Information processing method and device
By collecting user information and interface information in the game, using teaching models to generate teaching information, and updating the interface in real time, the problem of difficulty in self-study by gamers is solved and the game experience is improved.
Patent Information
- Application Number
- CN202411161004.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-22
- Publication Date
- 2024-12-06
AI Technical Summary
In the prior art, it is difficult for gamers to solve the problems encountered during the game process in a targeted manner during self-study, resulting in poor game experience.
By determining the initial interface for target users to perform target tasks, collect user information and interface information, input them into the teaching model, generate teaching information, update the interface in real time, and provide personalized teaching.
The learning experience of the target users is improved, and the user information and interface information are collected in real time, and prediction and display are made based on the teaching model to achieve personalized teaching of the target users.
Smart Images

Figure CN119088850A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer technology, and in particular to information processing methods and devices. Background Art
[0002] With the development of Internet technology, games have gradually become a popular form of entertainment. Playing games is naturally accompanied by a learning process. Under the current resource environment, players usually choose to find graphic guides or video tutorials through forums and other channels for self-study. However, most of these graphic guides and video tutorials are compiled by game enthusiasts for the purpose of sharing. Players who are learning cannot solve the problems encountered during the game in a targeted manner, and the gaming experience is poor. Therefore, an information processing method is urgently needed to solve the above problems. Summary of the invention
[0003] In view of this, the embodiment of the present application provides an information processing method to solve the technical defects existing in the prior art. The embodiment of the present application also provides an intelligent teaching system, an information processing device, a computing device, a computer-readable storage medium, and a computer program product.
[0004] According to a first aspect of an embodiment of the present application, there is provided an information processing method, including:
[0005] Determine an initial interface generated when a target user performs a target task, and collect user information and interface information in the initial interface;
[0006] Inputting the user information and the interface information into the teaching model to obtain teaching information, and displaying the teaching information in the initial interface;
[0007] An operation instruction submitted by the target user for the teaching information is received, and the initial interface is updated to a target interface based on the operation instruction.
[0008] Optionally, collecting user information and interface information in the initial interface includes:
[0009] Determining a target object and a target role corresponding to the target user in the initial interface;
[0010] The object information of the target object is used as the interface information, and the character action information of the target character is used as the user information.
[0011] Optionally, inputting the user information and the interface information into a teaching model to obtain teaching information includes:
[0012] Inputting the user information and the interface information into a teaching model, using an intention recognition module of the teaching model to recognize the user intention based on the user information, and to recognize the target object intention of the target object contained in the initial interface based on the interface information;
[0013] The processing module of the teaching model is used to process the user intention and the target object intention, and the teaching information is generated according to the processing results.
[0014] Optionally, after updating the initial interface to the target interface based on the operation instruction, the method further includes:
[0015] In a case where it is determined based on the target interface that the target user has not completed the target task, obtaining task execution information generated by the target user executing the target task;
[0016] The task execution information is input into the teaching model to obtain task experience information for the target user.
[0017] Optionally, the information processing method includes:
[0018] Collecting user emotion information generated by the target user performing the target task, and inputting the user emotion information into the teaching model to obtain emotion adjustment information;
[0019] The emotion adjustment information is displayed in the initial interface.
[0020] Optionally, the training of the teaching model includes:
[0021] Inputting historical task information and / or task rule information associated with the target task into an initial teaching model to obtain initial teaching information;
[0022] A loss value is calculated based on the initial teaching information and the reward function, and the initial teaching model is adjusted based on the loss value until a teaching model that meets the training stop condition is obtained.
[0023] Optionally, after updating the initial interface to the target interface based on the operation instruction, it also includes: obtaining historical data generated by the target user performing the target task, and user status data of the target user; performing intensive training on the teaching model based on the historical data and the user status data to obtain a target teaching model.
[0024] According to a second aspect of an embodiment of the present application, there is provided an intelligent teaching system, including:
[0025] The intelligent teaching system includes a teaching interface and a teaching model, including:
[0026] Receiving game information of the target game through the teaching interface;
[0027] The game information is input into the teaching model to obtain game teaching information, and the game teaching information is fed back to the game users of the target game.
[0028] According to a third aspect of an embodiment of the present application, there is provided an information processing device, including:
[0029] A determination module is configured to determine an initial interface generated when a target user performs a target task, and collect user information and interface information in the initial interface;
[0030] A display module, configured to input the user information and the interface information into the teaching model, obtain teaching information, and display the teaching information in the initial interface;
[0031] The updating module is configured to receive an operation instruction submitted by the target user for the teaching information, and update the initial interface to a target interface based on the operation instruction.
[0032] According to a fourth aspect of an embodiment of the present application, a computing device is provided, including:
[0033] Memory and processor;
[0034] The memory is used to store computer-executable instructions, and the processor implements the steps of the information processing method when executing the computer-executable instructions.
[0035] According to a fifth aspect of an embodiment of the present application, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the information processing method are implemented.
[0036] According to a sixth aspect of an embodiment of the present application, a chip is provided, which stores a computer program, and the computer program implements the steps of the information processing method when executed by the chip.
[0037] According to a seventh aspect of the embodiments of this specification, a computer program product is provided, comprising a computer program or instructions, which implement the steps of the above-mentioned information processing method when executed by a processor.
[0038] The information processing method provided by the present application determines the initial interface generated by the target user performing the target task, and collects user information and interface information in the initial interface; inputs the user information and interface information into the teaching model to obtain teaching information, and displays the teaching information in the initial interface; receives the operation instructions submitted by the target user for the teaching information, and updates the initial interface to the target interface based on the operation instructions. By collecting user information and interface information in the initial interface in real time, and predicting the collected user information and interface information based on the teaching model, the teaching information is obtained and displayed in the initial interface. The target user can perform subsequent operations based on the teaching information, thereby realizing personalized teaching for the target user and improving the learning experience of the target user. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] Figure 1 It is a structural diagram of an information processing method provided by an embodiment of the present application;
[0040] Figure 2 is a flow chart of an information processing method provided by an embodiment of the present application;
[0041] Figure 3 This is an architecture diagram of a game teaching system applied to game teaching provided by an embodiment of the present application;
[0042] Figure 4 It is a structural diagram of an intelligent teaching system provided by an embodiment of the present application;
[0043] Figure 5 is a structural diagram of an information processing device provided by an embodiment of the present application;
[0044] Figure 6 It is a structural block diagram of a computing device provided in one embodiment of the present application. DETAILED DESCRIPTION
[0045] Many specific details are described in the following description to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present application, so the present application is not limited by the specific implementation disclosed below.
[0046] The terms used in one or more embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of the present application. The singular forms of "a", "said" and "the" used in one or more embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of the present application refers to and includes any or all possible combinations of one or more associated listed items.
[0047] It should be understood that, although the terms first, second, etc. may be used to describe various information in one or more embodiments of the present application, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first.
[0048] First, the terms involved in one or more embodiments of the present invention are explained.
[0049] Deep Q-Network (DQN): A reinforcement learning method that combines the Q-learning algorithm with a deep neural network.
[0050] Policy Gradient: Directly optimizes policy parameters, rather than indirectly affecting the policy through the value function like Q learning. The goal of the policy gradient method is to minimize an expected cost function or maximize a reward function.
[0051] Monte Carlo Tree Search: An algorithm used for decision making, particularly in the field of gaming, such as board games.
[0052] A / B testing: Also known as split testing or bucket testing, it is a commonly used statistical method to evaluate the differences between two or more versions of a product, web page, advertisement, or other types of output. This test is often used in marketing, user experience design, website optimization, and other fields to determine which version is more effective or popular.
[0053] Natural Language Processing (NLP): A branch of computer science that focuses on enabling computers to understand, interpret, and generate human language. NLP combines knowledge from computer science, artificial intelligence, and linguistics to enable computers to process natural language data.
[0054] Figure 1It is a structural diagram of an information processing method provided by an embodiment of the present application; the information processing method can be applied to a game scene, then the target user is the game player, and the target task is the game task. Determine the initial interface generated by the target user performing the target task, and obtain the user information and interface information that can be reflected in the initial interface by performing image analysis on the initial interface. Input the user information and interface information into the teaching model, obtain the teaching information, and display the teaching information in the initial interface. After receiving the teaching information, the target user can perform the next step of the teaching and submit the operation instruction. Update the initial interface to the target interface based on the operation instruction. By collecting the user information and interface information in the initial interface in real time, and predicting the collected user information and interface information based on the teaching model, the teaching information is obtained and displayed in the initial interface. The target user can perform subsequent operations based on the teaching information, thereby realizing personalized teaching for the target user and improving the learning experience of the target user.
[0055] In the present application, an information processing method is provided. The present application also relates to an intelligent teaching system, an information processing device, a computing device, a computer-readable storage medium, and a computer program product. The following embodiments will be described in detail one by one.
[0056] Figure 2 A flowchart of an information processing method provided according to an embodiment of the present application is shown, which specifically includes the following steps:
[0057] Step 202: Determine an initial interface generated when a target user performs a target task, and collect user information and interface information in the initial interface.
[0058] Specifically, the target task can be a game task in a game scene, and the target user is the game player; the initial interface is the game interface generated when the target user performs the target task, or it can be a game video composed of multiple continuous game interfaces. The initial interface can include the game character controlled by the target user, and the non-game character fighting against the game character. User information can be user status information, or it can be information generated after the target user controls the game character to perform an action. Interface information refers to information that can be extracted from the game interface, which can be directly obtained from the game interface through text recognition. The text content can also be obtained through image recognition. The information contained in the game interface is obtained. The interface information includes but is not limited to the scene information, button information, icon information, game data, status information and action information of non-game characters in the game interface. Both user information and interface information can be obtained by performing image recognition on the initial interface. The time for collecting information in the initial interface can be a continuous period of time to ensure that the collected user information and interface information have higher availability.
[0059] Based on this, when the target user performs the target task, the initial interface generated by the target user performing the target task is determined, and image recognition is performed on the initial interface, user information is collected for the game character controlled by the target user, and interface information is collected for non-game characters in the initial interface.
[0060] Furthermore, considering that the initial interface contains a relatively rich number of objects, when collecting interface information and user information, targeted collection can be performed, which is specifically implemented as follows:
[0061] Determine a target object and a target role corresponding to the target user in the initial interface; use object information of the target object as interface information, and use role action information of the target role as user information.
[0062] Specifically, the target character can be a game character controlled by the target user, and the target object can be a teammate of the target character, an opponent of the target character, or a monster in an opposing state with the target character, etc., which needs to be attacked by the target character. Object information can be object state information, object attribute information, object intention information, and a brief introduction of the object; user information can be user state information, user attribute information, and user intention information of the user.
[0063] Based on this, the target object and the target role corresponding to the target user are determined in the initial interface, the collection time is determined, and the object information of the target object and the role information of the target role are collected within the collection time. The object information of the target object is used as the interface information, and the role action information of the target role is used as the user information.
[0064] For example, in a battle game scenario, the target user controls the game character to fight against the monster in the game scenario, and the game is won by defeating the monster. The interface where the game character is located is the initial interface, and the state information, attribute information, and intention information of the game character during the game process are used as user information. The state information, attribute information, and intention information of the monster, as well as the environmental information in the initial interface are used as interface information.
[0065] In summary, the interface information and user information are obtained for the initial interface respectively, so as to provide accurate and effective teaching assistance to the target user based on the interface information and user information later.
[0066] Step 204: input the user information and the interface information into the teaching model, obtain teaching information, and display the teaching information in the initial interface.
[0067] Specifically, after determining the initial interface generated by the target user performing the target task and collecting user information and interface information in the initial interface, the user information and interface information can be input into the teaching model to obtain teaching information, and the teaching information is displayed in the initial interface, wherein the teaching model is a large artificial intelligence model with image recognition, image analysis, semantic recognition, semantic analysis, personalized recommendation and other capabilities. The teaching information can be the recommended operation method for the target user, or the battle analysis and environment analysis information provided to the target user.
[0068] Based on this, after determining the initial interface generated by the target user performing the target task and collecting user information and interface information in the initial interface, the user information and interface information are input into the teaching model. The teaching model can generate teaching information for the target user by processing the user information and interface information, and display the teaching information in the initial interface for the target user to learn. The display of teaching information can be a graphical display method or a display method combined with virtual reality. The teaching information can be a video tutorial, detailed text description or precise demonstration operation. The teaching information can also be a clear and accurate explanation of the game rules and operation skills guidance, aiming to provide clear, detailed and vivid teaching content for the target user.
[0069] Furthermore, the teaching model has the function of image and text analysis, and can provide personalized teaching content for target users based on the analysis of user information and interface information. The specific implementation is as follows:
[0070] The user information and the interface information are input into the teaching model, and the intention recognition module of the teaching model is used to recognize the user intention based on the user information, and the target object intention of the target object contained in the initial interface is recognized based on the interface information; the user intention and the target object intention are processed by the processing module of the teaching model, and the teaching information is generated according to the processing results.
[0071] Specifically, the intention recognition module is used to recognize the user intention based on the user information, and to recognize the intention of the target object in the initial interface based on the interface information; the target object can be a character or monster that is opposite to the target user in the initial interface, or the target object can be an offensive level in the initial interface. The user intention can be the action tendency of the target user, such as the target user's intention to move forward or backward. The target object intention refers to the action tendency of the target object, such as the intention to attack and dodge. The processing module is used to analyze the interface information and user information in combination with the task rules of the target task.
[0072] Based on this, user information and interface information are input into the teaching model, and the intention recognition module of the teaching model is used to recognize the user intention of the target user based on the user information, and the target object intention of the target object contained in the initial interface is recognized based on the interface information. The processing module of the teaching model is used to analyze the user intention and the target object intention and formulate a response strategy in combination with the task rules of the target task, and generate teaching information for the target user.
[0073] Continuing with the above example, when the target user operates the game character, the target user's performance in the game is analyzed in real time based on the user information, and accurate feedback and targeted suggestions are provided in combination with the interface information to help the user improve his game skills. The teaching information can be a video tutorial, detailed text descriptions, and accurate demonstration operations. The teaching content can be a clear and accurate explanation of the game rules and guidance on operating skills. When the target object is a monster, the pre-actions of the monster's moves can be analyzed based on the interface information to analyze the corresponding response strategies. When the target user is determined to be confused in the game through analysis of user information, the teaching model gives operational suggestions such as skill points and equipment purchase.
[0074] In summary, the processing module of the teaching model is used to analyze the user intention and the target object intention and formulate a response strategy in combination with the task rules of the target task, and generate teaching information for the target user. This enables personalized teaching for the target user, prompts the target user in a timely manner, and improves the target user's gaming experience.
[0075] Step 206: receiving an operation instruction submitted by the target user for the teaching information, and updating the initial interface to a target interface based on the operation instruction.
[0076] Specifically, after the user information and interface information are input into the teaching model, the teaching information is obtained, and the teaching information is displayed in the initial interface, the operation instructions submitted by the target user for the teaching information can be received, and the initial interface can be updated to the target interface based on the operation instructions, wherein the operation instructions are used to operate the game character in the initial interface to make an action, or to operate the initial interface. The target interface is the interface generated after operating the things in the initial interface.
[0077] Based on this, after inputting user information and interface information into the teaching model, obtaining teaching information, and displaying the teaching information in the initial interface, the operation instructions submitted by the target user for the teaching information are received, and the objects in the initial interface are operated based on the operation instructions, and the initial interface is updated to the target interface.
[0078] Furthermore, considering that there is a possibility of task failure when the target user performs the target task, in the case of not completing the target task, task execution information can be obtained to summarize the task experience and provide task suggestions. The specific implementation is as follows:
[0079] When it is determined based on the target interface that the target user has not completed the target task, task execution information generated by the target user performing the target task is obtained; the task execution information is input into the teaching model to obtain task experience information for the target user.
[0080] Specifically, if the target user fails to complete the target task, it means that the target task execution has failed. The task execution information may be all information records generated by the target user executing the target task, or may be combat information or level-breaking information obtained by image processing of the task execution video generated by the target user executing the target task. The task experience information may be analysis information of the cause of the failure of the target task execution, or may be guidance information for executing the target task.
[0081] Based on this, when it is determined based on the target interface that the target user has not completed the target task, it means that the result of the target user performing the target task is a task execution failure. The target user performs the target task to generate a target video, and information is collected from the target video to obtain task execution information. The task execution information is input into the teaching model, and the teaching model is used to analyze the task execution information. By analyzing the operations and feedback of the target user and the operations and feedback of the target object, task experience information for the target user is obtained.
[0082] Continuing with the above example, when the target user controls the game character to fight a game and the game fails, obtain the game video generated from the start to the end of the game by the target user, extract information from each video frame in the game video, obtain task execution information, input the task execution information into the teaching model for experience summary, and obtain task experience information.
[0083] In summary, when the target user fails to perform the target task, the task execution information generated by the target user performing the target task is summarized to obtain the task experience information. Through the actual operation of the target user, the target user is given experience summary and task execution suggestions are provided, thereby improving the target user's task execution skills.
[0084] Furthermore, considering that the target user may have a significant change in emotions when performing the target task, emotion adjustment information can be provided according to the user's emotions, which is specifically implemented as follows:
[0085] Collect user emotion information generated by the target user performing the target task, input the user emotion information into the teaching model to obtain emotion adjustment information; and display the emotion adjustment information in the initial interface.
[0086] Specifically, user emotional information refers to the emotional fluctuations generated when the target user performs the target task, and the emotional adjustment information can be health tips or encouraging statements given to soothe the negative emotions of the target user, helping the target user maintain a positive attitude.
[0087] Based on this, the user emotion information generated by the target user performing the target task is collected, and the user emotion information is input into the teaching model to obtain emotion adjustment information. The emotion adjustment information is displayed in the initial interface to inform the target user to adjust his emotion, maintain a positive attitude, and reduce the target user's anxiety value.
[0088] Using the above example, when the target user controls the game character to play the game, he or she will inevitably encounter game failure, attack failure, and being hit by a monster. At this time, the target user may experience negative situations such as anxiety and anger. At this time, the target user's user emotion information can be collected, and the user emotion information can be analyzed using the teaching model to show the target user soothing and encouraging information.
[0089] To sum up, the emotion adjustment information is displayed in the initial interface to inform the target user to adjust his emotion and maintain a positive attitude, thereby reducing the target user's anxiety value and improving the target user's task experience, so that the target user can maintain a happy mood to perform the target task.
[0090] Furthermore, in the process of the target user performing the target task, the teaching model can be reinforced with training based on the historical data generated by the target user performing the target task and the user status data, so that the teaching model can provide personalized teaching to the target user. The specific implementation is as follows:
[0091] Acquire historical data generated by the target user performing the target task and user status data of the target user; perform intensive training on the teaching model based on the historical data and the user status data to obtain a target teaching model.
[0092] Specifically, historical data can be game data generated at any time during the target user's execution of the target task, including but not limited to battle data generated when the target user manipulates the game character to fight against non-game characters, and action data generated when the target user manipulates the game character to complete a specified action. User status data can be the status data of the game character after the target user manipulates the game character to attack or defend, or it can be the status data of the target user's psychological or physiological dimensions that is integrated by collecting data such as the target user's expression and heart rate.
[0093] Based on this, the data collection time is determined, and the historical data generated by the target user performing the target task is collected at the data collection time, and the user status data of the target user is determined. The historical data and user status data are used as training data to perform intensive training on the teaching model to obtain the target teaching model. Since the target teaching model is trained based on the data related to the target user, the target teaching model has the ability to provide personalized teaching for the target user.
[0094] Using the above example, any moment can be determined as a data collection moment during the process of the target user controlling the game character to play the game. At the data collection moment, the historical data generated by the target user controlling the game character to play the game is collected. At the same time, the user status data of the target user is collected by identifying the user's emotions, collecting the user's heart rate, etc. The collected historical data and user status data are used as training data to continue to strengthen the training of the teaching model, so that the teaching model can learn the target user's operation method in a targeted manner and provide targeted game teaching for the target user.
[0095] To sum up, the teaching model is strengthened by training the teaching model based on historical data and user status data, so that the obtained target teaching model can learn the operating habits of the target users. By analyzing the operating data of the target users, personalized teaching data can be provided to the target users to improve the gaming experience of the target users.
[0096] Furthermore, considering that the process of the target user performing the target task is a process of interacting with the target object corresponding to the target task, and the target user's operation is subjective, the teaching model can be trained to provide personalized teaching for the target user. The specific implementation is as follows:
[0097] Inputting historical task information and / or task rule information associated with the target task into the initial teaching model to obtain initial teaching information; calculating a loss value based on the initial teaching information and a reward function, and adjusting parameters of the initial teaching model based on the loss value until a teaching model that meets the training stop condition is obtained.
[0098] Specifically, historical task information refers to the task execution information generated when the target task is executed by the target user or other users; task rule information refers to the execution rules of the target task. When the target task is a game, the task rule information is the game rule information. The initial teaching model refers to the teaching model that has not yet been trained. The initial teaching information refers to the teaching information provided for the target task after the historical task information and / or task rule information are processed by the initial teaching model. The reward function is used to quantify the performance of the initial teaching model and guide the initial teaching model to learn and adopt the correct game strategy. The training stop condition can be a preset training round, prediction accuracy or preset training time.
[0099] Based on this, historical task information and / or task rule information associated with the target task is obtained, and the historical task information and task rule information can be input into the initial teaching model to obtain initial teaching information; the historical task information can be input into the initial teaching model to obtain initial teaching information, and the task rule information can also be input into the initial teaching model to obtain initial teaching information. The loss value is calculated based on the initial teaching information and the reward function, and the initial teaching model is adjusted based on the loss value to obtain an intermediate teaching model, and then the historical task information is obtained, combined with the task rule information, input into the intermediate teaching model to train the intermediate teaching model, until a teaching model that meets the training stop condition is obtained.
[0100] Continuing with the above example, when training the teaching model, we are committed to using a wide range of training data sets to enable the teaching model to deeply learn and understand the rules, strategies, and operation modes of the game. In the data collection and training stage, data collection technology is used to obtain a large amount of game status and its corresponding action and reward data, and these data are used to train the teaching model. The hyperparameters of the model are adjusted and optimized to further improve the performance of the AI model in the game. In order to improve the adaptability and competitiveness of the AI model, adversarial training technology is used to enable the AI model to cope with different types of opponents or environmental changes. Training the teaching model based on historical task information can improve the adaptability of the teaching model. According to the enemy attack information, the attack information of the game character, and the battle results recorded in the historical task information, the teaching model can learn battle experience, provide more effective battle skills, and realize personalized teaching. Training the teaching model based on task rule information can improve the teaching model's ability to understand the rules of the game and provide accurate game skills.
[0101] In summary, by training the initial teaching model, a teaching model that meets the training stop conditions is obtained, so that the teaching model has the teaching function of executing the target task and realizes personalized teaching for the target users.
[0102] The information processing method provided by the present application determines the initial interface generated by the target user performing the target task, and collects user information and interface information in the initial interface; inputs the user information and interface information into the teaching model to obtain teaching information, and displays the teaching information in the initial interface; receives the operation instructions submitted by the target user for the teaching information, and updates the initial interface to the target interface based on the operation instructions. By collecting user information and interface information in the initial interface in real time, and predicting the collected user information and interface information based on the teaching model, the teaching information is obtained and displayed in the initial interface. The target user can perform subsequent operations based on the teaching information, thereby realizing personalized teaching for the target user and improving the learning experience of the target user.
[0103] The following combination Figure 3 Taking the application of the information processing method provided in this application to game teaching as an example, the information processing method is further explained. Figure 3 The following is an architecture diagram of a game teaching system for game teaching provided by an embodiment of the present application, which is specifically implemented as follows:
[0104] The game teaching system includes game data collection, AI model training, game interaction interface, game teaching module, and user feedback and adjustment. Among them, the AI model is the teaching model, which has the function of game teaching.
[0105] The game data collection module continuously collects and analyzes the game data of players, so that the AI model can continuously update and improve its teaching strategy to provide more accurate and personalized guidance. In order for the AI model to fully understand and participate in the game, it can be provided with detailed interface information, clear rules descriptions, and real-time updated game status data, including but not limited to the visual presentation of the game screen, the location and function of user-operable buttons, the current score status, and the complete game rules description. In terms of image processing, image recognition technology is used to accurately identify various elements from the game screen, such as function buttons, text information, specific icons, etc., to provide accurate visual input for the AI model. For the game rule description and other text information, natural language processing technology is used for in-depth analysis to ensure that the AI model can clearly understand the various rules and operating requirements of the game.
[0106] For online games, considering the real-time and dynamic nature of data, web crawler technology is used to capture key data on the game interface, and advanced parsing technology is used to extract information useful for AI model decision-making. In addition, in order to continuously track and analyze the game status, monitoring and logging measures are also implemented to provide game data support for AI models by collecting and analyzing log files or event records generated by the game.
[0107] The AI model training module, in the process of using reinforcement learning or other related technologies, is committed to enabling the AI model to deeply learn and understand the rules, strategies and operation modes of the game through a wide range of training data sets. The concept of state space is clarified, and the state of the game is converted into a series of representative feature sets. These features include but are not limited to the pixel values of the game screen, the specific position of the player, and the current score. In the selection of model structure, deep reinforcement learning models such as deep Q network (DQN) and policy gradient are used, as well as value iteration-based methods such as Monte Carlo Tree Search. A reasonable reward function is involved to quantify the performance of the AI model in each state and ensure that the function can effectively guide the AI model to learn and adopt the correct game strategy. In the data collection and training stage, data collection technology is used to obtain a large amount of game states and their corresponding actions and reward data, and these data are used to train the AI model. During the training process, the hyperparameters of the model are adjusted and optimized to further improve the performance of the AI model in the game. In order to improve the adaptability and competitiveness of the AI model, adversarial training technology is used to enable the AI model to cope with different types of opponents or environmental changes.
[0108] Game interaction interface, game state perception function aims to conduct in-depth analysis of the game screen by applying image recognition technology to accurately extract key information, such as player position, enemy real-time status and specific location of props. This information is crucial for the AI model to understand the current game situation. In the decision-making stage, the AI model will make reasonable and effective decisions based on a comprehensive understanding of the game state. By using reinforcement learning models or other advanced decision-making models, the AI model can determine the next action strategy, such as moving, attacking or avoiding. To ensure that the AI model decision can be smoothly transformed into actual game operations, the formulated operation instructions are converted into operation commands that can be recognized by the game. This process may involve simulating key input, mouse operation or other ways to interact with the game. For online games, stable communication with the game server will also be achieved through the network interface. This communication process is not only used to send the operation instructions of the AI model, but also to receive real-time information on game status updates. In order to facilitate the AI model to interact efficiently with different types of games, all the above functions are encapsulated into a unified and standardized interface. This encapsulation strategy will ensure that the AI model can flexibly adapt and be applied to various game scenarios.
[0109] The game teaching module includes user modeling, natural language processing (NLP), personalized recommendation, real-time feedback and suggestions, and visual display. Among them, user modeling: using rigorous data analysis methods, through in-depth analysis of users' historical game data, operation habits and other information, comprehensive modeling of users is carried out, so as to accurately understand the user's game level and personalized needs. Natural language processing (NLP): when processing game rule documents and teaching materials, advanced NLP technology is used to ensure accurate parsing of text content, so as to provide users with clear and accurate explanations of game rules and operation skills guidance. Personalized recommendation: based on the precise results of user modeling, using efficient recommendation system algorithms, personalized teaching content is tailored for users, including video tutorials, detailed text descriptions, and precise demonstration operations, etc., to ensure that each user can get targeted learning support. Real-time feedback and suggestions: combined with advanced technologies such as reinforcement learning, real-time analysis of users' performance in the game is carried out, and accurate feedback and targeted improvement suggestions are provided accordingly to help users continuously improve their game skills and experience. Visual display: In order to enable users to understand the game rules and strategies more intuitively, the graphical interface and virtual reality technology are used to present game scenes and operating skills to users in a vivid and realistic way, enhancing the user's learning effect and immersion.
[0110] The user feedback and adjustment module includes data collection and analysis, natural language processing (NLP), machine learning model, model adjustment and A / B testing. Data collection and analysis: comprehensively collect user feedback data through multiple channels such as implementing user questionnaires, integrating in-game feedback system data, and monitoring user behavior data. Natural language processing (NLP): after collecting user feedback text, use NLP technology to perform sentiment analysis, topic extraction and other processing to ensure that users' specific opinions and suggestions on AI model game teaching can be deeply understood. Machine learning model: apply machine learning model to deeply mine and analyze user feedback data, aiming to reveal the focus of users' general concern and improvement suggestions. Model adjustment: based on the analysis results of the above user feedback data and machine learning model, key parts such as teaching content, feedback mechanism, recommendation system, etc. will be finely adjusted and optimized. A / B testing: to ensure the effectiveness and feasibility of improvement measures, new teaching modules are tested using methods such as A / B testing to verify whether they can significantly improve teaching results, and to judge the actual effectiveness of improvement work accordingly.
[0111] In summary, the game teaching system aims to achieve multiple functions such as detailed operation teaching, failure summary, detailed step explanation, monster characteristic analysis, in-depth analysis of gameplay, and learning guidance by teaching game play, scene judgment, and teaching knowledge. In this way, it provides users with personalized teaching services and improves their gaming experience. The game teaching system connects the construction and development of the game community. By providing in-game social functions and player interaction platforms, it can promote communication and cooperation between players and create a positive gaming atmosphere.
[0112] Corresponding to the above method embodiment, the present application also provides an intelligent teaching system, Figure 4 FIG. 1 shows a schematic diagram of the structure of an intelligent teaching system provided by an embodiment of the present application. Figure 4 As shown, the intelligent teaching system 400 includes a teaching interface 410 and a teaching model 420; the intelligent teaching system 400 receives game information of the target game through the teaching interface 410; inputs the game information into the teaching model 420, obtains game teaching information, and feeds back the game teaching information to the game users of the target game.
[0113] In actual applications, the intelligent teaching system provides a unified teaching interface, through which various games can be connected. After the target game is connected to the intelligent teaching system, the intelligent teaching system can receive game information generated by game users playing the target game through the teaching interface. The intelligent teaching system inputs the game information into the teaching model, and the teaching model can analyze the game information and output the game teaching information. The intelligent teaching system can feed back the game teaching information to the game users of the target game through the teaching interface. Game users can continue to play the game according to the game teaching information and obtain teaching content from the game teaching information.
[0114] In summary, the target game can be connected to the intelligent teaching system through the teaching interface, and the game information can be sent to the intelligent teaching system through the teaching interface. The intelligent teaching system uses the teaching model to process the game information and obtain the game teaching information. The teaching model can flexibly adapt to and be applied to various game scenarios, which improves the usability of the teaching model.
[0115] Corresponding to the above method embodiment, the present application also provides an information processing device embodiment, Figure 5 FIG. 1 shows a schematic diagram of the structure of an information processing device provided by an embodiment of the present application. Figure 5 As shown, the device comprises:
[0116] The determination module 502 is configured to determine an initial interface generated when a target user performs a target task, and collect user information and interface information in the initial interface;
[0117] A display module 504 is configured to input the user information and the interface information into the teaching model, obtain teaching information, and display the teaching information in the initial interface;
[0118] The updating module 506 is configured to receive an operation instruction submitted by the target user for the teaching information, and update the initial interface to a target interface based on the operation instruction.
[0119] In an optional embodiment, the determining module 502 is further configured to:
[0120] Determining a target object and a target role corresponding to the target user in the initial interface;
[0121] The object information of the target object is used as the interface information, and the character action information of the target character is used as the user information.
[0122] In an optional embodiment, the display module 504 is further configured to:
[0123] Inputting the user information and the interface information into a teaching model, using an intention recognition module of the teaching model to recognize the user intention based on the user information, and to recognize the target object intention of the target object contained in the initial interface based on the interface information;
[0124] The processing module of the teaching model is used to process the user intention and the target object intention, and the teaching information is generated according to the processing results.
[0125] In an optional embodiment, the updating module 506 is further configured to:
[0126] In a case where it is determined based on the target interface that the target user has not completed the target task, obtaining task execution information generated by the target user executing the target task;
[0127] The task execution information is input into the teaching model to obtain task experience information for the target user.
[0128] In an optional embodiment, the updating module 506 is further configured to:
[0129] Collecting user emotion information generated by the target user performing the target task, and inputting the user emotion information into the teaching model to obtain emotion adjustment information;
[0130] The emotion adjustment information is displayed in the initial interface.
[0131] In an optional embodiment, the updating module 506 is further configured to:
[0132] Inputting historical task information and / or task rule information associated with the target task into an initial teaching model to obtain initial teaching information;
[0133] A loss value is calculated based on the initial teaching information and the reward function, and the initial teaching model is adjusted based on the loss value until a teaching model that meets the training stop condition is obtained.
[0134] In an optional embodiment, the updating module 506 is further configured to:
[0135] Acquire historical data generated by the target user performing the target task, as well as user status data of the target user;
[0136] The teaching model is subjected to intensive training based on the historical data and the user status data to obtain a target teaching model.
[0137] The information processing method provided by the present application determines the initial interface generated by the target user performing the target task, and collects user information and interface information in the initial interface; inputs the user information and interface information into the teaching model to obtain teaching information, and displays the teaching information in the initial interface; receives the operation instructions submitted by the target user for the teaching information, and updates the initial interface to the target interface based on the operation instructions. By collecting user information and interface information in the initial interface in real time, and predicting the collected user information and interface information based on the teaching model, the teaching information is obtained and displayed in the initial interface. The target user can perform subsequent operations based on the teaching information, thereby realizing personalized teaching for the target user and improving the learning experience of the target user.
[0138] The above is a schematic scheme of an information processing device of this embodiment. It should be noted that the technical scheme of the information processing device and the technical scheme of the above-mentioned information processing method belong to the same concept. For details not described in detail in the technical scheme of the information processing device, please refer to the description of the technical scheme of the above-mentioned information processing method. In addition, each component in the device embodiment should be understood as a functional module that must be established to implement each step of the program flow or each step of the method, and each functional module is not an actual functional division or separation definition. The device claim defined by such a group of functional modules should be understood as a functional module architecture that mainly implements the solution through the computer program recorded in the specification, and should not be understood as a physical device that mainly implements the solution through hardware.
[0139] Figure 6The block diagram of a computing device 600 according to an embodiment of the present application is shown. The components of the computing device 600 include but are not limited to a memory 610 and a processor 620. The processor 620 is connected to the memory 610 via a bus 630, and the database 650 is used to store data.
[0140] The computing device 600 also includes an access device 640 that enables the computing device 600 to communicate via one or more networks 660. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 640 may include one or more of any type of network interface (e.g., a network interface card (NIC)) whether wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a World Wide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, a near field communication (NFC) interface, and the like.
[0141] In one embodiment of the present application, the above components of the computing device 600 and Figure 6 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 6 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of the present application. Those skilled in the art may add or replace other components as needed.
[0142] The computing device 600 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or PC. The computing device 600 may also be a mobile or stationary server.
[0143] The processor 620 is used to execute computer executable instructions of the information processing method.
[0144] The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the above information processing method belong to the same concept, and the details not described in detail in the technical scheme of the computing device can be referred to the description of the technical scheme of the above information processing method.
[0145] An embodiment of the present application further provides a computer-readable storage medium storing computer instructions, which are used in an information processing method when executed by a processor.
[0146] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the above information processing method belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the above information processing method.
[0147] An embodiment of the present application further provides a chip storing a computer program, which implements the steps of the information processing method when executed by the chip.
[0148] An embodiment of the present specification also provides a computer program product, including a computer program or instructions, which implement the steps of the above-mentioned information processing method when executed by a processor.
[0149] The above is a schematic scheme of a computer program product of this embodiment. It should be noted that the technical scheme of the computer program product and the technical scheme of the above information processing method belong to the same concept, and the details not described in detail in the technical scheme of the computer program product can be referred to the description of the technical scheme of the above information processing method.
[0150] The above describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0151] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.
[0152] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.
[0153] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0154] The preferred embodiments of the present application disclosed above are only used to help explain the present application. The optional embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the present application. The present application selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present application, so that those skilled in the art can understand and use the present application well. The present application is only limited by the claims and their full scope and equivalents.
Claims
1. An information processing method, characterized in that: include: Determine an initial interface generated when a target user performs a target task, and collect user information and interface information in the initial interface; Inputting the user information and the interface information into the teaching model to obtain teaching information, and displaying the teaching information in the initial interface; An operation instruction submitted by the target user for the teaching information is received, and the initial interface is updated to a target interface based on the operation instruction.
2. The information processing method according to claim 1, characterized in that: The collecting of user information and interface information in the initial interface includes: Determining a target object and a target role corresponding to the target user in the initial interface; The object information of the target object is used as the interface information, and the character action information of the target character is used as the user information.
3. The information processing method according to claim 1, characterized in that: The step of inputting the user information and the interface information into a teaching model to obtain teaching information includes: Inputting the user information and the interface information into a teaching model, using an intention recognition module of the teaching model to recognize the user intention based on the user information, and to recognize the target object intention of the target object contained in the initial interface based on the interface information; The processing module of the teaching model is used to process the user intention and the target object intention, and the teaching information is generated according to the processing results.
4. The information processing method according to claim 1, characterized in that: After the initial interface is updated to the target interface based on the operation instruction, the method further includes: In a case where it is determined based on the target interface that the target user has not completed the target task, obtaining task execution information generated by the target user executing the target task; The task execution information is input into the teaching model to obtain task experience information for the target user.
5. The information processing method according to any one of claims 1 to 4, characterized in that: The method comprises: Collecting user emotion information generated by the target user performing the target task, and inputting the user emotion information into the teaching model to obtain emotion adjustment information; The emotion adjustment information is displayed in the initial interface.
6. The information processing method according to claim 1, characterized in that: The training of the teaching model includes: Inputting historical task information and / or task rule information associated with the target task into an initial teaching model to obtain initial teaching information; A loss value is calculated based on the initial teaching information and the reward function, and the initial teaching model is adjusted based on the loss value until a teaching model that meets the training stop condition is obtained.
7. The information processing method according to claim 1, characterized in that: After the initial interface is updated to the target interface based on the operation instruction, the method further includes: Acquire historical data generated by the target user performing the target task, as well as user status data of the target user; The teaching model is subjected to intensive training based on the historical data and the user status data to obtain a target teaching model.
8. An intelligent teaching system, characterized in that: The intelligent teaching system includes a teaching interface and a teaching model, including: Receiving game information of the target game through the teaching interface; The game information is input into the teaching model to obtain game teaching information, and the game teaching information is fed back to the game users of the target game.
9. An information processing device, characterized in that: include: A determination module is configured to determine an initial interface generated when a target user performs a target task, and collect user information and interface information in the initial interface; A display module, configured to input the user information and the interface information into the teaching model, obtain teaching information, and display the teaching information in the initial interface; The updating module is configured to receive an operation instruction submitted by the target user for the teaching information, and update the initial interface to a target interface based on the operation instruction.
10. A computing device, characterized in that include: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the steps of the information processing method according to any one of claims 1 to 7.
11. A computer-readable storage medium storing computer instructions, characterized in that: When the instruction is executed by the processor, the steps of the information processing method described in any one of claims 1 to 7 are implemented.
12. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the steps of the information processing method described in any one of claims 1 to 7 are implemented.
Citation Information
Patent Citations
Legal consulting robot based emotional pacifying method
CN111300443A
Numerical control machine tool interaction method based on pre-training reinforcement learning and related equipment
CN115964115A
Game image processing method and device, equipment and storage medium
CN116966559A
