Chess interaction method and system

Abstract

The invention discloses a chess interaction method and system, and relates to the technical field of chess teaching, according to the system, a comprehensive chess teaching platform is built, a virtual chess game is utilized to carry out trainee training, AI game playing and online game playing, and game playing information is uploaded in real time. The platform collects game data of students and establishes a basic data set. On the basis of the data set, chess power indexes, calculation power indexes and intuitive decision indexes of the trainees are calculated, and personalized primary, intermediate and advanced training strategies are formulated by constructing an AI dynamic training model. After training, the trainees are subjected to redisk analysis, the understanding condition of the trainees is evaluated, and an explanation strategy is provided. And after the training period, calculating a learning progress index, evaluating the chess power change, and if the chess power is not advanced, adopting a chess style conversion strategy. Through the chess style correction index, the system analyzes the chess style adaptation degree of the trainee, provides a computational or intuitive training strategy, and ensures that the trainee is accurately trained and makes progress continuously in each stage.

Description

Technical Field

[0001] The present invention relates to the technical field of chess teaching, and in particular to a chess interactive system and method. Background Art

[0002] In recent years, the rapid development of artificial intelligence (AI) technology has driven intelligent upgrades across various fields. Among them, chess training and instruction, a field that relies on deep computing and decision-making capabilities, has gradually incorporated AI technology to improve teaching quality and training efficiency. Traditional chess training methods primarily rely on face-to-face instruction from professional players, or students improving through books and self-study software. However, these methods have limitations, such as limited training resources, insufficient personalization, and a lack of dynamic feedback mechanisms.

[0003] Existing chess training systems mostly focus on fixed-game matches or post-game analysis, lacking long-term tracking and adjustment of students' playing styles. Furthermore, quantitative analysis of core chess skill dimensions like calculation ability and intuitive decision-making is relatively crude, making it difficult to accurately identify students' weaknesses and provide personalized improvement plans. Furthermore, traditional chess skill assessment methods rely solely on win-loss records or ELO scores, failing to effectively integrate comprehensive analysis of multiple data points, such as the student's decision-making process and calculation depth. This results in relatively single-minded training plans that fail to meet the needs of diverse students. Summary of the Invention

[0004] In view of the deficiencies in the prior art, the present invention provides a chess interaction method and system to solve the problems mentioned in the background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a chess interactive system, comprising: a chess teaching platform module, a data acquisition module, a chess strength testing module, an AI dynamic training model module, a student comprehensive evaluation module, and a student chess style adjustment module; The chess teaching platform module is used to build a chess teaching platform and construct several virtual chess games and connect them to each other for student chess training, AI games and student online games, and upload the game information on the virtual chessboard interface to the chess teaching platform in real time; The data collection module is used to monitor students' thinking paths, decision-making time, calculation steps and intuitive choices in real time during the virtual chess game, and record students' game performance data at different stages of the game to establish a basic data set; The chess strength test module is used to monitor the student's chess strength foundation and calculate the student's chess strength index SI, calculation ability index CAI and intuitive decision index IDI according to the basic data set data; The AI dynamic training model module is used to build an AI dynamic training model, which is used as a primary training strategy, an intermediate training strategy, and an advanced training strategy to conduct AI game training for all students. After training, the students will review the game, calculate the review analysis index (RPI), analyze the students' understanding, and provide strategy explanations. The student comprehensive evaluation module is used to evaluate the students' chess skills after the training cycle, analyze the changes in students' chess skills by calculating the learning progress index (LPI), and provide chess style conversion strategies for students whose chess skills have not improved; The student chess style adjustment module is used to monitor the chess style of students whose chess skills have not improved, analyze the adaptability of the student's chess style by calculating the chess style correction index SXZ, and provide corresponding strategies.

[0006] Preferably, the chess teaching platform module is used to construct several virtual chess games and connect them to each other. The virtual chess games are used to create an immersive chess training environment for students based on preset chess rules including Go, Chinese chess and international chess through a touch-controlled electronic chessboard. The virtual chessboard supports AI games and student online games, and the game information on the virtual chessboard interface is uploaded to the chess teaching platform in real time.

[0007] Preferably, the data collection module is used to collect student game information uploaded to the chess teaching platform, including the student's chess game thinking path, decision-making time, calculation steps and intuitive choices, and record the student's game performance data at different stages of the chess game, and establish a basic data set.

[0008] Preferably, the chess strength testing module includes a first calculation unit and a second calculation unit; The first calculation unit is used to calculate the student's chess strength index SI, computing ability index CAI and intuitive decision index IDI respectively after dimensionless processing of the data in the basic data set. The formulas are as follows: ; Where, Indicates the number of games won by students during the monitoring period. Indicates the number of students and games during the monitoring period, Indicates the number of games lost by students during the monitoring period. represents the student's calculation and change ability score, w1, w2, w3 and w4 represent weight coefficients; ; Where, It means that the students have calculated the correct number of changes. It represents the total number of tricks the students have tried to calculate. represents the number of calculation steps of the student, w5 and w6 represent weight coefficients; ; Where, represents the number of correct decisions made by the students, represents the total number of student decisions, It represents the average time it takes for students to make decisions. Indicates the standard value for achieving quick decision-making.

[0009] Preferably, the AI dynamic training model module includes a model building unit, a third computing unit and a first analyzing unit; The model construction unit is used to use a convolutional neural network to construct an initial model of the convolutional neural network, and to train and test the initial model of the convolutional neural network using the student's basic data set data, and to use the trained initial model of the convolutional neural network as the AI dynamic training model. At the same time, the intermediate layer outputs of the student's chess strength index SI, computing power index CAI and intuitive decision index IDI are used as feature vectors to identify feature information, and the AI dynamic adjustment model is trained and tested through the acquired feature information. The trained AI dynamic adjustment model is used as a primary training strategy, an intermediate training strategy and an advanced training strategy respectively to perform AI game training on all students.

[0010] Preferably, the third calculation unit is used to review the game after the student and the AI are trained. After dimensionless processing, the replay analysis index RPI is calculated and obtained. The formula is as follows: ; Where, Indicates the correct number of hands that students should improve when reviewing the game. Indicates the total number of improved lots provided by the AI during the review, w7 and w8 represent weight coefficients; The first analysis unit is configured to preset a first threshold Q1 in advance and compare and analyze the replay analysis index RPI with the first threshold Q1 to obtain a first evaluation result, including: When the replay analysis index RPI ≥ the first threshold Q1, it means that the student can understand the game replay and no adjustments are made, and continuous monitoring is performed; When the replay analysis index RPI is less than the first threshold Q1, it means that the student cannot understand the game replay, triggering the first warning instruction and generating the first strategy: starting the AI replay explanation function and giving a step-by-step explanation.

[0011] Preferably, the student comprehensive evaluation module includes a fourth calculation unit and a second analysis unit; The fourth calculation unit is used to calculate the learning progress index LPI after the trainee has completed the training cycle, combined with the basic data of the trainee after training, after dimensionless processing, and the formula is as follows: ; Where, represents the time of a training cycle, Indicates the change in the student's chess strength index during a training cycle. Indicates the change in the student's computing power index during a training cycle. It indicates the change of the trainee's intuitive decision-making index in a training cycle.

[0012] Preferably, the second analysis unit is configured to preset a second threshold Q2 in advance and compare and analyze the learning progress index LPI with the second threshold Q2 to obtain the second evaluation result, including: When the learning progress index LPI ≥ the second threshold Q2, it means that the student's chess skills have improved through AI game training, and the second strategy is generated: increase the difficulty of AI game training and proceed to the next training cycle; When the learning progress index LPI is less than the second threshold Q2, it means that the student’s chess skills have not improved through AI game training, triggering the second warning instruction and generating the third strategy: changing the student’s chess style.

[0013] Preferably, the student chess style adjustment module includes a fifth calculation unit and a third analysis unit; The fifth calculation unit is used to perform chess style conversion on the student when receiving the second warning instruction, and calculate and obtain the chess style correction index SXZ after dimensionless processing, using the following formula: ; ; ; Where, Indicates the student's learning progress index. represents the chess style matching degree, SBI represents the chess style conversion benefit, It represents the student's calculation ability index, IDI represents the student's intuitive decision-making index, and SI represents the student's chess strength index. Indicates the chess strength index after changing the chess style. It represents the cycle time of the student's chess style change, and a1, a2 and a3 represent weight coefficients; The third analysis unit is used to preset a third threshold Q3 in advance, and compare and analyze the chess style correction index SXZ with the third threshold Q3, and obtain a third evaluation result including: When the chess style correction index SXZ = the third threshold Q3, it means that the student's chess style is suitable and no adjustment is needed, and continuous monitoring is required; When the chess style correction index SXZ is greater than the third threshold Q3, it indicates that the student's chess style adaptation is unqualified, triggering the third warning instruction and generating the fourth strategy: converting the student's chess style to a calculation-based style and increasing calculation training by 30%; When the chess style correction index SXZ is less than the third threshold Q3, it indicates that the student's chess style adaptation is unqualified, triggering the fourth warning instruction and generating the fifth strategy: converting the student's chess style to an intuitive style and increasing intuitive training by 30%.

[0014] Preferably, a chess interactive method comprises the following steps: Step 1: Build a chess teaching platform and create several virtual chess games that are interconnected for student chess training, AI games, and student online games. The game information on the virtual chessboard interface is uploaded to the chess teaching platform in real time. Step 2: Collect student game information uploaded to the chess teaching platform, including students' thinking paths, decision-making time, calculation steps, and intuitive choices, and record students' game performance data at different stages of the game to establish a basic data set; Step 3: By monitoring the student's chess strength foundation and calculating the student's chess strength index SI, calculation ability index CAI and intuitive decision index IDI based on the basic data set; Step 4: By building an AI dynamic training model, we use it as a primary training strategy, an intermediate training strategy, and an advanced training strategy to train all students in AI games. After training, we review the games with the students, calculate the review analysis index (RPI), analyze the students' understanding, and provide strategy explanations. Step 5: After the training period, the students' chess skills are evaluated, and the Learning Progress Index (LPI) is calculated to analyze the changes in their chess skills. For students whose chess skills have not improved, strategies for changing their chess style are provided. Step 6: By monitoring the chess style of students whose chess skills have not improved, calculate the chess style correction index SXZ, analyze the adaptability of the students' chess style, and provide corresponding strategies.

[0015] The present invention provides a chess interactive method and system, which has the following beneficial effects: (1) This chess interactive method and system, through a chess teaching platform and an AI dynamic training model, can formulate personalized training plans based on the students' chess strength index SI, computing power index CAI and intuitive decision index IDI, ensuring that students receive targeted intensive training and improving training efficiency.

[0016] (2) This chess interactive method and system, through the AI dynamic training model combined with the post-game analysis index RPI, can provide students with intelligent explanations and key move analysis during the post-game review process, helping students to have a deeper understanding of the chess game, improve their ability to adapt to different situations, and optimize the decision-making process.

[0017] (3) This chess interactive method and system can regularly evaluate the growth trajectory of students by calculating the learning progress index (LPI), and conduct quantitative analysis of the training effect, so that students can clearly understand their own progress and ensure the rationality of the training direction.

[0018] (4) This chess interactive method and system can calculate the chess style correction index SXZ. When a student's chess skills stagnate, it automatically analyzes his or her chess style adaptability and provides corresponding adjustment strategies, such as strengthening calculation training or intuitive training, to help students break through bottlenecks and improve their chess skills. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a flowchart diagram of a chess interactive system according to the present invention; Figure 2 The figure is a schematic diagram of the steps of a chess interactive method according to the present invention. DETAILED DESCRIPTION

[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0021] Example 1 See also Figure 1 , the present invention provides a chess interactive system, including a chess teaching platform module, a data acquisition module, a chess strength test module, an AI dynamic training model module, a student comprehensive evaluation module and a student chess style adjustment module; The chess teaching platform module is used to build a chess teaching platform and construct several virtual chess games and connect them to each other for student chess training, AI games and student online games, and upload the game information on the virtual chessboard interface to the chess teaching platform in real time; The data collection module is used to monitor students' thinking paths, decision-making time, calculation steps and intuitive choices in real time during the virtual chess game, and record students' game performance data at different stages of the game to establish a basic data set; The chess strength test module is used to monitor the student's chess strength foundation and calculate the student's chess strength index SI, calculation ability index CAI and intuitive decision index IDI according to the basic data set data; The AI dynamic training model module is used to build an AI dynamic training model, which is used as a primary training strategy, an intermediate training strategy, and an advanced training strategy to conduct AI game training for all students. After training, the students will review the game, calculate the review analysis index (RPI), analyze the students' understanding, and provide strategy explanations. The student comprehensive evaluation module is used to evaluate the students' chess skills after the training cycle, analyze the changes in students' chess skills by calculating the learning progress index (LPI), and provide chess style conversion strategies for students whose chess skills have not improved; The student chess style adjustment module is used to monitor the chess style of students whose chess skills have not improved, analyze the adaptability of the student's chess style by calculating the chess style correction index SXZ, and provide corresponding strategies.

[0022] In this embodiment, the system provides a virtual chess game interactive environment through the chess teaching platform module. Combined with the data acquisition module, it monitors students' thought processes, decision-making times, and calculation steps in real time, accurately recording their game performance. The chess strength testing module and the AI dynamic training model module work together to ensure students receive targeted training plans and optimize learning outcomes through the Replay Analysis Index (RPI). Furthermore, the student comprehensive assessment module and the student chess style adjustment module provide personalized chess style optimization solutions, ensuring continuous and precise improvement in students' chess skills, achieving scientific and efficient intelligent chess training.

[0023] Example 2: This example is explained in Example 1. Figure 1 Specifically, the chess teaching platform module is used to construct several virtual chess games and connect them to each other. The virtual chess games are used to create an immersive chess training environment for students based on preset chess rules including Go, Chinese chess and international chess through a touch-controlled electronic chessboard. The virtual chessboard supports AI games and student online games, and uploads the game information on the virtual chessboard interface to the chess teaching platform in real time.

[0024] In this embodiment, the system uses a chess teaching platform module to create virtual chess games, including Go, Chinese chess, and international chess. Using a touch-sensitive electronic chessboard, it provides students with a highly immersive chess training experience. Students can play against AI or online matches at any time. All game information is uploaded to the platform in real time, facilitating subsequent analysis and optimizing training plans, thereby improving learning efficiency and training effectiveness.

[0025] Example 3, this example is explained in Example 2, please refer to Figure 1Specifically, the data collection module is used to collect student game information uploaded to the chess teaching platform, including the student's chess game thinking path, decision-making time, calculation steps and intuitive choices, and record the student's game performance data at different stages of the chess game, and establish a basic data set.

[0026] In this embodiment, the system uses a data acquisition module to record the student's thinking process, decision-making time, calculation steps, and intuitive choices in real time. This comprehensive collection of performance data at different stages of the game creates a basic data set. This data supports subsequent precise analysis of the student's chess skills, helps develop personalized training plans, and improves the relevance and effectiveness of training.

[0027] Example 4: This example is explained in Example 3. Figure 1 Specifically, the chess strength testing module includes a first calculation unit and a second calculation unit; The first calculation unit is used to calculate the student's chess strength index SI, computing ability index CAI and intuitive decision index IDI respectively after dimensionless processing of the data in the basic data set. The formulas are as follows: ; Where, Indicates the number of games won by students during the monitoring period. Indicates the number of students and games during the monitoring period, Indicates the number of games lost by students during the monitoring period. Indicates the student's calculation and change ability score, as shown in the following table, w1, w2, w3 and w4 represent weight coefficients, , , , and ; ; ; Where, It means that the students have calculated the correct number of changes. It represents the total number of tricks the students have tried to calculate. Indicates the number of calculation steps of the student, w5 and w6 represent weight coefficients, , ,and ; ; Where, represents the number of correct decisions made by the students, represents the total number of student decisions, It represents the average time it takes for students to make decisions. Indicates the standard value for achieving quick decision-making.

[0028] In this embodiment, the system uses a chess strength testing module to calculate the chess strength index (SI), calculation ability index (CAI), and intuitive decision-making index (IDI) based on student game data. This dimensionless processing method enables fair comparison between students of different chess skill levels. This evaluation system not only focuses on win-loss results but also comprehensively calculates key indicators such as accuracy rate, number of calculation moves, and decision-making time. This provides a precise analysis of students' chess skills from multiple dimensions, providing a scientific basis for subsequent personalized training, improving the relevance and effectiveness of training.

[0029] Example 5: This example is explained in Example 4. Please refer to Figure 1 Specifically, the AI dynamic training model module includes a model building unit, a third computing unit and a first analyzing unit; The model construction unit is used to use a convolutional neural network to construct an initial model of the convolutional neural network, and to train and test the initial model of the convolutional neural network using the student's basic data set data, and to use the trained initial model of the convolutional neural network as the AI dynamic training model. At the same time, the intermediate layer outputs of the student's chess strength index SI, computing power index CAI and intuitive decision index IDI are used as feature vectors to identify feature information, and the AI dynamic adjustment model is trained and tested through the acquired feature information. The trained AI dynamic adjustment model is used as a primary training strategy, an intermediate training strategy and an advanced training strategy respectively to perform AI game training on all students.

[0030] In this embodiment, based on the AI dynamic training model module, the AI model can be dynamically adjusted in real time through training and testing of the initial convolutional neural network model and the student's basic data set, thereby generating a personalized training strategy based on the intermediate layer output of the student's chess strength index SI, computing power index CAI, and intuitive decision index IDI. Through the gradual optimization of primary, intermediate, and advanced training strategies, it is ensured that AI game training can be accurately adjusted according to the different levels of students, improving the students' learning efficiency and training quality, promoting the continuous improvement of students' chess skills, and accurately identifying the students' characteristic information during the training process, realizing a personalized and efficient training plan.

[0031] Example 6: This example is explained in Example 5. Please refer to Figure 1 Specifically, the third calculation unit is used to review the game after the student and AI are trained. After dimensionless processing, the replay analysis index RPI is calculated and obtained. The formula is as follows: ; Where, Indicates the correct number of hands that students should improve when reviewing the game. It represents the total number of improved lots provided by AI during the review, w7 and w8 represent weight coefficients, , ,and ; The first analysis unit is configured to preset a first threshold Q1 in advance and compare and analyze the replay analysis index RPI with the first threshold Q1 to obtain a first evaluation result, including: When the replay analysis index RPI ≥ the first threshold Q1, it means that the student can understand the game replay and no adjustments are made, and continuous monitoring is performed; When the replay analysis index RPI is less than the first threshold Q1, it means that the student cannot understand the game replay, triggering the first warning instruction and generating the first strategy: starting the AI replay explanation function and giving a step-by-step explanation.

[0032] In this embodiment, the replay analysis index (RPI) after the student and AI play is calculated and evaluated to accurately identify the student's understanding ability during the replay process. When the replay analysis index (RPI) is greater than or equal to the first threshold value (Q1), the system can confirm that the student has a good understanding of the game replay and maintain normal training monitoring. When the replay analysis index (RPI) is less than the first threshold value (Q1), the system will promptly trigger the early warning mechanism, activate the AI replay explanation function, and provide step-by-step explanations and guidance to the student. This process ensures that students can receive personalized help in the replay, improves learning outcomes, avoids training bottlenecks caused by insufficient understanding of the replay, and further promotes the improvement of students' chess skills.

[0033] Example 7, this example is explained in Example 6, please refer to Figure 1 ,Specifically,: the student comprehensive evaluation module includes a fourth calculation unit and a second analysis unit; The fourth calculation unit is used to calculate the learning progress index LPI after the trainee has completed the training cycle, combined with the basic data of the trainee after training, after dimensionless processing, and the formula is as follows: ; Where, represents the time of a training cycle, Indicates the change in the student's chess strength index during a training cycle. Indicates the change in the student's computing power index during a training cycle. It indicates the change of the trainee's intuitive decision-making index in a training cycle.

[0034] In this embodiment, after a student's training cycle, the Learning Progress Index (LPI) is calculated based on their basic training data. This index, after dimensionless processing, comprehensively considers the changes in the student's Go Skill Index, Computational Skill Index, and Intuitive Decision-Making Index during the training cycle, accurately measuring the student's overall learning progress during that cycle. Through this evaluation mechanism, the system can dynamically reflect the student's progress and promptly identify the extent of improvement in different areas. This provides a scientific basis for subsequent personalized training plans, helping students to adjust their learning priorities in a targeted manner and further optimize training outcomes.

[0035] Example 8: This example is explained in Example 7. Please refer to Figure 1 Specifically, the second analysis unit is used to preset a second threshold Q2 in advance and compare and analyze the learning progress index LPI with the second threshold Q2 to obtain a second evaluation result including: When the learning progress index LPI ≥ the second threshold Q2, it means that the student's chess skills have improved through AI game training, and the second strategy is generated: increase the difficulty of AI game training and proceed to the next training cycle; When the learning progress index LPI is less than the second threshold Q2, it means that the student’s chess skills have not improved through AI game training, triggering the second warning instruction and generating the third strategy: changing the student’s chess style.

[0036] In this embodiment, the system can dynamically evaluate the student's progress in AI game training based on a comparative analysis of the student's learning progress index (LPI) and a preset second threshold value (Q2). When the learning progress index (LPI) is greater than or equal to the second threshold value (Q2), the system confirms that the student has made progress in chess skills and generates a second strategy to increase the difficulty of AI game training and enter the next training cycle, ensuring that the student continues to face more challenging training tasks and further promotes chess skills improvement. When the learning progress index (LPI) is lower than the second threshold value (Q2), the system recognizes that the student's chess skills have not improved, promptly triggers the second warning instruction, generates a third strategy, adjusts the student's chess style, avoids falling into a training bottleneck, and ensures that the student can obtain a more effective training direction. This mechanism improves the student's training effect by precisely adjusting the training strategy, ensuring that the student receives appropriate challenges and guidance at each stage.

[0037] Example 9: This example is explained in Example 8. Figure 1 Specifically, the student chess style adjustment module includes a fifth calculation unit and a third analysis unit; The fifth calculation unit is used to perform chess style conversion on the student when receiving the second warning instruction, and calculate and obtain the chess style correction index SXZ after dimensionless processing, using the following formula: ; ;

[0038] Where, Indicates the student's learning progress index. represents the chess style matching degree, SBI represents the chess style conversion benefit, It represents the student's calculation ability index, IDI represents the student's intuitive decision-making index, and SI represents the student's chess strength index. Indicates the chess strength index after changing the chess style. It represents the cycle time for the student to change his chess style, a1, a2 and a3 represent the weight coefficients, , , ,and .

[0039] The third analysis unit is used to preset a third threshold Q3 in advance, and compare and analyze the chess style correction index SXZ with the third threshold Q3, and obtain a third evaluation result including: When the chess style correction index SXZ = the third threshold Q3, it means that the student's chess style is suitable and no adjustment is needed, and continuous monitoring is required; When the chess style correction index SXZ is greater than the third threshold Q3, it indicates that the student's chess style adaptation is unqualified, triggering the third warning instruction and generating the fourth strategy: converting the student's chess style to a calculation-based style and increasing calculation training by 30%; When the chess style correction index SXZ is less than the third threshold Q3, it indicates that the student's chess style adaptation is unqualified, triggering the fourth warning instruction and generating the fifth strategy: converting the student's chess style to an intuitive style and increasing intuitive training by 30%.

[0040] In this embodiment, upon receiving the second warning instruction, the system dynamically converts the student's chess style through the fifth calculation unit and calculates a chess style correction index SXZ, comprehensively considering factors such as the student's learning progress index, chess style compatibility, chess style conversion benefits, computational ability index, intuitive decision-making index, and chess strength index. The third analysis unit compares and analyzes the calculated chess style correction index SXZ with a preset third threshold value Q3 to determine the student's chess style adaptation. When the chess style correction index SXZ equals the third threshold value Q3, it indicates that the student's chess style has been adapted and the system continues monitoring. When the chess style correction index SXZ exceeds the third threshold value Q3, it indicates that the student's chess style adaptation is unsatisfactory. The system triggers the third warning instruction, generates a fourth strategy, adjusts to a computational chess style, and increases computational training by 30%. When the chess style correction index SXZ is below the third threshold value Q3, it indicates that the student's chess style adaptation is unsatisfactory. The system triggers the fourth warning instruction, generates a fifth strategy, adjusts to an intuitive chess style, and increases intuitive training by 30%. This mechanism enables students to accurately adapt their chess style during different training cycles through personalized chess style adjustments and training strategies, ensuring that the training content matches the students' characteristics, thereby improving training results and chess skills improvement.

[0041] Example 10, a chess interactive method, please refer to Figure 2 , including the following steps: Step 1: Build a chess teaching platform and create several virtual chess games that are interconnected for student chess training, AI games, and student online games. The game information on the virtual chessboard interface is uploaded to the chess teaching platform in real time. Step 2: Collect student game information uploaded to the chess teaching platform, including students' thinking paths, decision-making time, calculation steps, and intuitive choices, and record students' game performance data at different stages of the game to establish a basic data set; Step 3: By monitoring the student's chess strength foundation and calculating the student's chess strength index SI, calculation ability index CAI and intuitive decision index IDI based on the basic data set; Step 4: By building an AI dynamic training model, we use it as a primary training strategy, an intermediate training strategy, and an advanced training strategy to train all students in AI games. After training, we review the games with the students, calculate the review analysis index (RPI), analyze the students' understanding, and provide strategy explanations. Step 5: After the training period, the students' chess skills are evaluated, and the Learning Progress Index (LPI) is calculated to analyze the changes in their chess skills. For students whose chess skills have not improved, strategies for changing their chess style are provided. Step 6: By monitoring the chess style of students whose chess skills have not improved, calculate the chess style correction index SXZ, analyze the adaptability of the students' chess style, and provide corresponding strategies.

[0042] In this embodiment, based on the above steps, by building a comprehensive chess teaching platform and combining dynamic AI training, replay analysis and chess style adjustment strategies, personalized and comprehensive training support can be provided to students. The system collects students' game information in real time and builds a basic data set to accurately monitor students' performance at different stages, calculate students' chess strength index, calculation power index and intuitive decision index, and thus tailor primary, intermediate and advanced training strategies for students. In addition, through replay analysis and calculation of the learning progress index LPI, the system can timely evaluate students' chess strength changes, discover and solve problems with stagnant chess strength progress. If the student's chess style is not suitable, the system will further analyze and adjust the student's chess style through the chess style correction index SXZ, and provide appropriate conversion strategies, such as enhanced calculation-based or intuitive training, thereby effectively improving the student's overall chess skill level. This comprehensive training and evaluation system helps students get the most suitable training and guidance at each stage, ensuring their continuous progress and maximizing learning effects.

[0043] The threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technicians in this field for each set of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0044] The above formulas are obtained by collecting a large amount of data and performing software simulation, and a formula close to the actual value is selected. The coefficients in the formula are set by those skilled in the art according to actual conditions. The above is only a preferred specific implementation method of the present invention, but the protection scope of the present invention is not limited to this. Any technician familiar with this technical field, within the technical scope disclosed by the present invention, can make equivalent replacements or changes based on the technical solution and inventive concept of the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A chess interactive system, characterized by: It includes chess teaching platform module, data collection module, chess strength test module, AI dynamic training model module, student comprehensive evaluation module and student chess style adjustment module; The chess teaching platform module is used to build a chess teaching platform and construct several virtual chess games and connect them to each other for student chess training, AI games and student online games, and upload the game information on the virtual chessboard interface to the chess teaching platform in real time; The data collection module is used to monitor students' thinking paths, decision-making time, calculation steps and intuitive choices in real time during the virtual chess game, and record students' game performance data at different stages of the game to establish a basic data set; The chess strength test module is used to monitor the student's chess strength foundation and calculate the student's chess strength index SI, calculation ability index CAI and intuitive decision index IDI according to the basic data set data; The AI dynamic training model module is used to build an AI dynamic training model, which is used as a primary training strategy, an intermediate training strategy, and an advanced training strategy to conduct AI game training for all students. After training, the students will review the game, calculate the review analysis index (RPI), analyze the students' understanding, and provide strategy explanations. The student comprehensive evaluation module is used to evaluate the students' chess skills after the training cycle, analyze the changes in students' chess skills by calculating the learning progress index (LPI), and provide chess style conversion strategies for students whose chess skills have not improved; The student chess style adjustment module is used to monitor the chess style of students whose chess skills have not improved, analyze the adaptability of the student's chess style by calculating the chess style correction index SXZ, and provide corresponding strategies.

2. A chess interactive system according to claim 1, characterized in that: The chess teaching platform module is used to construct several virtual chess games and connect them to each other. The virtual chess games are used to create an immersive chess training environment for students based on preset chess rules including Go, Chinese chess and international chess through a touch-screen electronic chessboard. The virtual chessboard supports AI games and student online games, and uploads the game information on the virtual chessboard interface to the chess teaching platform in real time.

3. A chess interactive system according to claim 2, characterized in that: The data collection module is used to collect student game information uploaded to the chess teaching platform, including the student's chess game thinking path, decision-making time, calculation steps and intuitive choices, and record the student's game performance data at different chess game stages, and establish a basic data set.

4. A chess interactive system according to claim 3, characterized in that: The chess strength testing module includes a first calculation unit and a second calculation unit; The first calculation unit is used to calculate the student's chess strength index SI, computing ability index CAI and intuitive decision index IDI respectively after dimensionless processing of the data in the basic data set. The formulas are as follows: ； Where, Indicates the number of games won by students during the monitoring period. Indicates the number of students and games during the monitoring period, Indicates the number of games lost by students during the monitoring period. represents the student's calculation and change ability score, w1, w2, w3 and w4 represent weight coefficients; ； Where, It means that the students have calculated the correct number of changes. It represents the total number of tricks the students have tried to calculate. represents the number of calculation steps of the student, w5 and w6 represent weight coefficients; ； Where, represents the number of correct decisions made by the students, represents the total number of student decisions, It represents the average time it takes for students to make decisions. Indicates the standard value for achieving quick decision-making.

5. The chess interactive system according to claim 4, characterized in that: The AI dynamic training model module includes a model construction unit, a third computing unit and a first analysis unit; The model construction unit is used to use a convolutional neural network to construct an initial model of the convolutional neural network, and to train and test the initial model of the convolutional neural network using the student's basic data set data, and to use the trained initial model of the convolutional neural network as the AI dynamic training model. At the same time, the intermediate layer outputs of the student's chess strength index SI, computing power index CAI and intuitive decision index IDI are used as feature vectors to identify feature information, and the AI dynamic adjustment model is trained and tested through the acquired feature information. The trained AI dynamic adjustment model is used as a primary training strategy, an intermediate training strategy and an advanced training strategy respectively to perform AI game training on all students.

6. A chess interactive system according to claim 5, characterized in that: The third calculation unit is used to review the game after the student and the AI are trained. After dimensionless processing, the replay analysis index RPI is calculated and obtained. The formula is as follows: ； Where, Indicates the correct number of hands that students should improve when reviewing the game. Indicates the total number of improved lots provided by the AI during the review, w7 and w8 represent weight coefficients; The first analysis unit is configured to preset a first threshold Q1 in advance and compare and analyze the replay analysis index RPI with the first threshold Q1 to obtain a first evaluation result, including: When the replay analysis index RPI ≥ the first threshold Q1, it means that the student can understand the game replay and no adjustments are made, and continuous monitoring is performed; When the replay analysis index RPI is less than the first threshold Q1, it means that the student cannot understand the game replay, which triggers the first warning instruction and generates the first strategy: start the AI replay explanation function and explain step by step.

7. The chess interactive system according to claim 6, characterized in that: The student comprehensive evaluation module includes a fourth calculation unit and a second analysis unit; The fourth calculation unit is used to calculate the learning progress index LPI after the trainee has completed the training cycle, combined with the basic data of the trainee after training, after dimensionless processing, and the formula is as follows: ； Where, represents the time of a training cycle, Indicates the change in the student's chess strength index during a training cycle. Indicates the change in the student's computing power index during a training cycle. It indicates the change of the trainee's intuitive decision-making index in a training cycle.

8. A chess interactive system according to claim 7, characterized in that: The second analysis unit is configured to obtain a second evaluation result by presetting a second threshold Q2 and comparing and analyzing the learning progress index LPI with the second threshold Q2. The result includes: When the learning progress index LPI ≥ the second threshold Q2, it means that the student's chess skills have improved through AI game training, and the second strategy is generated: increase the difficulty of AI game training and proceed to the next training cycle; When the learning progress index LPI is less than the second threshold Q2, it means that the student’s chess skills have not improved through AI game training, triggering the second warning instruction and generating the third strategy: changing the student’s chess style.

9. The chess interactive system according to claim 8, characterized in that: The student chess style adjustment module includes a fifth calculation unit and a third analysis unit; The fifth calculation unit is used to perform chess style conversion on the student when receiving the second warning instruction, and calculate and obtain the chess style correction index SXZ after dimensionless processing, using the following formula: ； ； ； Where, Indicates the student's learning progress index. represents the chess style matching degree, SBI represents the chess style conversion benefit, It represents the student's calculation ability index, IDI represents the student's intuitive decision-making index, and SI represents the student's chess strength index. Indicates the chess strength index after changing the chess style. It represents the cycle time of the student's chess style change, and a1, a2 and a3 represent weight coefficients; The third analysis unit is used to preset a third threshold Q3 in advance, and compare and analyze the chess style correction index SXZ with the third threshold Q3, and obtain a third evaluation result including: When the chess style correction index SXZ = the third threshold Q3, it means that the student's chess style is suitable and no adjustment is needed, and continuous monitoring is required; When the chess style correction index SXZ is greater than the third threshold Q3, it indicates that the student's chess style adaptation is unqualified, triggering the third warning instruction and generating the fourth strategy: converting the student's chess style to a calculation-based style and increasing calculation training by 30%; When the chess style correction index SXZ is less than the third threshold Q3, it indicates that the student's chess style adaptation is unqualified, triggering the fourth warning instruction and generating the fifth strategy: converting the student's chess style to an intuitive style and increasing intuitive training by 30%.

10. A chess interactive method, comprising a chess interactive system according to any one of claims 1 to 9, characterized in that: The following steps are involved: Step 1: Build a chess teaching platform and create several virtual chess games that are interconnected for student chess training, AI games, and student online games. The game information on the virtual chessboard interface is uploaded to the chess teaching platform in real time. Step 2: Collect student game information uploaded to the chess teaching platform, including students' thinking paths, decision-making time, calculation steps, and intuitive choices, and record students' game performance data at different stages of the game to establish a basic data set; Step 3: By monitoring the student's chess strength foundation and calculating the student's chess strength index SI, calculation ability index CAI and intuitive decision index IDI based on the basic data set; Step 4: Build an AI dynamic training model, using primary, intermediate, and advanced training strategies as the basis for AI game training for all students. After training, we review the chess games with students, calculate the RPI (Review and Analysis Index), analyze their understanding, and provide strategy explanations. Step 5: After the training period, the students' chess skills are evaluated, and the Learning Progress Index (LPI) is calculated to analyze the changes in their chess skills. For students whose chess skills have not improved, strategies for changing their chess style are provided. Step 6: By monitoring the chess style of students whose chess skills have not improved, calculate the chess style correction index SXZ, analyze the adaptability of the students' chess style, and provide corresponding strategies.

Images