Intelligent self-optimized go teaching interaction platform system

Abstract

An intelligent self-optimization go teaching interaction platform system integrates dynamic interaction go board hardware, deep collaboration software and security encryption data, a 1: 1 equal ratio structure is used on the hardware, 0.1 mm precision pressure sensing and LED light and shadow linkage units are arranged in intersections, 2.5 D anti-blue-light polarization layers and temperature sensors are matched, and the dynamic interaction go board hardware and the deep collaboration software are integrated. The brightness can be adaptively adjusted according to the touch temperature, a rest is prompted, and the integration of accurate interaction and eye protection is realized; a teacher double-circulation professional score system is constructed on software, qualification is verified through block chain storage, service conversion and chess power improvement factors are fused to calculate professional scores, service sorting and reward accounting are associated, meanwhile, a chess power defect model is established based on a student chess behavior feature library, and a difficulty jump fallback mechanism and a three-dimensional anti-addiction system are matched; and an off-line intelligent replaying function supported by a chess style adaptation matching engine and edge calculation is also designed, so that the dynamic, precise and intelligent Go teaching is realized in an omnibearing manner.

Description

Technical Field

[0001] This invention relates to information and communication technologies for administrative, commercial, financial, management, or supervisory purposes, and more particularly to an intelligent, self-optimizing interactive Go teaching platform system. Background Technology

[0002] The current Go teaching field is undergoing a transformation from the traditional offline model to an "online + offline" integrated model, with digital tools gradually becoming the core teaching carrier. However, the existing system has significant shortcomings: the teaching end relies heavily on standardized courses and fixed question banks, making it difficult to adapt to the different skill levels of different students; the hardware end consists either of traditional Go boards without interactive functions or basic electronic Go boards with limited functionality, lacking consideration for user experience and health; in terms of supervision and health protection, management methods for underage users are simplistic, with anti-addiction designs limited to time limits and not deeply integrated with eye health; at the same time, there are also gaps in technical support for key scenarios such as teacher ability assessment, student playing style matching, and offline learning, resulting in overall teaching efficiency and user experience failing to meet the needs of industry development. To address these issues, existing technologies that have been attempted include: Chinese invention patent CN113946604A describes a phased Go teaching method, device, electronic device, and storage medium. This application provides a phased Go teaching method, device, electronic device, and storage medium. The method includes: acquiring target Go game data appropriate to the user's current Go teaching stage from a pre-established phased Go game database containing a certain number of Go game data; generating teaching games based on the target Go game data; conducting human-computer interactive Go games with the user based on the teaching games; recording process data generated during the human-computer interactive Go games; generating teaching feedback data based on the process data and providing feedback to the user.

[0003] Chinese invention patent CN111260513A discloses a children's Go teaching interconnected management system, including a student terminal. The student terminal includes a login module, a practice module, an AI practice module, and a real-person game module. The login module is used for account login, logout, registration, and password modification. The practice module accesses a practice question database on a cloud server and is used for simulated practice, answer submission, and correct / incorrect judgment of questions. The AI ​​practice module connects to an intelligent AI on the cloud server. The real-person game module matches and connects with other users. The student terminal also includes an insertion module, which provides information prompts about the strength and weakness of moves during the AI ​​practice or real-person game process. Children can practice questions, engage in AI practice, and play against real people through the student terminal, making learning fun and engaging. The student terminal allows for independent learning, and different information prompts are inserted during the game to guide children and improve their attention, easily conveying concepts of strength, weakness, correctness, and size to children.

[0004] While the existing technologies mentioned above have advanced the modernization of Go teaching to some extent, the following problems still exist: Regarding the precision of instruction, existing systems generally suffer from a "one-size-fits-all" problem. Most platforms push courses and assessment content based on preset difficulty levels, failing to analyze students' actual playing behavior to identify weaknesses and generate targeted reinforcement exercises. Level assessments often employ a linear progression model, requiring students to complete low-difficulty content one by one regardless of their accuracy, wasting time and making it difficult to accurately assess their true skill level. Furthermore, the assessment of students' skill levels does not consider the differences in opponent skill, leading to biased evaluation results. This situation prevents instruction from truly meeting students' needs and has become a core bottleneck restricting the improvement of learning efficiency. Regarding the management and incentive mechanisms for Go teachers, existing platforms rely heavily on static qualification reviews or simple student ratings for teacher evaluation. They fail to incorporate teaching effectiveness data (such as student course completion rates and the extent of improvement in Go skills) into the evaluation system, nor do they consider the time decay effect of ratings, making it difficult to dynamically reflect teachers' real-time teaching abilities. At the same time, the evaluation results lack a direct correlation with teachers' service display ranking and remuneration calculation, failing to effectively incentivize teachers to improve teaching quality. Furthermore, they do not provide teachers with customized ability development paths, resulting in the overall teaching level of the teaching staff being difficult to continuously improve, thus affecting the overall teaching quality of the platform. Regarding anti-addiction monitoring and offline learning functions, existing anti-addiction designs only limit usage to a fixed duration, failing to dynamically adjust permissions based on the user's eye health or to establish a complete "assessment-reminder-rest" closed loop. Monitoring permissions are concentrated on the parent's end, lacking function locking permissions on the teacher's end, and triggering restrictions often involves forced exit without saving learning progress, impacting the continuity of student learning. Furthermore, core learning functions (such as review) are highly dependent on the internet and cannot be used offline, preventing users from engaging in effective learning in environments without internet access, further limiting the platform's usability and convenience.

[0005] Furthermore, the interactive experience and health protection functions of hardware devices are severely lagging behind. Current mainstream electronic chessboards have low piece recognition accuracy, failing to capture subtle differences in operation. The light and shadow display effects are monotonous, making it difficult to clearly distinguish the state of the game. More importantly, the hardware design does not incorporate eye protection concepts and lacks health protection mechanisms for prolonged use. It cannot dynamically adjust hardware parameters based on the user's usage status (such as touch temperature and eye environment), leading to eye fatigue and even vision problems during use. There is also a disconnect in the data linkage between hardware and software, failing to create an integrated teaching experience. Summary of the Invention

[0006] In view of the problems described in the background art, the present invention proposes a technical solution for an intelligent self-optimizing interactive Go teaching platform system, the details of which are as follows: An intelligent self-optimizing Go teaching interactive platform system includes a dynamic interactive Go board hardware module, a deep collaborative software module, and a secure encrypted data interaction module; the deep collaborative software module includes an adaptive teaching module, an eye health linkage anti-addiction module, a Go intelligence interaction module, and a dynamic self-optimizing module. The adaptive teaching module includes a dynamic professional score calculation model for Go teachers. Go teacher users have a number of scores in the Go teaching interaction platform system. The weight of the scores is reduced according to the interval △T between the current calculation time T1 and the scoring time T2. The professional dynamic score of the Go teacher user is calculated according to the following formula.

[0007] Where: P is the professional dynamic score of the Go teacher user, which is the score given by students after the Go teacher user provides teaching. All scores are weighted and adjusted according to the time interval between the evaluation time and the current time, and the fluctuation range of the weight is compressed to the range of 0%-25%, that is, the result of the formula involved is compressed to the range of 75% to 100%; B is a weighted constant for adjusting the sensitivity of the user rating time interval to the influence of the weight coefficient of the professional dynamic score of the Go teacher.

[0008] The dynamic self-optimization module, designed for Go teacher users, constructs a dual-cycle professional score system: The first cycle is dynamic verification of the professional foundation score. After a Go teacher user uploads their qualification certificate, the system verifies the certificate's validity through blockchain storage, connecting with the official Go Association's storage platform. A foundation score is assigned based on the certificate's level, and this verification is automatically repeated quarterly. The second cycle is iterative optimization of the Go teacher's professional score. In addition to the Go teacher user's dynamic professional score P, a service conversion factor is added, namely the percentage of users who complete their learning goals after purchasing services, and a Go skill improvement factor, namely the average increase in students' skill assessment scores after learning with the Go teacher user. The Go teacher's professional score is calculated as follows: Go teacher's professional score = (P × 40%) + (service conversion factor × 30%) + (go skill improvement factor × 30%). The final professional level assessment result is calculated by combining 40% of the professional foundation score and 60% of the Go teacher's professional score, and then weighted by two factors: first, a service ranking weight, which adjusts the service display ranking based on user profile matching; and second, a compensation calculation weight, specifically calculated as follows: The service fee per Go teacher user = basic fee × (1 + Go teacher professional points / 100). An additional 15% bonus will be awarded if the evaluation result is ≥90. The dynamic interactive Go board hardware module features a 1:1 scale structure with built-in pressure sensors and LED light-and-shadow linkage units at each intersection. These units include a 0.1mm precision pressure sensor, adjustable three-primary-color eye-protection LED lights, and micro-angle light-reflecting lenses. The pressure sensor identifies the user's placement force, triggering the LED lights to output corresponding light and shadow intensities. The micro-angle light-reflecting lenses switch between three exclusive lighting modes: 45° refracted cool white light for white pieces, 135° refracted warm black light for black pieces, and 90° refracted soft light for a blank state. The board surface is covered with a 2.5D anti-blue light polarization layer. The pressure sensor and LED light-and-shadow linkage units also include a temperature sensor. When the detected user touch temperature is ≥37℃, the LED brightness is automatically reduced by 10%, and a "Resting a Rest" message is displayed at the edge of the board. The adaptive teaching module also includes a chess skill deficiency model built based on a user chess game behavior feature database, including move intervals, frequency of undoing moves, and key move thinking time. This model generates remedial assignments for practice scenarios. The skill assessment scenario uses a difficulty-skipping algorithm: if a user answers three questions correctly in a row, they skip the current difficulty level and proceed directly to the next higher level. The Go competition scenario includes a tactical reminder suppression mechanism with reminder thresholds set based on the user's skill level. Simultaneously, a two-tiered supervision system is configured for underage academic users: Level 1 allows parents to set daily / weekly / monthly usage time thresholds; Level 2 allows teachers to lock specific functions. When a user triggers the time threshold or violates the locked function, the system automatically saves the current progress and initiates a gradual lock, first locking entertainment functions, and then completely locking them if the user does not exit after 5 minutes. The chess skill deficiency model also introduces an opponent skill correction factor: if a user defeats an opponent two levels higher than themselves, the corresponding tactical deficiency judgment weight is reduced by 35%.

[0009] The eye health-linked anti-addiction module constructs a three-dimensional anti-addiction model: The first dimension is dynamic allocation of stamina points. Based on the user's daily eye health score, collected by the chessboard's built-in light and distance sensors (score range 0-100), stamina points are allocated as follows: a score ≥80 allocates 10 stamina points, a score <60 allocates 5 stamina points, each game consumes 2 points, and each assignment consumes 1 point. When stamina points are insufficient, only the eye protection mode for replaying games is enabled, brightness is reduced by 50%, and a mandatory 2-minute break is imposed every 10 minutes. The second dimension is closed-loop control of eye usage time, setting eye usage limits based on the user's age. For users aged 6-12, the daily cumulative limit is ≤ For users aged 13-18, the daily cumulative usage time is ≤120 minutes. When the limit is reached, an eye exercise guidance animation is automatically generated. Only after completing the animation can an additional 30 minutes of time be unlocked. The third dimension is a focus correlation mechanism. The pressure sensor identifies the frequency of invalid touches by the user. If there are ≥5 touches without the intention to place a piece within 1 minute, it is judged as a lack of focus. If there are 3 instances of lack of focus, a reminder to the monitoring user is triggered, and the current operation is paused. The eye health score also combines the user's historical vision test data. If the vision has decreased by ≥50 degrees in the past 3 months, the daily usage time threshold is automatically reduced by 20%, and vision protection training exercises are pushed. The chess-playing interaction module features a style-matching engine: by analyzing the user's attack rate (proportion of proactive moves), defense rate (proportion of defensive moves), and sacrifice rate (number of proactive sacrifices / total number of moves) from the last 10 games, it constructs style tags such as aggressive or conservative. During pairing, it prioritizes matching users with complementary styles (aggressive users with defensive users) and generates style-based strategy suggestions. A dedicated Go terminology translation unit is configured, supporting real-time voice / text translation with accompanying terminology annotations. The debriefing guidance unit employs a multi-dimensional game analysis algorithm, generating debriefing reports based on three dimensions: spatial efficiency (number of control points / total number of moves), time efficiency (average thinking time for key moves), and tactical coherence (matching tactical intent with move placement). Simultaneously, the intelligent robot teacher unit, based on historical data from deficiencies and reinforcement exercises, focuses on explaining tactics the user hasn't mastered during debriefing. The style-matching engine supports style preference settings, allowing users to manually adjust pairing preferences, and the system adjusts pairing weights according to user settings. When calculating the service conversion factor, the dynamic self-optimization module excludes user data that cancels services within 7 days and assigns double the weight to user data that purchases services after completing the learning objectives, ensuring the accuracy of the factor. The edge computing unit of the secure encrypted data interaction module also supports offline intelligent review. In offline mode, it can generate a simplified review report based on the locally stored mini tactical library, and automatically synchronize to the cloud to obtain the complete report after connecting to the network. The dynamic interactive Go board hardware module is also equipped with a vibration feedback unit. When the user places a stone at a critical break point or a vital point for life and death, it outputs micro-vibrations of different frequencies to help the user perceive the key positions on the board. The vibration intensity can be adjusted through the monitoring user's console. The difficulty level jump algorithm of the adaptive teaching module is equipped with a fallback mechanism. If the user's accuracy rate is less than 60% after jumping to a higher level, the system will automatically fall back to the previous difficulty level and generate a reinforcement plan for the failed jump. The dynamic self-optimization module is also configured with a growth path for Go teacher users. Based on the final professional level assessment results, it pushes ability improvement suggestions to Go teacher users. After completing the suggested courses, users can get an extra 5% bonus to their basic score, forming a closed-loop optimization of assessment-improvement-reassessment.

[0010] Compared with the prior art, the beneficial technical effects of the present invention are as follows: 1. A smart, self-optimizing interactive Go teaching platform system. Its dynamic interactive Go board hardware module innovatively achieves an integrated hardware architecture of "pressure sensing - LED light and shadow linkage - multi-dimensional health protection," forming a triple breakthrough of "dynamic energy saving - low radiation - real-time health monitoring." This overcomes the shortcomings of existing Go hardware technologies, which either only possess basic move recognition functions or solely emphasize eye protection, never achieving deep integration of pressure sensing, light and shadow linkage, temperature monitoring, and blue light protection. A dual-cycle professional scoring system for Go teachers is constructed, realizing dynamic, precise, and closed-loop optimization of teacher professional level assessment. Existing technologies for teacher assessment often remain at the level of static qualification review or a single scoring dimension. This system, however, ensures the authenticity and timeliness of qualifications through automatic re-verification in the first cycle; the second cycle innovatively introduces service conversion factors, ensuring the comprehensiveness of teacher assessment and incentivizing teachers to improve teaching quality, forming a virtuous cycle of "assessment-improvement-reassessment." This overcomes the shortcomings of existing technologies that lack such a multi-dimensional, dynamic teacher assessment system combined with incentive mechanisms.

[0011] 2. A smart, self-optimizing Go teaching interactive platform system constructs a dual-cycle professional score system for Go teachers, overcoming the shortcomings of existing technologies in teacher evaluation, such as static evaluation, single-dimensionality evaluation, and lack of incentive loops. Existing technologies mostly rely on fixed qualification verification or simple student ratings, failing to dynamically reflect changes in teacher teaching ability and lacking a mechanism linking evaluation with service and compensation. This system's first cycle verifies teacher qualifications through blockchain and updates base scores quarterly, ensuring the authenticity of qualifications. The second cycle integrates a dynamic professional score P, a service conversion factor (the percentage of students who complete their learning goals), and a Go skill improvement factor (the average improvement in student skill level) to calculate the professional score. The final evaluation result is not only used for service ranking (matched with user profiles) but also linked to compensation calculation (compensation per order = base compensation × (1 + professional score / 100), with an additional 15% reward for scores ≥90), forming a closed loop of "qualification verification - multi-dimensional scoring - incentive feedback," making teacher evaluation more accurate and incentives more effective, completely solving the problem of existing technology evaluation being disconnected from actual teaching value. 3. An intelligent, self-optimizing interactive Go teaching platform system. Its adaptive teaching module constructs a Go skill defect model and a scenario-based teaching mechanism, overcoming the shortcomings of existing technologies, such as homogeneous teaching content, poor scenario adaptability, and lack of dynamic correction in skill assessment. Existing technologies often use standardized assignments and fixed-difficulty assessments, failing to customize content for individual user weaknesses and ignoring the impact of opponent skill level on skill assessment. This system generates defect-reinforcing assignments based on behavioral characteristics such as move intervals and frequency of undoing moves. Skill assessment employs a "three consecutive correct answers to skip a level" algorithm with a fallback mechanism. Tactical reminder thresholds are set according to skill level in match scenarios. Simultaneously, an opponent skill level correction factor is introduced; defeating an opponent two levels higher reduces the weight of the corresponding tactical defect assessment by 35%, ensuring a more objective skill assessment. This design allows teaching content to precisely match user needs, solving the problem of low learning efficiency caused by the "one-size-fits-all" teaching methods of existing technologies. 4. A smart, self-optimizing Go (Weiqi) teaching interactive platform system that uses an eye health-linked anti-addiction module to create a three-dimensional anti-addiction model, overcoming the shortcomings of existing anti-addiction technologies that rely solely on single time limits, are disconnected from eye health, and lack tiered management. Existing technologies often simply set usage time limits without considering the user's eye condition and vision changes, resulting in rigid control methods. This system allocates physical strength points based on eye health scores collected by light and distance sensors (≥80 points = 10 points, <60 points = 5 points), with insufficient physical strength only allowing eye-care review sessions; the second dimension sets eye limits based on age (6-12 years old ≤90 minutes / day, 13-18 years old ≤120 minutes / day), requiring eye exercises to unlock additional time after reaching the limit; the third dimension identifies inattentive behavior (≥5 invalid touches per minute) through pressure sensors and triggers reminders, while also combining vision data from the past 3 months (a decrease of ≥50 degrees followed by a 20% reduction in time threshold). This design deeply integrates anti-addiction measures with eye health, solving the problem that existing technologies only limit the duration of use but cannot protect users' eyesight. 5. A smart, self-optimizing Go (Weiqi) teaching interactive platform system provides underage users with dual-level supervision permissions and a progressive locking mechanism, overcoming the shortcomings of existing technologies that offer only single-level supervision permissions, rigid locking methods, and easy interruption of learning progress. Existing technologies mostly only support parents setting time limits, lacking teacher supervision permissions, and forcibly exiting the learning process after triggering thresholds, impacting the learning experience. This system allows first-level supervision (parents) to set daily / weekly / monthly time thresholds, and second-level supervision (teachers) to lock specific functions; when thresholds are triggered or violations occur, entertainment functions are first locked, and if the user does not exit after 5 minutes, the function is fully locked, while automatically saving progress. This tiered supervision and progressive locking system addresses the management needs of both parents and teachers, avoids abrupt interruptions to learning, and solves the shortcomings of existing technologies in balancing supervision flexibility and user experience. 6. An intelligent, self-optimizing Go teaching and interactive platform system. The system's chess intelligence interaction module incorporates a style-matching engine and a multi-dimensional game review guidance mechanism, overcoming the shortcomings of existing technologies such as vague style matching, limited game review analysis dimensions, and a lack of targeted explanations. Existing technologies often randomly match opponents, and game reviews simply recount the game steps, failing to help users improve their tactical abilities. This system constructs style tags (aggressive / conservative) by analyzing the attack rate, defense rate, and sacrifice rate of the last 10 games, prioritizing matching complementary users and generating adversarial suggestions. Game reviews generate reports based on spatial efficiency (control point / placement ratio), time efficiency (thinking time for key moves), and tactical coherence (matching intent with placement). The intelligent robot also provides focused explanations of tactics not yet mastered based on the data of deficiencies in gameplay. This design makes playing more challenging and game reviews more instructive, addressing the shortcomings of existing technologies in terms of interactive experience and learning value. 7. An intelligent, self-optimizing Go teaching and interactive platform system. Its secure, encrypted data interaction module supports offline intelligent game review, overcoming the shortcomings of existing technologies that rely on internet connectivity and whose core learning functions fail offline. Existing technologies often require an internet connection to generate complete game review reports; offline, users cannot effectively review and learn, affecting the continuity of learning. This system's edge computing unit supports generating simplified game review reports based on a local mini-tactics library in offline mode. Upon connecting to the internet, it automatically synchronizes and retrieves the complete report from the cloud, ensuring users can still conduct game review and learning even without a network connection. This solves the network-dependent limitations of existing technologies and guarantees the convenience and continuity of learning. 8. An intelligent, self-optimizing Go teaching interactive platform system. In its adaptive teaching module, the Go teacher's professional dynamic score calculation model employs a time-decay weight correction mechanism, overcoming the shortcomings of existing technologies that ignore time factors in teacher scoring and suffer from distorted scores due to excessive weight fluctuations. Existing technologies often treat scores from different times equally or lack control over weight fluctuations, failing to reflect recent changes in the teacher's teaching level. This model uses a formula to perform time-decay calculations on scores and compresses weight fluctuations within the 75%-100% range, allowing recent scores to have a greater impact while maintaining controllable fluctuations. This ensures that the teacher's score dynamically and stably reflects their teaching ability, resolving the imbalance between timeliness and stability in existing scoring technologies. 9. A smart, self-optimizing interactive Go teaching platform system. The dynamic interactive Go board hardware module achieves deep linkage between the LED light and shadow linkage unit and multiple sensors, overcoming the shortcomings of existing Go hardware sensors being isolated and unable to achieve adaptive adjustment. In existing technologies, temperature and light sensors often operate independently, unable to link with the LED light source, and unable to adjust hardware parameters according to the user's status. In this system, the temperature sensor triggers LED brightness adjustment, the light sensor collects data for eye health scoring, the distance sensor assists in judging eye status, and the multi-sensor data linkage controls LED brightness and light effect mode. Simultaneously, it combines physical exertion values ​​to adjust the brightness of the review mode (reducing it by 50%), allowing the hardware status to adapt to the user's needs and health status in real time, solving the shortcomings of existing hardware functions being fragmented and unable to work collaboratively. 10. An intelligent, self-optimizing interactive Go teaching platform system. Its dynamic self-optimization module configures growth paths for Go teachers, overcoming the shortcomings of existing technologies that only focus on teacher evaluation and lack a mechanism for guiding skill development. Existing technologies mostly remain at the level of evaluating teacher skill, failing to provide targeted improvement plans and thus failing to support teacher skill growth. This system, based on the teacher's final professional level evaluation results, pushes customized skill improvement suggestions. Teachers who complete the suggested courses receive an additional 5% bonus to their base score, constructing a closed loop of "evaluation-suggestion-improvement-re-evaluation." This makes evaluation not only a judgment tool but also a booster for teacher growth, solving the problem of the disconnect between evaluation and skill development in existing technologies and contributing to improving the overall teaching quality of the platform. Attached Figure Description

[0012] Figure 1 This is a diagram showing the overall logical architecture of an intelligent, self-optimizing interactive Go teaching platform system. Detailed Implementation

[0013] To make an intelligent, self-optimizing Go teaching and interactive platform system more practical, we analyzed the user stickiness of the Go platform and found that it is very important for an intelligent Go platform to be convenient and practical, amplify users' interest in Go, give Go users a sense of honor and accomplishment, and enable Go users to benefit. Therefore, this invention has developed a technical solution based on these principles.

[0014] An intelligent self-optimizing Go teaching interactive platform system includes a dynamic interactive Go board hardware module, a deep collaborative software module, and a secure encrypted data interaction module; the deep collaborative software module includes an adaptive teaching module, an eye health linkage anti-addiction module, a Go intelligence interaction module, and a dynamic self-optimizing module. The adaptive teaching module includes a dynamic professional score calculation model for Go teachers. Each Go teacher user has *a* ratings within the Go teaching interaction platform system. Since each professional user providing services on the platform learns and improves daily, simply fixing a person's professional level in the past is unfair. Therefore, the technical solution of this invention uses time as a parameter variable, and the weight of the rating is attenuated based on the interval ΔT between the current calculation time T1 and the rating time T2, further ensuring the objectivity of the rating's impact on the professional user's score. Based on this technical analysis, the professional score influence factor of the mapped service provider is calculated according to the following formula.

[0015] The Go teacher user provides scores given by students after their lessons. P is the Go teacher user's professional dynamic score. All scores are weighted and adjusted based on the time interval between the evaluation and the current time, and the fluctuation range of the weight is compressed to 0%-25%. In other words, the result of the relevant formula is compressed to the range of 75% to 100%. B is a weighted constant that adjusts the sensitivity of the user's rating time interval to the weight coefficient of the user's professional dynamic score. The value of B can be adjusted as needed to control the sensitivity.

[0016] The dynamic interactive Go board hardware module adopts a 1:1 scale structure with a traditional Go board. Each intersection point incorporates a "pressure sensing-LED light and shadow linkage unit," which includes a 0.1mm precision pressure sensor, three-primary-color adjustable eye-protection LED lights, and a micro-angle light-refracting lens. The pressure sensor identifies the user's placement force (50-500g range), triggering the LED lights to output corresponding light and shadow intensities (the greater the force, the clearer the light and shadow edges). The micro-angle light-refracting lens switches between three exclusive light effect modes: 45° refracted cool white light for white pieces, 135° refracted warm black light for black pieces, and 90° refracted soft light for a blank state. Simultaneously, the board surface is covered with a 2.5D anti-blue light polarization layer, achieving triple interactive optimization of "force feedback + low radiation + anti-glare," solving the problems of traditional electronic Go boards lacking force perception and causing strong visual stimulation. The adaptive teaching module constructs a "chess skill deficiency model" based on the user's "chess game behavior feature library" (including move interval, frequency of undoing moves, and key move thinking time). It generates "deficiency reinforcement assignments" for homework practice scenarios (e.g., generating specific breakpoint training questions if the user's "weakness in breakpoint judgment" is identified). The skill assessment scenario employs a "dynamic difficulty skipping algorithm": if a user achieves a correct answer rate of ≥90% for 3 consecutive questions, they skip the current difficulty level and directly enter the next higher level of assessment. The Go competition scenario is equipped with a "tactical reminder suppression mechanism," setting reminder thresholds based on the user's skill level (e.g., beginner users can trigger 3 tactical hints per game, while professional users receive no hints). Simultaneously, it configures "dual-level supervision permissions" for underage academic users. Level 1 supervision (parents) can set daily / weekly / monthly usage time thresholds (accurate to 10-minute units), while level 2 supervision (teachers) can lock specific functions (e.g., prohibiting entertainment games during non-study periods). When a user triggers the time threshold or violates the locked function, the system automatically saves the current progress and initiates "progressive locking" (first locking entertainment functions, and then completely locking them if the user does not exit after 5 minutes). The eye health-linked anti-addiction module constructs a "three-dimensional anti-addiction model": The first dimension is "dynamic allocation of stamina points," which allocates stamina points based on the user's daily eye health score (collected by the chessboard's built-in light sensor and distance sensor, with a score range of 0-100) (score ≥ 80 allocates 10 stamina points, score < 60 allocates 5 stamina points). Each game consumes 2 points, and each assignment consumes 1 point. When stamina points are insufficient, only "eye protection mode replay" is enabled (brightness reduced by 50%, forced 2-minute rest every 10 minutes); the second dimension is... The "closed-loop control of screen time" sets screen time limits based on user age (6-12 years old, cumulative daily screen time ≤ 90 minutes; 13-18 years old, cumulative daily screen time ≤ 120 minutes). When the limit is reached, an "eye exercise guidance animation" is automatically generated. Only after completing the animation can an additional 30 minutes of screen time be unlocked. The third dimension is the "focus association mechanism," which uses pressure sensors to identify the user's "ineffective touch frequency" (≥ 5 touches without the intention to place a piece within 1 minute are considered as lack of focus). If a user is found to be unfocused 3 times, a reminder will be triggered to monitor the user, and the current operation will be paused. The chess intelligence interaction module innovatively designs a "play style matching engine": by analyzing the user's "attack rate" (proportion of proactive moves), "defense rate" (proportion of defensive moves), and "sacrifice rate" (number of proactive sacrifices / total number of moves) from the user's last 10 games, it constructs play style tags (such as "aggressive attacking type" and "stable defensive type"). During matching, it prioritizes matching users with complementary play styles (aggressive type matches defensive type) and generates "play style confrontation strategy suggestions" (such as prompting aggressive users to use the "breakpoint breakthrough method" to deal with defensive types). It is also equipped with a "dedicated translation unit for Go terminology" with a built-in four-language database containing more than 300 professional Go terms (such as "ko" in Japanese, "고" in Korean, and English). The system supports real-time voice / text translation, and the translation results are accompanied by "terminology analysis annotations" (such as explaining "tactics of achieving shape transformation through flexible sacrifice" when translating "Teng Nuo"). The debriefing guidance unit uses a "multi-dimensional game deconstruction algorithm" to generate debriefing reports from three dimensions: "space efficiency" (number of control points / total number of moves), "time efficiency" (average thinking time for key moves), and "tactical coherence" (matching degree between tactical intent and moves). At the same time, the intelligent robot teacher unit will focus on explaining tactics that the user has not mastered during the debriefing based on historical data of "deficiency reinforcement assignments" (such as prioritizing the analysis of breakpoint responses in the game if the user's previous breakpoint training accuracy was low). The dynamic self-optimization module designs a "multi-factor scoring weight model": when quantifying user evaluation resources, it introduces a "behavioral correlation factor" (if an evaluating user has purchased the services of a Go teacher user, the weight increases by 20%), combined with a "scoring deviation factor" (assuming the average score is μ, the individual user's score is x, the deviation factor = 1 - |x - μ| / μ, μ ≠ 0), and the final user score weight = deviation factor × (1 + behavioral correlation factor) × (1 - time decay factor); for Go teacher users, a "dual-cycle professional score system" is constructed: the first cycle is "dynamic verification of professional basic score". After a Go teacher user uploads qualification certificates (Go dan certificate, teaching qualification certificate, etc.), the system verifies the validity of the certificate through "blockchain evidence verification" (connected to the official evidence storage platform of the Go Association), and assigns basic points according to the certificate level (e.g., 80 points for professional 5-dan, 60 points for amateur 7-dan). The system automatically re-verifies every quarter, and the certificate is invalid. The first cycle resets the base score to zero; the second cycle is "professional dynamic score iterative optimization," which, in addition to referencing user reviews, adds "service conversion factor" (the percentage of users who complete their learning goals after purchasing the service) and "chess skill improvement factor" (the average improvement in skill assessment scores after students learn from Go teacher users). The Go teacher's professional score = (user review score × 40%) + (service conversion factor × 30%) + (chess skill improvement factor × 30%). The final professional level assessment result is "professional base score × 40% + Go teacher's professional score × 60%", which is converted into a dual weight: first, "service ranking weight", which adjusts the service display ranking based on user profile matching (e.g., prioritizing Go teacher users who are good at teaching young children); second, "compensation calculation weight", where the compensation for each Go teacher user service order = base compensation × (1 + final professional level assessment result / 100), with an additional 15% bonus when the assessment result is ≥ 90 points. The secure encrypted data interaction module adopts an "edge-cloud dual-level processing architecture": the dynamic interactive Go board hardware module has a built-in edge computing unit that processes information with high real-time requirements, such as pressure sensing data and light and shadow control data, locally, while only encrypting and uploading non-real-time data such as game data and user behavior data to the cloud; the data transmission adopts a "custom Go terminology encryption protocol" to convert the raw data into Go terminology encoding (such as "placement coordinates (3,5)" encoded as "three-three placement"), and then transmits it through the AES-256 encryption algorithm. At the same time, a "supervisory access log" is configured for the data of underage users to record all operations that access the data (including access time and operation content) to ensure data security and traceability. The "pressure sensing-LED light and shadow linkage unit" of the dynamic interactive Go board hardware module is also equipped with a temperature sensor. When the temperature of the user's touch is detected to be ≥37℃ (which may indicate fatigue and sweating), the brightness of the LED light is automatically reduced by 10%, and a "rest recommended" light prompt is displayed on the edge of the Go board. The adaptive teaching module's "chess strength defect model" also introduces an "opponent level correction factor." If a user defeats an opponent whose level is two levels higher than their own, the defect judgment weight of the corresponding tactic (such as "standard opening") is reduced by 30%, avoiding misjudgments caused by the opponent's level. The "eye health score" of the eye health linkage anti-addiction module also combines the user's historical vision test data (uploaded with user authorization). If the vision has decreased by ≥50 degrees in the past 3 months, the daily usage time threshold will be automatically reduced by 20%, and "vision protection special training" assignments will be pushed. The chess-playing interaction module's "chess style matching engine" supports "chess style preference settings," allowing users to manually adjust matching tendencies. One specific example is prioritizing matching with aggressive opponents; the system adjusts the matching weights based on user settings (increasing preference weights by 40%). When calculating the "service conversion factor" in the dynamic self-optimization module, user data that "cancelled service within 7 days" is excluded, and user data that "purchased service after completing learning goals" is given double the weight to ensure factor accuracy. The edge computing unit of the secure encrypted data interaction module also supports "offline intelligent review". In offline mode, it can generate a simplified review report based on the locally stored "mini tactical library" (containing 100+ basic tactical models). After connecting to the network, it will automatically synchronize to the cloud to obtain the complete report. The dynamic interactive Go board hardware module is also equipped with a "vibration feedback unit". When the user places a stone at a "key breakpoint" or "life-and-death point", it outputs micro-vibrations of different frequencies (1 vibration / second for breakpoints and 2 vibrations / second for life-and-death points) to help the user perceive key positions on the board. The vibration intensity can be adjusted through the monitoring user console (the default intensity is ≤30% for underage users). The adaptive teaching module's "dynamic difficulty jump algorithm" also has a "fallback mechanism." If the user's accuracy rate is less than 60% after jumping a level, the user will automatically fall back to the previous difficulty level and generate a "failure jump reinforcement plan" (such as generating special training for tactics to address mistakes after jumping a level). The dynamic self-optimization module is also configured with a "Go teacher user growth path". Based on the final professional level assessment results, it pushes "ability improvement suggestions" to Go teacher users. In a specific example, if the assessment result is less than 70 points, a "teaching skills course for young children" is recommended. After completing the recommended course, an additional 5% bonus to the basic score can be obtained, forming a closed-loop optimization of "assessment-improvement-reassessment".

[0017] A specific embodiment of an intelligent self-optimizing Go teaching interactive platform system is presented, using a youth Go training school in a prefecture-level city as the application scenario. The school has 30 classes, covering 800 students aged 6-18, and is equipped with 25 professional Go teachers. During platform deployment, each classroom is equipped with a dynamic interactive Go board hardware device. The teacher's end uses a customized tablet computer, while the student end supports access via tablet computers, smartphones, and dedicated learning terminals. The system backend is deployed on the school's private cloud server and is also connected to the local Go association's official evidence storage platform. The secure encrypted data interaction module uses the national cryptographic SM4 algorithm to encrypt transmitted data. The edge computing unit is deployed in the micro-server built into each dynamic interactive Go board to ensure that basic functions can still be realized in offline mode. When implementing the dynamic interactive Go board hardware module, the Go board adopts a 1:1 scale standard Go board size. A 0.1mm precision pressure sensor, three-primary-color adjustable eye-protection LED light, and a micro-angle light-refracting lens are precisely installed at each intersection. The board surface is covered with a 2.5D anti-blue light polarization layer. After installation, pressure sensing tests were conducted to ensure accurate recognition of the force applied during a move (5-500g). The LED lights were also tested to output corresponding light intensities of 5-100 cd / m² based on the applied force. Simultaneously, the temperature sensor was adjusted to simulate human touch temperatures (37℃, 38℃, 39℃) to verify whether the LED brightness automatically decreased by 10% and displayed a "Resting is recommended" indicator at the edge of the board. After 100 simulation tests, the accuracy rate reached 100%. Simulated move operation tests were also conducted. The micro-angle light refraction lens features three light effect modes: when a white chess piece is placed, the lens switches to 45° refracted cool white light (brightness stable at 80 cd / m²); when a black chess piece is placed, it switches to 135° refracted warm black light (brightness stable at 60 cd / m²); and when there are no pieces, it switches to 90° refracted soft light (brightness stable at 40 cd / m²). The switching response time is less than 0.5 seconds. A vibration feedback unit is installed at the bottom of the chessboard, with two vibration frequencies set according to different scenarios such as key breakpoints and life-and-death points. The vibration frequency is 2 times / second for key breakpoints and 1 time / second for life-and-death points. Teachers can adjust the vibration intensity to high, medium, and low levels (corresponding to amplitudes of 0.5mm, 0.3mm, and 0.1mm respectively) via the control panel to meet the perceptual needs of students of different ages. When implementing the adaptive teaching module, the system initially collected teaching evaluation data from each Go teacher over the past three months. Assume teacher A received a total of 20 evaluations (Z1-Z1) over the past three months. 20 The time interval between the scoring time and the current time is △T1-△T. 20Taking a weighting constant B=30 days, and using one score (Zᵢ=9 points, △Tᵢ=10 days) as an example, the weight of this score is calculated according to the formula: ((10+30) / (4×10+2×30))+1 / 2=0.9 (i.e., 90%, within the 75%-100% range). All 20 scores are weighted in this way and summed, then divided by 20 to obtain Teacher A's professional dynamic score P=8.6 points. The system establishes a user chess game behavior feature database by collecting data from 100 past chess games. Taking student Xiaoming (10 years old, chess level 3) as an example, his average move interval is 15 seconds, his frequency of undoing moves is 3 times per game, and his average thinking time for key moves is 40 seconds. Based on this, the system constructs a chess skill deficiency model and finds that Xiaoming has a significant deficiency in the "life and death calculation" stage. In the homework practice scenario, 10 life and death calculation problems are generated for him. For related reinforcement exercises, in a proficiency assessment scenario, if Xiaoming answers three consecutive Level 3 difficulty questions correctly, the system will activate a difficulty jump algorithm to directly enter Level 2 difficulty assessment. If Xiaoming's accuracy rate in Level 2 difficulty assessment is less than 60%, the system will automatically drop back to Level 3 difficulty and generate a reinforcement plan consisting of 5 Level 2 error-prone questions and 10 Level 3 basic questions. For underage students, a two-level supervision system is configured. Taking student Xiaohong (8 years old) as an example, her parents set a daily usage time threshold of 60 minutes through the parent app, and the teacher sets the "entertainment battle" function to be locked through the teacher app. When Xiaohong's daily usage time reaches 60 minutes, the system automatically saves the current progress, first locking the "entertainment battle" function, and if she does not exit after 5 minutes, the account will be completely locked. If Xiaohong tries to enter the "entertainment battle" function, the system will prompt that the function has been locked by the teacher. When implementing the eye health-linked anti-addiction module, a three-dimensional anti-addiction model is constructed. The first dimension is the dynamic allocation of energy points. Taking student Xiao Li (12 years old) as an example, when he uses the platform in the morning, the built-in light sensor of the chessboard detects an ambient light intensity of 500 lux, and the distance sensor detects that the distance between Xiao Li and the chessboard is 30cm. The system gives an eye health score of 85 points and allocates 10 energy points to him. Xiao Li consumes 2 energy points per game and 1 energy point per assignment. When he has 2 energy points left, the system only opens the eye protection mode for replaying games (brightness reduced by 50%, and a forced 2-minute break every 10 minutes). The second dimension is the closed-loop control of eye usage time. Based on Xiao Li's age of 12, the daily eye usage limit is set to 90 minutes. When Xiao Li's cumulative daily usage time reaches 9... At 0 minutes, the system automatically generates an eye exercise tutorial animation (5 minutes long). After completing the animation, an additional 30 minutes of time is unlocked. The third dimension is a focus-related mechanism. During the game, pressure sensors detect Xiao Li's touch. If there are 5 touches without the intention to place a piece within 1 minute, the system judges it as a lack of focus. After 3 instances of lack of focus, a reminder message is sent to Xiao Li's parent app, and the current game is paused. If the vision test data of student Xiao Wang (14 years old) over the past 3 months shows a decrease of 60 degrees in vision, the system automatically reduces his daily usage time threshold by 20% from 120 minutes (adjusted to 96 minutes) and pushes a vision protection-specific training assignment containing 5 eye relaxation exercises and 10 Go visual training questions, requiring Xiao Wang to complete 3 times a week. When the chess intelligence interaction module is implemented, the system analyzes the data of the student Xiao Zhang (15 years old) from the past 10 games, calculating his attack rate of 60% (proportion of proactive moves), defense rate of 30% (proportion of defensive moves), and sacrifice rate of 10% (number of proactive sacrifices / total number of moves). An "aggressive attacking" style label is generated for Xiao Zhang. During matchmaking, Xiao Zhang is prioritized to be matched with Xiao Liu (16 years old, attack rate 30%, defense rate 60%, sacrifice rate 10%), a student with a "steady defensive" style. The system also generates a strategy suggestion: "For a steady defensive opponent, strengthen flank breakthroughs and reduce central entanglement." Xiao Zhang can manually adjust the pairing preference in his personal settings, increasing the weight of "steady defensive" opponents to 80%. The system adjusts subsequent pairing priorities based on this setting. After Xiao Zhang and Xiao Liu's game, the system uses a multi-dimensional game analysis algorithm to generate a replay report, calculating Xiao Zhang's piece control cross-space efficiency. The number of moves was 85 (total number of moves was 120, space efficiency ≈ 70.8%). In terms of time efficiency, Xiao Zhang's average thinking time for key moves was 55 seconds (better than the average of 65 seconds for students of the same level). In terms of tactical coherence, 80% of Xiao Zhang's moves were consistent with his "aggressive attacking" tactical intentions. At the same time, based on Xiao Zhang's past data on remedial exercises, the intelligent robot teacher found that Xiao Zhang was weak in the "ko tactic" and focused on explaining three key steps related to ko during the review. During the game and review, Xiao Zhang input "Is this move a reverse boot?" via voice. The system's dedicated Go terminology translation unit converted the voice into text in real time and added an explanation and annotation: "Reverse boot, a Go term, refers to the move of capturing the opponent's stones after the opponent has captured one's own stones. It is often used in life-and-death struggles." If Xiao Zhang input the text "Golden Rooster Stands Alone", the system will also provide the corresponding voice translation and explanation. When implementing the dynamic self-optimization module, a dual-cycle professional score system is constructed. The first cycle is the dynamic verification of the professional foundation score. Teacher B uploads a 5-dan certificate issued by the Go Association. The system verifies the certificate's validity by connecting to the local Go Association's official certificate storage platform via blockchain. Based on the certificate level (5-dan), a foundation score of 90 points is assigned. The system is set to automatically re-verify every quarter. At the beginning of the next quarter, a certificate verification reminder is automatically sent to Teacher B. After Teacher B re-uploads the certificate, the system completes the verification and maintains the foundation score of 90 points. The second cycle is the iterative optimization of the Go teacher's professional score. Teacher B's dynamic professional score P = The service conversion factor was calculated as 8.8 points. Data from 10 students who cancelled their service within 7 days was excluded. Data from 20 students who subsequently purchased services after achieving their learning goals were weighted twice, resulting in a service conversion factor of 85%. The chess skill improvement factor was calculated as the average increase in students' skill assessment scores after learning from Teacher B (based on data from 30 students, the average improvement was 1.5 levels, equivalent to a chess skill improvement factor of 80%). The Go teacher's professional score was calculated using the formula: (8.8 × 40%) + (85% × 30%) + (80% × 30%) = 4.015 points. The professional level assessment result = (90 × 40%) + (4.015 × 60%) = 38.409 points (which can be converted to a percentage system in practical applications); Based on Teacher B's final professional level assessment result, in terms of service ranking weight, the system combines student profiles (such as chess level, learning goals, etc.) to prioritize displaying Teacher B's courses in the interface of students with chess level 3-5 and whose learning goal is to improve practical skills. In terms of remuneration calculation weight, the basic remuneration is set at 200 yuan per lesson, and Teacher B's service remuneration per order = 200 × (1 + 4.015 / 100) ≈ 20 The fee is 8.03 yuan. If Teacher B's final professional level assessment result is ≥90 points (out of 100), an additional 15% bonus will be given. The service fee per order = 200 × (1 + professional score / 100) × (1 + 15%). Based on Teacher B's final professional level assessment result (assuming a score of 75 out of 100), the system will push courses such as "Advanced Go Mid-Game Tactics" and "Student Psychological Guidance Techniques" to help him improve his abilities. After Teacher B completes these courses, the system will give him an additional 5% bonus to his base score (increasing his base score from 90 to 94.5), forming a closed-loop optimization of assessment-improvement-reassessment. When the secure encrypted data interaction module is implemented, all data (such as personal information, game data, teaching data, etc.) transmitted by students, teachers, and parents during platform use is encrypted using the national cryptographic SM4 algorithm. The data interaction between the system backend and the edge computing unit also uses this encryption method. When student Xiao Li uses the dynamic interactive Go board in an offline environment, the edge computing unit generates a simplified review report for Xiao Li based on the locally stored mini tactical library (containing 1,000 basic tactical cases). The report includes analysis of key steps in the game, comments on the application of basic tactics, etc. When Xiao Li connects to the network, the system automatically synchronizes the offline review data to the cloud and obtains a complete review report containing detailed tactical breakdown, comparative analysis of similar games, personalized improvement suggestions, etc. After three months of operation, the platform's effectiveness was evaluated. Regarding teaching outcomes, data from 800 students showed an average improvement of 0.8 levels in chess skill (a 166.7% increase compared to the traditional 0.3 levels), with homework completion rate rising from 75% to 92% and exam pass rate increasing from 80% to 95%. In terms of teacher professionalism, the final professional evaluation results for 25 teachers showed an average improvement of 8 points, with 8 teachers receiving additional rewards for outstanding evaluations. Teacher motivation significantly increased, and course booking rates rose by 40%. Regarding eye health and anti-addiction measures, a 3D anti-addiction model and eye health protection measures were implemented. The system ensures that students' average daily usage time is kept within the prescribed thresholds (75-90 minutes for students aged 6-12 and 100-120 minutes for students aged 13-18). The number of students experiencing vision decline has decreased by 30%, and parental satisfaction with the platform has reached 90%. In terms of hardware user experience, the dynamic interactive Go board's pressure sensitivity accuracy, light effect mode switching response speed, and vibration feedback effect have all been recognized by students and teachers. A questionnaire survey shows that 92% of students believe the Go board is easy to operate and has clear light effects, and 88% of teachers believe the vibration feedback unit helps students perceive key positions on the board. Special Note: The terms "embodiments" and similar expressions used in this specification refer to specific features, elements, or characteristics described in connection with those embodiments, which are included in the general description of the embodiments in this application. The appearance of the same expression in multiple places in the specification does not necessarily mean that it specifically refers to the same embodiment. That is, when a specific feature, element, or characteristic is described in connection with any embodiment, the intention is to claim that such a feature, element, or characteristic is implemented in conjunction with other embodiments, and this is included within the scope of the claims of this application. The embodiments are multiple illustrative examples of the present invention described with reference to the logical framework and concept of the invention, but the scope of protection of the present invention is not limited thereto. Those skilled in the art can design many other modifications and implementation methods within the framework of the technical solutions of the present invention, and can make various non-essential variations and improvements to the key points and / or layout of the technical solutions. Other uses will be obvious to those skilled in the art, and non-substantial changes or substitutions can be easily conceived. These modifications and implementation methods will fall within the scope and spirit of the principles disclosed in this application.

Claims

1. An intelligent, self-optimizing interactive Go teaching platform system, characterized in that: The system includes a dynamic interactive Go board hardware module, a deep collaborative software module, and a secure encrypted data interaction module. The deep collaborative software module includes an adaptive teaching module, an eye health-linked anti-addiction module, a Go intelligence interaction module, and a dynamic self-optimization module. The adaptive teaching module includes a dynamic professional score calculation model for Go teachers. Go teacher users have a number of scores in the Go teaching interaction platform system. The weight of the scores is decayed according to the interval △T between the current calculation time T1 and the scoring time T2. The professional dynamic score of the Go teacher user is calculated according to the following formula. ; Where: P is the professional dynamic score of the Go teacher user, which is the score given by students after the Go teacher user provides teaching. All scores are weighted and adjusted according to the time interval between the evaluation time and the current time, and the fluctuation range of the weight is compressed to the range of 0%-25%, that is, the result of the formula involved is compressed to the range of 75% to 100%; B is a weighted constant for adjusting the sensitivity of the user rating time interval to the weight coefficient of the professional dynamic score of the Go teacher. The dynamic self-optimization module, designed for Go teacher users, constructs a dual-cycle professional score system: The first cycle is dynamic verification of the professional foundation score. After a Go teacher user uploads their qualification certificate, the system verifies the certificate's validity through blockchain storage, connecting with the official Go Association's storage platform. A foundation score is assigned based on the certificate's level, and this verification is automatically repeated quarterly. The second cycle is iterative optimization of the Go teacher's professional score. In addition to the Go teacher user's dynamic professional score P, a service conversion factor is added, namely the percentage of users who complete their learning goals after purchasing services, and a Go skill improvement factor, namely the average increase in students' skill assessment scores after learning with the Go teacher user. The Go teacher's professional score is calculated as follows: Go teacher's professional score = (P × 40%) + (service conversion factor × 30%) + (go skill improvement factor × 30%). The final professional level assessment result is calculated by combining 40% of the professional foundation score and 60% of the Go teacher's professional score, and then weighted by two factors: first, a service ranking weight, which adjusts the service display ranking based on user profile matching; and second, a compensation calculation weight, specifically calculated as follows: The service fee for each Go teacher user is calculated as follows: Basic fee × (1 + Go teacher's professional score / 100). An additional 15% bonus will be awarded if the evaluation result is ≥90.

2. The intelligent self-optimizing Go teaching interactive platform system according to claim 1, characterized in that, The dynamic interactive Go board hardware module features a 1:1 scale structure with built-in pressure sensors and LED light-and-shadow linkage units at each intersection. These units include a 0.1mm precision pressure sensor, adjustable three-primary-color eye-protection LED lights, and micro-angle light-reflecting lenses. The pressure sensor identifies the user's placement force, triggering the LED lights to output corresponding light and shadow intensities. The micro-angle light-reflecting lenses switch between three exclusive lighting modes: 45° refracted cool white light for white pieces, 135° refracted warm black light for black pieces, and 90° refracted soft light for a blank state. The board surface is covered with a 2.5D anti-blue light polarization layer. The pressure sensor and LED light-and-shadow linkage units also include a temperature sensor. When the detected user touch temperature is ≥37℃, the LED brightness is automatically reduced by 10%, and a "Resting is recommended" message is displayed at the edge of the board.

3. The intelligent self-optimizing Go teaching interactive platform system according to claim 1, characterized in that, The adaptive teaching module also includes a chess skill deficiency model built based on a user chess game behavior feature database, including move intervals, frequency of undoing moves, and key move thinking time. This model generates remedial assignments for practice scenarios. The skill assessment scenario uses a difficulty-skipping algorithm: if a user answers three questions correctly in a row, they skip the current difficulty level and proceed directly to the next higher level. The Go competition scenario includes a tactical reminder suppression mechanism with reminder thresholds set based on the user's skill level. Simultaneously, a two-tiered supervision system is configured for underage academic users: Level 1 allows parents to set daily / weekly / monthly usage time thresholds; Level 2 allows teachers to lock specific functions. When a user triggers the time threshold or violates the locked function, the system automatically saves the current progress and initiates a gradual lock, first locking entertainment functions, and then completely locking them if the user does not exit after 5 minutes. The chess skill deficiency model also introduces an opponent skill correction factor: if a user defeats an opponent two levels higher than themselves, the corresponding tactical deficiency judgment weight is reduced by 35%.

4. The intelligent self-optimizing Go teaching interactive platform system according to claim 1, characterized in that, The eye health-linked anti-addiction module constructs a three-dimensional anti-addiction model: The first dimension is the dynamic allocation of stamina points. Based on the user's daily eye health score, collected by the chessboard's built-in light and distance sensors, the score range is 0-100. A score ≥80 allocates 10 stamina points, and a score <60 allocates 5 stamina points. Each game consumes 2 stamina points, and each assignment consumes 1 stamina point. When stamina points are insufficient, only the eye protection mode for replaying games is enabled, with brightness reduced by 50% and a mandatory 2-minute break every 10 minutes. The second dimension is the closed-loop control of eye usage time. Based on the user's age, eye usage limits are set: ≤90 minutes per day for 6-12 years old, and ≤120 minutes per day for 13-18 years old. When the limit is reached, an eye exercise guidance animation is automatically generated. Only after completing the animation can an additional 30 minutes of time be unlocked. The third dimension is the focus correlation mechanism, which identifies the frequency of invalid touches by users through pressure sensors. If there are ≥5 touches without the intention to place a piece within 1 minute, it is judged as a lack of focus. If there are 3 instances of lack of focus, a reminder will be triggered to monitor the user and the current operation will be paused. The eye health score also combines the user's historical vision test data. If the vision has decreased by ≥50 degrees in the past 3 months, the daily usage time threshold will be automatically reduced by 20%, and vision protection training assignments will be pushed.

5. The intelligent self-optimizing Go teaching interactive platform system according to claim 1, characterized in that, The chess-playing interaction module features a style-matching engine: by analyzing the user's attack rate (proportion of proactive moves), defense rate (proportion of defensive moves), and sacrifice rate (number of proactive sacrifices / total number of moves) from the last 10 games, it constructs style tags such as aggressive or conservative. During pairing, it prioritizes matching users with complementary styles (aggressive users with defensive users) and generates style-based strategy suggestions. A dedicated Go terminology translation unit is configured, supporting real-time voice / text translation with accompanying terminology annotations. The debriefing guidance unit employs a multi-dimensional game analysis algorithm, generating debriefing reports based on three dimensions: spatial efficiency (number of control points / total number of moves), time efficiency (average thinking time for key moves), and tactical coherence (matching tactical intent with move placement). Simultaneously, the intelligent robot teacher unit, based on historical data from deficiencies and reinforcement exercises, focuses on explaining tactics the user hasn't mastered during debriefing. The style-matching engine supports style preference settings, allowing users to manually adjust pairing preferences, and the system adjusts pairing weights according to user settings.

6. The intelligent self-optimizing Go teaching interactive platform system according to claim 1, characterized in that, When calculating the service conversion factor, the dynamic self-optimization module excludes user data that cancels services within 7 days and assigns double the weight to user data that purchases services after completing the learning objectives, ensuring the accuracy of the factor.

7. The intelligent self-optimizing Go teaching interactive platform system according to claim 1, characterized in that, The edge computing unit of the secure encrypted data interaction module also supports offline intelligent review. In offline mode, it can generate a simplified review report based on the locally stored mini tactical library, and automatically synchronize to the cloud to obtain the complete report after connecting to the network.

8. The intelligent self-optimizing Go teaching interactive platform system according to claim 1, characterized in that, The dynamic interactive Go board hardware module is also equipped with a vibration feedback unit. When the user places a stone at a critical break point or a vital point for life and death, it outputs micro-vibrations of different frequencies to help the user perceive the key positions on the board. The vibration intensity can be adjusted through the monitoring user's console.

9. The intelligent self-optimizing Go teaching interactive platform system according to claim 3, characterized in that, The difficulty level jump algorithm of the adaptive teaching module is equipped with a fallback mechanism. If the user's accuracy rate is less than 60% after jumping to a higher level, the system will automatically fall back to the previous difficulty level and generate a reinforcement plan for the failed jump.

10. The intelligent self-optimizing Go teaching interactive platform system according to claim 1, characterized in that, The dynamic self-optimization module is also configured with a growth path for Go teacher users. Based on the final professional level assessment results, it pushes ability improvement suggestions to Go teacher users. After completing the suggested courses, users can get an extra 5% bonus to their basic score, forming a closed-loop optimization of assessment-improvement-reassessment.

Images