tasks. Alternatively, server 102 performs secondary computing tasks, while the terminal devices perform primary computing tasks. Alternatively, a distributed computing architecture can be used between the terminal devices and server 102 for collaborative computing.

[0045] For example, a terminal device may be any electronic device that can interact with a user through one or more methods such as a keyboard, touchpad, remote control, voice interaction, or handwriting device. For example, a terminal device may be a smartphone, tablet computer, laptop computer, desktop computer, smart speaker, smart watch, PC (Personal Computer), mobile phone, PDA (Personal Digital Assistant), wearable device, PPC (Pocket PC), smart car computer, smart TV, etc.

[0046] A terminal device may generally refer to one of multiple terminal devices. The embodiments of this application are described using terminal devices as examples. Those skilled in the art will appreciate that the number of terminal devices may be greater or lesser. For example, there may be only one terminal device, or there may be dozens, hundreds, or even more terminal devices. The embodiments of this application do not limit the number or type of terminal devices.

[0047] The server 102 is a single server, or a server cluster consisting of multiple servers, or any one of a cloud computing platform and a virtualization center, which is not limited in the embodiments of the present application. The server 102 is directly or indirectly connected to the terminal device via a wired or wireless communication method. The server 102 has a data receiving function, a data processing function, and a data sending function. Of course, the server 102 may also have other functions, which are not limited in the embodiments of the present application.

[0048] Those skilled in the art should understand that the above-mentioned terminal device and server 102 are only examples. Other terminal devices or servers, if applicable to this application, should also be included in the scope of protection of the embodiments of this application and are included here by reference.

[0049] The present application provides a game interaction method, which can be applied to the implementation environment shown in Figure 1. Taking the flowchart of the game interaction method shown in Figure 2 as an example, the method can be executed by the terminal device in Figure 1. As shown in Figure 2, the method includes the following steps 201 to 203.

[0050] In step 201, a game page is displayed, in which original clothing is displayed.

[0051] In the exemplary embodiments of the present application, a game client is installed and running on the terminal device. The game client can be a client for any type of game, and the embodiments of the present application do not limit this. The display interface of the terminal device displays relevant information about the game client. The relevant information about the game client can be the name of the game client, an icon of the game client, or other information that can uniquely represent the game client. The embodiments of the present application do not limit the relevant information about the game client.

[0052] When the game object wants to run the game client, the game object selects the relevant information of the game client. The terminal device receives the selection operation for the relevant information of the game client, launches the game client, and displays the game homepage. The game homepage displays a virtual object, which is a virtual object controlled by the game object in the game client. The game object is the user object of the terminal device. The relevant information of the game client selected by the game object can be the relevant information of the game client clicked by the game object. The game object can also select the relevant information of the game client in other ways, and the embodiments of the present application are not limited to this.

[0053] In one possible implementation, the virtual object displayed on the game homepage is wearing the original clothing. The game homepage may also display a clothing generation control for generating clothing. When the game object wishes to generate new clothing for the virtual object, the game object selects the clothing generation control. The terminal device receives a triggering operation for the clothing generation control and displays the game page, which displays the original clothing.

[0054] Displaying original clothing on the game page means that the virtual object displayed on the game page is wearing the original clothing. The game object selecting the clothing generation control may mean that the game object clicks the clothing generation control. The game object may also select the clothing generation control in other ways, and the embodiments of the present application are not limited to this.

[0055] FIG3 is a schematic diagram of a game page provided by an embodiment of the present application. In the game page shown in FIG3 , a virtual object 301 is displayed, wherein the virtual object 301 is wearing original clothing 302 .

[0056] In step 202 , in response to a first triggering operation on a generating function, a first keyword and original clothing information of the original clothing are acquired.

[0057] The original garment information includes at least one of a first intrinsic color map, a first normal map, and a first texture map. The first intrinsic color map indicates the style and color of the original garment, the first normal map indicates the visual effect of the original garment, and the first texture map indicates the material of the original garment. The material of the original garment can be cotton, linen, silk, leather, etc.

[0058] In one possible implementation, the game page also displays a first keyword area for obtaining first keywords. For example, as shown in first keyword area 303 in Figure 3 , the first keywords obtained in first keyword area 303 may be positive keywords. Positive keywords are positive descriptive words used to describe the desired final target clothing item for the game object. In other words, positive keywords provide information on the basis of which the style of the final target clothing item is calculated and generated.

[0059] When the game object wants to generate a new costume, the game object enters text content in the first keyword area, and then the text content entered by the game object is displayed in the first keyword area of ​​the game page. In one implementation, the game object can enter a long text (i.e., the original input text whose text length is greater than the length threshold) in the first keyword area, and the terminal device can perform text recognition on the long text to obtain at least one keyword in the long text, i.e., obtain the first keyword, and display the recognized first keyword in the first keyword area. In another implementation, the game object can directly enter at least one keyword in the first keyword area, and the terminal device can display the at least one keyword entered by the game object as the first keyword in the first keyword area.

[0060] In some embodiments, a generation control is further displayed on the game page, such as generation control 304 in FIG3 . When the game object selects the generation control, the terminal device receives a first trigger operation for the generation function. In response to the first trigger operation for the generation function, the terminal device obtains the first keyword and the original clothing information of the original clothing.

[0061] In an embodiment of the present application, the process of a terminal device acquiring a first keyword includes: acquiring text content displayed in a first keyword area, and using the text content displayed in the first keyword area as the first keyword. Alternatively, using the keyword corresponding to the text content displayed in the first keyword area as the first keyword. The process of the terminal device acquiring original clothing information of an original garment includes: the terminal device generating a clothing information acquisition request, the clothing information acquisition request carrying an identifier of the original garment. The identifier of the original garment may be the name of the original garment, the number of the original garment, or another identifier that uniquely identifies the original garment, which is not limited in this embodiment of the present application. The terminal device sends the clothing information acquisition request to a clothing information server. The clothing information server receives the clothing information acquisition request sent by the terminal device, parses the clothing information acquisition request, and obtains the identifier of the original garment. The clothing information server stores clothing information of each garment and the corresponding relationship between the identifier of each garment and the clothing information of the corresponding garment. The clothing information server determines the original clothing information of the original garment based on the identifier of the original garment and the corresponding relationship between the identifier of each garment and the clothing information of the corresponding garment. The clothing information server sends the original clothing information of the original garment to the terminal device, so that the terminal device acquires the original clothing information of the original garment.

[0062] In step 203, a target garment generated based on the original garment information and matching the first keyword is displayed, and game interaction is performed based on the target garment.

[0063] In a possible implementation, before displaying the target clothing matching the first keyword generated based on the original clothing information, it is necessary to first generate the target clothing matching the first keyword based on the original clothing information.

[0064] In response to a second trigger operation for the generation function, a second keyword, a target sampling number, and a target matching degree may also be obtained; the second keyword is a keyword that does not match the target garment, the target sampling number is the number of repetitions of the sampling process for obtaining the target garment information of the target garment, and the target matching degree is the matching degree between the target garment and the first keyword. The target garment information includes at least one of a second intrinsic color map, a second normal map, and a second texture map. The second intrinsic color map is used to indicate the style and color of the target garment, the second normal map is used to indicate the visual effect of the target garment, and the second texture map is used to indicate the material of the target garment.

[0065] The game page may also display a second keyword area, a sampling number area, and a matching degree area. The second keyword area is used to obtain a second keyword, the sampling number area is used to obtain a target sampling number, and the matching degree area is used to obtain a target matching degree. For example, the second keyword area 305, the sampling number area 306, and the matching degree area 307 in Figure 3 . The second keyword obtained in the second keyword area 305 may be a reverse keyword. A reverse keyword refers to a descriptive word used to describe the opposite of the final target clothing that the game object does not want to generate, that is, the reverse keyword provides information that the style of the calculated final target clothing will not be based on.

[0066] The game object can enter text content in the second keyword area, determine the target sampling times by sliding the sliding control in the sampling times area, and determine the target matching degree by sliding the sliding control in the matching degree area. Then, the input text content is displayed in the second keyword area of ​​the game page, the target sampling times is displayed in the sampling times area, and the target matching degree is displayed in the matching degree area. Figure 4 is a display diagram of another game page provided by an embodiment of the present application. The text content displayed in the first keyword area of ​​the game page shown in Figure 4 is "long sleeves, skirts, gentleness, fashion", and the text content displayed in the second keyword area is "short sleeves, thin clothes, plastic feeling", the target sampling times displayed in the sampling times area is "20", and the target matching degree displayed in the matching degree area is "0.4".

[0067] In response to the second trigger operation for the generate function, the process of obtaining the second keyword includes: obtaining the text content displayed in the second keyword area, and using the text content displayed in the second keyword area as the second keyword. Alternatively, the keyword corresponding to the text content displayed in the second keyword area is used as the second keyword. The process of obtaining the target sampling number includes: using the sampling number displayed in the sampling number area as the target sampling number. The process of obtaining the target matching degree includes: using the matching degree displayed in the matching degree area as the target matching degree.

[0068] The process of generating a target garment matching a first keyword based on the original garment information includes: generating the target garment by sampling the target garment a target number of times based on the first keyword, the second keyword, the target matching degree, and the original garment information. The matching degree between the target garment and the first keyword is the target matching degree, and the target garment does not match the second keyword.

[0069] In one possible implementation, a generation progress bar can be displayed on the game page in response to a triggering operation for the generation function. The generation progress bar indicates the generation progress of the target garment. FIG5 is a schematic diagram of another game page display provided in an embodiment of the present application. FIG5 shows a generation progress bar 501 displayed on the game page. As can be seen from the displayed generation progress bar, the target garment is being generated and has reached 20% of its generation.

[0070] In an embodiment of the present application, the process of generating target clothing by sampling by a target sampling number according to the first keyword, the second keyword, the target matching degree and the original clothing information includes: obtaining target clothing information of the target clothing by sampling by a target sampling number according to the first keyword, the second keyword, the target matching degree and the original clothing information; then, generating the target clothing according to the target clothing information.

[0071] In one possible implementation, based on the original clothing information including a first intrinsic color map and the target clothing information including a second intrinsic color map, the second intrinsic color map of the target clothing can be acquired by sampling a target number of times based on the first keyword, the second keyword, the target matching degree, and the first intrinsic color map. Based on the original clothing information including a first normal map and the target clothing information including a second normal map, the second normal map of the target clothing can be acquired by sampling a target number of times based on the first keyword, the second keyword, the target matching degree, and the first normal map. Based on the original clothing information including a first material map and the target clothing information including a second material map, the second material map of the target clothing can be acquired by sampling a target number of times based on the first keyword, the second keyword, the target matching degree, and the first material map.

[0072] The process of obtaining the second intrinsic color map of the target clothing by sampling the target sampling times according to the first keyword, the second keyword, the target matching degree and the first intrinsic color map, the process of obtaining the second normal map of the target clothing by sampling the target sampling times according to the first keyword, the second keyword, the target matching degree and the first normal map, and the process of obtaining the second material map of the target clothing by sampling the target sampling times according to the first keyword, the second keyword, the target matching degree and the first material map are similar. The embodiment of the present application only takes the process of obtaining the second intrinsic color map of the target clothing by sampling the target sampling times according to the first keyword, the second keyword, the target matching degree and the first intrinsic color map as an example to illustrate.

[0073] In some embodiments, the process of obtaining the second inherent color map of the target clothing by sampling a target sampling number of times according to the first keyword, the second keyword, the target matching degree and the first inherent color map includes: obtaining target text features according to the first keyword and the second keyword, and the target text features are used to characterize the first keyword and the second keyword; obtaining first image features according to the first inherent color map, and the first image features are used to characterize the first inherent color map; obtaining second image features by sampling a target sampling number of times according to the target text features, the first image features and the target matching degree, and the second image features are used to characterize the second inherent color map; decoding the second image features to obtain a second inherent color map.

[0074] The present application does not limit the method for obtaining target text features based on the first keyword and the second keyword. The process of obtaining target text features based on the first keyword and the second keyword includes: obtaining a first text feature for representing the first keyword; obtaining a second text feature for representing the second keyword; and obtaining target text features based on the first text feature and the second text feature.

[0075] Among them, the process of obtaining the first text feature for characterizing the first keyword is similar to the process of obtaining the second text feature for characterizing the second keyword. The embodiment of the present application only takes the process of obtaining the first text feature for characterizing the first keyword as an example for explanation. The process of obtaining the first text feature for characterizing the first keyword includes: inputting the first keyword into a contrastive language-image pre-training (CLIP) encoder, and using the content output by the CLIP encoder as the first text feature. Among them, the CLIP encoder is a pre-training model for comparing text and pictures. The role of the CLIP encoder is to link pictures and text. In the embodiment of the present application, the text encoder of the CLIP encoder is mainly used to convert text into text features.

[0076] In some embodiments, the first text feature and the second text feature have the same dimension. The process of obtaining the target text feature based on the first text feature and the second text feature includes: adding the values ​​of the first text feature and the second text feature at corresponding positions to obtain the target text feature; or multiplying the values ​​of the first text feature and the second text feature at corresponding positions to obtain the target text feature; or determining the average value of the values ​​of the first text feature and the second text feature at corresponding positions, and obtaining the target text feature based on the average value of the values ​​of the first text feature and the second text feature at corresponding positions.

[0077] For example, the first text feature is (A, B, C), the second text feature is (D, E, F), and the target text feature is (A+D, B+E, C+F).

[0078] Alternatively, the first text feature is (A, B, C), the second text feature is (D, E, F), and the target text feature is (AD, BE, CF).

[0079] Or, if the first text feature is (A, B, C) and the second text feature is (D, E, F), then the target text feature is

[0080] In some embodiments, if the dimension of the first text feature is greater than the dimension of the second text feature, the second text feature is subjected to dimensionality upscaling to obtain a second text feature after dimensionality upscaling, where the dimension of the second text feature after dimensionality upscaling is the same as the dimension of the first text feature; and then, a target text feature is obtained based on the first text feature and the second text feature after dimensionality upscaling. The process of obtaining the target text feature based on the first text feature and the second text feature after dimensionality upscaling is similar to the process of obtaining the target text feature based on the first text feature and the second text feature described above, and will not be further described here.

[0081] In some embodiments, if the dimension of the first text feature is smaller than the dimension of the second text feature, the first text feature is subjected to dimensionality upscaling to obtain a first text feature after dimensionality upscaling, where the dimension of the first text feature after dimensionality upscaling is the same as the dimension of the second text feature; and then, a target text feature is obtained based on the first and second text features after dimensionality upscaling. The process of obtaining the target text feature based on the first and second text features after dimensionality upscaling is similar to the process of obtaining the target text feature based on the first and second text features described above, and will not be further described here.

[0082] In a possible implementation, the target text feature can be obtained based on the first text feature and the second text feature in the following manner: inputting the first text feature and the second text feature into a CLIP encoder, and using the content output by the CLIP encoder as the target text feature.

[0083] In some embodiments, obtaining the first image features based on the first intrinsic color map includes: compiling the first intrinsic color map, performing dimensionality reduction processing, and adding random noise to the first intrinsic color map using a variational autoencoder (VAE) to obtain a noise map, and obtaining the first image features based on the noise map. The VAE includes an encoder and a decoder, wherein the encoder is configured to convert an image into image features in a latent space, and the decoder is configured to convert the image features in the latent space into an image.

[0084] For example, the first intrinsic color map is 512*512 pixels after compilation and becomes 64*64 pixels after dimensionality reduction.

[0085] In some embodiments, the process of obtaining the second image feature by sampling the target sampling times according to the target text feature, the first image feature and the target matching degree includes: for the first time in the target sampling times, first, obtaining the first text noise feature and the first image noise feature according to the target text feature, the first image feature and the first numerical value; then, determining the first reference feature according to the first text noise feature, the first image noise feature, the target matching degree and the first image feature; the first reference feature is the feature obtained by denoising the first image feature for the first time, the first text noise feature and the first image noise feature are matched with the target text feature and the first image feature respectively, and the first numerical value is used to represent the first time. For the non-first time in the target sampling times, first, the second text noise feature and the second image noise feature are obtained according to the target text feature, the reference feature and the second numerical value; then, the second reference feature is determined according to the second text noise feature, the second image noise feature, the target matching degree and the reference feature; the second reference feature is the feature obtained by denoising the first image feature for the non-first time, the second text noise feature and the second image noise feature are matched with the target text feature and the reference feature respectively, the reference feature is the feature obtained by the last sampling of the non-first sampling, and the second numerical value is used to indicate that it is not the first time; the feature obtained by the last sampling of the target sampling times is used as the second image feature.

[0086] For example, the first value for indicating the first time is 1, and if the non-first time is the Nth time, the second value for indicating the non-first time is N. N is an integer greater than 1. For example, if the non-first time is the third time, the second value is 3.

[0087] The process of obtaining the first text noise feature and the first image noise feature according to the target text feature, the first image feature and the first numerical value includes: obtaining the first text noise feature and the first image noise feature according to the target text feature, the first image feature, the first numerical value and the inherent color map model.

[0088] Among them, before obtaining the first text noise feature and the first image noise feature according to the target text feature, the first image feature, the first numerical value and the intrinsic color mapping model, it is necessary to first obtain the intrinsic color mapping model. The process of obtaining the intrinsic color mapping model includes: first, obtaining the sample image and the text corresponding to the sample image; then, inputting the sample image and the text corresponding to the sample image into the initial intrinsic color mapping model; performing multiple noise additions on the sample image through the initial intrinsic color mapping model, and recording the noise features added each time the sample image is noised; finally, the sample image, the text corresponding to the sample image, and the noise features added each time the sample image is noised are stored in the initial intrinsic color mapping model, thereby obtaining the intrinsic color mapping model. That is, the intrinsic color mapping model stores the sample image, the text corresponding to the sample image, and the noise features added each time the sample image is noised.

[0089] The initial intrinsic color map model may be a Denoising Diffusion Probabilistic Model (DDPM).

[0090] Figure 6 is a diagram illustrating a process for obtaining an intrinsic color mapping model according to an embodiment of the present application. In Figure 6, a sample image and the text corresponding to the sample image ("A cat in the snow") are input into the initial intrinsic color mapping model. After multiple noise additions, the noise characteristics added during each noise addition and the resulting image are obtained. The sample image, the text corresponding to the sample image, and the noise characteristics added during each noise addition are stored in the initial intrinsic color mapping model, thereby obtaining the intrinsic color mapping model.

[0091] In some embodiments, the process of obtaining the first text noise feature and the first image noise feature based on the target text feature, the first image feature, the first numerical value, and the intrinsic color mapping model includes: using the noise feature added to the sample image corresponding to the first text in the intrinsic color mapping model when the noise is increased by the first numerical value as the first text noise feature, and using the noise added to the first image in the intrinsic color mapping model when the noise is increased by the first numerical value as the first image noise feature. Among them, the first text is the text whose matching degree between the corresponding text feature and the target text feature meets the matching requirements, and the first image is the sample image whose matching degree between the corresponding image feature and the first image feature meets the matching requirements. The matching degree meeting the matching requirements can be the highest matching degree, and the matching degree meeting the matching requirements can also be other, which is not limited in the embodiments of the present application.

[0092] FIG7 is a diagram illustrating a process for obtaining a first text noise feature and a first image noise feature according to an embodiment of the present application. In FIG7 , target text feature 701 , first image feature 702 , and first value 703 are input into intrinsic color mapping model 704 , from which first text noise feature 705 and first image noise feature 706 are obtained.

[0093] Exemplarily, the intrinsic color map model stores sample image 1, text 1 corresponding to sample image 1, noise feature 1, noise feature 2, and noise feature 3 added to sample image 1 during three noise additions, sample image 2, text 2 corresponding to sample image 2, and noise feature 4, noise feature 5, and noise feature 6 added to sample image 2 during three noise additions. If the text with the highest degree of match with the target text feature is text 1, then noise feature 1 added to sample image 1 corresponding to text 1 during the first noise addition is used as the first text noise feature. If the sample image with the highest degree of match with the first image feature is sample image 2, then noise feature 4 added to sample image 2 during the first noise addition is used as the first image noise feature.

[0094] After obtaining the first text noise feature and the first image noise feature, the process of determining the first reference feature based on the first text noise feature, the first image noise feature, the target matching degree and the first image feature includes: first, determining the intermediate noise feature based on the first text noise feature, the first image noise feature and the target matching degree; then, determining the first reference feature based on the intermediate noise feature and the first image feature.

[0095] In an embodiment of the present application, the process of determining an intermediate noise feature based on a first text noise feature, a first image noise feature, and a target matching degree includes: first, determining the difference between the first text noise feature and the first image noise feature; then, determining the product of the difference and the target matching degree; and finally, using the sum of the product and the first image noise as the intermediate noise feature. The process of determining a first reference feature based on the intermediate noise feature and the first image feature includes: using the difference between the first image feature and the intermediate noise feature as the first reference feature.

[0096] For example, based on the first text noise feature, the first image noise feature and the target matching degree, the intermediate noise feature can be determined according to the following formula (1).

[0097] W=(XY)*Z+Y Formula (1)

[0098] In the above formula (1), W is the intermediate noise feature, X is the first text noise feature, Y is the first image noise feature, and Z is the target matching degree.

[0099] According to the intermediate noise feature and the first image feature, the first reference feature can be determined according to the following formula (2).

[0100] H=YW Formula (2)

[0101] In the above formula (2), H is the first reference feature, Y is the first image noise feature, and W is the intermediate noise feature.

[0102] In one possible implementation, the process of obtaining the second text noise feature and the second image noise feature based on the target text feature, the reference feature and the second numerical value is similar to the process of obtaining the first text noise feature and the first image noise feature based on the target text feature, the first image feature and the first numerical value; the process of determining the second reference feature based on the second text noise feature, the second image noise feature, the target matching degree and the reference feature is similar to the process of determining the first reference feature based on the first text noise feature, the first image noise feature, the target matching degree and the first image feature, and they will not be described one by one here.

[0103] For example, the target sampling times is 3 times, and the target matching degree is 0.4. Based on the target text feature, the first image feature, and 1, text noise feature 1 and image noise feature 1 are obtained. Based on text noise feature 1, image noise feature 1, 0.4, and the first image feature, reference feature 1 is determined. Based on the target text feature, reference features 1, and 2, text noise feature 2 and image noise feature 2 are obtained. Based on text noise feature 2, image noise feature 2, 0.4, and reference feature 1, reference feature 2 is determined. Based on the target text feature, reference features 2, and 3, text noise feature 3 and image noise feature 3 are obtained. Based on text noise feature 3, image noise feature 3, 0.4, and reference feature 2, reference feature 3 is determined. At this point, three sampling processes have been performed, so reference feature 3 is used as the second image feature.

[0104] As shown in Figure 8, a process diagram for obtaining the second image feature provided by an embodiment of the present application is shown. In Figure 8, the target sampling times 801, the first image feature 702 and the target text feature 802 are input into the U-NET neural network 803 (the network for generating clothing) to obtain the first text noise feature 705 and the first image noise feature 706; the intermediate noise feature 805 is determined based on the target matching degree 804, the first text noise feature 705 and the first image noise feature 706; the first reference feature 806 is determined based on the intermediate noise feature 805 and the first image feature 702; the first reference feature 806 is input into the U-NET neural network 803 to continue sampling until the feature obtained by the last sampling is obtained, and the feature obtained by the last sampling is used as the second image feature. Among them, the U-NET neural network is embedded with an intrinsic color mapping model.

[0105] After acquiring the second image feature, the second image feature is decoded to obtain the second intrinsic color map. The process includes: decoding the second image feature to obtain a pixel map corresponding to the second image feature; and generating a second intrinsic color map based on the pixel map corresponding to the second image feature. The second image feature is decoded by VAE to obtain a pixel map corresponding to the second image feature, and the pixel map corresponding to the second image feature is transmitted back to the file generation server, and the second intrinsic color map is generated by the file generation server. The file generation server and the clothing information server mentioned above can be the same server or different servers, and the embodiments of the present application do not limit this.

[0106] In some embodiments, the U-NET neural network is further embedded with a normal map model and a material map model. The acquisition process of the normal map model and the material map model is similar to the acquisition process of the above-mentioned intrinsic color map model, and will not be repeated here. Based on the original clothing information including the first normal map and the target clothing information including the second normal map, according to the first keyword, the second keyword, the target matching degree and the first normal map, the process of sampling and obtaining the second normal map by the target sampling number is similar to the above-mentioned process of sampling and obtaining the second intrinsic color map by the target sampling number based on the first keyword, the second keyword, the target matching degree and the first intrinsic color map. Based on the original clothing information including the first material map and the target clothing information including the second material map, according to the first keyword, the second keyword, the target matching degree and the first material map, the process of sampling and obtaining the second material map by the target sampling number is similar to the above-mentioned process of sampling and obtaining the second intrinsic color map by the target sampling number based on the first keyword, the second keyword, the target matching degree and the first intrinsic color map, and will not be repeated here in detail in the embodiments of the present application.

[0107] The terminal device also stores a clothing model. After acquiring target clothing information of the target clothing, a process of generating the target clothing based on the target clothing information includes mapping the target clothing information onto the clothing model to obtain the target clothing. The target clothing information includes a second intrinsic color map, a second normal map, and a second texture map. The second intrinsic color map, the second normal map, and the second texture map are respectively mapped onto the clothing model to obtain the target clothing.

[0108] In a possible implementation, after the target garment is generated, the target garment may be displayed on the game page. The process of displaying the target garment on the game page includes: canceling the original garment displayed on the game page and displaying the target garment on the game page.

[0109] When the original clothing is displayed on the game page, the virtual object displayed on the game page is wearing the original clothing. After the target clothing is generated, the process of displaying the target clothing on the game page includes: replacing the clothing worn by the virtual object on the game page from the original clothing to the target clothing, so as to achieve the purpose of displaying the target clothing on the game page.

[0110] The game interaction method provided in the embodiment of the present application generates target clothing for virtual objects through artificial intelligence technology, which can be widely used in at least the following scenarios: (1) Game development: During the game production process, the game interaction method provided in the embodiment of the present application can help designers quickly generate target clothing in various styles, thereby improving design efficiency. This technology is particularly useful for games that require a large number of characters. In addition, the game interaction method provided in the embodiment of the present application can also automatically adjust the clothing style and elements according to the setting of the game world and the background story of the character to ensure the consistency and accuracy of the design. (2) Personalization: Players can use the game interaction method provided in the embodiment of the present application to customize unique clothing according to their favorite style or the characteristics of the game character. This personalized service can enhance the player's gaming experience and the personalized expression of the character. (3) Virtual try-on: The game interaction method provided in the embodiment of the present application can realize the try-on function of the virtual character in the game. Players can preview the effect of the clothing on the character before purchasing the clothing, thereby improving the satisfaction of clothing purchases and reducing the return rate. (4) Cross-platform content creation: Content creators can use the game interaction method provided in the embodiment of the present application to quickly create clothing designs related to game characters on different platforms, including social media, 3D printing, virtual reality and other fields. (5) Cultural inheritance and innovation: The game interaction method provided in the embodiment of the present application can innovatively design the costumes of game characters on the basis of respecting and protecting traditional culture. It can integrate traditional elements and modern design to promote and inherit excellent traditional culture. (6) Marketing and promotion: In marketing activities, game companies can attract players through the clothing designs generated by the game interaction method provided in the embodiment of the present application, such as holding clothing design competitions to increase player participation and game popularity. (7) Education and training: In the education and training of game design and development, the clothing generation technology provided by the game interaction method provided in the embodiment of the present application can be used as a tool to help students better understand character design and the construction of the game world. (8) Prototype testing: In the early stages of game development, the game interaction method provided in the embodiment of the present application can quickly generate a variety of clothing prototypes for designers and testers to evaluate and provide feedback, thereby accelerating the process of game development.

[0111] FIG9 is a schematic diagram showing another game page provided by an embodiment of the present application. In FIG9 , a virtual object 901 is shown wearing a target outfit 902 .

[0112] In one possible implementation, after the target costume is generated, the generation control displayed on the game page is canceled, and a save control and a regenerate control are displayed on the game page. The save control is used to save the target costume, and the regenerate control is used to regenerate the costume based on the modified information after changing at least one of the first keyword, the second keyword, the target sampling number, and the target matching degree. The process of regenerating the costume is similar to the process of generating the target costume and will not be described in detail here. For example, 903 in Figure 9 is the save control, and 904 is the regenerate control.

[0113] In the embodiment of the present application, after saving the target clothing, the process of performing game interaction based on the target clothing includes any of the following: controlling a virtual object to wear the target clothing to play the game; selling the target clothing; participating in a game evaluation activity based on the target clothing.

[0114] Selling the target costume grants the player in-game resources, allowing them to purchase other virtual items within the game. The player can also participate in a game evaluation based on the target costume. If the target costume receives enough votes to qualify, the player can receive the corresponding reward resources. This can include receiving the highest number of votes, in which case the player can receive the corresponding reward resources.

[0115] In one possible implementation, when a virtual object displayed in a game page is wearing original clothing, in response to a trigger operation on the virtual object, a clothing page is displayed, and at least one optional clothing is displayed on the clothing page; in response to a trigger operation on any of the at least one optional clothing, the clothing worn by the virtual object displayed in the game page is replaced from the original clothing to any of the clothing; in response to a trigger operation on a generation function, clothing information of any clothing is obtained, and new clothing is generated by sampling through a target sampling number of times based on the clothing information of any clothing, a first keyword, a second keyword, and a target matching degree.

[0116] The clothing information of any garment includes at least one of an intrinsic color map of any garment, a normal map of any garment, and a material map of any garment. The intrinsic color map of any garment is used to indicate the style and color of any garment, the normal map of any garment is used to indicate the visual effect of any garment, and the material map of any garment is used to indicate the material of any garment. The process of generating a new garment by sampling a target number of times based on the clothing information of any garment, the first keyword, the second keyword, and the target matching degree is similar to the process of generating a target garment by sampling a target number of times based on the first keyword, the second keyword, the target matching degree, and the original clothing information in the above process, and will not be repeated here.

[0117] After obtaining the first keyword and the original clothing information of the original clothing, the above method displays target clothing that matches the first keyword, generated based on the original clothing information. This method improves the flexibility and diversity of generating target clothing. Furthermore, because the first keyword accurately expresses the player's preferences, and the generated target clothing matches the first keyword, the generated target clothing is a clothing that matches the player, making the generated clothing more suitable for the player's needs and more compatible with the player. Players can not only select clothing provided in the game, but also generate their own clothing, expanding the player's range of clothing choices and thereby enhancing the player's gaming experience. Players can interact in the game based on the target clothing, increasing the diversity and flexibility of game interactions.

[0118] In addition, players can generate new clothes by themselves, so game developers do not need to design more clothes, which can save game developers' art production costs and cycles and reduce the cost of game development.

[0119] Figure 10 is a flow chart of a game interaction method provided by an embodiment of the present application. As shown in Figure 10, the process includes: obtaining a first keyword, a second keyword, a target sampling number, a target matching degree, a first intrinsic color map of the original clothing, a first normal map, and a first material map. The first keyword and the second keyword are processed by a CLIP encoder to obtain target text features. The first intrinsic color map is VAE-encoded to obtain image features of the first intrinsic color map, the first normal map is VAE-encoded to obtain image features of the first normal map, and the first material map is VAE-encoded to obtain image features of the first material map. The target text features, target sampling number, target matching degree, and image features of the first intrinsic color map are input into a U-NET neural network to obtain image features of the second intrinsic color map. The target text features, target sampling number, target matching degree, and image features of the first normal map are input into a U-NET neural network to obtain image features of the second normal map. The target text features, target sampling number, target matching degree, and image features of the first material map are input into a U-NET neural network to obtain image features of the second material map. Perform VAE decoding on the image features of the second intrinsic color map to obtain a pixel map corresponding to the image features of the second intrinsic color map; perform VAE decoding on the image features of the second normal map to obtain a pixel map corresponding to the image features of the second normal map; perform VAE decoding on the image features of the second texture map to obtain a pixel map corresponding to the image features of the second texture map. Obtain a second intrinsic color map based on the pixel map corresponding to the image features of the second intrinsic color map; obtain a second normal map based on the pixel map corresponding to the image features of the second normal map; and obtain a second texture map based on the pixel map corresponding to the image features of the second texture map. Generate the target garment based on the second intrinsic color map, the second normal map, and the second texture map.

[0120] FIG11 is a schematic diagram showing the structure of a game interaction device provided in an embodiment of the present application. As shown in FIG11 , the device includes:

[0121] The display module 1101 is configured to display a game page in which the original clothing is displayed; the acquisition module 1102 is configured to obtain a first keyword and original clothing information of the original clothing in response to a first trigger operation for a generation function; the original clothing information includes at least one of a first intrinsic color map, a first normal map, and a first material map, the first intrinsic color map is used to indicate the style and color of the original clothing, the first normal map is used to indicate the visual effect of the original clothing, and the first material map is used to indicate the material of the original clothing; the display module 1101 is also configured to display a target clothing that matches the first keyword and is generated based on the original clothing information; the interaction module 1103 is configured to perform game interaction based on the target clothing.

[0122] In some embodiments, a virtual object is also displayed in the game page, and the virtual object wears the original clothing; the display module 1101 is further configured to replace the clothing worn by the virtual object displayed in the game page from the original clothing to the target clothing.

[0123] In some embodiments, the interaction module 1103 is further configured to perform at least one of the following: controlling a virtual object to wear a target garment to play a game; selling the target garment; and participating in a game evaluation activity based on the target garment.

[0124] In some embodiments, the acquisition module 1102 is further configured to acquire a second keyword, a target sampling number and a target matching degree in response to a second trigger operation for the generation function; the second keyword is a keyword that does not match the target clothing, the target sampling number is the number of repetitions of the sampling process for obtaining the target clothing information of the target clothing, and the target matching degree is the matching degree between the target clothing and the first keyword; the target clothing information includes at least one of a second intrinsic color map, a second normal map and a second material map, the second intrinsic color map is used to indicate the style and color of the target clothing, the second normal map is used to indicate the visual effect of the target clothing, and the second material map is used to indicate the material of the target clothing; the device also includes: a generation module 1104, configured to generate the target clothing by sampling according to the target sampling number based on the first keyword, the second keyword, the target matching degree and the original clothing information; the matching degree between the target clothing and the first keyword is the target matching degree, and the target clothing does not match the second keyword.

[0125] In some embodiments, the generation module 1104 is further configured to obtain target clothing information of the target clothing by sampling according to the target sampling number of times based on the first keyword, the second keyword, the target matching degree and the original clothing information; and generate the target clothing based on the target clothing information.

[0126] In some embodiments, the original clothing information includes a first inherent color map, and the target clothing information includes a second inherent color map; the generation module 1104 is further configured to obtain target text features based on the first keyword and the second keyword; the target text features are used to represent the first keyword and the second keyword; according to the first inherent color map, a first image feature is obtained; the first image feature is used to represent the first inherent color map; according to the target text feature, the first image feature and the target matching degree, the second image feature is sampled according to the target sampling number of times to obtain the second image feature; the second image feature is used to represent the second inherent color map; the second image feature is decoded to obtain the second inherent color map.

[0127] In some embodiments, the generation module 1104 is further configured to, for the first time in the target sampling times, obtain a first text noise feature and a first image noise feature based on the target text feature, the first image feature, and the first numerical value; determine a first reference feature based on the first text noise feature, the first image noise feature, the target matching degree, and the first image feature; the first reference feature is a feature obtained by denoising the first image feature for the first time, the first text noise feature matches the target text feature, the first image noise feature matches the first image feature, and the first numerical value is used to indicate the first time; for the non-first time in the target sampling times, obtain a second text noise feature and a second image noise feature based on the target text feature, the reference feature, and the second numerical value; determine a second reference feature based on the second text noise feature, the second image noise feature, the target matching degree, and the reference feature; the second reference feature is a feature obtained by denoising the first image feature for the non-first time, the second text noise feature matches the target text feature, the second image noise feature matches the reference feature, the reference feature is a feature obtained by sampling last than the non-first time, and the second numerical value is used to indicate the non-first time; and determine the feature obtained by sampling last than the target sampling times as the second image feature.

[0128] In some embodiments, the generation module 1104 is further configured to determine an intermediate noise feature based on the first text noise feature, the first image noise feature, and the target matching degree; and determine a first reference feature based on the intermediate noise feature and the first image feature.

[0129] In some embodiments, the generation module 1104 is further configured to obtain a first text feature for representing the first keyword; obtain a second text feature for representing the second keyword; and obtain a target text feature based on the first text feature and the second text feature.

[0130] In some embodiments, the dimension of the first text feature is the same as the dimension of the second text feature; the generating module 1104 is further configured to add the values ​​of the first text feature and the second text feature at corresponding positions to obtain the target text feature.

[0131] In some embodiments, the dimension of the first text feature is the same as the dimension of the second text feature; the generating module 1104 is further configured to multiply the values ​​of the first text feature and the second text feature at corresponding positions to obtain the target text feature.

[0132] In some embodiments, the generation module 1104 is further configured to decode the second image feature to obtain a pixel map corresponding to the second image feature; and generate a second intrinsic color map based on the pixel map corresponding to the second image feature.

[0133] After obtaining a first keyword and the original clothing information of the original clothing, the device displays a target clothing item that matches the first keyword, generated based on the original clothing information. The method implemented by this device improves the flexibility and diversity of generating target clothing items. Furthermore, because the first keyword accurately expresses the player's preferences, and the generated target clothing item matches the first keyword, the generated target clothing item is a clothing item that matches the player, making the generated clothing item more suitable for the player's needs and providing a higher degree of match. Players can not only select clothing items provided in the game, but can also generate their own clothing items, expanding the player's range of clothing options and thereby enhancing the player's gaming experience. Players can interact in the game based on the target clothing item, increasing the diversity and flexibility of game interactions.

[0134] In addition, players can generate new clothes by themselves, so game developers do not need to design more clothes, which can save game developers' art production costs and cycles and reduce the cost of game development.

[0135] It should be understood that the above-mentioned device is merely an example of the division of the above-mentioned functional modules when implementing its functions. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiments are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0136] FIG12 shows a block diagram of a terminal device 1200 provided in accordance with an exemplary embodiment of the present application. The terminal device 1200 may be any electronic device capable of human-computer interaction with a user through one or more methods, such as a keyboard, touchpad, remote control, voice interaction, or handwriting device. Examples include a personal computer (PC), mobile phone, smartphone, personal digital assistant (PDA), wearable device, Pocket PC (PPC), tablet computer, smart car computer, smart TV, smart speaker, smart watch, etc.

[0137] Typically, the terminal device 1200 includes a processor 1201 and a memory 1202 .

[0138] The processor 1201 may include one or more processing cores, such as a quad-core processor, an octa-core processor, and the like. The processor 1201 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), and programmable logic array (PLA). The processor 1201 may also include a main processor and a coprocessor. The main processor is a processor for processing data in an awake state, also known as a central processing unit (CPU); the coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor 1201 may be integrated with a graphics processing unit (GPU), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 1201 may also include an artificial intelligence (AI) processor, which is used to process computing operations related to machine learning.

[0139] The memory 1202 may include one or more computer-readable storage media, which may be non-transitory. The memory 1202 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices and flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 1202 is used to store at least one computer instruction, which is used to be executed by the processor 1201 to implement the game interaction method provided in the method embodiment of the present application.

[0140] In some embodiments, terminal device 1200 may optionally include a peripheral device interface 1203 and at least one peripheral device. The processor 1201, memory 1202, and peripheral device interface 1203 may be connected via a bus or signal lines. Each peripheral device may be connected to peripheral device interface 1203 via a bus, signal lines, or circuit boards. The peripheral device may include at least one of a radio frequency circuit 1204, a display screen 1205, a camera assembly 1206, an audio circuit 1207, and a power supply 1209.

[0141] The peripheral device interface 1203 can be used to connect at least one input / output (I / O)-related peripheral device to the processor 1201 and the memory 1202. In some embodiments, the processor 1201, the memory 1202, and the peripheral device interface 1203 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 1201, the memory 1202, and the peripheral device interface 1203 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0142] The radio frequency circuit 1204 is used to receive and transmit radio frequency (RF) signals, also known as electromagnetic signals. The radio frequency circuit 1204 communicates with communication networks and other communication devices via electromagnetic signals. The radio frequency circuit 1204 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals into electrical signals. The radio frequency circuit 1204 includes an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, and the like. The radio frequency circuit 1204 can communicate with other terminal devices via at least one wireless communication protocol. Such wireless communication protocols include, but are not limited to, at least one of the World Wide Web, a metropolitan area network, an intranet, various generations of mobile communication networks (2G, 3G, 4G, and 5G), a wireless local area network, and a wireless fidelity (WiFi) network. In some embodiments, the radio frequency circuit 1204 may also include circuits related to near field communication (NFC), which is not limited in this application.

[0143] The display screen 1205 is used to display a user interface (UI). The UI may include graphics, text, icons, videos, and any combination thereof. When the display screen 1205 is a touch screen display, the display screen 1205 also has the ability to collect touch signals on or above the surface of the display screen 1205. The touch signal can be input as a control signal to the processor 1201 for processing. In this case, the display screen 1205 can also be used to provide at least one of a virtual button and a virtual keyboard, also known as at least one of a soft button and a soft keyboard. In some embodiments, there can be one display screen 1205, which is disposed on the front panel of the terminal device 1200; in other embodiments, there can be at least two display screens 1205, which are disposed on different surfaces of the terminal device 1200 or in a foldable design; in other embodiments, the display screen 1205 can be a flexible display screen, which is disposed on a curved surface or a foldable surface of the terminal device 1200. The display screen 1205 can even be configured as a non-rectangular irregular shape, that is, a special-shaped screen. The display screen 1205 can be made of materials such as a liquid crystal display (LCD) and an organic light-emitting diode (OLED).

[0144] The camera assembly 1206 is used to capture images or videos. The camera assembly 1206 includes a front camera and a rear camera. Typically, the front camera is arranged on the front panel of the terminal device 1200, and the rear camera is arranged on the back of the terminal device 1200. In some embodiments, there are at least two rear cameras, which are any one of a main camera, a depth of field camera, a wide-angle camera, and a telephoto camera, so as to realize the fusion of the main camera and the depth of field camera to realize the background blur function, the fusion of the main camera and the wide-angle camera to realize panoramic shooting and virtual reality (VR) shooting function or other fusion shooting functions. In some embodiments, the camera assembly 1206 may also include a flash. The flash can be a single-color temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm light flash and a cold light flash, which can be used for light compensation at different color temperatures.

[0145] The audio circuit 1207 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, converting them into electrical signals that are then input into the processor 1201 for processing, or into the RF circuit 1204 for voice communication. For stereo sound collection or noise reduction, multiple microphones may be provided, located in different locations within the terminal device 1200. The microphone may also be an array microphone or an omnidirectional microphone. The speaker is used to convert electrical signals from the processor 1201 or the RF circuit 1204 into sound waves. The speaker may be a traditional thin-film speaker or a piezoelectric ceramic speaker. A piezoelectric ceramic speaker can convert electrical signals not only into audible sound waves but also into inaudible sound waves for purposes such as distance measurement. In some embodiments, the audio circuit 1207 may also include a headphone jack.

[0146] The power supply 1209 is used to power the various components in the terminal device 1200. The power supply 1209 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When the power supply 1209 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery that is charged via a wired line, while a wireless rechargeable battery is a battery that is charged via a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0147] In some embodiments, the terminal device 1200 further includes one or more sensors 1210 , including but not limited to: an acceleration sensor 1211 , a gyroscope sensor 1212 , a pressure sensor 1213 , an optical sensor 1215 , and a proximity sensor 1216 .

[0148] The accelerometer 1211 can detect the magnitude of acceleration along the three coordinate axes of the coordinate system established by the terminal device 1200. For example, the accelerometer 1211 can be used to detect the components of gravity acceleration along the three coordinate axes. The processor 1201 can control the display screen 1205 to display the user interface in a landscape or portrait view based on the gravity acceleration signal collected by the accelerometer 1211. The accelerometer 1211 can also be used to collect game or user motion data.

[0149] The gyroscope sensor 1212 can detect the body orientation and rotation angle of the terminal device 1200. The gyroscope sensor 1212 can work with the acceleration sensor 1211 to collect the user's 3D movements of the terminal device 1200. Based on the data collected by the gyroscope sensor 1212, the processor 1201 can implement the following functions: motion sensing (such as changing the UI based on the user's tilt operation), image stabilization during shooting, game control, and inertial navigation.

[0150] The pressure sensor 1213 can be set in the lower layer of at least one of the side frame of the terminal device 1200 and the display screen 1205. When the pressure sensor 1213 is set in the side frame of the terminal device 1200, it can detect the user's grip signal of the terminal device 1200, and the processor 1201 performs left and right hand recognition or shortcut operations based on the grip signal collected by the pressure sensor 1213. When the pressure sensor 1213 is set in the lower layer of the display screen 1205, the processor 1201 controls the operable controls on the UI interface based on the user's pressure operation on the display screen 1205. Operable controls include at least one of button controls, scroll bar controls, icon controls, and menu controls.

[0151] Optical sensor 1215 is used to detect ambient light intensity. In one embodiment, processor 1201 can control the display brightness of display screen 1205 based on the ambient light intensity detected by optical sensor 1215. When the ambient light intensity is high, the display brightness of display screen 1205 is increased; when the ambient light intensity is low, the display brightness of display screen 1205 is decreased. In another embodiment, processor 1201 can also dynamically adjust the shooting parameters of camera assembly 1206 based on the ambient light intensity detected by optical sensor 1215.

[0152] Proximity sensor 1216, also known as a distance sensor, is typically located on the front panel of terminal device 1200. Proximity sensor 1216 is used to detect the distance between the user and the front of terminal device 1200. In one embodiment, when proximity sensor 1216 detects that the distance between the user and the front of terminal device 1200 is gradually decreasing, processor 1201 controls display screen 1205 to switch from the screen-on state to the screen-off state. When proximity sensor 1216 detects that the distance between the user and the front of terminal device 1200 is gradually increasing, processor 1201 controls display screen 1205 to switch from the screen-off state to the screen-on state.

[0153] Those skilled in the art will understand that the structure shown in FIG12 does not constitute a limitation on the terminal device 1200 , and may include more or fewer components than shown in the figure, or combine certain components, or adopt a different component arrangement.

[0154] FIG13 is a schematic diagram of the structure of the server provided in an embodiment of the present application. The server 1300 may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) 1301 and one or more memories 1302, wherein the one or more memories 1302 store at least one program code, and the at least one program code is loaded and executed by the one or more processors 1301 to implement the game interaction methods provided in the above-mentioned various method embodiments. Of course, the server 1300 may also have components such as a wired or wireless network interface, a keyboard, and an input and output interface for input and output. The server 1300 may also include other components for implementing device functions, which will not be described in detail here.

[0155] In an exemplary embodiment, a computer-readable storage medium is further provided, in which at least one computer instruction is stored. The at least one computer instruction is loaded and executed by a processor to enable a computer device to implement any of the above-mentioned game interaction methods.

[0156] The computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, or the like.

[0157] In an exemplary embodiment, a computer program product is further provided. The computer program product stores at least one computer instruction, which is loaded and executed by a processor to enable a computer device to implement any of the above-mentioned game interaction methods.

[0158] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, storage, and display, etc.), and signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data must comply with the relevant laws, regulations, and standards of the relevant countries and regions. For example, the clothing information involved in this application was obtained with full authorization.

[0159] It should be understood that the term "plurality" as used herein refers to two or more than two. The character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0160] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0161] The above description is merely an exemplary embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A game interaction method, the method being executed by a computer device, the method comprising: Displaying a game page, wherein the game page displays the original costume; In response to a first trigger operation for a generation function, a first keyword and original clothing information of the original clothing are acquired; the original clothing information includes at least one of a first intrinsic color map, a first normal map, and a first material map, the first intrinsic color map is used to indicate the style and color of the original clothing, the first normal map is used to indicate the visual effect of the original clothing, and the first material map is used to indicate the material of the original clothing; displaying target clothing generated based on the original clothing information and matching the first keyword; Game interaction is performed based on the target clothing.

2. The method according to claim 1, wherein: A virtual object is also displayed in the game page, and the virtual object is wearing the original clothing; The displaying of the target clothing matching the first keyword generated based on the original clothing information includes: The clothing worn by the virtual object displayed in the game page is replaced from the original clothing to the target clothing.

3. The method according to claim 1 or 2, wherein: The game interaction based on the target clothing includes at least one of the following: Controlling the virtual object to wear the target clothing to play the game; selling said target garments; Participate in a competition activity of the game based on the target clothing.

4. The method according to any one of claims 1 to 3, wherein: The method further comprises: In response to a second trigger operation for the generation function, a second keyword, a target sampling number and a target matching degree are obtained; the second keyword is a keyword that does not match the target clothing, the target sampling number is the number of repetitions of a sampling process for obtaining target clothing information of the target clothing, and the target matching degree is the matching degree between the target clothing and the first keyword; the target clothing information includes at least one of a second intrinsic color map, a second normal map and a second material map, the second intrinsic color map is used to indicate the style and color of the target clothing, the second normal map is used to indicate the visual effect of the target clothing, and the second material map is used to indicate the material of the target clothing; Before displaying the target clothing generated based on the original clothing information and matching the first keyword, the method further includes: According to the first keyword, the second keyword, the target matching degree and the original clothing information, the target clothing is generated by sampling according to the target sampling number; the matching degree between the target clothing and the first keyword is the target matching degree, and the target clothing does not match the second keyword.

5. The method according to any one of claims 1 to 4, wherein: The step of generating the target clothing by sampling according to the target sampling times according to the first keyword, the second keyword, the target matching degree and the original clothing information includes: According to the first keyword, the second keyword, the target matching degree and the original clothing information, sampling is performed according to the target sampling number to obtain the target clothing information of the target clothing; The target clothing is generated according to the target clothing information.

6. The method according to any one of claims 1 to 5, wherein: The original clothing information includes the first intrinsic color map, and the target clothing information includes the second intrinsic color map; The step of sampling and acquiring target clothing information of the target clothing according to the target sampling times based on the first keyword, the second keyword, the target matching degree and the original clothing information includes: According to the first keyword and the second keyword, a target text feature is obtained; the target text feature is used for representing the first keyword and the second keyword; According to the first intrinsic color map, a first image feature is obtained; the first image feature is used to characterize the first intrinsic color map; According to the target text feature, the first image feature and the target matching degree, sampling is performed according to the target sampling times to obtain a second image feature; the second image feature is used to characterize the second intrinsic color map; The second image feature is decoded to obtain the second intrinsic color map.

7. The method according to any one of claims 1 to 6, wherein: The acquiring of the second image feature by sampling according to the target sampling times according to the target text feature, the first image feature and the target matching degree includes: For the first time in the target sampling times, a first text noise feature and a first image noise feature are obtained according to the target text feature, the first image feature and the first value; a first reference feature is determined according to the first text noise feature, the first image noise feature, the target matching degree and the first image feature; the first reference feature is a feature obtained by denoising the first image feature for the first time, the first text noise feature matches the target text feature, the first image noise feature matches the first image feature, and the first value is used to represent the first time; For the non-first sampling times of the target, a second text noise feature and a second image noise feature are obtained according to the target text feature, the reference feature and the second value; a second reference feature is determined according to the second text noise feature, the second image noise feature, the target matching degree and the reference feature; the second reference feature is a feature obtained by denoising the first image feature for the non-first time, the second text noise feature matches the target text feature, the second image noise feature matches the reference feature, the reference feature is a feature obtained by sampling last time of the non-first sampling, and the second value is used to indicate the non-first time; The feature obtained by the last sampling of the target sampling times is determined as the second image feature.

8. The method according to any one of claims 1 to 7, wherein: The determining of the first reference feature according to the first text noise feature, the first image noise feature, the target matching degree and the first image feature includes: Determining an intermediate noise feature according to the first text noise feature, the first image noise feature, and the target matching degree; The first reference feature is determined according to the intermediate noise feature and the first image feature.

9. The method according to any one of claims 1 to 8, wherein: The acquiring target text features according to the first keyword and the second keyword includes: Acquire a first text feature for characterizing the first keyword; Acquire a second text feature for characterizing the second keyword; The target text feature is determined according to the first text feature and the second text feature.

10. The method according to any one of claims 1 to 9, wherein: The dimension of the first text feature is the same as the dimension of the second text feature; Determining the target text feature according to the first text feature and the second text feature includes: The values ​​of the first text feature and the second text feature at corresponding positions are added to obtain the target text feature.

11. The method according to any one of claims 1 to 10, wherein: The dimension of the first text feature is the same as the dimension of the second text feature; Determining the target text feature according to the first text feature and the second text feature includes: The target text feature is obtained by multiplying the values ​​of the first text feature and the second text feature at corresponding positions.

12. The method according to any one of claims 1 to 11, wherein: The decoding of the second image feature to obtain the second intrinsic color map includes: Decoding the second image feature to obtain a pixel map corresponding to the second image feature; The second intrinsic color map is generated according to the pixel map corresponding to the second image feature.

13. A game interaction device, comprising: A display module configured to display a game page, wherein the game page displays original clothing; an acquisition module, configured to acquire, in response to a first trigger operation for a generation function, a first keyword and original clothing information of the original clothing; the original clothing information includes at least one of a first intrinsic color map, a first normal map, and a first material map, the first intrinsic color map being used to indicate the style and color of the original clothing, the first normal map being used to indicate the visual effect of the original clothing, and the first material map being used to indicate the material of the original clothing; The display module is further configured to display target clothing matching the first keyword generated based on the original clothing information; An interaction module is configured to perform game interaction based on the target clothing.

14. A computer device, comprising a processor and a memory, wherein the memory stores at least one computer instruction, and the at least one computer instruction is loaded and executed by the processor so that the computer device implements the game interaction method as described in any one of claims 1 to 12.

15. A computer-readable storage medium, wherein at least one computer instruction is stored in the computer-readable storage medium, and the at least one computer instruction is loaded and executed by a processor to enable a computer device to implement the game interaction method as described in any one of claims 1 to 12.

16. A computer program product, wherein at least one computer instruction is stored in the computer program product, and the at least one computer instruction is loaded and executed by a processor to enable a computer device to implement the game interaction method as described in any one of claims 1 to 12.

Images