A learning progress monitoring method and system of an online education platform

Abstract

This invention provides a method and system for monitoring learning progress on an online education platform, applicable to the field of online data processing. Through multi-dimensional data collection and intelligent analysis, this invention improves the accuracy of learning behavior monitoring, precisely judges users' learning achievements, ensures the objectivity of assessment, and comprehensively tracks users' learning behavior by combining multiple types of learning data, avoiding the limitations of single-dimensional assessment. Furthermore, by monitoring active learning, passive learning, and non-learning behaviors, it further refines users' learning status, improves data authenticity, and collects personalized learning habit data to dynamically construct an Ebbinghaus forgetting curve, enabling precise review time recommendations. Combined with the changing trends of test scores, it can adaptively optimize review periods, ensuring users review at the optimal time and improving knowledge retention.

Description

Technical Field

[0001] This invention relates to the field of online data processing, and in particular to a method and system for monitoring the learning progress of an online education platform. Background Technology

[0002] With the rapid development of online education, learning progress monitoring technology has become an important means of measuring students' learning outcomes. Current online education platforms mainly rely on data analysis and artificial intelligence technology to track learners' learning paths, course completion, assignment submission records, and exam scores.

[0003] However, existing learning monitoring technologies mainly rely on explicit data, such as video viewing time and assignment submission status, while lacking effective monitoring methods for learners' implicit behaviors such as reading comprehension, pauses in thought, and note-taking. In other words, there is a lack of records of learners' behavior in informal learning (such as independent searching, discussion, and practical activities), resulting in incomplete assessment of learning progress. Summary of the Invention

[0004] This invention aims to address how to improve the accuracy of learning behavior monitoring, and provides a method and system for monitoring learning progress on an online education platform.

[0005] The present invention employs the following technical means to solve the technical problem:

[0006] This invention provides a method for monitoring learning progress on an online education platform, comprising:

[0007] Based on the learning performance preset by the education platform for platform users, identify the test scores of the platform users on the education platform;

[0008] Determine whether the test results meet the learning performance target;

[0009] If not, then restrict the platform users' exam privileges on the education platform, collect the platform users' behavioral information based on the platform users' multi-type learning data, and detect the learning progress gap of the platform users in the current learning quarter based on the historical learning achievements pre-collected by the education platform. The multi-type learning data specifically includes basic data, interaction data, and biological data, and the behavioral information specifically includes active learning behavior, passive learning behavior, and non-learning behavior.

[0010] Determine whether the learning progress gap exceeds a preset threshold;

[0011] If the data exceeds the limit, the platform user's learning habit data is collected. Based on the learning habit data, the Ebbinghaus forgetting curve of the platform user is dynamically constructed. The optimal review period for the knowledge point is calculated through the Ebbinghaus forgetting curve. The optimal review period is adaptively adjusted according to the test results. The learning habit data specifically includes the average daily study time, the habitual study time period, and the speed at which the user has mastered the knowledge in the past.

[0012] Furthermore, the step of collecting the behavioral information of the platform users also includes:

[0013] Based on the connection device preset by the platform user, the platform learns and interacts with the connection device through the education platform to obtain the characteristic information of the platform user, wherein the characteristic information specifically includes facial expressions, eye movement trajectory, head movement and body posture.

[0014] Determine whether the feature information matches the identity features pre-entered by the platform user;

[0015] If so, then based on the feature information, the pupil trajectory of the platform user when facing the connected device is tracked, and based on the pupil trajectory, the key features corresponding to the platform user during the learning process are extracted synchronously, wherein the key features specifically include tone of voice, speaking speed, pauses and volume changes.

[0016] Furthermore, before the step of dynamically constructing the Ebbinghaus forgetting curve for the platform users, the method further includes:

[0017] Based on the knowledge mastery standards preset by the education platform for its users, practice data of the users on preset knowledge points is collected. Specifically, the practice data includes accuracy, completion time, and number of attempts.

[0018] Determine whether the practice data meets the knowledge mastery standard;

[0019] If not, then based on the practice data, obtain the practice error types of the platform users, identify the error sources of the preset knowledge points according to the practice error types, and divide the misconception distribution corresponding to the error sources on the education platform. Specifically, the practice error types include conceptual errors, calculation errors, and careless errors.

[0020] Furthermore, before the step of detecting the learning progress gap of the platform users in the current learning quarter, the method further includes:

[0021] Based on the course content of the current learning quarter, obtain the average learning progress of all platform users on the course content, wherein the course content specifically includes chapter progress, exercises and assignments, key quizzes and expected learning time;

[0022] Determine whether the platform users can complete the average learning progress;

[0023] If not, then based on the behavioral information, calculate the learning lag rate of the platform user, and based on the learning lag rate, benchmark against the lag level preset by the education platform. Through the lag level, dynamically adjust the tutoring content of the platform user on the education platform. The lag level specifically includes slight lag, moderate lag, and severe lag, and the tutoring content specifically includes recommending priority learning tasks, providing personalized review content, and emergency intervention contact persons.

[0024] Furthermore, the step of determining whether the test score can achieve the learning performance includes:

[0025] Based on the learning performance structure preset by the education platform, the score weights of the test scores are identified;

[0026] Determine whether the weighting of the grades meets the various standards of the learning performance structure;

[0027] If not, then based on the aforementioned performance weights, collect the knowledge gap information corresponding to the platform user, mark the knowledge modules of the knowledge gap information, and divide the knowledge content that the platform user needs to tutor from the knowledge modules.

[0028] Furthermore, the step of determining whether the learning progress gap exceeds a preset threshold also includes:

[0029] Based on the learning cycle preset by the platform users, the learning progress of the platform users after they have completed the learning is dynamically updated.

[0030] Determine whether the learning progress has reached the preset minimum progress limit for a single session;

[0031] If so, the learning duration of the platform user is generated based on the content already learned by the platform user, and the learning objectives of the platform user are dynamically updated based on the learning duration. The content already learned specifically includes course chapter information, exercise information, and test information completed within the current period.

[0032] Furthermore, after the step of identifying the test scores of platform users on the education platform based on the learning performance preset by the education platform, the method further includes:

[0033] Identify the learning interaction methods pre-selected by the platform users on the education platform, wherein the learning interaction methods specifically include video learning, text learning, and interactive learning;

[0034] Determine whether the learning interaction method is suitable for the current learning quarter;

[0035] If not, the learning path of the platform user will be dynamically adjusted based on the test results. The learning path specifically includes the course content structure and the exercise assessment method.

[0036] This invention also provides a learning progress monitoring system for an online education platform, comprising:

[0037] The identification module is used to identify the test scores of the platform users on the education platform based on the learning performance preset by the education platform.

[0038] The judgment module is used to determine whether the test score can achieve the learning performance.

[0039] The execution module is used to restrict the platform user's examination privileges on the education platform if no, collect the platform user's behavioral information based on the platform user's multi-type learning data, and detect the learning progress gap of the platform user in the current learning quarter based on the historical learning achievements pre-collected by the education platform. The multi-type learning data specifically includes basic data, interaction data and biological data, and the behavioral information specifically includes active learning behavior, passive learning behavior and non-learning behavior.

[0040] The second judgment module is used to determine whether the learning progress gap exceeds a preset threshold.

[0041] The second execution module is used to collect the learning habit data of the platform users if the limit is exceeded, dynamically construct the Ebbinghaus forgetting curve of the platform users based on the learning habit data, calculate the best review period for the platform users on the knowledge points through the Ebbinghaus forgetting curve, and adaptively adjust the best review period according to the test results. The learning habit data specifically includes the average daily study time, the habitual study time period, and the speed at which the knowledge was mastered in the past.

[0042] Furthermore, the execution module also includes:

[0043] The acquisition unit is used to acquire the user's feature information by interacting with the connected device through the education platform based on the connection device preset by the user of the platform. The feature information specifically includes facial expressions, eye movement trajectory, head movement and body posture.

[0044] The judgment unit is used to determine whether the feature information matches the identity features pre-entered by the platform user;

[0045] An execution unit is configured to, if so, track the pupil trajectory of the platform user when facing the connected device based on the feature information, and simultaneously extract the key features corresponding to the platform user during the learning process based on the pupil trajectory, wherein the key features specifically include tone of voice, speech rate, pauses, and volume changes.

[0046] Furthermore, it also includes:

[0047] The data collection module is used to collect practice data of the platform users on preset knowledge points based on the knowledge mastery standards preset by the education platform. The practice data specifically includes accuracy rate, completion time and number of times the questions are answered.

[0048] The third judgment module is used to determine whether the practice data can reach the knowledge mastery standard;

[0049] The third execution module is used to, if not, obtain the error type of the platform user based on the exercise data, identify the error source of the preset knowledge point based on the error type, and divide the misconception distribution corresponding to the error source on the education platform. The error type specifically includes conceptual error, calculation error and carelessness error.

[0050] This invention provides a method and system for monitoring the learning progress of an online education platform, which has the following beneficial effects:

[0051] This invention improves the accuracy of learning behavior monitoring through multi-dimensional data collection and intelligent analysis, accurately judges users' learning achievement, ensures the objectivity of the assessment, and comprehensively tracks users' learning behavior by combining multiple types of learning data, avoiding the limitations of single-dimensional assessment. At the same time, by monitoring active learning, passive learning, and non-learning behaviors, it further refines users' learning status, improves the authenticity of data, and collects users' personalized learning habit data to dynamically construct the Ebbinghaus forgetting curve, enabling precise review time recommendations. Combined with the changing trends of test scores, it can adaptively optimize review periods to ensure that users review at the best time and improve knowledge retention. Attached Figure Description

[0052] Figure 1 This is a flowchart illustrating an embodiment of the learning progress monitoring method for an online education platform according to the present invention.

[0053] Figure 2 This is a structural block diagram of an embodiment of the learning progress monitoring system of the online education platform of the present invention. Detailed Implementation

[0054] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. The realization of the purpose, functional features, and advantages of the invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings.

[0055] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0056] Reference Appendix Figure 1 A learning progress monitoring method for an online education platform according to an embodiment of the present invention includes:

[0057] S1: Based on the learning performance preset by the education platform for platform users, identify the test scores of the platform users on the education platform;

[0058] S2: Determine whether the test results can achieve the learning performance;

[0059] S3: If not, then restrict the platform user's exam privileges on the education platform, collect the platform user's behavioral information based on the platform user's multi-type learning data, and detect the learning progress gap of the platform user in the current learning quarter based on the historical learning achievements pre-collected by the education platform. The multi-type learning data specifically includes basic data, interaction data, and biological data, and the behavioral information specifically includes active learning behavior, passive learning behavior, and non-learning behavior.

[0060] S4: Determine whether the learning progress gap exceeds a preset threshold;

[0061] S5: If the above is exceeded, the learning habit data of the platform users will be collected. Based on the learning habit data, the Ebbinghaus forgetting curve of the platform users will be dynamically constructed. The optimal review period for the knowledge points of the platform users will be calculated through the Ebbinghaus forgetting curve. The optimal review period will be adaptively adjusted according to the test results. The learning habit data specifically includes the average daily study time, the habitual study time period, and the speed at which the knowledge was mastered in the past.

[0062] In this embodiment, the system identifies the user's test scores on the educational platform based on pre-set learning performance targets. The system then determines whether these test scores meet the learning performance targets and executes corresponding steps accordingly. For example, when the system determines that a user's test scores on the educational platform meet the learning performance targets, the system considers the user's learning progress and knowledge mastery to meet the expected goals, meaning the current learning path and review strategy are effective. The system records the user's current learning stage completion status, marking the knowledge point or course as "mastered" or "met the target," and updates the user's learning achievements in the learning record to improve the completeness of the learning profile. It also recommends higher-level learning content, such as... Advanced courses, case studies, and practical training are provided to help users deepen their understanding and application of knowledge. Users can choose whether to proceed to the next stage of learning or take short breaks to optimize their learning pace. Based on historical learning data, future learning paths are adjusted to better align with users' learning habits and interests. For example, if the system determines that a user's test scores on the educational platform are not meeting learning performance expectations, it will consider the user's learning progress and knowledge acquisition speed to be below expectations, indicating potentially ineffective learning. In this case, the system will temporarily restrict the user's exam access on the educational platform, based on various types of learning data, including basic data and interaction data. By combining biological data with platform user behavior information, including active learning, passive learning, and non-learning behaviors, and based on the platform's pre-collected historical learning achievements, the system detects the learning progress gap of users in the current learning quarter. By comparing test scores with learning performance, the system can promptly identify user learning deficiencies, preventing users from continuing to advance in courses without mastering the knowledge, thus avoiding ineffective learning. Restricting exam access ensures that users do not try to pass by chance through repeated attempts, but rather guide them to solve learning problems first and truly master the knowledge before taking tests. Simultaneously, by analyzing the platform's historical learning achievements, the system helps to determine the user's progress gap in the current learning quarter. To assess whether a user's learning progress meets the target, the system provides personalized learning path adjustment plans. For users with significant learning gaps, the system can push supplementary learning resources, increase targeted exercises, and optimize review strategies to ensure that users are not passively pushed to more complex learning stages before mastering the knowledge points. Furthermore, by intelligently analyzing learning progress and user behavior, the platform can provide more accurate and personalized learning support, making learning assessment more scientific. Through real-time monitoring and dynamic adjustment of learning status, the system ensures that users truly master the knowledge, rather than just "passing the exam," thereby improving the overall learning quality. The system then determines whether the user's learning progress gap in the current learning quarter exceeds a pre-set threshold and executes corresponding steps accordingly.For example, when the system determines that a user's learning progress gap in the current learning quarter does not exceed a pre-set threshold, the system will consider the user's learning progress to be basically in line with expectations. Even if test scores do not yet meet learning performance standards, it may be due to short-term fluctuations, temporary poor performance, or incomplete understanding of some knowledge points, rather than long-term learning problems. The system will appropriately increase personalized review tasks, such as inserting targeted reinforcement exercises into the learning plan, to help users consolidate the knowledge points they performed weakly in the test. Combining user learning habit data (such as learning time periods and learning frequency), the system will fine-tune its review recommendation strategy to better match the user's cognitive rhythm, while providing positive feedback through the learning platform. Incentives, such as small rewards, badges, and learning incentive notifications, are used to maintain user motivation. Learning reports are generated to provide feedback on the user's current learning status and offer suggestions, such as "Your learning progress is basically up to standard, but there is still room for improvement in some knowledge points; appropriate review is recommended." The system continues to track user performance changes in subsequent tests. If test scores show significant improvement, the user's learning path is confirmed to be effective; if they remain below the learning performance target, further intervention is considered. For example, when the system determines that a user's learning progress gap in the current learning quarter exceeds a pre-set threshold, the system considers the user's learning progress unsatisfactory and collects data on the user's learning habits. Habitual data specifically includes average daily study time, habitual study time periods, and the speed at which past knowledge was mastered. Based on this study habit data, an Ebbinghaus forgetting curve is dynamically constructed for platform users. This curve is used to calculate the optimal review time for each user's knowledge points, and the system adaptively adjusts the optimal review time based on different test scores. By dynamically constructing an Ebbinghaus forgetting curve based on individual user data, the system can accurately predict the rate at which users forget knowledge points, thus pushing review tasks at the appropriate time. This avoids wasting time by reviewing too early or causing excessive forgetting by reviewing too late. The system also adaptively adjusts based on user test scores, ensuring that the review pace matches the user's level of knowledge mastery. To ensure effective reinforcement of learning content, the system can identify users' learning patterns and optimize review schedules accordingly. For example, for users with fragmented study time, the system can appropriately increase short, high-frequency review tasks, while for users with concentrated study sessions, the review intervals can be optimized to better align with memory patterns. This personalized adjustment can effectively reduce learning progress gaps, help inefficient learners improve their learning outcomes, and ensure that users with different test scores receive appropriate learning suggestions, making the learning path more flexible. For example, for users with lower test scores, the system can increase review frequency to reinforce key knowledge, while for users with scores close to passing, repetitive reviews can be appropriately reduced to avoid learning fatigue.

[0063] It should be noted that the platform collects learning habit data from its users. Based on this data, an Ebbinghaus forgetting curve is dynamically constructed for each user. The optimal review period for each knowledge point is then calculated using this forgetting curve. A specific example is as follows:

[0064] Suppose that Xiaoming, a user on the platform, is a college student who is using the educational platform to learn about "Newton's Three Laws of Motion"; the system has recorded the following data about his learning habits:

[0065] Average daily study time: 2 hours;

[0066] My preferred study time is 19:00-21:00.

[0067] In the past, it typically took four reviews to achieve a 90% mastery rate of knowledge.

[0068] Forgetting rate: The system analyzed his past learning data and found that he forgot 40% on the first day, 70% on the third day, and 90% on the seventh day, indicating that Xiaoming's forgetting rate is relatively fast;

[0069] Recent test results: In the test on March 5th, Xiaoming scored 50% on this knowledge point, indicating a poor grasp of the material.

[0070] The system's processing flow: First learning session (March 1st): Xiaoming learned "Newton's Three Laws" from 19:00 to 21:00 on March 1st; the system detected that his forgetting curve was relatively steep, so a personalized review plan was immediately formulated after the learning session;

[0071] The system generates an initial review plan.

[0072] March 2nd (Day 1): First review (to prevent short-term forgetting and consolidate memory);

[0073] March 4 (Day 3): Second review (strengthening memory and improving proficiency);

[0074] March 7 (Day 6): Third review (to improve long-term memory);

[0075] March 14 (Day 13): Fourth review (to ensure long-term mastery of key knowledge points);

[0076] Test scores will affect revision adjustments (March 5th);

[0077] In the test on March 5th, Xiaoming scored 50% on Newton's three laws, indicating a lack of understanding.

[0078] The system detected low test scores and adjusted the study plan, making the following optimizations:

[0079] Added intensive review on March 6th (with extra practice);

[0080] The review period on March 7th has been extended (to provide a more in-depth review).

[0081] Added review tasks for March 10th (shortening the interval and accelerating knowledge consolidation);

[0082] Revised final review plan:

[0083] March 2nd (Day 1): First review session;

[0084] March 4th (Day 3): Second review session;

[0085] March 6 (New): Intensive Review (The system will push extra practice questions to improve understanding);

[0086] March 7 (Day 6): Third review session (extended time);

[0087] March 10 (Added): Additional review (to check on reinforcement);

[0088] March 14 (Day 13): Fourth review session;

[0089] In summary, the ultimate effect of the above examples is that the system makes Xiaoming's study plan more precise, effectively reduces forgetting, and improves test scores. This is because the system dynamically adjusts review time based on Xiaoming's forgetting patterns and test feedback, making learning more efficient. Simultaneously, the system combines Xiaoming's preferred study time with the push of review tasks during his most comfortable periods, improving learning effectiveness. In other words, through personalized Ebbinghaus forgetting curve analysis and test data analysis, the system achieves intelligent review scheduling, making Xiaoming's learning process more targeted and efficient.

[0090] In this embodiment, step S3, which involves collecting the behavioral information of the platform users, further includes:

[0091] S31: Based on the connection device preset by the platform user, the platform interacts with the connection device through the education platform to obtain the characteristic information of the platform user, wherein the characteristic information specifically includes facial expressions, eye movement trajectory, head movement and body posture.

[0092] S32: Determine whether the feature information matches the identity features pre-entered by the platform user;

[0093] S33: If so, then based on the feature information, track the pupil trajectory of the platform user when facing the connected device, and based on the pupil trajectory, synchronously extract the key features corresponding to the platform user during the learning process, wherein the key features specifically include tone of voice, speech rate, pauses and volume changes.

[0094] In this embodiment, the system uses a pre-set connection device by the platform user to interact with the device through the education platform, obtaining the user's permissions granted to the platform. The system then acquires the user's feature information from the device's camera, specifically including facial expressions, eye movements, head movements, and body posture. The system then determines whether this feature information matches the user's pre-recorded identity features to execute corresponding steps. For example, if the system determines that the user's feature information does not match the user's pre-recorded identity features, the system considers the user interacting with the platform to be potentially not the actual user, posing a risk of identity fraud, proxy learning, or proxy testing. The system will then temporarily... The system locks the user's learning permissions, preventing them from taking exams, submitting assignments, or performing other critical operations. The user is prompted to re-verify their identity, requiring them to adjust their posture (e.g., looking directly at the camera, turning their head left or right) until more complete feature information is obtained. This information is then compared again with the platform's pre-stored identity information. Multiple authentication methods, such as SMS verification codes, facial recognition + password, and fingerprint verification, are used for further identity confirmation. If the user passes the second authentication, they are allowed to continue learning and interacting, and their feature information database is updated to accommodate possible feature changes (e.g., wearing glasses, changes in lighting). For example, when the system determines that the user's feature information matches the user's pre-entered identity features, the system considers the current activity to be... The users interacting with the learning platform are the platform users themselves. The system tracks the pupil trajectory of the platform user when facing the connected device based on this characteristic information. Based on different pupil trajectories, it simultaneously extracts key features corresponding to the platform user's learning process, specifically including tone of voice, speaking speed, pauses, and volume changes. Through pupil trajectory tracking, the system can determine whether the user's gaze is focused on the learning content, identify whether the user's attention is scattered, or whether there is prolonged lack of focus, thereby assessing their concentration. Combined with eye-tracking pattern analysis, the system can determine whether the user is quickly scanning, carefully reading, reviewing, or even staring at the same content for a long time, detecting whether there are comprehension difficulties. Simultaneously, through voice feature analysis (tone of voice, speaking speed, pauses, and volume changes), the system can further enhance the learning experience. The system can detect learners' emotional changes, such as anxiety, confusion, excitement, and fatigue. If a user's speaking speed suddenly slows down, pauses more, or volume decreases while reading aloud or answering questions, it may indicate that the user is thinking or encountering difficulties. Conversely, if the speaking speed increases and the volume rises, it may indicate that the user is more familiar with the content or more confident. In addition, the system can provide real-time adaptive adjustments based on the user's learning status. For example, when it detects a decline in concentration or significant emotional fluctuations, it can push short break reminders or adjust the learning pace to prevent learning fatigue. If it detects that the user's speech expression of a certain knowledge point is not fluent or the tone is abnormal, the system can infer that the understanding of the knowledge point may be insufficient, automatically mark the content, and provide personalized review recommendations later.

[0095] In this embodiment, before step S5 of dynamically constructing the Ebbinghaus forgetting curve of the platform user, the method further includes:

[0096] S501: Based on the knowledge mastery standards preset by the education platform for the platform users, collect practice data of the platform users on preset knowledge points, wherein the practice data specifically includes accuracy rate, completion time and number of answers;

[0097] S502: Determine whether the practice data meets the knowledge mastery standard;

[0098] S503: If not, then based on the practice data, obtain the practice error type of the platform user, identify the error source of the preset knowledge point according to the practice error type, and divide the misconception distribution corresponding to the error source on the education platform, wherein the practice error type specifically includes conceptual error, calculation error and careless error.

[0099] In this embodiment, the system collects practice data from platform users on pre-set knowledge mastery standards based on the educational platform. This practice data includes accuracy, completion time, and number of attempts. The system then determines whether this practice data meets the knowledge mastery standards and executes corresponding steps accordingly. For example, if the system determines that a user's practice data on a pre-set knowledge point meets the knowledge mastery standards, the system considers the user to have reached the expected level in that knowledge point, demonstrating a high accuracy rate, reasonable completion time, and a number of attempts that meets the learning objectives. The system then updates the status of that knowledge point in the user's learning profile to "Mastered" and reduces the recommended frequency of subsequent repetitive practice, allowing for further learning. Users can skip basic exercises for a given knowledge point and directly move on to more advanced application problems or related knowledge points. Simultaneously, by incorporating the Ebbinghaus forgetting curve, the system predicts the user's potential forgetting time and sets appropriate review reminders, avoiding frequent and ineffective repetition. Based on the user's learning habits, the system can adjust review content accordingly, such as using different question types or practical applications to prevent rote memorization. Furthermore, it provides incentives such as learning points, badges, and achievement unlocks to enhance learning motivation and sends learning achievement reports, allowing users to visually see their progress and increase their sense of accomplishment. For example, if the system determines that a user's practice data for a pre-set knowledge point has not reached the required mastery level, the system will consider that the user's level for that knowledge point has not met expectations. Based on different practice data, the system identifies the types of errors users make during practice. These errors include conceptual errors, calculation errors, and careless mistakes. It then identifies the sources of these errors for pre-defined knowledge points and categorizes the corresponding misconceptions on the educational platform. By recognizing common error types (such as conceptual errors, calculation errors, or careless mistakes) during practice, the system can accurately determine users' weaknesses in understanding knowledge points. Combined with the misconception distribution, the system can further analyze the source of errors, such as whether they are due to unclear basic concepts, unfamiliarity with calculation methods, or inattention. Furthermore, the system can dynamically adjust the user's learning content for different types of errors, such as conceptual... When errors occur, the system recommends that users relearn the core theories of the knowledge point, providing detailed explanations and examples. For instance, if a calculation error occurs, the system guides users through calculation training, providing step-by-step analysis to improve calculation accuracy. If a careless error occurs, the system enhances the user's attention in similar problems, adds verification steps, or provides an error review function. Through personalized adjustments, the system ensures that users strengthen their knowledge in the correct direction, rather than simply repeating incorrect exercises. Furthermore, by collecting and analyzing a large amount of user error data, the system can construct a knowledge point misconception distribution map, helping educational platforms optimize question settings and teaching content. The misconception distribution can also be used for group analysis to identify knowledge points that most users tend to make mistakes on, thereby adjusting teaching strategies and improving overall learning efficiency.

[0100] In this embodiment, before step S3 of detecting the learning progress gap of the platform user in the current learning quarter, the method further includes:

[0101] S301: Based on the course content of the current learning quarter, obtain the average learning progress of all platform users on the course content, wherein the course content specifically includes chapter progress, exercises and assignments, key quizzes and expected learning time;

[0102] S302: Determine whether the platform user can complete the average learning progress;

[0103] S303: If not, then calculate the learning lag rate of the platform user based on the behavioral information, and benchmark the lag rate against the lag level preset by the education platform. Based on the lag level, dynamically adjust the tutoring content of the platform user on the education platform. The lag level specifically includes slight lag, moderate lag, and severe lag. The tutoring content specifically includes recommending priority learning tasks, providing personalized review content, and emergency intervention contact persons.

[0104] In this embodiment, the system obtains the average learning progress of all platform users based on the course content of the current learning quarter, which specifically includes chapter progress, exercises and assignments, key quizzes, and expected learning time. The system then determines whether a user can achieve the average learning progress of all platform users and executes corresponding steps accordingly. For example, if the system determines that a user can achieve the average learning progress of all platform users, it considers the user's learning pace to be in line with the group's learning level, indicating that the user is not significantly behind or ahead in the current learning quarter's course progress and their learning status is relatively stable. The system will combine the user's exercise data and quiz results to recommend additional knowledge consolidation exercises, such as extension questions, case studies, or advanced thinking questions, to enhance the depth of knowledge mastery. If the user performs slightly poorly in certain key quizzes or assignments, the system can intelligently push corresponding reinforcement exercises to help the user further improve their learning quality. Simultaneously, if the user's progress is stable but slightly ahead, the system can provide advanced courses or more practical tasks to guide the user in deeper learning. To prevent users from losing interest in learning due to being ahead of the curve, if a user's progress is stable but close to the lower end of the average, the system can provide appropriate learning reminders or time management suggestions to help them maintain long-term learning motivation. It can also recommend learning discussion groups or interactive exchanges with users at the same progress level to improve engagement and sustainability. Furthermore, it provides data visualization feedback, such as learning progress curves and achievement badges, to enhance users' sense of accomplishment and self-motivation. For example, if the system determines that a user cannot complete the average learning progress of all users on the platform, it will consider that the user's learning pace is not in line with the group's learning level and that there may be a significant lag in the current learning quarter's course progress. The system will calculate the user's learning lag rate based on their behavioral information and, according to different lag rates, align with the pre-set lag levels on the education platform. These lag levels include slight lag, moderate lag, and severe lag. Based on these different lag levels, the system will dynamically adjust the user's supplementary learning content on the education platform, including recommending priority learning tasks, providing personalized review content, and providing emergency intervention contacts.The system calculates users' learning lag rate and categorizes it into mild, moderate, and severe lags, avoiding a one-size-fits-all approach. Users with mild lags receive appropriate learning reminders and priority task recommendations, while those with severe lags trigger stronger interventions, such as arranging tutoring or notifying parents. Based on current learning progress, the system intelligently prioritizes the most needed supplementary material, ensuring efficient tutoring rather than passively following a fixed order. Combining past practice data and learning habits, the system pushes frequently missed knowledge points, reinforcement exercises, or mini-courses to enhance knowledge recovery. For severely lagging users, the system contacts tutors, homeroom teachers, or parents to ensure timely intervention and provide offline or online tutoring to prevent further decline. Through adaptive adjustments to the tutoring plan, users can narrow the learning gap in a way that best suits their individual circumstances, avoiding anxiety or loss of motivation due to excessive lag. Personalized task recommendations and review plans enhance the focus and efficiency of learning, enabling users to improve their grades more quickly and catch up with the group.

[0105] It should be noted that, based on the behavioral information, the learning lag rate of the platform user is calculated. Based on this learning lag rate, the user is compared to a preset lag level on the education platform. Using this lag level, the supplementary learning content for the platform user on the education platform is dynamically adjusted. A specific example is as follows:

[0106] Suppose Xiaoming is a junior high school student learning a "Basic Algebra" course on an online education platform. The course has a total of 10 chapters, including basic operations, solving equations, function graphs, geometric applications, etc. To help students master the knowledge, the platform sets an average learning progress standard and judges their learning progress by collecting users' learning data.

[0107] Currently, the average learning progress of all students is 6 chapters, but Xiaoming has only completed 4 chapters;

[0108] Step 1: The system calculates the learning lag rate. The formula for calculating the learning lag rate is as follows:

[0109]

[0110] According to the preset lag level classification,

[0111] Slight lag (<10%): No intervention is needed; the system will only remind the user to speed up their learning progress.

[0112] Moderate lag (10%-30%): The system pushes personalized tutoring tasks and provides intelligent recommendations for learning content;

[0113] Severely lagging behind (>30%): The system will implement a mandatory tutoring plan, notify parents or tutors to intervene, and adjust the learning path;

[0114] Xiaoming's learning lag rate reached 33.33%, which is considered a serious lag. The system has initiated emergency remedial measures.

[0115] Step 2: The system analyzes learning behavior information. The system collected Xiaoming's behavior information, which mainly includes the following data:

[0116] Study time:

[0117] On average, he studies for 20 minutes a day, while other students study for an average of 45 minutes a day.

[0118] The frequency of study is low, only 3 days a week, while other students study an average of 5-6 days a week;

[0119] Practice data:

[0120] Low accuracy rate: The accuracy rate of exercises in some chapters is only 50%, while the overall accuracy rate should reach more than 80% to meet the mastery standard;

[0121] Error type analysis:

[0122] Conceptual errors (60%): Misunderstanding of the basic concept of "factorization" often leads to choosing the wrong method;

[0123] Calculation errors (30%): Frequently missing negative signs or writing the wrong numbers during calculations;

[0124] Careless mistakes (10%): Skipping steps when answering questions, leading to calculation errors;

[0125] Study habits:

[0126] Xiaoming is used to studying after 10 p.m., but his concentration is low at this time, which leads to a decrease in his comprehension efficiency.

[0127] The number of review sessions is too low; there is almost no review of the material learned, and intensive study is only conducted before the exam.

[0128] Step 3: The system executes targeted remedial measures. Since Xiaoming is judged to be "severely lagging behind," the system adopts the following remedial strategies:

[0129] First, the system pushes priority learning tasks, marking Xiaoming's factorization chapter as "priority tutoring content" and displaying it at the top of the learning homepage; in the daily learning recommendations, the system automatically pushes practice questions related to "factorization" to Xiaoming's task list; since Xiaoming is more likely to study after 10 pm, but his concentration is lower at this time, the system suggests adjusting his study time, recommending to arrange review tasks between 7 pm and 9 pm, and setting study reminders;

[0130] Following this is personalized review content. Based on the Ebbinghaus forgetting curve, the system calculates the optimal review time for Xiaoming and automatically schedules it:

[0131] Day 1: Review basic concepts;

[0132] Specialized practice will be conducted on the third day;

[0133] A mock test will be conducted on the 7th day to reinforce memory;

[0134] The system will recommend micro-lesson videos related to "factorization" to Xiaoming and provide voice interaction function so that he can ask questions;

[0135] By intelligently detecting practice errors, it provides specialized practice questions, such as correcting conceptual errors, supplementing basic knowledge points of factorization, and providing interactive exercises. Through calculation error practice, it generates "computation enhancement" exercises to help Xiaoming reduce basic mistakes.

[0136] Finally, emergency intervention measures were initiated. Due to Xiaoming's high lag rate, the system automatically sent notifications to his parents and tutors, reminding them to pay attention to Xiaoming's learning progress. The system provided a one-on-one online Q&A function, suggesting that Xiaoming book an online tutoring session with a teacher to help solve conceptual understanding problems. If the learning progress still does not improve after a week, the system will automatically arrange for a tutor or learning consultant to follow up on the learning and provide more detailed learning suggestions.

[0137] Through continuous monitoring and adjustment, the system will continuously monitor Xiaoming's learning progress over the next week and adopt dynamic adjustment strategies: if Xiaoming completes 6 chapters within 7 days, the system will lift the learning restrictions and continue to provide normal learning recommendations; if Xiaoming is still lagging behind, the system will further tighten learning permissions, such as restricting access to new courses and increasing the priority of tutoring tasks.

[0138] In summary, the examples above objectively assess whether a user's learning progress meets the group standard by calculating the learning lag rate. Based on user error types and learning habits, personalized learning paths are provided to improve learning outcomes. Furthermore, intelligent practice and review reminders enhance the user's mastery of knowledge points. For users with severe learning delays, collaboration between teachers and parents ensures improvement. In other words, the system helps Xiaoming identify problems and adjust his learning strategies in a timely manner, enabling him to gradually catch up with the course and improve overall learning effectiveness.

[0139] In this embodiment, step S2, which determines whether the test score can reach the learning performance, further includes:

[0140] S21: Based on the learning performance structure preset by the education platform, identify the performance weight of the test scores;

[0141] S22: Determine whether the weighting of the grades meets the various standards of the learning performance structure;

[0142] S23: If not, then based on the performance weight, collect the knowledge gap information corresponding to the platform user, mark the knowledge blocks of the knowledge gap information, and divide the knowledge content that the platform user needs to tutor from the knowledge blocks.

[0143] In this embodiment, the system identifies the weight of test scores based on the learning performance structure pre-set by the education platform. The system then determines whether the weight of the test score meets the various standards of the learning performance structure and executes the corresponding steps accordingly. For example, when the system determines that the weight of the test score meets the various standards of the learning performance structure, the system considers that the user's learning performance at the current stage has reached the expected goals, possesses the corresponding level of knowledge mastery, and meets the learning performance evaluation requirements set by the education platform. The system will automatically award the user learning points, badges, certificates, or upgrade their learning level to encourage continued learning. If the user's test score weight meets the requirements of a higher level... Based on the learning requirements of each stage, the system can recommend users to unlock more challenging learning content, such as advanced courses, challenge tasks, or advanced assessments. Simultaneously, based on user performance, it can recommend related knowledge points to encourage users to expand their learning scope. For example, if a user performs exceptionally well in a math test, the system can recommend more complex word problems or math competition content. Based on the user's learning interests and test scores, the system can push high-quality learning materials, such as thematic lectures, academic papers, and online experiments. Even after a user meets performance standards, the system will still analyze their answer characteristics, such as whether they have weak grasp of certain knowledge points, to provide targeted reinforcement exercises and continuously monitor the user's learning trends to ensure their continued progress. The system helps maintain stable performance throughout the learning process and provides review reminders for potential knowledge forgetting. For example, if the system determines that a test score's weighting does not meet the various standards of the learning performance structure, it considers the user's current learning performance below expectations. Based on this weighting, the system collects information on the user's corresponding knowledge gaps, marks the knowledge modules containing these gaps on the educational platform, and then divides the knowledge content from these modules for the user to remediate. The system can accurately pinpoint a user's weak knowledge points based on their weighting, avoiding a "one-size-fits-all" review strategy and improving learning efficiency through knowledge module division. For addressing knowledge gaps, the system ensures that tutoring content is precisely matched to the user's knowledge deficiencies, avoiding over-reviewing already mastered material. It dynamically recommends tutoring content based on the user's weak areas, including targeted exercises, video explanations, and interactive courses, making tutoring more focused. Tutoring priorities are adjusted to ensure users strengthen core foundational knowledge before moving on to more advanced topics, preventing knowledge gaps from impacting overall learning progress. The system continuously monitors tutoring effectiveness to ensure users can fill knowledge gaps and improve overall academic performance. Appropriate interventions are provided for low-performing users, such as learning guidance, AI-powered Q&A, and one-on-one teacher tutoring, reducing the risk of inadequate knowledge acquisition.

[0144] In this embodiment, step S4, which determines whether the learning progress gap exceeds a preset threshold, further includes:

[0145] S41: Based on the learning cycle preset by the platform user, dynamically update the learning progress of the platform user after completing the learning;

[0146] S42: Determine whether the learning progress has reached the preset minimum progress limit for a single session;

[0147] S43: If so, then based on the learning content already learned by the platform user, generate the learning duration of the platform user, and dynamically update the learning objectives of the platform user based on the learning duration. The learning content already learned specifically includes course chapter information, exercise information, and test information completed within the current period.

[0148] In this embodiment, the system dynamically updates the learning progress of platform users after they have completed their learning based on a pre-set learning cycle. The system then determines whether this progress has reached a pre-set minimum progress threshold for a single session, and executes corresponding steps accordingly. For example, if the system determines that the user's learning progress after completion has not reached the pre-set minimum progress threshold, the system considers that the user has not completed enough learning content during this learning process, potentially indicating insufficient learning time, low focus, or low learning efficiency. The system will then collect the user's learning duration to determine if there are excessively short learning periods and detect interactive data during the learning process (such as mouse clicks). The system monitors user attention (such as swiping and answering frequency) to identify prolonged periods of stagnation or passive learning, tracks facial expressions and eye movements using a camera, analyzes for frequent distractions or low engagement, and prompts users to adjust their study schedules, suggesting increased daily study time. Based on the user's current learning progress, the system re-plans the next stage of learning tasks to ensure overall progress is not affected, and guides users to supplement their learning with activities such as quizzes, reinforcement exercises, or knowledge review to improve learning quality. For example, if the system determines that a user's learning progress has reached a pre-set minimum for a single session, the system considers the user to be at a higher level. During this learning process, the basic learning content has been completed. The system will generate the user's learning time based on the content already learned, specifically including completed course chapters, exercises, and tests within the current cycle. The system will then dynamically update the user's learning goals based on this learning time. By determining whether the learning progress meets the minimum requirements, the system ensures that the user completes the basic learning tasks within each learning cycle, preventing procrastination or the accumulation of incomplete content. Dynamically adjusting learning goals based on learning time allows the goals to better align with the user's learning pace, avoiding fatigue from over-learning or insufficient learning due to overly low goals. Furthermore, based on the average learning progress... The system compares the user's existing learning content (course chapters, exercises, tests) with the learning objectives to ensure that the user's learning covers the necessary knowledge points without repeating what they have already learned. By dynamically adjusting the learning time, the system can identify the user's learning pace (such as fast learning or slow, in-depth learning) and optimize subsequent learning arrangements accordingly to ensure that the learning pace matches the user's ability. Real-time updates to learning objectives allow users to clearly understand their learning progress, enhancing their motivation and sense of accomplishment. Based on different learning durations, the system will intelligently recommend more suitable review times and learning methods, such as short-term high-efficiency learning mode or in-depth intensive learning mode, making learning more in line with the user's habits.

[0149] In this embodiment, after step S1 of identifying the test scores of the platform users on the education platform based on the learning performance preset by the education platform for platform users, the method further includes:

[0150] S101: Identify the learning interaction method pre-selected by the platform user on the education platform, wherein the learning interaction method specifically includes video learning, text learning and interactive learning;

[0151] S102: Determine whether the learning interaction method is suitable for the current learning quarter;

[0152] S103: If not, then based on the test results, dynamically adjust the learning path of the platform users, wherein the learning path specifically includes the course content structure and exercise assessment method.

[0153] In this embodiment, the system identifies the learning interaction methods pre-selected by the platform user on the education platform. These methods include video learning, text learning, and interactive learning. The system then determines whether the learning interaction method is suitable for the current learning quarter and executes corresponding steps accordingly. For example, if the system determines that the learning interaction method pre-selected by the platform user on the education platform is suitable for the current learning quarter, the system considers the user's learning method to be adapted to the course characteristics and teaching needs of the current quarter, thereby effectively improving learning efficiency and knowledge absorption. Based on the user's selection of video learning, text learning, or interactive learning, the system automatically matches the optimal teaching resources (such as video courses, reading materials, and online interactive exercises) to ensure that the learning method matches the teaching objectives. Simultaneously, the system analyzes the user's past learning time, progress, and comprehension, dynamically adjusting learning tasks. For example, for users accustomed to video learning, the system can add more efficient micro-lesson videos, reduce lengthy content, improve the learning experience, and add real-time quizzes, interactive Q&A, and gamified learning tasks to increase user participation and ensure maximum learning effectiveness. For example, when the system determines that the platform user on the education platform… If the pre-selected learning interaction method is not suitable for the current learning quarter, the system will consider that the user's learning style is not adapted to the characteristics and teaching needs of the current quarter's courses. Based on different test scores, the system will dynamically adjust the user's learning path on the platform. The learning path specifically includes the course content structure and exercise assessment methods. By proactively adjusting the learning path, the system ensures that the user's learning style is compatible with the teaching content. For example, if the current quarter leans towards practical training, and the user has chosen text-based learning, the system will guide the user to participate more in interactive exercises and case analysis to enhance practical skills. Simultaneously, based on the user's test scores, the system analyzes the user's knowledge mastery and dynamically adjusts the presentation order of course content. For example, if a user shows insufficient mastery of basic concepts in the test, the system may first strengthen the explanation of basic knowledge and then gradually move to advanced content, rather than proceeding in a fixed order. Furthermore, different users have different adaptability to exercise types. The system can adjust the difficulty and feedback methods of exercises based on the user's test performance. For example, for users who are good at logical reasoning but perform poorly on application questions, the system can add case analysis questions and provide step-by-step problem-solving guidance to improve the user's mastery of this type of problem.

[0154] Reference Appendix Figure 2 A learning progress monitoring system for an online education platform, as described in one embodiment of the present invention, includes:

[0155] The identification module 10 is used to identify the test scores of the platform users on the education platform based on the learning performance preset by the education platform for the platform users;

[0156] The judgment module 20 is used to determine whether the test score can achieve the learning performance.

[0157] The execution module 30 is used to restrict the platform user's examination privileges on the education platform if no, collect the platform user's behavioral information based on the platform user's multi-type learning data, and detect the learning progress gap of the platform user in the current learning quarter based on the historical learning achievements pre-collected by the education platform. The multi-type learning data specifically includes basic data, interaction data and biological data, and the behavioral information specifically includes active learning behavior, passive learning behavior and non-learning behavior.

[0158] The second judgment module 40 is used to determine whether the learning progress gap exceeds a preset threshold.

[0159] The second execution module 50 is used to collect the learning habit data of the platform users if the limit is exceeded, dynamically construct the Ebbinghaus forgetting curve of the platform users based on the learning habit data, calculate the best review period for the platform users on the knowledge points through the Ebbinghaus forgetting curve, and adaptively adjust the best review period according to the test results. The learning habit data specifically includes the average daily study time, the habitual study time period, and the speed at which the knowledge was mastered in the past.

[0160] In this embodiment, the identification module 10 identifies the test scores of platform users on the education platform based on the pre-set learning performance of the platform users. Then, the judgment module 20 determines whether these test scores meet the learning performance requirements and executes the corresponding steps. For example, when the system determines that the test scores of platform users on the education platform meet the learning performance requirements, the system will consider that the user's learning progress and knowledge mastery meet the expected goals, meaning that the current learning path and review strategy are effective. The system will record the completion status of the user's current learning stage, mark the knowledge point or course as "mastered" or "met the standard", and update the user's learning achievements in the learning record to improve the completeness of the learning profile and recommend higher-level learning content. The system provides content such as advanced courses, case studies, and practical training to help users deepen their understanding and application of knowledge. It also allows users to choose whether to proceed to the next stage of learning or to take short breaks to optimize their learning pace. Based on users' historical learning data, the system adjusts future learning paths to better align with their learning habits and interests. For example, if the system determines that a user's test scores on the education platform are not meeting learning performance targets, the execution module 30 will consider that the user's learning progress and knowledge acquisition speed are not meeting expectations, indicating that the user may be engaging in ineffective learning. The system will then temporarily restrict the user's exam access on the education platform, based on the user's various learning data, including basic data, interactive data, and other relevant information. The system collects behavioral information from platform users, including active learning, passive learning, and non-learning behaviors, using both interactive and biological data. Based on the platform's pre-recorded historical learning achievements, it detects the learning progress gap of users in the current learning quarter. By comparing test scores with learning performance, the system can promptly identify user learning deficiencies, preventing users from continuing to advance in courses without mastering the knowledge, thus avoiding ineffective learning. Restricting exam access ensures that users do not try to pass by chance through repeated attempts, but rather guides them to solve learning problems first and truly master the knowledge before taking tests. Furthermore, the system's analysis of users' progress gap in the current learning quarter based on historical learning achievements helps in assessing user performance. To assess whether the learning outcomes meet the standards, the system provides personalized learning path adjustment plans. For users with significant learning gaps, the system can push supplementary learning resources, increase targeted exercises, and optimize review strategies to ensure that users are not passively pushed to more complex learning stages before mastering the knowledge points. Furthermore, by intelligently analyzing learning progress and user behavior, the platform can provide more accurate and personalized learning support, making learning assessment more scientific. Through real-time monitoring and dynamic adjustment of learning status, the system ensures that users truly master the knowledge, rather than just "passing the exam," thereby improving the overall learning quality. Then, the second judgment module 40 determines whether the user's learning progress gap in the current learning quarter exceeds a pre-set threshold, and executes the corresponding steps accordingly.For example, when the system determines that a user's learning progress gap in the current learning quarter does not exceed a pre-set threshold, the system will consider the user's learning progress to be basically in line with expectations. Even if test scores do not yet meet learning performance standards, it may be due to short-term fluctuations, temporary poor performance, or incomplete understanding of some knowledge points, rather than long-term learning problems. The system will appropriately increase personalized review tasks, such as inserting targeted reinforcement exercises into the learning plan, to help the user consolidate the knowledge points that were weaker in the test. Combining the user's learning habit data (such as learning time periods and learning frequency), the system will fine-tune the review recommendation strategy to better match the user's cognitive rhythm, while providing positive incentives through the learning platform. Incentives, such as small rewards, badges, and learning motivation notifications, are used to maintain user motivation. Learning reports are generated to provide feedback on the user's current learning status and offer suggestions, such as "Your learning progress is basically up to standard, but there is still room for improvement in some knowledge points; appropriate review is recommended." The system continues to track user performance changes in subsequent tests. If test scores show significant improvement, the user's learning path is confirmed to be effective; if they remain below the learning performance target, further intervention is considered. For example, when the system determines that a user's learning progress gap in the current learning quarter exceeds a pre-set threshold, the second execution module 50 will consider the user's learning progress unsatisfactory, and the system will collect data on the user's learning habits. Learning habit data specifically includes average daily study time, habitual study periods, and the speed at which past knowledge was mastered. Based on this data, an Ebbinghaus forgetting curve is dynamically constructed for each user on the platform. This curve is used to calculate the optimal review period for each user's knowledge points, and the system adaptively adjusts this optimal review period based on different test scores. By dynamically constructing the Ebbinghaus forgetting curve based on individual user data, the system can accurately predict the rate at which users forget knowledge points, thus pushing review tasks at the appropriate time. This avoids wasting time by reviewing too early or causing excessive forgetting by reviewing too late. The system also adaptively adjusts based on user test scores, ensuring that the review pace matches the user's level of knowledge mastery. The system is designed to ensure effective reinforcement of learning content and can identify users' learning patterns to optimize review schedules accordingly. For example, for users with fragmented study time, the system can appropriately increase short, high-frequency review tasks, while for users with concentrated study sessions, the review intervals can be optimized to better align with memory patterns. This personalized adjustment effectively reduces gaps in learning progress, helps inefficient learners improve their learning outcomes, and ensures that users with different test scores receive appropriate learning suggestions, making the learning path more flexible. For example, for users with lower test scores, the system can increase review frequency to reinforce key knowledge, while for users with scores close to passing, repetitive reviews can be appropriately reduced to avoid learning fatigue.

[0161] In this embodiment, the execution module further includes:

[0162] The acquisition unit is used to acquire the user's feature information by interacting with the connected device through the education platform based on the connection device preset by the user of the platform. The feature information specifically includes facial expressions, eye movement trajectory, head movement and body posture.

[0163] The judgment unit is used to determine whether the feature information matches the identity features pre-entered by the platform user;

[0164] An execution unit is configured to, if so, track the pupil trajectory of the platform user when facing the connected device based on the feature information, and simultaneously extract the key features corresponding to the platform user during the learning process based on the pupil trajectory, wherein the key features specifically include tone of voice, speech rate, pauses, and volume changes.

[0165] In this embodiment, the system uses a pre-set connection device by the platform user to interact with the device through the education platform, obtaining the user's permissions granted to the platform. The system then acquires the user's feature information from the device's camera, specifically including facial expressions, eye movements, head movements, and body posture. The system then determines whether this feature information matches the user's pre-recorded identity features to execute corresponding steps. For example, if the system determines that the user's feature information does not match the user's pre-recorded identity features, the system considers the user interacting with the platform to be potentially not the actual user, posing a risk of identity fraud, proxy learning, or proxy testing. The system will then temporarily... The system locks the user's learning permissions, preventing them from taking exams, submitting assignments, or performing other critical operations. The user is prompted to re-verify their identity, requiring them to adjust their posture (e.g., looking directly at the camera, turning their head left or right) until more complete feature information is obtained. This information is then compared again with the platform's pre-stored identity information. Multiple authentication methods, such as SMS verification codes, facial recognition + password, and fingerprint verification, are used for further identity confirmation. If the user passes the second authentication, they are allowed to continue learning and interacting, and their feature information database is updated to accommodate possible feature changes (e.g., wearing glasses, changes in lighting). For example, when the system determines that the user's feature information matches the user's pre-entered identity features, the system considers the current activity to be... The users interacting with the learning platform are the platform users themselves. The system tracks the pupil trajectory of the platform user when facing the connected device based on this characteristic information. Based on different pupil trajectories, it simultaneously extracts key features corresponding to the platform user's learning process, specifically including tone of voice, speaking speed, pauses, and volume changes. Through pupil trajectory tracking, the system can determine whether the user's gaze is focused on the learning content, identify whether the user's attention is scattered, or whether there is prolonged lack of focus, thereby assessing their concentration. Combined with eye-tracking pattern analysis, the system can determine whether the user is quickly scanning, carefully reading, reviewing, or even staring at the same content for a long time, detecting whether there are comprehension difficulties. Simultaneously, through voice feature analysis (tone of voice, speaking speed, pauses, and volume changes), the system can further enhance the learning experience. The system can detect learners' emotional changes, such as anxiety, confusion, excitement, and fatigue. If a user's speaking speed suddenly slows down, pauses more, or volume decreases while reading aloud or answering questions, it may indicate that the user is thinking or encountering difficulties. Conversely, if the speaking speed increases and the volume rises, it may indicate that the user is more familiar with the content or more confident. In addition, the system can provide real-time adaptive adjustments based on the user's learning status. For example, when it detects a decline in concentration or significant emotional fluctuations, it can push short break reminders or adjust the learning pace to prevent learning fatigue. If it detects that the user's speech expression of a certain knowledge point is not fluent or the tone is abnormal, the system can infer that the understanding of the knowledge point may be insufficient, automatically mark the content, and provide personalized review recommendations later.

[0166] In this embodiment, it also includes:

[0167] The data collection module is used to collect practice data of the platform users on preset knowledge points based on the knowledge mastery standards preset by the education platform. The practice data specifically includes accuracy rate, completion time and number of times the questions are answered.

[0168] The third judgment module is used to determine whether the practice data can reach the knowledge mastery standard;

[0169] The third execution module is used to, if not, obtain the error type of the platform user based on the exercise data, identify the error source of the preset knowledge point based on the error type, and divide the misconception distribution corresponding to the error source on the education platform. The error type specifically includes conceptual error, calculation error and carelessness error.

[0170] In this embodiment, the system collects practice data from platform users on pre-set knowledge mastery standards based on the educational platform. This practice data includes accuracy, completion time, and number of attempts. The system then determines whether this practice data meets the knowledge mastery standards and executes corresponding steps accordingly. For example, if the system determines that a user's practice data on a pre-set knowledge point meets the knowledge mastery standards, the system considers the user to have reached the expected level in that knowledge point, demonstrating a high accuracy rate, reasonable completion time, and a number of attempts that meets the learning objectives. The system then updates the status of that knowledge point in the user's learning profile to "Mastered" and reduces the recommended frequency of subsequent repetitive practice, allowing for further learning. Users can skip basic exercises for a given knowledge point and directly move on to more advanced application problems or related knowledge points. Simultaneously, by incorporating the Ebbinghaus forgetting curve, the system predicts the user's potential forgetting time and sets appropriate review reminders, avoiding frequent and ineffective repetition. Based on the user's learning habits, the system can adjust review content accordingly, such as using different question types or practical applications to prevent rote memorization. Furthermore, it provides incentives such as learning points, badges, and achievement unlocks to enhance learning motivation and sends learning achievement reports, allowing users to visually see their progress and increase their sense of accomplishment. For example, if the system determines that a user's practice data for a pre-set knowledge point has not reached the required mastery level, the system will consider that the user's level for that knowledge point has not met expectations. Based on different practice data, the system identifies the types of errors users make during practice. These errors include conceptual errors, calculation errors, and careless mistakes. It then identifies the sources of these errors for pre-defined knowledge points and categorizes the corresponding misconceptions on the educational platform. By recognizing common error types (such as conceptual errors, calculation errors, or careless mistakes) during practice, the system can accurately determine users' weaknesses in understanding knowledge points. Combined with the misconception distribution, the system can further analyze the source of errors, such as whether they are due to unclear basic concepts, unfamiliarity with calculation methods, or inattention. Furthermore, the system can dynamically adjust the user's learning content for different types of errors, such as conceptual... When errors occur, the system recommends that users relearn the core theories of the knowledge point, providing detailed explanations and examples. For instance, if a calculation error occurs, the system guides users through calculation training, providing step-by-step analysis to improve calculation accuracy. If a careless error occurs, the system enhances the user's attention in similar problems, adds verification steps, or provides an error review function. Through personalized adjustments, the system ensures that users strengthen their knowledge in the correct direction, rather than simply repeating incorrect exercises. Furthermore, by collecting and analyzing a large amount of user error data, the system can construct a knowledge point misconception distribution map, helping educational platforms optimize question settings and teaching content. The misconception distribution can also be used for group analysis to identify knowledge points that most users tend to make mistakes on, thereby adjusting teaching strategies and improving overall learning efficiency.

[0171] In this embodiment, it also includes:

[0172] The acquisition module is used to acquire the average learning progress of all platform users on the course content based on the course content of the current learning quarter. The course content specifically includes chapter progress, exercises and assignments, key quizzes and expected learning time.

[0173] The fourth judgment module is used to determine whether the platform user can complete the average learning progress.

[0174] The fourth execution module is used to calculate the learning lag rate of the platform user based on the behavioral information if no, and to dynamically adjust the tutoring content of the platform user on the education platform according to the learning lag rate and the preset lag level of the education platform. The lag level specifically includes slight lag, moderate lag, and severe lag, and the tutoring content specifically includes recommending priority learning tasks, providing personalized review content, and providing emergency intervention contacts.

[0175] In this embodiment, the system obtains the average learning progress of all platform users based on the course content of the current learning quarter, which specifically includes chapter progress, exercises and assignments, key quizzes, and expected learning time. The system then determines whether a user can achieve the average learning progress of all platform users and executes corresponding steps accordingly. For example, if the system determines that a user can achieve the average learning progress of all platform users, it considers the user's learning pace to be in line with the group's learning level, indicating that the user is not significantly behind or ahead in the current learning quarter's course progress and their learning status is relatively stable. The system will combine the user's exercise data and quiz results to recommend additional knowledge consolidation exercises, such as extension questions, case studies, or advanced thinking questions, to enhance the depth of knowledge mastery. If the user performs slightly poorly in certain key quizzes or assignments, the system can intelligently push corresponding reinforcement exercises to help the user further improve their learning quality. Simultaneously, if the user's progress is stable but slightly ahead, the system can provide advanced courses or more practical tasks to guide the user in deeper learning. To prevent users from losing interest in learning due to being ahead of the curve, if a user's progress is stable but close to the lower end of the average, the system can provide appropriate learning reminders or time management suggestions to help them maintain long-term learning motivation. It can also recommend learning discussion groups or interactive exchanges with users at the same progress level to improve engagement and sustainability. Furthermore, it provides data visualization feedback, such as learning progress curves and achievement badges, to enhance users' sense of accomplishment and self-motivation. For example, if the system determines that a user cannot complete the average learning progress of all users on the platform, it will consider that the user's learning pace is not in line with the group's learning level and that there may be a significant lag in the current learning quarter's course progress. The system will calculate the user's learning lag rate based on their behavioral information and, according to different lag rates, align with the pre-set lag levels on the education platform. These lag levels include slight lag, moderate lag, and severe lag. Based on these different lag levels, the system will dynamically adjust the user's supplementary learning content on the education platform, including recommending priority learning tasks, providing personalized review content, and providing emergency intervention contacts.The system calculates users' learning lag rate and categorizes it into mild, moderate, and severe lags, avoiding a one-size-fits-all approach. Users with mild lags receive appropriate learning reminders and priority task recommendations, while those with severe lags trigger stronger interventions, such as arranging tutoring or notifying parents. Based on current learning progress, the system intelligently prioritizes the most needed supplementary material, ensuring efficient tutoring rather than passively following a fixed order. Combining past practice data and learning habits, the system pushes frequently missed knowledge points, reinforcement exercises, or mini-courses to enhance knowledge recovery. For severely lagging users, the system contacts tutors, homeroom teachers, or parents to ensure timely intervention and provide offline or online tutoring to prevent further decline. Through adaptive adjustments to the tutoring plan, users can narrow the learning gap in a way that best suits their individual circumstances, avoiding anxiety or loss of motivation due to excessive lag. Personalized task recommendations and review plans enhance the focus and efficiency of learning, enabling users to improve their grades more quickly and catch up with the group.

[0176] In this embodiment, the determination module further includes:

[0177] The identification unit is used to identify the score weight of the test score based on the learning performance structure preset by the education platform.

[0178] The second judgment unit is used to determine whether the performance weights meet the various standards of the learning performance structure.

[0179] The second execution unit is used to, if not, collect the knowledge gap information corresponding to the platform user according to the performance weight, mark the knowledge blocks of the knowledge gap information, and divide the knowledge content that the platform user needs to tutor from the knowledge blocks.

[0180] In this embodiment, the system identifies the weight of test scores based on the learning performance structure pre-set by the education platform. The system then determines whether the weight of the test score meets the various standards of the learning performance structure and executes the corresponding steps accordingly. For example, when the system determines that the weight of the test score meets the various standards of the learning performance structure, the system considers that the user's learning performance at the current stage has reached the expected goals, possesses the corresponding level of knowledge mastery, and meets the learning performance evaluation requirements set by the education platform. The system will automatically award the user learning points, badges, certificates, or upgrade their learning level to encourage continued learning. If the user's test score weight meets the requirements of a higher level... Based on the learning requirements of each stage, the system can recommend users to unlock more challenging learning content, such as advanced courses, challenge tasks, or advanced assessments. Simultaneously, based on user performance, it can recommend related knowledge points to encourage users to expand their learning scope. For example, if a user performs exceptionally well in a math test, the system can recommend more complex word problems or math competition content. Based on the user's learning interests and test scores, the system can push high-quality learning materials, such as thematic lectures, academic papers, and online experiments. Even after a user meets performance standards, the system will still analyze their answer characteristics, such as whether they have weak grasp of certain knowledge points, to provide targeted reinforcement exercises and continuously monitor the user's learning trends to ensure their continued progress. The system helps maintain stable performance throughout the learning process and provides review reminders for potential knowledge forgetting. For example, if the system determines that a test score's weighting does not meet the various standards of the learning performance structure, it considers the user's current learning performance below expectations. Based on this weighting, the system collects information on the user's corresponding knowledge gaps, marks the knowledge modules containing these gaps on the educational platform, and then divides the knowledge content from these modules for the user to remediate. The system can accurately pinpoint a user's weak knowledge points based on their weighting, avoiding a "one-size-fits-all" review strategy and improving learning efficiency through knowledge module division. For addressing knowledge gaps, the system ensures that tutoring content is precisely matched to the user's knowledge deficiencies, avoiding over-reviewing already mastered material. It dynamically recommends tutoring content based on the user's weak areas, including targeted exercises, video explanations, and interactive courses, making tutoring more focused. Tutoring priorities are adjusted to ensure users strengthen core foundational knowledge before moving on to more advanced topics, preventing knowledge gaps from impacting overall learning progress. The system continuously monitors tutoring effectiveness to ensure users can fill knowledge gaps and improve overall academic performance. Appropriate interventions are provided for low-performing users, such as learning guidance, AI-powered Q&A, and one-on-one teacher tutoring, reducing the risk of inadequate knowledge acquisition.

[0181] In this embodiment, the second determination module further includes:

[0182] The update unit is used to dynamically update the learning progress of the platform user after the learning is completed, based on the learning cycle preset by the platform user.

[0183] The third judgment unit is used to determine whether the learning progress has reached the preset single progress lower limit;

[0184] The third execution unit is configured to, if so, generate the learning duration of the platform user based on the learning content already learned by the platform user, and dynamically update the learning objectives of the platform user based on the learning duration, wherein the learning content already learned specifically includes course chapter information, exercise information, and test information completed within the current period.

[0185] In this embodiment, the system dynamically updates the learning progress of platform users after they have completed their learning based on a pre-set learning cycle. The system then determines whether this progress has reached a pre-set minimum progress threshold for a single session, and executes corresponding steps accordingly. For example, if the system determines that the user's learning progress after completion has not reached the pre-set minimum progress threshold, the system considers that the user has not completed enough learning content during this learning process, potentially indicating insufficient learning time, low focus, or low learning efficiency. The system will then collect the user's learning duration to determine if there are excessively short learning periods and detect interactive data during the learning process (such as mouse clicks). The system monitors user attention (such as swiping and answering frequency) to identify prolonged periods of stagnation or passive learning, tracks facial expressions and eye movements using a camera, analyzes for frequent distractions or low engagement, and prompts users to adjust their study schedules, suggesting increased daily study time. Based on the user's current learning progress, the system re-plans the next stage of learning tasks to ensure overall progress is not affected, and guides users to supplement their learning with activities such as quizzes, reinforcement exercises, or knowledge review to improve learning quality. For example, if the system determines that a user's learning progress has reached a pre-set minimum for a single session, the system considers the user to be at a higher level. During this learning process, the basic learning content has been completed. The system will generate the user's learning time based on the content already learned, specifically including completed course chapters, exercises, and tests within the current cycle. The system will then dynamically update the user's learning goals based on this learning time. By determining whether the learning progress meets the minimum requirements, the system ensures that the user completes the basic learning tasks within each learning cycle, preventing procrastination or the accumulation of incomplete content. Dynamically adjusting learning goals based on learning time allows the goals to better align with the user's learning pace, avoiding fatigue from over-learning or insufficient learning due to overly low goals. Furthermore, based on the average learning progress... The system compares the user's existing learning content (course chapters, exercises, tests) with the learning objectives to ensure that the user's learning covers the necessary knowledge points without repeating what they have already learned. By dynamically adjusting the learning time, the system can identify the user's learning pace (such as fast learning or slow, in-depth learning) and optimize subsequent learning arrangements accordingly to ensure that the learning pace matches the user's ability. Real-time updates to learning objectives allow users to clearly understand their learning progress, enhancing their motivation and sense of accomplishment. Based on different learning durations, the system will intelligently recommend more suitable review times and learning methods, such as short-term high-efficiency learning mode or in-depth intensive learning mode, making learning more in line with the user's habits.

[0186] In this embodiment, it also includes:

[0187] The second identification module is used to identify the learning interaction method pre-selected by the platform user on the education platform, wherein the learning interaction method specifically includes video learning, text learning and interactive learning;

[0188] The fifth judgment module is used to determine whether the learning interaction method is suitable for the current learning quarter;

[0189] The fifth execution module is used to dynamically adjust the learning path of the platform user based on the test results if no, wherein the learning path specifically includes the course content structure and exercise evaluation method.

[0190] In this embodiment, the system identifies the learning interaction methods pre-selected by the platform user on the education platform. These methods include video learning, text learning, and interactive learning. The system then determines whether the learning interaction method is suitable for the current learning quarter and executes corresponding steps accordingly. For example, if the system determines that the learning interaction method pre-selected by the platform user on the education platform is suitable for the current learning quarter, the system considers the user's learning method to be adapted to the course characteristics and teaching needs of the current quarter, thereby effectively improving learning efficiency and knowledge absorption. Based on the user's selection of video learning, text learning, or interactive learning, the system automatically matches the optimal teaching resources (such as video courses, reading materials, and online interactive exercises) to ensure that the learning method matches the teaching objectives. Simultaneously, the system analyzes the user's past learning time, progress, and comprehension, dynamically adjusting learning tasks. For example, for users accustomed to video learning, the system can add more efficient micro-lesson videos, reduce lengthy content, improve the learning experience, and add real-time quizzes, interactive Q&A, and gamified learning tasks to increase user participation and ensure maximum learning effectiveness. For example, when the system determines that the platform user on the education platform… If the pre-selected learning interaction method is not suitable for the current learning quarter, the system will consider that the user's learning style is not adapted to the characteristics and teaching needs of the current quarter's courses. Based on different test scores, the system will dynamically adjust the user's learning path on the platform. The learning path specifically includes the course content structure and exercise assessment methods. By proactively adjusting the learning path, the system ensures that the user's learning style is compatible with the teaching content. For example, if the current quarter leans towards practical training, and the user has chosen text-based learning, the system will guide the user to participate more in interactive exercises and case analysis to enhance practical skills. Simultaneously, based on the user's test scores, the system analyzes the user's knowledge mastery and dynamically adjusts the presentation order of course content. For example, if a user shows insufficient mastery of basic concepts in the test, the system may first strengthen the explanation of basic knowledge and then gradually move to advanced content, rather than proceeding in a fixed order. Furthermore, different users have different adaptability to exercise types. The system can adjust the difficulty and feedback methods of exercises based on the user's test performance. For example, for users who are good at logical reasoning but perform poorly on application questions, the system can add case analysis questions and provide step-by-step problem-solving guidance to improve the user's mastery of this type of problem.

[0191] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for monitoring learning progress on an online education platform, characterized in that, Includes the following steps: Based on the learning performance preset by the education platform for platform users, identify the test scores of the platform users on the education platform; Determine whether the test results meet the learning performance target; If not, then restrict the platform users' exam privileges on the education platform, collect the platform users' behavioral information based on the platform users' multi-type learning data, and detect the learning progress gap of the platform users in the current learning quarter based on the historical learning achievements pre-collected by the education platform. The multi-type learning data specifically includes basic data, interaction data, and biological data, and the behavioral information specifically includes active learning behavior, passive learning behavior, and non-learning behavior. Determine whether the learning progress gap exceeds a preset threshold; If the data exceeds the limit, the learning habit data of the platform users will be collected. Based on the learning habit data, the Ebbinghaus forgetting curve of the platform users will be dynamically constructed. The optimal review period for the knowledge points of the platform users will be calculated through the Ebbinghaus forgetting curve. The optimal review period will be adaptively adjusted according to the test results. The learning habit data specifically includes the average daily study time, the habitual study time period, and the speed at which the knowledge was mastered in the past. The step of collecting the behavioral information of the platform users further includes: Based on the connection device preset by the platform user, the platform learns and interacts with the connection device through the education platform to obtain the characteristic information of the platform user, wherein the characteristic information specifically includes facial expressions, eye movement trajectory, head movement and body posture. Determine whether the feature information matches the identity features pre-entered by the platform user; If so, then based on the feature information, the pupil trajectory of the platform user when facing the connected device is tracked, and based on the pupil trajectory, the key features corresponding to the platform user during the learning process are extracted synchronously, wherein the key features specifically include tone of voice, speaking speed, pauses and volume changes.

2. The learning progress monitoring method for an online education platform according to claim 1, characterized in that, Before the step of dynamically constructing the Ebbinghaus forgetting curve for the platform users, the method further includes: Based on the knowledge mastery standards preset by the education platform for its users, practice data of the users on preset knowledge points is collected. Specifically, the practice data includes accuracy, completion time, and number of attempts. Determine whether the practice data meets the knowledge mastery standard; If not, then based on the practice data, obtain the practice error types of the platform users, identify the error sources of the preset knowledge points according to the practice error types, and divide the misconception distribution corresponding to the error sources on the education platform. Specifically, the practice error types include conceptual errors, calculation errors, and careless errors.

3. The learning progress monitoring method for an online education platform according to claim 1, characterized in that, Before the step of detecting the learning progress gap of the platform users in the current learning quarter, the method further includes: Based on the course content of the current learning quarter, obtain the average learning progress of all platform users on the course content, wherein the course content specifically includes chapter progress, exercises and assignments, key quizzes and expected learning time; Determine whether the platform users can complete the average learning progress; If not, then based on the behavioral information, calculate the learning lag rate of the platform user, and based on the learning lag rate, benchmark against the lag level preset by the education platform. Through the lag level, dynamically adjust the tutoring content of the platform user on the education platform. The lag level specifically includes slight lag, moderate lag, and severe lag, and the tutoring content specifically includes recommending priority learning tasks, providing personalized review content, and emergency intervention contact persons.

4. The learning progress monitoring method for an online education platform according to claim 1, characterized in that, The step of determining whether the test score can achieve the learning performance also includes: Based on the learning performance structure preset by the education platform, the score weights of the test scores are identified; Determine whether the weighting of the grades meets the various standards of the learning performance structure; If not, then based on the aforementioned performance weights, collect the knowledge gap information corresponding to the platform user, mark the knowledge modules of the knowledge gap information, and divide the knowledge content that the platform user needs to tutor from the knowledge modules.

5. The learning progress monitoring method for an online education platform according to claim 1, characterized in that, The step of determining whether the learning progress gap exceeds a preset threshold further includes: Based on the learning cycle preset by the platform users, the learning progress of the platform users after they have completed the learning is dynamically updated. Determine whether the learning progress has reached the preset minimum progress limit for a single session; If so, the learning duration of the platform user is generated based on the content already learned by the platform user, and the learning objectives of the platform user are dynamically updated based on the learning duration. The content already learned specifically includes course chapter information, exercise information, and test information completed within the current period.

6. The learning progress monitoring method for an online education platform according to claim 1, characterized in that, After the step of identifying the test scores of platform users on the education platform based on the learning performance preset by the education platform, the method further includes: Identify the learning interaction methods pre-selected by the platform users on the education platform, wherein the learning interaction methods specifically include video learning, text learning, and interactive learning; Determine whether the learning interaction method is suitable for the current learning quarter; If not, the learning path of the platform user will be dynamically adjusted based on the test results. The learning path specifically includes the course content structure and the exercise assessment method.

7. A learning progress monitoring system for an online education platform, characterized in that, include: The identification module is used to identify the test scores of the platform users on the education platform based on the learning performance preset by the education platform. The judgment module is used to determine whether the test score can achieve the learning performance. The execution module is used to restrict the platform user's examination privileges on the education platform if no, collect the platform user's behavioral information based on the platform user's multi-type learning data, and detect the learning progress gap of the platform user in the current learning quarter based on the historical learning achievements pre-collected by the education platform. The multi-type learning data specifically includes basic data, interaction data and biological data, and the behavioral information specifically includes active learning behavior, passive learning behavior and non-learning behavior. The second judgment module is used to determine whether the learning progress gap exceeds a preset threshold. The second execution module is used to collect the learning habit data of the platform users if the limit is exceeded, dynamically construct the Ebbinghaus forgetting curve of the platform users based on the learning habit data, calculate the best review time for the platform users on the knowledge points through the Ebbinghaus forgetting curve, and adaptively adjust the best review time according to the test results. The learning habit data specifically includes the average daily study time, the habitual study time period, and the speed at which the knowledge was mastered in the past. The execution module further includes: The acquisition unit is used to acquire the user's feature information by interacting with the connected device through the education platform based on the connection device preset by the user of the platform. The feature information specifically includes facial expressions, eye movement trajectory, head movement and body posture. The judgment unit is used to determine whether the feature information matches the identity features pre-entered by the platform user; An execution unit is configured to, if so, track the pupil trajectory of the platform user when facing the connected device based on the feature information, and simultaneously extract the key features corresponding to the platform user during the learning process based on the pupil trajectory, wherein the key features specifically include tone of voice, speech rate, pauses, and volume changes.

8. The learning progress monitoring system for an online education platform according to claim 7, characterized in that, Also includes: The data collection module is used to collect practice data of the platform users on preset knowledge points based on the knowledge mastery standards preset by the education platform. The practice data specifically includes accuracy rate, completion time and number of times the questions are answered. The third judgment module is used to determine whether the practice data can reach the knowledge mastery standard; The third execution module is used to, if not, obtain the error type of the platform user based on the exercise data, identify the error source of the preset knowledge point based on the error type, and divide the misconception distribution corresponding to the error source on the education platform. The error type specifically includes conceptual error, calculation error and carelessness error.

Images