Data processing method, apparatus and electronic device

Abstract

The application provides a data processing method and device and electronic equipment, obtains offline feature data and synchronization feature data corresponding to a target game; performs feature verification processing on target data based on a preset feature verification rule to obtain a processing result, and displays the processing result in a preset panel; the target data includes offline feature data and / or synchronization feature data; the feature verification rule matches the type of the target data, and is used for verifying the data attribute of sub-data in the target data or the matching between the sub-data. In this way, the offline feature data and / or synchronization feature data are verified based on the feature verification rule, and the processing result is displayed in the panel, so that the user can determine the correctness of the offline feature data and the synchronization feature data through the result displayed in the panel, thereby ensuring the correctness of the offline feature data used for supervised learning training and the synchronization feature data used for testing, and improving the training effect of the supervised learning.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a data processing method, apparatus, and electronic device. Background Technology

[0002] Game AI refers to "human-like players," or virtual players, controlled by pre-programmed instructions in games. Game AI is an essential element for many games; a well-developed intelligent game AI can provide a better gaming experience for real players. In MOBA games, for example, there are game AIs that control heroes just like real players, engaging in combat or cooperation with them.

[0003] In related technologies, game AI is usually trained using supervised learning methods. During the training process, in order to verify the training effect of the game AI, the output results of certain nodes in the target model are visualized after the target model is trained using supervised learning methods. However, this method cannot visualize the features of the training data used in the entire supervised learning process, making it impossible for users to check the correctness of the training data used to train the game AI. As a result, the final training effect of the game AI may be poor due to incorrect training data. Summary of the Invention

[0004] The purpose of this invention is to provide a data processing method, apparatus, and electronic device to improve the accuracy of training data used in supervised learning of game AI, thereby improving the final training effect of game AI.

[0005] In a first aspect, the present invention provides a data processing method, the method comprising: acquiring offline feature data and synchronous feature data corresponding to a target game; wherein, the offline feature data indicates the characteristics of historical game data experienced by the target game from start to finish; the synchronous feature data indicates the characteristics of real-time game data of the target game in progress; performing feature verification processing on the target data based on preset feature verification rules to obtain a processing result; wherein, the target data includes offline feature data and / or synchronous feature data; the feature verification rules are matched with the type of target data, and the feature verification rules are used to: verify the data attributes of sub-data in the target data or the matching between sub-data; and displaying the processing result in a preset panel according to preset display rules.

[0006] Secondly, the present invention provides a data processing apparatus, comprising: a data acquisition module for acquiring offline feature data and synchronous feature data corresponding to a target game; wherein the offline feature data indicates the characteristics of historical game data experienced by the target game from start to finish; and the synchronous feature data indicates the characteristics of real-time game data of the target game in progress; a data verification module for performing feature verification processing on the target data based on preset feature verification rules to obtain processing results; wherein the target data includes offline feature data and / or synchronous feature data; the feature verification rules are matched with the types of the target data, and the feature verification rules are used to verify the data attributes of sub-data in the target data or the matching between sub-data; and a data display module for displaying the processing results in a preset panel according to preset display rules.

[0007] Thirdly, the present invention provides an electronic device including a processor and a memory, the memory storing machine-executable instructions that can be executed by the processor, the processor executing the machine-executable instructions to implement the above-described data processing method.

[0008] Fourthly, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when invoked and executed by a processor, cause the processor to implement the aforementioned data processing method.

[0009] The embodiments of the present invention bring the following beneficial effects:

[0010] This invention provides a data processing method, apparatus, and electronic device. First, it acquires offline and synchronous feature data corresponding to a target game. Then, based on preset feature verification rules, it performs feature verification processing on the target data to obtain processing results. The target data includes offline and / or synchronous feature data. The feature verification rules match the types of target data and are used to verify the data attributes of sub-data or the matching between sub-data. Finally, according to preset display rules, the processing results are displayed in a preset panel. This method verifies offline and / or synchronous feature data based on feature verification rules and displays the processing results in a panel. Users can then determine the correctness of the offline and synchronous feature data through the results displayed on the panel and process incorrect data. This ensures the correctness of the offline feature data used for supervised learning training and the synchronous feature data used for testing after training, thereby improving the training effect of supervised learning.

[0011] Other features and advantages of the invention will be set forth in the following description, or some features and advantages may be inferred from the description or determined without doubt, or may be learned by practicing the techniques described above.

[0012] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0013] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0014] Figure 1 A flowchart of a data processing method provided in an embodiment of the present invention;

[0015] Figure 2 A flowchart of another data processing method provided in an embodiment of the present invention;

[0016] Figure 3 This is a schematic diagram showing the difference features between synchronous feature data and offline feature data provided in an embodiment of the present invention;

[0017] Figure 4 A flowchart of another data processing method provided in an embodiment of the present invention;

[0018] Figure 5 A flowchart of another data processing method provided in an embodiment of the present invention;

[0019] Figure 6 A schematic diagram of a feature verification framework provided in an embodiment of the present invention;

[0020] Figure 7 This is a schematic diagram of the structure of a data processing device provided in an embodiment of the present invention;

[0021] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0023] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0024] Game AI (Artificial Intelligence) refers to "human-like players," or virtual players, controlled by pre-programmed instructions in games. Game AI is an essential element for many games; a well-performing AI can enhance the gaming experience for real players. In MOBA (Multiplayer Online Battle Arena) games, AI can control heroes just like real players, engaging in combat or cooperation. Supervised learning is an important and increasingly used method for training MOBA game AI. When using supervised learning, effective visualization tools can significantly improve development efficiency. Supervised learning involves adjusting the parameters of a classifier or regressor using a set of training data with known categories to achieve the desired performance.

[0025] In related technologies, during the training process using supervised learning methods, in order to verify the training effect of game AI, the output results of certain nodes in the target model are visualized after the target model is trained using supervised learning methods. However, this method cannot visualize the features of the training data used throughout the supervised learning process, making it impossible for users to check the correctness of the training data used to train the game AI. As a result, the final training effect of the game AI may be poor due to incorrect training data.

[0026] To address the aforementioned issues, embodiments of the present invention provide a data processing method, apparatus, and electronic device. This technology can be applied to the verification and display of training data in machine learning or supervised learning, particularly in the visualization of training data in supervised learning of game AI.

[0027] To facilitate understanding of the embodiments of the present invention, a data processing method disclosed in the embodiments of the present invention will first be described in detail, such as... Figure 1 As shown, the method includes the following specific steps:

[0028] Step S102: Obtain offline feature data and synchronous feature data corresponding to the target game; wherein, offline feature data indicates the characteristics of historical game data experienced by the target game from start to finish; synchronous feature data indicates the characteristics of real-time game data of the target game in progress.

[0029] The target game mentioned above can be a MOBA game or other games, depending on the development needs. In implementation, offline feature data can be obtained from a pre-defined offline feature file, synchronous feature data can be obtained from a pre-defined online feature file, or synchronous feature data (also known as online feature data) can be directly obtained from the target game during gameplay. Offline feature data refers to the features of the historical game data experienced by the target game after it ends; synchronous feature data refers to the features of the real-time game data extracted while the target game is in progress.

[0030] Step S104: Based on the preset feature verification rules, perform feature verification processing on the target data to obtain the processing result; wherein, the target data includes offline feature data and / or synchronous feature data; the feature verification rules are matched with the types of target data, and the feature verification rules are used to verify the data attributes of sub-data in the target data or the matching between sub-data.

[0031] The above feature verification rules can be set according to R&D needs. These feature verification rules are used to verify the correctness of the data attributes of the sub-data contained in the target data, and also to verify the matching of synchronous feature data and offline feature data with the same number of frames in the target data (that is, to verify the feature consistency of synchronous feature data and offline feature data with the same number of frames).

[0032] In specific implementation, the target data mentioned above may include only synchronous feature data, so that feature verification can be performed only on the synchronous feature data to determine the accuracy of synchronous feature data extraction; the target data may also include only offline feature data, so that feature verification can be performed only on the offline feature data to determine the accuracy of offline feature data extraction; the target data may also include both synchronous and offline feature data, to verify the consistency between offline and synchronous feature data, that is, to determine the differences between offline and synchronous feature data for each frame of the target game.

[0033] Step S106: Display the above processing results in the preset panel according to the preset display rules.

[0034] The above preset display rules can be set according to R&D needs, and are not specifically limited here. For example, the processing results can be directly displayed in the preset panel, or the different categories of sub-data contained in the processing results can be displayed in different areas of the preset panel. By displaying the processing results in the preset panel, users can verify the correctness of the target data or the matching between the sub-data in the target data.

[0035] In practical applications, when training game AI using supervised learning methods, offline feature data is used for training, while synchronous feature data is used for testing performance after training. In implementation, if the offline feature data used for training does not perfectly correspond to the synchronous feature data used for testing, it will have a significant negative impact on the performance of the supervised learning model. Therefore, ensuring the consistency between offline and synchronous feature data is crucial. This invention can verify the consistency between offline and synchronous feature data by performing feature verification, and display the verification results in a panel for visualization. When the synchronous and offline feature data are inconsistent, the correctness of the synchronous feature data can be determined by the processing results displayed in the panel, and the correctness of the offline feature data can also be determined by the processing results displayed in the panel. This allows users to re-extract features from incorrect data to ensure its accuracy.

[0036] This invention provides a data processing method that first acquires offline and synchronous feature data corresponding to a target game; then, based on preset feature verification rules, performs feature verification processing on the target data to obtain processing results; wherein, the target data includes offline feature data and / or synchronous feature data; the feature verification rules are matched with the types of target data, and the feature verification rules are used to verify the data attributes of sub-data in the target data or the matching between sub-data; then, according to preset display rules, the processing results are displayed in a preset panel. This method verifies offline and / or synchronous feature data based on feature verification rules and displays the processing results in a panel, so that users can determine the correctness of offline and synchronous feature data through the results displayed in the panel, and process incorrect data, thereby ensuring the correctness of the offline feature data used for supervised learning training and the synchronous feature data used for testing after training, thereby improving the training effect of supervised learning.

[0037] This invention also provides another data processing method, which is implemented based on the above embodiments. This method focuses on describing the specific process of obtaining the offline and synchronous feature data corresponding to the target game when the target data includes offline and synchronous feature data (implemented through step S202 below), and the specific process of performing feature verification processing on the target data based on preset feature verification rules to obtain the processing result (implemented through steps S204-S206 below); Figure 2 As shown, the method includes the following specific steps:

[0038] Step S202: Obtain offline feature data of the target game from the offline feature file; obtain synchronous feature data of the target game from the online feature file; wherein, the offline feature data is used to indicate the offline features corresponding to each frame of the game in the target game, and the synchronous feature data is used to indicate the online features corresponding to each frame of the game in the target game.

[0039] In practical implementation, before obtaining the offline and synchronous feature data of the target game, it is necessary to save the target game data exchanged between the client and the game server in the target game to a preset recording file during the target game, and extract features from the target game data to obtain the synchronous feature data of the target game, and save the synchronous feature data to a preset online feature file; after the target game ends, extract features from the target game data in the recording file to obtain the offline feature data of the target game, and save the offline feature data to a preset offline feature file.

[0040] The target game data exchanged between the client and the game server in the aforementioned target game can also be referred to as packets executed by the target game. Specifically, the video recording file stores game data, which are the packets executed by the game. Using the packets stored in the video recording file, the game can be re-executed, essentially replaying the previously completed game scene. Therefore, based on this re-verification, an offline feature file can be generated, containing offline feature data. The online feature file stores synchronous feature data. The consistency check verifies whether the data in the offline feature file is consistent with the data in the online feature file; consistency indicates no errors.

[0041] The synchronous feature data stored in the aforementioned online feature files is obtained by extracting features from the target game data exchanged between the client and the game server during the target game's execution. The aforementioned offline feature files store the training data (i.e., offline feature data) used when training the supervised learning model, while the aforementioned online feature files store the test data (i.e., synchronous feature data) used to test the model after the supervised learning model has been trained.

[0042] Step S204: For each frame of the game screen, subtract the offline feature data of the current frame from the synchronization feature data of the current frame to obtain the difference feature of the current frame; wherein, the difference feature is used to indicate the matching between the synchronization feature data and the offline feature data of the current frame.

[0043] In practical applications, there is a correspondence between synchronous feature data and offline feature data. The sub-thread can subtract each dimension of the synchronous feature data and the offline feature data for each frame to obtain the difference feature for each frame. This difference feature can indicate the difference between the synchronous feature data and the offline feature data. The existence of a difference indicates that the synchronous feature data and the offline feature data do not match, while the absence of a difference indicates that the synchronous feature data and the offline feature data match.

[0044] Step S206: Use the difference features corresponding to each frame of the game in the target game as the processing result.

[0045] Step S208: Display the above processing results in the preset panel according to the preset display rules.

[0046] In its implementation, the differences between synchronous and offline feature data are displayed in a preset panel, visualizing the differences between offline and synchronous features for each frame of the game, thus verifying the consistency of the offline and synchronous feature data. This function combines the visualization process of offline and synchronous feature data, adding a subtraction operation step in the middle, and then rendering the subtraction result (i.e., the difference feature) graphically, such as... Figure 3 The diagram shown is a display of the difference features between synchronous feature data and offline feature data provided in an embodiment of the present invention.

[0047] Figure 3 Each rectangle represents the difference feature between the synchronous feature data and the offline feature data for each frame. Figure 3 Darker rectangles indicate frames where offline and online feature data differ, while white rectangles indicate frames where the features are identical. In practice, differing frames can be represented by different colors; for example, a blue rectangle indicates a larger feature value in the offline data for that frame, while a red rectangle indicates a larger feature value in the synchronous data for that frame. This clear comparison allows users to determine the consistency between offline and synchronous feature data and make subsequent adjustments. For instance, if inconsistencies are found, users can check for errors in the offline and online feature data, thereby improving the accuracy of the data used in supervised learning.

[0048] The aforementioned data processing method displays the differences between synchronous and offline feature data in a preset panel, visualizing the differences between offline and synchronous features for each frame of the game, thus facilitating the verification of the consistency between offline and synchronous feature data. Simultaneously, it ensures the consistency between the connection feature data and synchronous feature data used in supervised learning, improving the performance of the model trained through supervised learning.

[0049] This invention also provides another data processing method, which is implemented based on the above embodiments. This method focuses on describing the specific process of performing feature verification processing on the target data based on preset feature verification rules to obtain the processing result when the target data includes offline feature data (specifically implemented through steps S404-S406 below), and the specific process of displaying the above processing result on a preset panel according to preset display rules (implemented through steps S408-S412 below); as follows; Figure 4 As shown, the method includes the following specific steps:

[0050] Step S402: Obtain the offline feature data corresponding to the target game.

[0051] This embodiment can verify only the offline feature data, thus allowing the acquisition of only the offline feature data corresponding to the target game. Specifically, the offline feature data corresponding to the target game can be obtained from the offline feature file.

[0052] Step S404: Divide the offline feature data into multiple sub-data according to the preset attribute categories, and set attribute tags for the sub-data according to the attribute categories corresponding to the sub-data; wherein, one sub-data corresponds to one attribute category, and each attribute category corresponds to its own attribute tag.

[0053] In practical implementation, the preset attribute categories are determined based on the functional types of the data. Specifically, the attribute categories of sub-data can include the following four categories: numerical characteristics of the target object in the scene map of the target game, operation tags of the client on the target object in the target game, global features of the target game, and local features of the target game. Each attribute category also has a corresponding display area in the preset panel, which can be set according to development needs. For example, the numerical characteristics of the target object in the scene map of the target game can be displayed in the upper left corner of the preset panel, the operation tags of the client on the target object in the target game can be displayed in the upper right corner of the preset panel, the global features of the target game can be displayed in the lower left corner of the preset panel, and the local features of the target game can be displayed in the lower right corner of the preset panel.

[0054] The numerical characteristics of the target object in the aforementioned target game on the scene map may include the target object's position on the scene map, as well as the player characters of the factions included in the scene map; the operation tags of the aforementioned client on the target object in the aforementioned target game may include the controls operated by the player in the current game screen, the skills used, etc.; the global characteristics of the aforementioned target game may include the target object's position and movement speed on the minimap, etc.; the local characteristics of the aforementioned target game may include the target object's position and movement speed within the map area displayed on the screen, etc.

[0055] Step S406: The above multiple sub-data and the attribute tags corresponding to each sub-data are determined as the processing result of offline feature data.

[0056] Step S408: Save the processing results to a preset data display queue; wherein, the data display queue stores the processing results corresponding to each frame of the game in the target game.

[0057] The data display queue mentioned above is maintained by the main thread, and the processing results can be saved to the data display queue in real time.

[0058] Step S410: Take the first data from the data display queue according to the preset sampling rules.

[0059] In practical implementation, the main thread can retrieve the first data from the data display queue of the data processing sub-thread according to a preset sampling rule. The preset sampling rule can be set according to development needs. For example, the last input data in the data display queue can be retrieved and designated as the first data.

[0060] Step S412: Render the first data into a graphic to obtain the rendering result, and display the rendering result in the preset panel.

[0061] In practical implementation, the data display queue also stores multiple sub-data contained in each processing result, as well as attribute tags for each sub-data; each attribute tag has a corresponding display area in the preset panel; by performing the following steps 10-12 for each sub-data contained in the first data, the rendering result of the first data can be displayed in the preset panel:

[0062] Step 10: Determine the target display area corresponding to the current sub-data in the preset panel based on the attribute marker of the current sub-data.

[0063] Step 11: Render the current sub-data according to the rendering rules corresponding to the target display area to obtain the rendering result of the current sub-data.

[0064] Since each display area has a different attribute tag, the attributes of the displayed sub-data are also different. Therefore, each display area has its own rendering rules, which can be set according to R&D needs.

[0065] Step 12: Display the rendering result of the current sub-data on the target display area.

[0066] The offline feature data is visualized in the preset panel to verify the accuracy of the offline feature data extraction. In other words, users can determine whether the offline feature data is correct by viewing the processing results of the offline feature data in the preset panel.

[0067] In the specific implementation, when displaying the processing results of offline feature data in the preset panel, a drag bar is displayed at the top of the preset panel interface. Users can use this drag bar to control the display of the processing results of offline feature data for each frame; this is a main thread operation. The logic processing sub-thread asynchronously retrieves the data of the frame number dragged by the user from the data display queue according to the current computing power and performs feature verification processing. Finally, the main thread completes the graphical rendering of the offline feature data processing results and displays the rendering results in the preset panel. Specifically, the data display queue stores the processing results of offline feature data corresponding to each frame. When the user moves the drag bar from frame 0 to frame 10, the processing result of the offline feature data corresponding to frame 10 is directly retrieved from the data display queue, and then the retrieved data is graphically rendered and displayed in the preset panel.

[0068] The above data processing method can display the feature verification results of offline feature data in a preset panel, visualize the offline features, and thus facilitate the verification of the accuracy of offline feature data. This ensures the accuracy of the training data used in supervised learning and helps improve the training effect of supervised learning.

[0069] This invention also provides another data processing method, which is implemented based on the above embodiments. This method focuses on describing the specific process of obtaining the synchronization feature data of the target game when the target data includes synchronization feature data (implemented through step S502 below), and the specific process of performing feature verification processing on the target data based on preset feature verification rules to obtain the processing result (specifically implemented through steps S504-S506 below); as follows... Figure 5 As shown, the method includes the following specific steps:

[0070] Step S502: During the target game, feature extraction is performed on the target game data exchanged between the client and the game server in the target game to obtain the synchronization feature data of the target game.

[0071] Step S504: Divide the synchronization feature data into multiple sub-data according to the preset attribute categories, and set attribute tags for the sub-data according to the attribute categories corresponding to the sub-data; wherein, one sub-data corresponds to one attribute category, and each attribute category corresponds to its own attribute tag.

[0072] In practical implementation, the preset attribute categories are determined based on the functional types of the data. Specifically, the attribute categories of sub-data can include the following four categories: numerical characteristics of the target object in the scene map of the target game, operation tags of the client on the target object in the target game, global characteristics of the target game, and local characteristics of the target game. Furthermore, each attribute category has a corresponding display area in the preset panel, and the display area for each attribute category can be set according to development needs.

[0073] Step S506: The multiple sub-data and the attribute tags corresponding to each sub-data are determined as the processing result of the synchronous feature data.

[0074] Step S508: Save the processing result to a preset data display queue; wherein, the data display queue stores the processing result corresponding to the synchronization feature data.

[0075] Step S510: Take the second data from the data display queue according to the preset sampling rules.

[0076] The above-mentioned preset sampling rules can be set according to R&D needs. For example, the last input data in the data display queue can be taken out and the taken out data can be determined as the second data. That is, the last data in the data display queue can be taken out as the second data.

[0077] Step S512: For each sub-data contained in the second data, determine the target display area corresponding to the current sub-data in the preset panel according to the attribute mark of the current sub-data; perform graphic rendering on the current sub-data according to the rendering rules corresponding to the target display area to obtain the rendering result of the current sub-data; and display the rendering result of the current sub-data on the target display area.

[0078] In practice, the result of processing the synchronous feature data is that the graphics rendering is updated synchronously as the real-time game progresses, and the result is displayed in the preset panel.

[0079] like Figure 6 The diagram shows a feature verification framework provided by an embodiment of the present invention. First, the target game data exchanged between the client and the game server in the online game is saved to a video file, and features are extracted from the target game data to obtain the synchronous feature data of the target game. The synchronous feature data is then saved to an online feature file. After the target game ends, features are extracted from the target game data in the video file to obtain the offline feature data of the target game. The offline feature data is then saved to a feature file. Figure 6 The framework mainly includes three functions:

[0080] Function 1: Offline Feature Validation. Visualizes offline features to verify the accuracy of offline feature data extraction.

[0081] Function 2: Synchronization Feature Verification. Visualizes synchronization features to verify the accuracy of synchronization feature data extraction.

[0082] Function 3: Feature Consistency Verification. This function visualizes the differences between offline and synchronous features for each frame of the game, verifying the consistency between offline and synchronous feature data.

[0083] The above three functions are implemented using the same underlying framework, namely Figure 6 The framework shown. The steps consist of the following 5 steps:

[0084] 1. Data Parsing: The data parsing process for synchronous and offline feature data is basically the same. Both involve separating the feature data according to attribute classes to obtain multiple sub-data sets, and adding a category label to each sub-data set. This entire process occurs in the data processing sub-thread. When implementing function three, proceed to step 2; when implementing functions one and two, proceed to step 3.

[0085] 2. Verify and compare the processed data: The sub-thread subtracts each dimension of the synchronous feature data and the offline feature data of each frame to obtain the difference feature of each frame, and then proceeds to step 3;

[0086] 3. Data enters the display queue: The main thread maintains a data display queue and stores the data processed by the child threads in steps 1 and 2 into it.

[0087] 4. Retrieve data from the display queue: The main thread retrieves data from the data display queue of the data processing sub-thread according to a preset sampling rule, such as retrieving the last data sample in the display queue.

[0088] 5. Refresh Panel: The main thread's display module extracts the data according to the category tags attached to the data, performs graphic rendering, and displays the rendering results in the corresponding marked area of ​​the panel.

[0089] The framework described above is highly reusable, with the same set of framework logic supporting the feature verification functions of three different stages of supervised learning. At the same time, the framework is also highly decoupled, causing virtually no logical intrusion into the supervised learning process. In addition, the framework is highly efficient, using sub-threads to handle high-consumption IO read / write and data processing logic, while the main thread samples and retrieves data from the queue based on its own load, ensuring smooth performance throughout the entire process.

[0090] The above data processing method can display the feature verification results of synchronous feature data in a preset panel, visualize offline features, thereby facilitating the verification of the accuracy of synchronous feature data, ensuring the accuracy of the training data used in supervised learning testing, and improving the effect of supervised learning training.

[0091] In accordance with the above-described method embodiments, this invention also provides a data processing apparatus, such as... Figure 7 As shown, the device includes:

[0092] The data acquisition module 70 is used to acquire offline feature data and synchronous feature data corresponding to the target game; wherein, the offline feature data indicates the characteristics of the historical game data experienced by the target game from start to finish; and the synchronous feature data indicates the characteristics of the real-time game data of the target game in progress.

[0093] The data verification module 71 is used to perform feature verification processing on the target data based on preset feature verification rules to obtain the processing result; wherein, the target data includes offline feature data and / or synchronous feature data; the feature verification rules are matched with the types of target data, and the feature verification rules are used to verify the data attributes of sub-data in the target data or the matching between sub-data.

[0094] The data display module 72 is used to display the above processing results in a preset panel according to preset display rules.

[0095] The aforementioned data processing device first acquires offline and synchronous feature data corresponding to the target game; then, based on preset feature verification rules, it performs feature verification processing on the target data to obtain processing results; wherein, the target data includes offline feature data and / or synchronous feature data; the feature verification rules are matched with the types of target data, and the feature verification rules are used to verify the data attributes of sub-data or the matching between sub-data in the target data; then, according to preset display rules, the processing results are displayed in a preset panel. This method verifies offline and / or synchronous feature data based on feature verification rules and displays the processing results in the panel, so that users can determine the correctness of offline and synchronous feature data through the results displayed in the panel, and process incorrect data, thereby ensuring the correctness of the offline feature data used for supervised learning training and the synchronous feature data used for testing after training, thereby improving the training effect of supervised learning.

[0096] Specifically, the aforementioned device further includes a data storage module, used for: before acquiring the offline feature data and synchronous feature data corresponding to the target game, during the target game, saving the target game data exchanged between the client and the game server in the target game to a preset recording file, extracting features from the target game data to obtain the synchronous feature data of the target game, and saving the synchronous feature data to a preset online feature file; after the target game ends, extracting features from the target game data in the recording file to obtain the offline feature data of the target game, and saving the offline feature data to a preset offline feature file.

[0097] Furthermore, the aforementioned data acquisition module 70 is used to: acquire offline feature data of the target game from the offline feature file; and acquire synchronous feature data of the target game from the online feature file.

[0098] In specific implementation, the target data includes offline feature data and synchronous feature data; the offline feature data is used to indicate the offline features corresponding to each frame of the game in the target game, and the synchronous feature data is used to indicate the online features corresponding to each frame of the game in the target game; the data verification module 71 is used to: for each frame of the game, subtract the offline feature data of the current frame from the synchronous feature data of the current frame to obtain the difference feature of the current frame; wherein, the difference feature is used to indicate the matching between the synchronous feature data and the offline feature data of the current frame; and the difference feature corresponding to each frame of the game in the target game is used as the processing result.

[0099] In some embodiments, the target data includes offline feature data; the data verification module 71 is configured to: divide the offline feature data into multiple sub-data according to preset attribute categories, and set attribute tags for the sub-data according to the attribute categories corresponding to the sub-data; wherein, one sub-data corresponds to one attribute category, and each attribute category corresponds to its own attribute tag; and determine the multiple sub-data and the attribute tags corresponding to each sub-data as the processing result of the offline feature data.

[0100] In practical applications, the attribute categories of the above sub-data include: the numerical characteristics of the target object in the scene map of the target game, the operation labels of the client on the target object in the target game, the global characteristics of the target game, and the local characteristics of the target game.

[0101] Furthermore, the aforementioned target data includes synchronization feature data; the aforementioned data acquisition module 60 is used to: extract features from the target game data exchanged between the client and the game server in the target game during the game's execution, thereby obtaining the target game's synchronization feature data; the aforementioned data verification module 71 is used to: divide the synchronization feature data into multiple sub-data according to preset attribute categories, and set attribute tags for the sub-data according to the attribute categories corresponding to the sub-data; wherein, one sub-data corresponds to one attribute category, and each attribute category corresponds to its own attribute tag; and determine the processing result of the multiple sub-data and the attribute tags corresponding to each sub-data as the synchronization feature data.

[0102] In specific implementation, the above data display module 72 is used to: save the processing results to a preset data display queue; wherein the data display queue stores the processing results corresponding to each frame of the game screen in the target game; retrieve the first data from the data display queue according to the preset sampling rules; perform graphic rendering on the first data to obtain the rendering result, and display the rendering result in a preset panel.

[0103] Furthermore, the aforementioned data display module 72 is also used to: retrieve the last input data from the data display queue and determine the retrieved data as the first data.

[0104] Specifically, the data display queue also stores attribute tags of the sub-data contained in each processing result; each attribute tag has a corresponding display area in the preset panel; the data display module 72 is also used to perform the following operations for each sub-data contained in the first data: determine the target display area corresponding to the current sub-data in the preset panel according to the attribute tag of the current sub-data; perform graphic rendering on the current sub-data according to the rendering rules corresponding to the target display area to obtain the rendering result of the current sub-data; and display the rendering result of the current sub-data on the target display area.

[0105] The data processing apparatus provided in this embodiment of the invention has the same implementation principle and technical effects as the request processing method embodiment. For the sake of brevity, any parts not mentioned in the apparatus embodiment can be referred to the corresponding content in the foregoing method embodiment.

[0106] This invention also provides an electronic device, such as... Figure 8 As shown, the electronic device includes a processor and a memory. The memory stores machine-executable instructions that can be executed by the processor, which executes the machine-executable instructions to implement the data processing method described above.

[0107] Specifically, the above data processing method includes: acquiring offline feature data and synchronous feature data corresponding to the target game; wherein, offline feature data indicates the characteristics of historical game data experienced by the target game from start to finish; synchronous feature data indicates the characteristics of real-time game data of the target game in progress; performing feature verification processing on the target data based on preset feature verification rules to obtain processing results; wherein, the target data includes offline feature data and / or synchronous feature data; the feature verification rules are matched with the types of target data, and the feature verification rules are used to: verify the data attributes of sub-data in the target data or the matching between sub-data; and displaying the processing results in a preset panel according to preset display rules.

[0108] The above data processing method is based on feature verification rules to verify offline feature data and / or synchronous feature data, and displays the processing results in the panel. Users can then determine the correctness of offline and synchronous feature data through the results displayed in the panel, and process incorrect data to ensure the correctness of the offline feature data used for supervised learning training and the synchronous feature data used for testing after training, thereby improving the training effect of supervised learning.

[0109] In an optional embodiment, before the steps of obtaining the offline feature data and synchronous feature data corresponding to the target game, the method further includes: during the target game, saving the target game data exchanged between the client and the game server in the target game to a preset video file, extracting features from the target game data to obtain the synchronous feature data of the target game, and saving the synchronous feature data to a preset online feature file; after the target game ends, extracting features from the target game data in the video file to obtain the offline feature data of the target game, and saving the offline feature data to a preset offline feature file.

[0110] In an optional embodiment, the steps of obtaining the offline feature data and synchronous feature data corresponding to the target game include: obtaining the offline feature data of the target game from the offline feature file; and obtaining the synchronous feature data of the target game from the online feature file.

[0111] In an optional embodiment, the target data includes offline feature data and synchronous feature data; the offline feature data is used to indicate the offline features corresponding to each frame of the game in the target game, and the synchronous feature data is used to indicate the online features corresponding to each frame of the game in the target game; the step of performing feature verification processing on the target data based on preset feature verification rules to obtain the processing result includes: for each frame of the game, subtracting the offline feature data of the current frame from the synchronous feature data of the current frame to obtain the difference feature of the current frame; wherein, the difference feature is used to indicate the matching between the synchronous feature data and the offline feature data of the current frame; and using the difference feature corresponding to each frame of the game in the target game as the processing result.

[0112] In an optional embodiment, the target data includes offline feature data; the step of performing feature verification processing on the target data based on preset feature verification rules to obtain the processing result includes: dividing the offline feature data into multiple sub-data according to preset attribute categories, and setting attribute tags for the sub-data according to the attribute categories corresponding to the sub-data; wherein, one sub-data corresponds to one attribute category, and each attribute category corresponds to its own attribute tag; and determining the multiple sub-data and the attribute tag corresponding to each sub-data as the processing result of the offline feature data.

[0113] In an optional embodiment, the attribute categories of the above-mentioned sub-data include: numerical characteristics of the target object in the scene map in the target game, operation tags of the client on the target object in the target game, global features of the target game, and local features of the target game.

[0114] In an optional embodiment, the target data includes synchronization feature data; the step of obtaining the synchronization feature data corresponding to the target game includes: extracting features from the target game data exchanged between the client and the game server during the target game to obtain the synchronization feature data of the target game. The step of performing feature verification processing on the target data based on preset feature verification rules to obtain the processing result includes: dividing the synchronization feature data into multiple sub-data according to preset attribute categories, and setting attribute tags for the sub-data according to the attribute categories corresponding to the sub-data; wherein, one sub-data corresponds to one attribute category, and each attribute category corresponds to its own attribute tag; and determining the multiple sub-data and the attribute tags corresponding to each sub-data as the processing result of the synchronization feature data.

[0115] In an optional embodiment, the step of displaying the processing result in a preset panel according to a preset display rule includes: saving the processing result to a preset data display queue; wherein the data display queue stores the processing result corresponding to each frame of the game screen in the target game; retrieving first data from the data display queue according to a preset sampling rule; performing graphic rendering on the first data to obtain a rendering result, and displaying the rendering result in the preset panel.

[0116] In an optional embodiment, the step of retrieving the first data from the data display queue according to a preset sampling rule includes: retrieving the last input data from the data display queue and determining the retrieved data as the first data.

[0117] In an optional embodiment, the data display queue also stores attribute tags of the sub-data contained in each processing result; wherein each attribute tag has a corresponding display area in a preset panel; the steps of performing graphic rendering on the first data to obtain a rendering result and displaying the rendering result in the preset panel include: performing the following operations on each sub-data contained in the first data: determining the target display area corresponding to the current sub-data in the preset panel according to the attribute tag of the current sub-data; performing graphic rendering on the current sub-data according to the rendering rules corresponding to the target display area to obtain a rendering result of the current sub-data; and displaying the rendering result of the current sub-data on the target display area.

[0118] Furthermore, Figure 8The electronic device shown also includes a bus 102 and a communication interface 103, with the processor 101, the communication interface 103 and the memory 100 connected via the bus 102.

[0119] The memory 100 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 103 (which can be wired or wireless), such as the Internet, wide area network, local area network, or metropolitan area network. The bus 102 may be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 8 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0120] Processor 101 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of processor 101 or by instructions in software form. Processor 101 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a readily available storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 100, and processor 101 reads information from memory 100 and, in conjunction with its hardware, completes the steps of the method described in the foregoing embodiments.

[0121] This invention also provides a computer-readable storage medium storing computer-executable instructions. When these computer-executable instructions are invoked and executed by a processor, they cause the processor to implement the aforementioned data processing method. For specific implementation details, please refer to the method embodiments, which will not be repeated here.

[0122] Specifically, the above data processing method includes: acquiring offline feature data and synchronous feature data corresponding to the target game; wherein, offline feature data indicates the characteristics of historical game data experienced by the target game from start to finish; synchronous feature data indicates the characteristics of real-time game data of the target game in progress; performing feature verification processing on the target data based on preset feature verification rules to obtain processing results; wherein, the target data includes offline feature data and / or synchronous feature data; the feature verification rules are matched with the types of target data, and the feature verification rules are used to: verify the data attributes of sub-data in the target data or the matching between sub-data; and displaying the processing results in a preset panel according to preset display rules.

[0123] The above data processing method is based on feature verification rules to verify offline feature data and / or synchronous feature data, and displays the processing results in the panel. Users can then determine the correctness of offline and synchronous feature data through the results displayed in the panel, and process incorrect data to ensure the correctness of the offline feature data used for supervised learning training and the synchronous feature data used for testing after training, thereby improving the training effect of supervised learning.

[0124] In an optional embodiment, before the steps of obtaining the offline feature data and synchronous feature data corresponding to the target game, the method further includes: during the target game, saving the target game data exchanged between the client and the game server in the target game to a preset video file, extracting features from the target game data to obtain the synchronous feature data of the target game, and saving the synchronous feature data to a preset online feature file; after the target game ends, extracting features from the target game data in the video file to obtain the offline feature data of the target game, and saving the offline feature data to a preset offline feature file.

[0125] In an optional embodiment, the steps of obtaining the offline feature data and synchronous feature data corresponding to the target game include: obtaining the offline feature data of the target game from the offline feature file; and obtaining the synchronous feature data of the target game from the online feature file.

[0126] In an optional embodiment, the target data includes offline feature data and synchronous feature data; the offline feature data is used to indicate the offline features corresponding to each frame of the game in the target game, and the synchronous feature data is used to indicate the online features corresponding to each frame of the game in the target game; the step of performing feature verification processing on the target data based on preset feature verification rules to obtain the processing result includes: for each frame of the game, subtracting the offline feature data of the current frame from the synchronous feature data of the current frame to obtain the difference feature of the current frame; wherein, the difference feature is used to indicate the matching between the synchronous feature data and the offline feature data of the current frame; and using the difference feature corresponding to each frame of the game in the target game as the processing result.

[0127] In an optional embodiment, the target data includes offline feature data; the step of performing feature verification processing on the target data based on preset feature verification rules to obtain the processing result includes: dividing the offline feature data into multiple sub-data according to preset attribute categories, and setting attribute tags for the sub-data according to the attribute categories corresponding to the sub-data; wherein, one sub-data corresponds to one attribute category, and each attribute category corresponds to its own attribute tag; and determining the multiple sub-data and the attribute tag corresponding to each sub-data as the processing result of the offline feature data.

[0128] In an optional embodiment, the attribute categories of the above-mentioned sub-data include: numerical characteristics of the target object in the scene map in the target game, operation tags of the client on the target object in the target game, global features of the target game, and local features of the target game.

[0129] In an optional embodiment, the target data includes synchronization feature data; the step of obtaining the synchronization feature data corresponding to the target game includes: extracting features from the target game data exchanged between the client and the game server during the target game to obtain the synchronization feature data of the target game. The step of performing feature verification processing on the target data based on preset feature verification rules to obtain the processing result includes: dividing the synchronization feature data into multiple sub-data according to preset attribute categories, and setting attribute tags for the sub-data according to the attribute categories corresponding to the sub-data; wherein, one sub-data corresponds to one attribute category, and each attribute category corresponds to its own attribute tag; and determining the multiple sub-data and the attribute tags corresponding to each sub-data as the processing result of the synchronization feature data.

[0130] In an optional embodiment, the step of displaying the processing result in a preset panel according to a preset display rule includes: saving the processing result to a preset data display queue; wherein the data display queue stores the processing result corresponding to each frame of the game screen in the target game; retrieving first data from the data display queue according to a preset sampling rule; performing graphic rendering on the first data to obtain a rendering result, and displaying the rendering result in the preset panel.

[0131] In an optional embodiment, the step of retrieving the first data from the data display queue according to a preset sampling rule includes: retrieving the last input data from the data display queue and determining the retrieved data as the first data.

[0132] In an optional embodiment, the data display queue also stores attribute tags of the sub-data contained in each processing result; wherein each attribute tag has a corresponding display area in a preset panel; the steps of performing graphic rendering on the first data to obtain a rendering result and displaying the rendering result in the preset panel include: performing the following operations on each sub-data contained in the first data: determining the target display area corresponding to the current sub-data in the preset panel according to the attribute tag of the current sub-data; performing graphic rendering on the current sub-data according to the rendering rules corresponding to the target display area to obtain a rendering result of the current sub-data; and displaying the rendering result of the current sub-data on the target display area.

[0133] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a terminal device, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0134] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0135] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A data processing method, characterized in that, The method includes: Obtain offline feature data and synchronous feature data corresponding to the target game; wherein, the offline feature data indicates the characteristics of the historical game data experienced by the target game from start to finish; the synchronous feature data indicates the characteristics of the real-time game data of the target game during its progress; Based on preset feature verification rules, feature verification processing is performed on the target data to obtain the processing result; wherein, the target data includes the offline feature data and / or the synchronous feature data; the feature verification rules are matched with the type of the target data, and the feature verification rules are used to: verify the data attributes of sub-data in the target data or the matching between sub-data, and verify the matching between synchronous feature data and offline feature data with the same number of frames in the target data; According to the preset display rules, the processing results are displayed in the preset panel so as to determine the correctness of the offline feature data used for supervised learning training and the synchronous feature data used for testing through the processing results; If the target data includes the offline feature data and the synchronous feature data; the offline feature data is used to indicate the offline features corresponding to each frame of the game in the target game, and the synchronous feature data is used to indicate the online features corresponding to each frame of the game in the target game; the step of performing feature verification processing on the target data based on preset feature verification rules to obtain the processing result includes: For each frame of the game, the synchronization feature data of the current frame is subtracted from the offline feature data of the current frame to obtain the difference feature of the current frame; wherein, the difference feature is used to indicate the matching between the synchronization feature data and the offline feature data of the current frame; the difference feature corresponding to each frame of the game in the target game is used as the processing result; If the target data is the offline feature data or the synchronous feature data; the step of performing feature verification processing on the target data based on preset feature verification rules to obtain the processing result includes: The target data is divided into multiple sub-data according to preset attribute categories, and attribute tags are set for the sub-data according to the attribute categories corresponding to the sub-data; wherein, one sub-data corresponds to one attribute category, and each attribute category corresponds to its own attribute tag; the multiple sub-data and the attribute tags corresponding to each sub-data are determined as the processing result of the target data; The attribute categories of the sub-data include: the numerical characteristics of the target object in the scene map of the target game, the operation tags of the client on the target object in the target game, the global features of the target game, and the local features of the target game.

2. The method according to claim 1, characterized in that, Before the step of obtaining the offline feature data and synchronous feature data corresponding to the target game, the method further includes: During the target game, the target game data exchanged between the client and the game server in the target game is saved to a preset recording file, and the target game data is subjected to feature extraction to obtain the synchronization feature data of the target game. The synchronization feature data is then saved to a preset online feature file. After the target game ends, feature extraction is performed on the target game data in the video file to obtain offline feature data of the target game, and the offline feature data is saved to a preset offline feature file.

3. The method according to claim 2, characterized in that, The steps of obtaining offline feature data and synchronous feature data corresponding to the target game include: Obtain the offline feature data of the target game from the offline feature file; The synchronization feature data of the target game is obtained from the online feature file.

4. The method according to claim 1, characterized in that, If the target data includes synchronization feature data; The steps for obtaining synchronization feature data corresponding to the target game include: extracting features from the target game data exchanged between the client and the game server in the target game during the game's execution, thereby obtaining the synchronization feature data of the target game.

5. The method according to claim 1, characterized in that, The step of displaying the processing result in a preset panel according to preset display rules includes: The processing results are saved to a preset data display queue; wherein, the data display queue stores the processing results corresponding to each frame of the game in the target game; According to the preset sampling rules, the first data is retrieved from the data display queue; The first data is rendered graphically to obtain a rendering result, which is then displayed in the preset panel.

6. The method according to claim 5, characterized in that, The step of retrieving the first data from the data display queue according to a preset sampling rule includes: The last input data is retrieved from the data display queue, and the retrieved data is identified as the first data.

7. The method according to claim 5, characterized in that, The data display queue also stores attribute tags for the sub-data contained in each processing result; wherein each attribute tag has a corresponding display area in the preset panel; The step of performing graphic rendering on the first data to obtain a rendering result and displaying the rendering result in the preset panel includes: For each sub-data element contained in the first data, perform the following operations: Based on the attribute markers of the current sub-data, determine the target display area corresponding to the current sub-data in the preset panel; Based on the rendering rules corresponding to the target display area, the current sub-data is rendered graphically to obtain the rendering result of the current sub-data. The rendering result of the current sub-data is displayed on the target display area.

8. A data processing apparatus, characterized in that, The device includes: The data acquisition module is used to acquire offline feature data and synchronous feature data corresponding to the target game; wherein, the offline feature data indicates the characteristics of the historical game data experienced by the target game from start to finish; and the synchronous feature data indicates the characteristics of the real-time game data of the target game during its progress. The data verification module is used to perform feature verification processing on target data based on preset feature verification rules to obtain processing results; wherein, the target data includes the offline feature data and / or the synchronous feature data; the feature verification rules are matched with the type of the target data, and the feature verification rules are used to: verify the data attributes of sub-data in the target data or the matching between sub-data, and verify the matching between synchronous feature data and offline feature data with the same number of frames in the target data; The data display module is used to display the processing results in a preset panel according to preset display rules, so as to determine the correctness of the offline feature data used for supervised learning training and the synchronous feature data used for testing through the processing results; If the target data includes the offline feature data and the synchronous feature data; the offline feature data is used to indicate the offline features corresponding to each frame of the game in the target game, and the synchronous feature data is used to indicate the online features corresponding to each frame of the game in the target game; the data verification module is further used to: for each frame of the game, subtract the offline feature data of the current frame from the synchronous feature data of the current frame to obtain the difference feature of the current frame; wherein, the difference feature is used to indicate the matching between the synchronous feature data and the offline feature data of the current frame; and the difference feature corresponding to each frame of the game in the target game is used as the processing result; If the target data is the offline feature data or the synchronous feature data; the data verification module is further configured to: divide the target data into multiple sub-data according to preset attribute categories, and set attribute tags for the sub-data according to the attribute categories corresponding to the sub-data; wherein, one sub-data corresponds to one attribute category, and each attribute category corresponds to its own attribute tag; and determine the multiple sub-data and the attribute tag corresponding to each sub-data as the processing result of the target data; The attribute categories of the sub-data include: the numerical characteristics of the target object in the scene map of the target game, the operation tags of the client on the target object in the target game, the global features of the target game, and the local features of the target game.

9. An electronic device, characterized in that, The electronic device includes a processor and a memory, the memory storing machine-executable instructions that can be executed by the processor, the processor executing the machine-executable instructions to implement the data processing method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when invoked and executed by a processor, cause the processor to implement the data processing method according to any one of claims 1 to 7.

Images