Chess teaching intelligent chessboard based on large model and interaction method thereof

Abstract

The invention provides a chess teaching intelligent chessboard based on a large model and an interaction method thereof, and relates to the technical field of chess intelligent teaching, the intelligent chessboard is characterized in that multiple rows and columns of chess points are arranged in parallel, each chess point is set as an LED indicating lamp, and each LED indicating lamp is controlled by pressing a trigger circuit; left pins of each row of pressing chess points of the pressing trigger circuit are connected to form a plurality of row lines. The right side pins of each column of pressing chess points are connected to form a plurality of column lines; the pressing trigger circuit is connected with the plurality of control chips; a key switch of the circuit board can be triggered by pressing each chess point; the pressing trigger circuit realizes detection of multi-row and multi-column digital signals in a row and column scanning mode, and identifies the positions of chess pieces placed on chess points of the chessboard; electric signals of the microswitches at the positions of the chess pieces are sent to the microcontroller, the microcontroller converts the electric signals into chess state change data and sends the data to the large model AI for analysis, and teaching interaction of the teaching intelligent chessboard is achieved through the large model.

Description

Technical Field

[0001] The present disclosure relates to the technical field of intelligent chess teaching, and in particular to an intelligent chess board for chess teaching based on a large model and an interaction method thereof. Background Art

[0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art.

[0003] Existing chess teaching tools have limitations in terms of portability, cost-effectiveness, and teaching interactivity. These tools mainly rely on traditional chessboards and chess pieces. Although they have a long history in chess culture, they show obvious deficiencies in modern teaching environments. Traditional chess games, such as Go, are designed with separate chessboards and chess pieces. The Go chessboard is large and not easy to carry, which limits the flexibility of teaching activities and venue selection, making the setup and storage process in outdoor or non-fixed classroom environments cumbersome. Secondly, the technologies commonly used in existing smart chessboards, such as NFC, are expensive, making smart chessboards expensive, and once the chess pieces are lost, users need to bear additional pairing or purchase costs; and technical limitations are also a problem. RFID technology is expensive and difficult to control in terms of accuracy, while magnetic sensing technology cannot effectively identify the identity of chess pieces, which may lead to missed records or recording errors when quickly capturing pieces. At the same time, in terms of circuit driving, insulated gate power devices such as MOSFET and IGBT require large dynamic driving power, have current tailing effects, and require negative voltage driving to improve anti-interference. The driver isolated by the optocoupler reacts slowly, has a large delay time, and requires an isolated auxiliary power supply. In addition, traditional Go teaching lacks interactivity, and players tend to passively accept knowledge, lacking a sense of participation and practice opportunities. At the same time, it is difficult for teachers to obtain players' game data in real time, making it difficult to provide personalized teaching. These problems not only affect the intelligentization of the Go board, but also reduce the user experience, and are the main challenges that current technology needs to focus on solving.

[0004] With the development of artificial intelligence technology, Go AI has become an important tool for high-level games and training, but these technologies are often not effectively integrated with teaching tools. Existing Go teaching tools lack compatibility with modern teaching technologies (such as online learning platforms, data analysis tools, etc.), which limits the innovation of teaching methods. At the same time, high-quality Go teaching resources are unevenly distributed, especially in areas with limited resources, where learners have difficulty accessing professional teaching content and high-level game practice. Go teaching content is updated slowly, making it difficult to keep up with the latest developments in Go tactics and theory. In addition, traditional Go teaching tools have poor adaptability in different light, temperature and other environments, which affects teaching effectiveness, and in special education environments, such as Go teaching for visually impaired learners, traditional tools cannot meet their special needs. Summary of the invention

[0005] In order to solve the above problems, the present invention proposes a large-model-based intelligent chessboard for chess teaching and an interactive method thereof. By improving and simplifying the circuit structure inside the chessboard, the position of chess pieces is detected by row and column scanning, and remote access rights are configured to allow chess learners to access smart classrooms at different locations. Large-model AI is used to provide remote teaching support, and a data synchronization mechanism is established between the intelligent chessboard and the Web terminal to ensure that the status of the chess game is updated in real time, thereby realizing real-time interaction and display of Go teaching content and exercises.

[0006] According to some embodiments, the present disclosure adopts the following technical solutions: An intelligent chessboard for chess teaching based on a large model, wherein the intelligent chessboard is a square structure, chess points are arranged on the square structure, and the chess points are arranged in parallel in multiple rows and columns, and each chess point is set as an LED indicator light, and each LED indicator light is controlled by a press trigger circuit; the left pins of each row of the press chess points of the press trigger circuit are connected to form multiple row lines; the right pins of each column of the press chess points are connected to form multiple column lines; the press trigger circuit is connected to multiple control chips; Pressing each chess point can trigger the key switch of the circuit board, providing physical interaction between the user and the chessboard. The press-trigger circuit detects multiple rows and columns of digital signals through row and column scanning through multiple control chips, and identifies the position of the chess piece placed on the chess point on the chessboard.

[0007] According to some embodiments, the present disclosure adopts the following technical solutions: The interactive method of the chess teaching intelligent chessboard based on the large model includes: Create a smart classroom environment, connect smart chessboards, assign a unique serial number to each smart chessboard, and record its location in the classroom; The system is initialized to pair the user with the smart chessboard to ensure that each user is paired with the smart chessboard uniquely; Configure remote access permissions to allow users to access the smart classroom from different locations and use large models and web terminals to achieve remote interaction; Obtain switch signals, the press trigger circuit obtains press signals by row and column scanning, the press information activates the corresponding row and column lines, the column scanning circuit detects multiple column line signals, the row power supply circuit drives multiple row lines, the processor reads signals through multiple GPIOs to determine the chess piece position, and the control unit drives the corresponding LED light to display according to the specific chess piece position; The electrical signal of the micro switch of the chess piece position is sent to the microcontroller, which converts the electrical signal into data of chess game status change and sends it to the large model AI for analysis; After receiving the data on the changes in the chess game status, the large model AI starts to calculate, analyze the current chess game situation, and predict possible moves and results; Based on the analysis results, the big model AI determines the best next move and provides feedback to the user to achieve teaching interaction.

[0008] According to some embodiments, the present disclosure adopts the following technical solutions: The interactive system of chess teaching intelligent chessboard based on large model includes: The initialization module is used to create a smart classroom environment, connect to smart chessboards, assign a unique serial number to each smart chessboard, and record its location in the classroom; initialize the system, pair users with smart chessboards, and ensure that each user is paired with a smart chessboard uniquely; configure remote access rights, allowing users to access the smart classroom at different locations, and use large models and web terminals to achieve remote interaction; The chess piece position detection module is used to obtain the switch signal. The press trigger circuit obtains the press signal by row and column scanning. The press information activates the corresponding row and column lines. The column scanning circuit detects multiple column line signals. The row power supply circuit drives multiple row lines. The processor reads the signal through multiple GPIOs to determine the chess piece position. The control unit drives the corresponding LED light to display according to the specific chess piece position. The analysis and interaction module is used to send the electrical signal of the micro switch of the chess piece position to the microcontroller, which converts the electrical signal into data of chess game state changes and sends it to the large model AI for analysis; after receiving the data of chess game state changes, the large model AI starts to calculate, analyze the current chess game situation, and predict possible moves and results; based on the analysis results, the large model AI determines the best move for the next step and feeds it back to the user to achieve teaching interaction; Or users can interact with large model AI in natural language.

[0009] According to some embodiments, the present disclosure adopts the following technical solutions: A computer program product includes a computer program, and when the computer program is executed by a processor, the interactive method of the chess teaching intelligent chessboard based on a large model is implemented.

[0010] According to some embodiments, the present disclosure adopts the following technical solutions: A non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the interactive method of the chess teaching intelligent chessboard based on a large model is implemented.

[0011] According to some embodiments, the present disclosure adopts the following technical solutions: An electronic device comprises: a processor, a memory and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device executes the interactive method of the large-model-based chess teaching intelligent chessboard.

[0012] Compared with the prior art, the present invention has the following beneficial effects: The disclosed chess teaching intelligent chessboard based on a large model has a simplified circuit system embedded inside the chessboard, which can trigger the key switch on the circuit board by pressing a key and is used to detect the position of the chess piece. The circuit of the chessboard adopts an integrated design, making the chessboard more compact, maintaining the simplicity of operation, and suitable for all go enthusiasts. In addition, the circuit design focuses on cost-effectiveness, adopts low-power components to extend battery life, and makes the chessboard have better portability and longer use time. At the same time, the combination of buttons and LED indicators provides users with an intuitive interactive experience, making the go learning process more vivid and interactive. By simplifying the circuit design and integrated control process, accurate detection of the position of the chess piece and convenient operation of user interaction are realized, which significantly improves the user experience. The use of low-power components extends the battery life and enhances the portability of the chessboard. The combination of silicone buttons and LED indicators provides users with an intuitive interactive experience, making the go learning process more vivid and interactive.

[0013] The disclosed large-scale model-based chess teaching intelligent chessboard adopts the traditional wood color of Go, such as dark brown or light brown, imitating the texture and color of natural wood, aiming to inherit the traditional attributes of Go. This color design not only enhances the aesthetics of the chessboard, but also makes it closer to the essence of Go culture, allowing chess learners to feel the profound heritage of Go history during use. The overall design style is friendly and interesting, suitable for the aesthetics of children learning chess, and the chess piece buttons are made of soft silicone material to ensure comfort and safety.

[0014] The disclosed large-scale model-based chess teaching intelligent chessboard is lightweight and easy to carry, and supports multiple chess game modes, such as Go and Gobang, which can be achieved by simple button switching. This design is extremely novel in Go teaching equipment. The intelligent Go chessboard not only improves the interactivity and personalization level of Go teaching, but also expands the popularity and flexibility of Go education by reducing costs and improving portability, providing strong technical support for the dissemination of Go culture and the modernization of education.

[0015] The disclosed interactive method of the chess teaching intelligent chessboard based on a large model, through the innovative integration of large model AI technologies such as KataGo and GPT-4o, can not only play Go games, but also realize natural language interaction, bringing unprecedented personalized and intelligent experience to Go teaching. The intelligent chessboard can synchronize data with the Web terminal in real time, so that students can access the smart classroom through the Web terminal to learn and practice Go no matter where they are. This cross-platform real-time interactive function is innovative in the field of Go teaching.

[0016] The disclosed interactive method of the chess teaching intelligent chessboard based on a large model takes into account the adaptability of different environments and can maintain a stable teaching effect even under conditions of large changes in light and temperature. The system adopts innovative teaching methods, such as displaying the AI ​​recommended moves through LED indicators, which enhances the interactivity and fun of teaching, improves the learning experience, and improves the interactivity and efficiency of Go teaching. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings constituting a part of the present disclosure are used to provide a further understanding of the present disclosure. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation on the present disclosure.

[0018] Figure 1 A front view of the teaching intelligent chessboard according to an embodiment of the present disclosure; Figure 2 A side view of the teaching intelligent chessboard according to an embodiment of the present disclosure; Figure 3 This is a reverse side view of the teaching intelligent chessboard according to an embodiment of the present disclosure; Figure 4 This is a circuit diagram of an intelligent Go teaching chessboard according to an embodiment of the present disclosure; Figure 5 This is a circuit diagram of the LED lights on the intelligent Go teaching chessboard according to an embodiment of the present disclosure; Figure 6 This is the process of the intelligent chessboard AI teaching system in the embodiment of the present disclosure; Figure 7 The intelligent chessboard AI teaching system architecture of the embodiment of the present disclosure; Figure 8 A physical picture of a smart chessboard according to an embodiment of the present disclosure; Fig. 9 ESP32 module circuit structure diagram of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0019] The present disclosure is further described below in conjunction with the accompanying drawings and embodiments.

[0020] It should be noted that the following detailed descriptions are all illustrative and are intended to provide further explanation of the present disclosure. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present disclosure belongs.

[0021] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present disclosure. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0022] Example 1 In one embodiment of the present disclosure, a large-scale model-based intelligent chessboard for chess teaching is provided. The intelligent chessboard is a square structure, and chess points are arranged on the square structure. The chess points are arranged in parallel in multiple rows and columns. Each chess point is set as an LED indicator, and each LED indicator is controlled by a press trigger circuit; the left pins of each row of the press chess points of the press trigger circuit are connected to form multiple row lines; the right pins of each column of the press chess points are connected to form multiple column lines; the press trigger circuit is connected to multiple control chips; Pressing each chess point can trigger the key switch of the circuit board, providing physical interaction between the user and the chessboard. The press-trigger circuit detects multiple rows and columns of digital signals through row and column scanning through multiple control chips, and identifies the position of the chess piece placed on the chess point on the chessboard.

[0023] As an embodiment, the present disclosure provides an intelligent chessboard for Go teaching, which solves the limitations of existing Go teaching tools in terms of portability, cost-effectiveness and teaching interactivity, and provides a new Go teaching solution by integrating advanced large-model artificial intelligence technology.

[0024] like Figure 1 , Figure 2 As shown, the Go teaching intelligent chessboard is a square chessboard, and chess points are set on the square structure chessboard. The chess points are the intersection points for placing chess pieces, and the chess points are set in parallel in multiple rows and columns. The present invention sets the chess points to 19 rows * 19 columns. The appearance of the Go product adopts the traditional wood color appearance of Go, which combines the versatility and user-friendliness of Go teaching, ensuring safety and durability.

[0025] Furthermore, each chess point is set as an LED indicator light, and each LED indicator light is controlled by a press trigger circuit; the left pins of each row of press chess points of the press trigger circuit are connected to form multiple row lines; the right pins of each column of press chess points are connected to form multiple column lines; the press trigger circuit is connected to multiple control chips; Pressing each chess point can trigger the key switch of the circuit board, providing physical interaction between the user and the chessboard. The press-trigger circuit detects multiple rows and columns of digital signals through row and column scanning through multiple control chips, and identifies the position of the chess piece placed on the chess point on the chessboard.

[0026] like Figure 4 , Figure 5 As shown in the figure, a simplified circuit system is embedded inside the chessboard, which can trigger the key switch on the circuit board by pressing the key and is used to detect the position of the chess piece; the circuit of the chessboard adopts an integrated design, making the chessboard more compact and easy to operate, suitable for all Go enthusiasts. In addition, the circuit design focuses on cost-effectiveness and uses low-power components to extend battery life, making the chessboard more portable and longer in use. At the same time, the combination of buttons and LED indicators provides users with an intuitive interactive experience, making the Go learning process more vivid and interactive.

[0027] Specifically, the built-in press trigger circuit of the chessboard uses a 74HC165 chip to detect the position of the chess piece. The circuit accurately identifies the position of the chess piece by scanning rows and columns. The left pins of the keys in each row are connected together to form 19 row lines; the right pins of the keys in each column are connected together to form 19 column lines. By using three 74HC165 chips, only two GPIOs of the processor are needed to detect 19 digital signals.

[0028] Furthermore, the push trigger circuit uses row and column scanning, and the row power supply circuit and the column scanning circuit respectively use different control chips. The row power supply circuit provides a stable power supply for the rows of the chessboard, and the column scanning circuit realizes the scanning of the chessboard columns, and works together with the row power supply circuit to form a complete chess piece detection network. Among them, the row power supply circuit uses the XL74HC595 chip to provide a stable power supply for the rows of the chessboard to ensure the accuracy of chess piece detection; the column scanning circuit uses the 74HC165 chip to realize the scanning of the chessboard columns. The design of this structure focuses on cost-effectiveness and uses low-power components, which helps to extend battery life and is suitable for frequent use.

[0029] Furthermore, pressing the 19*19 matrix buttons can trigger the key switches on the circuit board, providing physical interaction between the user and the chessboard. These buttons include each intersection on the chessboard to detect the placement of chess pieces.

[0030] Furthermore, two chess piece positions with LED lights of different colors are set on each chess point, representing different users playing chess respectively. An LED driver chip is used to control all LED lights on the chessboard, and a serial input and parallel output shift register is used to control the LED indicator lights, indicating the positions of chess pieces of different users and key points of the chess game in the form of visual display.

[0031] The XL74HC595 serial-input parallel-output shift register is used to control LED indicators, which are used to display the position of chess pieces or key points of the game. The TM1680 LED driver chip is used to control 722 LED lights on the chessboard (2 for each chess piece) to visually indicate the position of chess pieces or key points of the game.

[0032] Furthermore, the voltage and current of the LED lights are precisely calculated to ensure that they can provide appropriate brightness in different usage environments while maintaining energy efficiency and reducing energy consumption. Orange and green LED lights are used to indicate black and white pieces respectively.

[0033] As an embodiment, function keys are also provided on the chessboard, including a power key, a sound key, a level up key, a level down key, a first and last move key, a prompt key, an undo key, a game end key, a game start key and a chess play confirmation key. The sound key has a multi-level adjustment key and can be adjusted in three levels. The design disclosed in the present invention has an easy-to-operate undo button, which allows children learning chess to undo their moves within a few steps, so as to facilitate learning and progress.

[0034] As an embodiment, the Go board disclosed in the present invention adopts the traditional wood color of Go, such as dark brown or light brown, imitating the texture and color of natural wood, aiming to inherit the traditional attributes of Go. This color design not only enhances the aesthetics of the board, but also makes it closer to the essence of Go culture, allowing Go learners to feel the profound heritage of Go history during use. The overall design style is friendly and interesting, suitable for the aesthetics of children learning Go, and the chess piece buttons are made of soft silicone material to ensure comfort and safety in use.

[0035] As an embodiment, the length and width of the smart chessboard can be set within 480 mm respectively; Preferably, the length and width of the 19-way intelligent chessboard designed in the present disclosure are 270mm*280mm, which is easy to put into a schoolbag, light in weight, and easy to carry and use outdoors. Silicone buttons and LED lights are used to represent the placement of chess pieces, providing tactile and visual feedback. It also integrates the functions of human-computer game and human-human game of Go and Gobang, and can adjust the brightness of the light and the volume of the sound to remind the user to place the piece, and there is a button to regret the move.

[0036] Furthermore, it is also designed with speaker openings and type-c charging openings to facilitate sound output and charging.

[0037] As an embodiment, the teaching smart chessboard disclosed in the present invention also supports multiple chess modes such as Go and Gobang, which can be switched by buttons to meet different game needs; the interface design is simple, and the main functions such as brightness, sound and AI difficulty adjustment are represented by intuitive icons, which are easy for children to understand.

[0038] The teaching intelligent chessboard disclosed in the present invention is provided with obvious "start" and "end" buttons, as well as a game status indicator light, which clearly displays the current game status.

[0039] The disclosed teaching intelligent chessboard has rounded corners and no sharp edges to prevent children learning chess from getting injured during use; the surface is specially treated to be easy to clean and disinfect, and is suitable for frequent use.

[0040] As an embodiment, the circuit control process and function implementation of the smart chessboard disclosed in the present invention include: 1) Power on: The user presses and holds the power button (K374) for 2.5 seconds, triggering the U13 chip's pin 1 to output a high-level power-on signal, starting the DC / DC buck circuit, outputting 3.3V power to power the entire device, and the ESP32 module starts working, controlling the U9 voice chip to play the power-on prompt tone.

[0041] 2) Network configuration and remote connection: Voice prompts guide users to use their mobile phones to scan the QR code to complete the network configuration process on the device side. The ESP32 module connects to the local WiFi network and interacts with the remote server for data.

[0042] 3) User function setting: Users use silicone buttons to set functions, such as volume adjustment, Go / chess mode selection, first move selection, brightness adjustment, etc. The 74HC165 chip detects the button position, and the XL74HC595 chip controls the LED indicator to feedback the setting status.

[0043] 4) Chess piece placement and detection: The user places a chess piece on the chessboard, a button is pressed, and the corresponding row and column lines are activated. The 74HC165 chip detects 19 column line signals, and the XL74HC595 chip drives 19 row lines. The processor reads the signal through 2 GPIOs to determine the chess piece position. The TM1680 LED driver chip drives the corresponding orange or green LED light according to the chess piece position to display the chess piece position.

[0044] 5) Power management and charging monitoring: Use the ESP32 module to manage the power of the chessboard, such as Fig. 9As shown in the figure, the ESP32 module has a built-in ADC to collect the battery voltage. If the voltage is low, a voice prompt is issued through the WT588F voice chip to remind the user to charge. The user connects to the 5V power supply through the USB interface, and the TP4056 charging management chip starts the charging process. During the charging process, the orange indicator D1495 lights up, and the green indicator D1498 lights up after charging is completed.

[0045] 6) Shutdown: The user presses the power button (K374) for 2.5 seconds, and pin 1 of the U13 chip outputs a low level, cutting off the enable signal of the U15 chip, stopping the DC / DC buck circuit from working, and the entire machine enters the shutdown state.

[0046] Example 2 In one embodiment of the present disclosure, a method for interacting with a chess teaching intelligent chessboard based on a large model is provided, comprising: Create a smart classroom environment, connect smart chessboards, assign a unique serial number to each smart chessboard, and record its location in the classroom; The system is initialized to pair the user with the smart chessboard to ensure that each user is paired with the smart chessboard uniquely; Configure remote access permissions to allow users to access the smart classroom from different locations and use large models and web terminals to achieve remote interaction; Obtain switch signals, the press trigger circuit obtains press signals by row and column scanning, the press information activates the corresponding row and column lines, the column scanning circuit detects multiple column line signals, the row power supply circuit drives multiple row lines, the processor reads signals through multiple GPIOs to determine the chess piece position, and the control unit drives the corresponding LED light to display according to the specific chess piece position; The electrical signal of the micro switch of the chess piece position is sent to the microcontroller, which converts the electrical signal into data of chess game status change and sends it to the large model AI for analysis; After receiving the data on the changes in the chess game status, the large model AI starts to calculate, analyze the current chess game situation, and predict possible moves and results; Based on the analysis results, the big model AI determines the best next move and provides feedback to the user to achieve teaching interaction.

[0047] As an embodiment, the specific implementation process of the interactive method of the chess teaching intelligent chessboard based on the large model disclosed in the present invention is as follows: Step 1: Create a smart classroom environment, connect smart chessboards, assign a unique serial number to each smart chessboard, and record its location in the classroom; Specifically, 1) Class creation: Develop an administration interface that allows administrators to input student information such as name, age, and Go level, which is used to recommend personalized teaching content.

[0048] 2) Classroom creation: Configure the classroom hardware environment, including the installation and testing of the smart chessboard and related equipment, to ensure that the large model AI can be seamlessly integrated into the teaching environment.

[0049] 3) Equipment information entry: Assign a unique serial number to each smart chess board and record its location in the classroom.

[0050] Step 2: Initialize the system and pair the user with the smart chessboard to ensure that each user is uniquely paired with the smart chessboard, including a binding operation. The binding operation is to pair the chess learner with the smart chessboard through the system interface to ensure that each chess learner can use his or her own device.

[0051] Step 3: Configure remote access rights to allow users to access the smart classroom from different locations and use the big model and the web client to achieve remote interaction; specifically, including: 1) Remote access settings: Configure remote access rights to allow chess learners to access the smart classroom at different locations and use large-scale AI models to provide remote teaching support.

[0052] 2) Interactive interface settings: Web-based interactive interface, which provides Go teaching content and practice platform, and monitors the status of Go learners and teaching management.

[0053] 3) Integration of smart chessboard and web terminal: Establish a data synchronization mechanism between the smart chessboard and the web terminal to ensure that the chess game status is updated in real time and provide real-time data input for the large model AI.

[0054] 4) Reverse proxy configuration: Set up a reverse proxy server to manage request forwarding between the smart chessboard and the Web client, and optimize the response speed of large model AI.

[0055] 5) User interface synchronization: Ensure that the physical interface of the smart chessboard and the virtual interface of the web are displayed synchronously.

[0056] 6) Engine application: Apply existing Go engines and integrate large-model AI, such as KataGo, for playing and teaching, providing high-level Go strategies and teaching suggestions.

[0057] 7) AI teaching logic: Implement AI teaching logic, including game analysis, teaching suggestions and real-time feedback, which are all based on the deep learning and strategy generation capabilities of large-model AI.

[0058] Deep learning algorithms process and interpret complex data by building and training multi-layer neural networks. Using existing algorithms, the core advantage of the algorithm is that it can automatically learn features from large amounts of data and output results based on input samples. The process of implementing a deep learning algorithm usually includes several key steps: (1) Data preprocessing, which includes data cleaning and normalization to improve algorithm performance; (2) Model design, which requires selecting a suitable neural network structure according to the specific task, such as a convolutional neural network (CNN) or a recurrent neural network (RNN); the next step is to train the model, using a large amount of labeled data to optimize the network weights through the back-propagation algorithm; (3) Evaluation and testing: evaluate model performance on an independent test set and adjust hyperparameters to improve accuracy; (4) Deploy applications: deploy the trained model to actual applications to perform prediction or classification tasks.

[0059] 8) Cloud computing resource configuration: Use cloud servers to provide additional computing resources to support complex calculations of large-model AI and ensure the real-time and accuracy of teaching content.

[0060] Specifically, in large-model AI, complex computing is mainly reflected in the following aspects: (1) Large-scale data processing: Large-model AI requires processing massive amounts of data, including data loading, batch processing, and optimization algorithms. These computing processes usually require high-performance computing resources, such as GPUs or TPUs, to accelerate data processing and model training.

[0061] (2) High-dimensional feature space: Deep learning models can automatically extract and process high-dimensional features, which is particularly important in fields such as image and speech recognition. For example, in the interactive method of the Go board, AI needs to process the high-dimensional state space on the board to determine the best strategy for placing pieces.

[0062] (3) Nonlinear transformation: Deep learning models learn complex representations of data through multiple layers of nonlinear transformations. These computational processes involve a large number of matrix operations and back-propagation algorithms, which require efficient numerical computing libraries and hardware acceleration.

[0063] The above complex computational processes are all existing and can be implemented through modern deep learning frameworks such as TensorFlow and PyTorch. Through these frameworks, deep learning models can be built, trained, and deployed to solve various complex computational problems. These frameworks provide easy-to-use, highly modular designs, and seamless integration capabilities, relying on powerful underlying support to make model building intuitive. Dynamic computational graphs make model debugging and modification extremely convenient, while supporting GPU accelerated training. The advanced features and optimization strategies of these frameworks, such as learning rate adjustment and transfer learning, further enhance the ability of large model AI to handle complex calculations.

[0064] 9) Knowledge base construction: Build a knowledge base containing Go teaching content to support teaching and learning. These contents will interact with the large model AI to provide richer teaching resources.

[0065] 10) Large language model integration: Integrate large language models, such as GPT-4o, for natural language interaction and teaching content generation. These models can understand students’ natural language questions and provide accurate teaching information.

[0066] 11) Intelligent question-answering system: Develop an intelligent question-answering system that allows students to interact with the system through natural language and obtain teaching information. This is based on the natural language processing capabilities of large-model AI.

[0067] Step 4: Obtain the switch signal. The press trigger circuit obtains the press signal by row and column scanning. The press information activates the corresponding row and column lines. The column scanning circuit detects multiple column line signals. The row power supply circuit drives multiple row lines. The processor reads the signal through multiple GPIOs to determine the chess piece position. The control unit drives the corresponding LED light display according to the specific chess piece position. The electrical signal of the micro switch of the chess piece position is sent to the microcontroller. The microcontroller converts the electrical signal into data of chess game status changes and sends it to the large model AI for analysis.

[0068] Step 5: After receiving the data on the changes in the chess game status, the big model AI starts to perform deep learning algorithm calculations, analyzes the current situation of the chess game, and predicts possible moves and results. Based on the analysis results, the big model AI determines the best move for the next step and feeds it back to the user to achieve teaching interaction.

[0069] Specifically, it can be achieved based on existing deep learning technology and large model AI analysis capabilities. This process usually includes the following key steps: 1. Data input: First, the data of the chess game status changes are input into the deep learning model. This data may include information such as the position of chess pieces and the layout of the chessboard.

[0070] 2. Feature extraction: The deep learning model automatically extracts the features of the chess game through a multi-layer neural network. These features may include the relative positions of the pieces, the pattern of the chess game, and potential threats or opportunities.

[0071] 3. Game analysis: Using deep learning algorithms, large-model AI analyzes the current situation of the game, which involves an in-depth understanding of the characteristics of the game and pattern recognition.

[0072] 4. Predicting moves: Based on the analysis of the chess game, the large model AI predicts possible moves and results. This usually involves a combination of Monte Carlo Tree Search (MCTS) and deep neural networks to evaluate the winning rate and effect of different moves.

[0073] 5. Determine the best move: By comparing the prediction results of different moves, the big model AI determines the best move for the next step. This step may involve complex decision trees and probability calculations.

[0074] 6. Feedback to users: Finally, the big model AI will give feedback to users on the best moves to achieve teaching interaction. This process not only provides suggestions for moves, but may also include explanations and teaching suggestions for moves to help users understand the strategies and thinking processes behind them.

[0075] Integrate existing deep learning algorithms into many advanced Go AIs, such as KataGo. These AIs are able to provide high-level Go strategies and teaching suggestions through deep learning and large model technology.

[0076] Step 6: After the game is over, the system collects the scores and feedback updates of each move of the user and the large model AI.

[0077] As an embodiment, the present disclosure innovatively integrates large-model AI technology, such as KataGo. The present invention can not only play Go games, but also realize natural language interaction, bringing unprecedented personalized and intelligent experience to Go teaching. The specific control process is as follows: (1) When the chessboard is started, the system automatically detects and loads the preset large model parameters, such as the large model parameters of KataGo.

[0078] When the board starts up, the built-in microcontroller first performs a hardware self-test to confirm that all components are working properly.

[0079] After the self-test is completed, the microcontroller reads the preset large model parameters through the built-in storage medium.

[0080] Based on the chessboard's hardware configuration and the user's historical settings, the microcontroller selects the most appropriate large model parameters to load.

[0081] During the loading process, the system may need to fine-tune large models to adapt to different hardware performance and user preferences.

[0082] (2) The system adjusts the teaching strategy and difficulty of the large model AI according to the teaching difficulty level selected by the user.

[0083] According to the user's Go chess skill level, select the teaching difficulty level on the control panel of the chessboard.

[0084] After receiving the teaching difficulty level, the microcontroller adjusts the teaching strategy of the large model AI, such as changing the AI's thinking algorithm and search depth.

[0085] For beginners, the system may provide more detailed step-by-step explanations and more teaching tips; for professional players, it may provide fewer tips and more complex strategy analysis.

[0086] (3) The user simulates placing a “chess piece” by pressing a silicone button, which triggers the corresponding LED light display, for example, green for black pieces and orange for white pieces.

[0087] The user presses a specific button and the micro switch built into the button sends a signal to the control unit.

[0088] The control unit recognizes the signal, activates the LED light at the corresponding position, and displays the current "chess piece".

[0089] The color and brightness of the LED light changes according to the rules of the game to distinguish the chess pieces of different players.

[0090] (4) The chessboard button triggers the micro switch, which converts the key information into an electrical signal.

[0091] Each button is connected to a micro switch, and when the user presses the button, the micro switch closes, generating an electrical signal.

[0092] The micro switch converts the mechanical action into an electrical signal which is sent to the microcontroller.

[0093] The microcontroller converts the electrical signals into data on changes in the state of the chess game and sends them to the large model AI for analysis.

[0094] (5) The large-model AI analyzes the state of the game, identifies possible threats and opportunities, and prepares feedback.

[0095] After the large model AI receives the data on changes in the state of the chess game, it begins calculating using the deep learning algorithm.

[0096] AI analyzes the current chess game situation and predicts possible moves and outcomes.

[0097] Based on the analysis results, AI determines the best next move and prepares feedback to the user.

[0098] As an embodiment, 1) after the user simulates placing the black chess piece by pressing a button, the large model AI calculates the best response position for the white chess piece.

[0099] After the user places the black chess piece by pressing a button, the system sends the current chess game status to the large model AI.

[0100] The AI ​​calculates the best white chess response position based on the current chess game and the preset strategy.

[0101] The AI ​​sends its calculations back to the system, which prepares to display the recommendation to the user.

[0102] 2) The system lights up the LED on the corresponding button in white, and recommends that the user simulate placing a white chess piece at that position.

[0103] 3) After the system receives the white chess piece position recommended by AI, it controls the LED driver chip TM1680 to light up the LED light of the corresponding button. When the user sees the LED light on, he knows that AI recommends placing the white chess piece at this position.

[0104] Users can choose to follow the AI's suggestions or decide on their own what to do next.

[0105] As an embodiment, the present disclosure can implement natural language interaction, and the implementation process is as follows: 1) Obtain user inquiries, such as "How should I defend this corner?", and input the questions through the microphone built into the chessboard. The user asks the questions into the microphone built into the chessboard.

[0106] 2) The microphone captures the sound signal and converts it into an electrical signal.

[0107] 3) The electrical signal is sent to the system's speech recognition module for processing.

[0108] 4) Large model AI (such as GPT-4o) understands the problem and retrieves relevant information from the Go knowledge base.

[0109] 5) The speech recognition module converts the electrical signal into text information.

[0110] 6) After receiving the text information, the large model AI uses natural language processing technology to analyze the content of the question.

[0111] 7) AI retrieves relevant information from the built-in Go knowledge base and finds the most appropriate answer.

[0112] 8) The system answers the user's questions through a speech synthesizer.

[0113] 9) The big model AI converts the answer it finds into text information and sends it to the speech synthesizer.

[0114] 10) Speech synthesizer converts text information into speech signals.

[0115] 11) The speaker on the chessboard plays a voice signal and the user hears the AI’s answer.

[0116] Furthermore, the learning effect is evaluated based on the interaction results, including: (1) After the game is over, the system collects the user’s every move and the score of the large model AI.

[0117] During the game, the system records every move of the user in real time, including the position of the chess pieces and the time of placement.

[0118] The system also records the big model AI's scores and suggestions for each move.

[0119] After the game is over, the system will summarize all the data and prepare for the evaluation of learning effects.

[0120] (2) Big model AI analyzes the user’s overall performance and identifies weaknesses and strengths.

[0121] After the big model AI receives all the user's moves and scoring data, it begins analysis.

[0122] AI identifies the user's weaknesses and strengths by comparing the user's moves with the best moves recommended by AI.

[0123] AI analyzes the user's chess style and common mistakes and provides personalized feedback to the user.

[0124] (3) The system provides feedback.

[0125] Based on the analysis results of the big model AI, the system prepares feedback information.

[0126] Feedback information can be displayed directly to the user through the display of the chessboard, or provided in the form of speech through a speech synthesizer.

[0127] Users adjust their playing style and strategy based on the feedback to improve their Go skills.

[0128] Furthermore, according to the learning effect evaluation results, formulate teaching process management and feedback strategies, including: 1) Homework distribution: To implement homework distribution, teachers can send Go exercises to students. These questions may be generated by large model AI based on the students' level.

[0129] 2) Homework completion tracking: Track students’ homework completion and collect data for analysis. This data will be used to optimize the teaching strategy of large-model AI.

[0130] 3) Learning effect evaluation: Analyze students’ game and homework completion data, evaluate learning effects, and provide personalized feedback. These are all based on the data analysis capabilities of large-model AI.

[0131] 4) Teaching content update: Update and optimize teaching content based on students’ learning progress and feedback to ensure the timeliness and relevance of teaching content. This is achieved through the learning ability of large model AI.

[0132] Example 3 In one embodiment of the present disclosure, an interactive system of a chess teaching intelligent chessboard based on a large model is provided, comprising: The initialization module is used to create a smart classroom environment, connect to smart chessboards, assign a unique serial number to each smart chessboard, and record its location in the classroom; initialize the system, pair users with smart chessboards, and ensure that each user is paired with a smart chessboard uniquely; configure remote access rights, allowing users to access the smart classroom at different locations, and use large models and web terminals to achieve remote interaction; The chess piece position detection module is used to obtain the switch signal. The press trigger circuit obtains the press signal by row and column scanning. The press information activates the corresponding row and column lines. The column scanning circuit detects multiple column line signals. The row power supply circuit drives multiple row lines. The processor reads the signal through multiple GPIOs to determine the chess piece position. The control unit drives the corresponding LED light to display according to the specific chess piece position. The analysis and interaction module is used to send the electrical signal of the micro switch of the chess piece position to the microcontroller, which converts the electrical signal into data on the change of the chess game state and sends it to the large model AI for analysis. After receiving the data on the change of the chess game state, the large model AI starts to calculate, analyze the current situation of the chess game, and predict possible moves and results. Based on the analysis results, the large model AI determines the best move for the next step and feeds back to the user to achieve teaching interaction.

[0133] Example 4 In one embodiment of the present disclosure, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the interactive method of the large-model-based chess teaching intelligent chessboard is implemented.

[0134] Example 5 In one embodiment of the present disclosure, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the interactive method of the large-model-based chess teaching intelligent chessboard is implemented.

[0135] Example 6 In one embodiment of the present disclosure, an electronic device is provided, including: a processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device executes the interactive method of the large-model-based chess teaching intelligent chessboard.

[0136] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0137] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0138] Although the above describes the specific implementation methods of the present disclosure in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present disclosure. Technical personnel in the relevant field should understand that on the basis of the technical solution of the present disclosure, various modifications or variations that can be made by those skilled in the art without creative work are still within the scope of protection of the present disclosure.

Claims

1. An intelligent chessboard for chess teaching based on a large model, characterized by: include: The smart chessboard is a square structure, on which chess points are arranged, and the chess points are arranged in parallel in multiple rows and columns. Each chess point is set as an LED indicator, and each LED indicator is controlled by a press trigger circuit; the left pins of each row of the press chess points of the press trigger circuit are connected to form multiple row lines; the right pins of each column of the press chess points are connected to form multiple column lines; the press trigger circuit is connected to multiple control chips; Pressing each chess point can trigger the key switch of the circuit board, providing physical interaction between the user and the chessboard. The press-trigger circuit detects multiple rows and columns of digital signals through row and column scanning through multiple control chips, and identifies the position of the chess piece placed on the chess point on the chessboard.

2. The large-model-based chess teaching intelligent chessboard according to claim 1, characterized in that: Two chess pieces with LED lights of different colors are set on each chess point, representing different users playing chess. An LED driver chip is used to control all the LED lights on the chessboard, and a serial input and parallel output shift register is used to control the LED indicator lights, indicating the positions of chess pieces of different users and key points of the game in the form of visual display.

3. The large-model-based chess teaching intelligent chessboard according to claim 1, characterized in that: The push trigger circuit uses row and column scanning, and the row power supply circuit and the column scanning circuit use different control chips respectively. The row power supply circuit provides a stable power supply for the rows of the chessboard, and the column scanning circuit realizes the scanning of the columns of the chessboard, and works together with the row power supply circuit to form a complete chess piece detection network.

4. The large-model-based chess teaching intelligent chessboard according to claim 1, characterized in that: Function keys are arranged on the chessboard, and the function keys include a power key, a sound key, a level up key, a level down key, a first and last move key, a prompt key, an undo key, a game end key, a game start key and a chess play confirmation key, and the sound key is a multi-level adjustment key.

5. The large-model-based chess teaching intelligent chessboard according to claim 1, characterized in that: When the user places a chess piece on a chess point on the chessboard, the button is pressed, activating the corresponding row and column lines of the press-trigger circuit, the column scanning circuit detects multiple column line signals, the row power supply circuit drives multiple row lines, the processor reads the signal through multiple GPIOs to determine the chess piece position, and the LED driver chip drives the LED lights of different colors displayed according to the chess piece position to display the chess piece position.

6. The interactive method of the chess teaching intelligent chessboard based on a large model according to any one of claims 1 to 5, characterized in that: include: Create a smart classroom environment, connect smart chessboards, assign a unique serial number to each smart chessboard, and record its location in the classroom; The system is initialized to pair the user with the smart chessboard to ensure that each user is paired with the smart chessboard uniquely; Configure remote access permissions to allow users to access the smart classroom from different locations and use large models and web terminals to achieve remote interaction; Obtain switch signals, the press trigger circuit obtains press signals by row and column scanning, the press information activates the corresponding row and column lines, the column scanning circuit detects multiple column line signals, the row power supply circuit drives multiple row lines, the processor reads signals through multiple GPIOs to determine the chess piece position, and the control unit drives the corresponding LED light to display according to the specific chess piece position; The electrical signal of the micro switch of the chess piece position is sent to the microcontroller, which converts the electrical signal into data of chess game status change and sends it to the large model AI for analysis; After receiving the data on the changes in the chess game status, the large model AI starts to calculate, analyze the current chess game situation, and predict possible moves and results; Based on the analysis results, the big model AI determines the best way to proceed and provides feedback to the user to achieve interactive teaching. Or users can interact with large model AI in natural language.

7. An interactive system of chess teaching intelligent chessboard based on a large model, characterized in that: include: The initialization module is used to create a smart classroom environment, connect to the smart chessboard, assign a unique serial number to each smart chessboard, and record its location in the classroom; the system is initialized to pair the user with the smart chessboard to ensure that each user is paired with the smart chessboard uniquely; Configure remote access permissions to allow users to access the smart classroom from different locations and use large models and web terminals to achieve remote interaction; The chess piece position detection module is used to obtain the switch signal. The press trigger circuit obtains the press signal by row and column scanning. The press information activates the corresponding row and column lines. The column scanning circuit detects multiple column line signals. The row power supply circuit drives multiple row lines. The processor reads the signal through multiple GPIOs to determine the chess piece position. The control unit drives the corresponding LED light to display according to the specific chess piece position. The analysis and interaction module is used to send the electrical signal of the micro switch of the chess piece position to the microcontroller, which converts the electrical signal into data on the change of the chess game state and sends it to the large model AI for analysis. After receiving the data on the change of the chess game state, the large model AI starts to calculate, analyze the current situation of the chess game, and predict possible moves and results. Based on the analysis results, the large model AI determines the best move for the next step and feeds back to the user to achieve teaching interaction.

8. A computer program product, comprising a computer program, characterized in that When the computer program is executed by the processor, the interactive method of the large-model-based chess teaching intelligent chessboard described in claim 6 is implemented.

9. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by the processor, the interactive method of the large-model-based chess teaching intelligent chessboard as claimed in claim 6 is implemented.

10. An electronic device, characterized in that: include: A processor, a memory and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory to enable the electronic device to implement the interactive method of the large-model-based chess teaching intelligent chessboard as described in claim 6.

Images