Learning progress monitoring method and system for online education platform

Abstract

The invention provides a learning progress monitoring method and system for an online education platform, and is applied to the field of online data processing. Through multi-dimensional data acquisition and intelligent analysis, the learning behavior monitoring accuracy is improved, the learning achievement degree of the user is accurately judged, the evaluation objectivity is ensured, the learning behaviors of the user are comprehensively tracked in combination with multiple types of learning data, the limitation of single-dimensional evaluation is avoided, and the user experience is improved. Meanwhile, through monitoring of active learning, passive learning and non-learning behaviors, the learning state of the user is further refined, the authenticity of data is improved, personalized learning habit data of the user is collected, an Ebbinghaus forgetting curve is dynamically constructed, accurate review time recommendation is achieved, the review time period can be adaptively optimized in combination with the change trend of test results, and the review efficiency is improved. The user can review at the best time, and the knowledge retention rate is improved.

Description

Technical Field

[0001] The present invention relates to the field of online data processing, and particularly to a method and system for monitoring the learning progress of an online education platform. Background Art

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

[0003] However, existing learning monitoring technologies mainly rely on explicit data, such as the time of watching videos, homework submission situations, etc., and lack effective monitoring means for learners' implicit behaviors, such as reading comprehension, thinking pauses, note-taking, etc., that is, lack of records of learners' behaviors in informal learning (such as independent search, discussion, practical activities), resulting in incomplete learning progress evaluation. Summary of the Invention

[0004] The present invention aims to solve the problem of how to improve the accuracy of learning behavior monitoring, and provides a method and system for monitoring the learning progress of an online education platform.

[0005] The present invention adopts the following technical means to solve the technical problems: The present invention provides a method for monitoring the learning progress of an online education platform, including: Identifying the test scores of platform users on the education platform based on the learning performance preset for the platform users by the education platform; Judging whether the test scores can reach the learning performance; If not, restricting the exam rights of the platform users on the education platform, collecting the behavior information of the platform users according to the multi-type learning data of the platform users, and detecting the learning progress gap of the platform users in the current learning quarter based on the historical learning achievements pre-recorded by the education platform, wherein the multi-type learning data specifically includes basic data, interaction data, and biological data, and the behavior information specifically includes active learning behaviors, passive learning behaviors, and non-learning behaviors; Judging whether the learning progress gap exceeds a preset threshold; If it exceeds, collecting the learning habit data of the platform users, dynamically constructing the Ebbinghaus forgetting curve of the platform users based on the learning habit data, calculating the best review period for the platform users to master knowledge points through the Ebbinghaus forgetting curve, and adaptively adjusting the best review period according to the test scores, wherein the learning habit data specifically includes the average daily learning duration, the habitual learning time period, and the mastery speed of past learned knowledge.

[0006] Further, in the step of collecting the behavior information of the platform user, the following is also included: Based on the connection device preset by the platform user, the education platform conducts learning interaction with the connection device to obtain the characteristic information of the platform user, where the characteristic information specifically includes facial expressions, eye movement trajectories, head movements, and body postures; Judge whether the characteristic information matches the identity characteristics pre-entered by the platform user; If so, according to the characteristic information, track the pupil trajectory of the platform user when facing the connection device, and based on the pupil trajectory, synchronously extract the corresponding key characteristics of the platform user during the learning process, where the key characteristics specifically include intonation, speech rate, pauses, and volume changes.

[0007] Further, before the step of dynamically constructing the Ebbinghaus forgetting curve of the platform user, the following is also included: Based on the knowledge mastery standard preset by the education platform for the platform user, collect the practice data of the platform user for the preset knowledge points, where the practice data specifically includes the correct rate, completion time, and number of answer attempts; Judge whether the practice data can meet the knowledge mastery standard; If not, according to the practice data, obtain the types of practice errors of the platform user, and based on the types of practice errors, identify the sources of errors of the preset knowledge points, and divide the distribution of misunderstandings corresponding to the sources of errors on the education platform, where the types of practice errors specifically include conceptual errors, calculation errors, and careless errors.

[0008] Further, before the step of detecting the learning progress gap of the platform user in the current learning quarter, the following is also included: Based on the course content of the current learning quarter, obtain the average learning progress of all platform users for the course content, where the course content specifically includes chapter progress, exercises and assignments, key quizzes, and expected learning duration; Judge whether the platform user can complete the average learning progress; If not, according to the behavior information, calculate the learning lag rate of the platform user, and based on the learning lag rate, benchmark the lag levels preset by the education platform, and through the lag levels, dynamically adjust the tutoring content of the platform user on the education platform, where the lag levels specifically include slight lag, moderate lag, and severe lag, and the tutoring content specifically includes recommended priority learning tasks, providing personalized review content, and emergency intervention contacts.

[0009] Further, in the step of judging whether the test score can reach the learning performance, the following is also included: Based on the learning performance structure preset in the education platform, identify the score weights of the test scores; Determine whether the score weights meet the various criteria of the learning performance structure; If not, according to the score weights, collect the knowledge short-board information corresponding to the platform user, mark the knowledge sections of the knowledge short-board information, and divide the knowledge content that the platform user needs to make up from the knowledge sections.

[0010] Furthermore, in the step of determining whether the learning progress gap exceeds a preset threshold, it further includes: Based on the learning cycle preset for the platform user, dynamically update the learning progress of the platform user after learning; Determine whether the learning progress has reached the preset lower limit of the single progress; If so, generate the learning duration of the platform user according to the learned content of the platform user, and dynamically update the learning goal of the platform user according to the learning duration, where the learned content specifically includes the course chapter information, exercise information, and test information completed within the current cycle.

[0011] Furthermore, after the step of identifying the test scores of the platform user on the education platform based on the learning performance preset for the platform user by the education platform, it further includes: Identify the learning interaction methods pre-selected by the platform user on the education platform, where the learning interaction methods specifically include video-based learning, text-based learning, and interactive learning; Determine whether the learning interaction methods conform to the current learning quarter; If not, based on the test scores, dynamically adjust the learning path of the platform user, where the learning path specifically includes the course content structure and the exercise evaluation method.

[0012] The present invention also provides a learning progress monitoring system for an online education platform, including: An identification module for identifying the test scores of the platform user on the education platform based on the learning performance preset for the platform user by the education platform; A judgment module for judging whether the test scores can reach the learning performance; An execution module, configured to, if not, restrict the examination permission of the platform user on the education platform, collect the behavior information of the platform user according to the multi-type learning data of the platform user, and detect the learning progress gap of the platform user in the current learning quarter based on the historical learning achievements pre-recorded by the education platform, wherein the multi-type learning data specifically includes basic data, interaction data, and biological data, and the behavior information specifically includes active learning behavior, passive learning behavior, and non-learning behavior; A second judgment module, configured to judge whether the learning progress gap exceeds a preset threshold; A second execution module, configured to, if it exceeds, collect the learning habit data of the platform user, dynamically construct the Ebbinghaus forgetting curve of the platform user based on the learning habit data, calculate the optimal review period of the platform user for knowledge points through the Ebbinghaus forgetting curve, and adaptively adjust the optimal review period according to the test scores, wherein the learning habit data specifically includes the average daily learning duration, the habitual learning time period, and the mastery speed of past learned knowledge.

[0013] Further, the execution module further includes: An acquisition unit, configured to, based on the connection device preset by the platform user, perform learning interaction on the connection device through the education platform to acquire the feature information of the platform user, wherein the feature information specifically includes facial expressions, eye movement trajectories, head movements, and body postures; A judgment unit, configured to judge whether the feature information matches the identity features pre-entered by the platform user; An execution unit, configured to, if so, track the pupil trajectory of the platform user when facing the connection device according to the feature information, and synchronously extract the corresponding key features of the platform user during the learning process based on the pupil trajectory, wherein the key features specifically include intonation, speech rate, pauses, and volume changes.

[0014] Further, it further includes: An acquisition module, configured to collect the practice data of the platform user for preset knowledge points based on the knowledge mastery standard preset by the education platform for the platform user, wherein the practice data specifically includes the correct rate, the completion time, and the number of answer attempts; A third judgment module, configured to judge whether the practice data can meet the knowledge mastery standard; A third execution module, configured to, if not, obtain the practice error types of the platform user according to the practice data, identify the error sources of the preset knowledge points based on the practice error types, and divide the distribution of the error areas corresponding to the error sources on the education platform, wherein the practice error types specifically include concept errors, calculation errors, and carelessness errors.

[0015] The present invention provides a method and system for monitoring the learning progress of an online education platform, which has the following beneficial effects: Through multi-dimensional data collection and intelligent analysis, the present invention improves the accuracy of learning behavior monitoring, accurately judges the learning achievement of users, ensures the objectivity of evaluation, combines various types of learning data, comprehensively tracks the learning behavior of users, avoids the limitations of single-dimensional evaluation, and at the same time, through the monitoring of active learning, passive learning and non-learning behaviors, further refines the learning status of users, improves the authenticity of data, collects data on users' personalized learning habits, dynamically constructs the Ebbinghaus forgetting curve, realizes the recommendation of accurate review time, and can adaptively optimize the review period in combination with the change trend of test scores to ensure that users can review at the best time and improve the knowledge retention rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic flowchart of an embodiment of the method for monitoring the learning progress of the online education platform of the present invention; Figure 2 It is a structural block diagram of an embodiment of the system for monitoring the learning progress of the online education platform of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. The implementation, functional features and advantages of the present invention will be further described in conjunction with the embodiments and with reference to the accompanying drawings.

[0018] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0019] Referring to the attached Figure 1 , a method for monitoring the learning progress of an online education platform in an embodiment of the present invention includes: S1: Based on the learning performance preset for the platform users by the education platform, identify the test scores of the platform users on the education platform; S2: Judge whether the test scores can reach the learning performance; S3: If not, restrict the examination rights of the platform user on the education platform, collect the behavior information of the platform user according to the multi-type learning data of the platform user, and detect the learning progress gap of the platform user in the current learning quarter based on the historical learning achievements pre-recorded by the education platform. The multi-type learning data specifically includes basic data, interaction data, and biological data, and the behavior information specifically includes active learning behavior, passive learning behavior, and non-learning behavior; S4: Determine whether the learning progress gap exceeds a preset threshold; S5: If it exceeds, collect the learning habit data of the platform user, dynamically construct the Ebbinghaus forgetting curve of the platform user based on the learning habit data, calculate the optimal review period of the platform user for knowledge points through the Ebbinghaus forgetting curve, and adaptively adjust the optimal review period according to the test scores. The learning habit data specifically includes the average daily learning duration, the habitual learning time period, and the mastery speed of past learned knowledge.

[0020] In this embodiment, the system identifies the test scores of platform users on the education platform based on the learning performance preset for the platform users in advance by the education platform, and then the system determines whether these test scores can meet the learning performance to execute corresponding steps. For example, when the system determines that the test scores of platform users on the education platform can meet the learning performance, the system will consider that the learning progress and knowledge mastery degree of the user meet the expected goals, which means 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 "qualified", and at the same time update the user's learning achievements in the learning record, improve the integrity of the learning file, recommend higher-level learning content, such as advanced courses, case studies, and practical training, etc., to help users deeply understand and apply knowledge, and allow users to independently choose whether to enter the next stage of learning, or give a short rest period to optimize the learning rhythm, combine the user's historical learning data, and adjust the future learning path to make it more in line with the user's learning habits and interests. For example, when the system determines that the test scores of platform users on the education platform cannot meet the learning performance, at this time the system will consider that the learning progress and knowledge mastery speed of the user do not meet the expected goals, that is, the user may be engaged in ineffective learning. The system will temporarily restrict the examination permission of the platform user on the education platform, collect the behavior information of the platform user according to the multi-type learning data of the platform user, and the multi-type learning data specifically includes basic data, interaction data, and biological data. The behavior information specifically includes active learning behavior, passive learning behavior, and non-learning behavior, and detect the learning progress gap of the platform user in the current learning quarter based on the historical learning achievements pre-recorded by the education platform. By comparing the test scores with the learning performance, the system can timely discover the learning deficiencies of users, prevent users from continuing to advance the course without mastering the knowledge, thereby avoiding ineffective learning. Restricting the examination permission can ensure that users will not pass by chance through repeated attempts at the examination, but guide them to first solve the learning problems, truly master the knowledge and then take the test. At the same time, based on the historical learning achievements of the education platform, detecting the progress gap of the user in the current learning quarter helps to judge whether the learning effect of the user meets the standard and provides a personalized learning path adjustment plan for the user. For users with a large learning gap, the system can push supplementary learning resources, increase targeted practice, and optimize the review strategy to ensure that users will not be forced to advance to a more complex learning stage before mastering the knowledge points. And through intelligent analysis of the learning progress and user behavior, the platform can provide more accurate and personalized learning support, make the learning assessment more scientific, and ensure that users truly master the knowledge through real-time monitoring and dynamic adjustment of the learning status, rather than just "passing the exam", thereby improving the overall learning quality. Then the system determines whether the learning progress gap of the platform user in the current learning quarter exceeds the preset threshold to execute corresponding steps;For example, when the system determines that the learning progress gap of the platform user in the current learning quarter does not exceed the pre-set threshold, the system will consider that the user's learning progress basically meets the expectations. Even if the test score has not yet reached the learning performance, it may be due to short-term fluctuations, temporary poor state, or incomplete consolidation of the understanding of some knowledge points, rather than long-term learning problems. The system will appropriately increase personalized review tasks, such as inserting targeted intensive exercises into the learning plan, to help the user consolidate the knowledge points that are weak in the test. Combining the user's learning habit data (such as learning time period, learning frequency), fine-tuning the system's review recommendation strategy to make it more in line with the user's cognitive rhythm. At the same time, providing positive incentives through the learning platform, such as small rewards, medals, learning incentive notifications, etc., to maintain the user's learning motivation, generating a learning report, feedbacking the user's current learning status to the user, and providing suggestions, such as "Your learning progress basically meets the standard, but there is still room for improvement in some knowledge points, and appropriate review can be carried out", and continuing to track the change of the user's score in the subsequent test. If the test score has a significant improvement, it is confirmed that the user's learning path is effective; if it is still lower than the learning performance, further intervention is considered; for example, when the system determines that the learning progress gap of the platform user in the current learning quarter exceeds the pre-set threshold, at this time the system will consider that the user's learning progress does not meet the expectations. The system will collect the learning habit data of the platform user. The learning habit data specifically includes the average daily learning duration, the habitual learning time period, and the mastery speed of the knowledge learned in the past. Based on these learning habit data, dynamically construct the Ebbinghaus forgetting curve of the platform user. Through the Ebbinghaus forgetting curve, calculate the best review time period for the platform user to master the knowledge points, and adaptively adjust the best review time period according to different test scores; by dynamically constructing the Ebbinghaus forgetting curve based on the user's individual data, the system can accurately predict the forgetting speed of the user's knowledge points, so as to push review tasks at the appropriate time, avoiding wasting time caused by premature review or excessive forgetting caused by late review, and making adaptive adjustments in combination with the user's test scores, so that the review rhythm matches the degree of knowledge mastery, ensuring that the learning content can be effectively consolidated, and at the same time being able to identify the user's learning mode and optimize the review arrangement accordingly. For example, for users with scattered learning time, the system can appropriately increase short-term and high-frequency review tasks, while for users with concentrated learning, the review interval can be optimized to make it more in line with the memory law. This personalized adjustment can effectively narrow the learning progress gap, help low-efficiency learners improve their learning effects, and ensure that users with different test scores can get appropriate learning suggestions, making the learning path more flexible. For example, for users with low test scores, the system can increase the review frequency and strengthen the consolidation of key knowledge, while for users with scores close to passing, the repetitive review can be appropriately reduced to avoid learning fatigue.;

[0021] It should be noted that the learning habit data of the platform users is collected, and based on the learning habit data, the Ebbinghaus forgetting curve of the platform users is dynamically constructed. Through the Ebbinghaus forgetting curve, the best review period for the platform users to master knowledge points is calculated. The specific example is as follows: Suppose Xiaoming, a platform user, is a college student who is using an educational platform to study "Newton's Three Laws"; the system records his learning habit data as follows: Average daily learning duration: 2 hours; Habituated learning time period: 19:00 - 21:00; Past knowledge mastery speed: Usually, it takes 4 reviews to reach 90% mastery; Forgetting speed: By analyzing his past learning data, the system finds that he forgets 40% on the first day, 70% on the third day, and 90% on the seventh day, indicating that Xiaoming has a relatively fast forgetting speed; Score of the most recent test: In the test on March 5, Xiaoming scored 50% on this knowledge point, indicating a poor mastery; Processing flow of the system. For the first learning (March 1), Xiaoming learned "Newton's Three Laws" from 19:00 to 21:00 on March 1; the system detected that his forgetting curve was relatively steep, so a personalized review plan was immediately formulated after learning; Initial review plan generated by the system, March 2 (the first day): First review (to prevent short-term forgetting and consolidate memory); March 4 (the third day): Second review (to strengthen memory and improve proficiency); March 7 (the sixth day): Third review (to enhance long-term memory); March 14 (the 13th day): Fourth review (to ensure long-term mastery of knowledge points); Influence of test scores on review adjustment (March 5); In the test on March 5, Xiaoming scored 50% on Newton's Three Laws, indicating insufficient understanding; The system detected a low test score and adjusted the review plan for the following optimizations: Add an intensive review on March 6 (increase additional practice); Extend the review time on March 7 (provide a more in-depth review); Add a review task on March 10 (shorten the interval and accelerate knowledge consolidation); Final review plan after adjustment: March 2 (the first day): First review; March 4 (the third day): Second review; March 6 (New): Intensive review (the system pushes additional practice questions to improve understanding); March 7 (Day 6): Third review (extended time); March 10 (New): Additional review (to detect consolidation); March 14 (Day 13): Fourth review; In summary, for the final effect of the above example content, the system makes Xiaoming's learning plan more accurate, effectively reduces forgetting, and improves test scores; because the system dynamically adjusts the review time according to Xiaoming's forgetting characteristics and test feedback, making learning more efficient; at the same time, the system combines Xiaoming's habitual learning time and pushes review tasks during the most suitable period for him to improve learning effects; that is, through personalized Ebbinghaus forgetting curve and test data analysis, the system realizes intelligent review arrangement, making Xiaoming's learning process more targeted and efficient.

[0022] In this embodiment, in step S3 of collecting the behavior information of the platform user, it further includes: S31: Based on the connection device preset by the platform user, perform learning interaction with the connection device through the education platform to obtain the characteristic information of the platform user, where the characteristic information specifically includes facial expression, eye movement trajectory, head movement, and body posture; S32: Determine whether the characteristic information matches the identity characteristics pre-entered by the platform user; S33: If so, according to the characteristic information, track the pupil trajectory of the platform user when facing the connection device, and based on the pupil trajectory, synchronously extract the corresponding key characteristics of the platform user during the learning process, where the key characteristics specifically include intonation, speech rate, pause, and volume change.

[0023] In this embodiment, the system, based on the connection devices preset by the platform users, conducts learning interactions with the connection devices through the education platform, obtains the permission grant of the platform users to the education platform, and acquires the feature information of the platform users from the cameras of the connection devices. The feature information specifically includes facial expressions, eye movement trajectories, head movements, and body postures. Then, the system determines whether these feature information match the identity features pre-entered by the platform users to execute corresponding steps. For example, when the system determines that the feature information of the platform users cannot match the identity features pre-entered by the platform users, the system will consider that the user currently conducting the learning interaction may not be the actual platform user himself / herself, and there is a risk of violations such as identity forgery, proxy learning, and proxy exam-taking. The system will temporarily lock the learning permissions of the user, prevent them from performing key operations such as taking exams and submitting assignments, prompt the user to re-verify their identity, and require the user to adjust their posture (such as looking directly at the camera, turning the head left and right, etc.) until more complete feature information is obtained and compared with the pre-stored identity information on the platform again. At the same time, through multiple authentication methods, such as SMS verification codes, face recognition + passwords, fingerprint verification, etc., further identity confirmation is carried out. And if the user passes the secondary authentication, they are allowed to continue the learning interaction and update their feature information database to adapt to possible feature changes (such as wearing glasses, light changes, etc.). For example, when the system determines that the feature information of the platform users can match the identity features pre-entered by the platform users, at this time, the system will consider that the user currently conducting the learning interaction belongs to the actual platform user himself / herself. The system will track the pupil trajectory of the platform user when facing the connection device based on these feature information, and synchronously extract the corresponding key features of the platform user during the learning process according to different pupil trajectories. The key features specifically include intonation, speech rate, pauses, and volume changes. Through pupil trajectory tracking, the system can determine whether the user's attention is focused on the learning content, identify whether the user has problems such as distracted attention and long-term lack of focus, so as to evaluate their concentration. Combining with eye movement pattern analysis, the system can judge whether the user is quickly skimming, carefully reading, or re-reading, and even detect whether there are difficulties in understanding when staring at the same content for a long time. At the same time, through voice feature analysis (intonation, speech rate, pauses, volume changes), the system can judge the emotional changes of the learner, such as anxiety, confusion, excitement, fatigue, etc. If the user suddenly slows down the speech rate, increases the pauses, or lowers the volume when reading aloud or answering questions, it may indicate that the user is thinking or encountering difficulties. On the contrary, if the speech rate speeds up and the volume rises, it may mean that the user is more familiar with the content or more confident. And combining with the user's learning status, the system can provide real-time adaptive adjustments, such as pushing short rest reminders or adjusting the learning rhythm in a timely manner when detecting a decrease in concentration or large emotional fluctuations to prevent learning fatigue. If it is detected that the user's speech expression of a certain knowledge point is less fluent or the intonation is abnormal, the system can infer that the understanding of this knowledge point may be insufficient, automatically mark this content, and give personalized review recommendations later.

[0024] In this embodiment, before step S5 of dynamically constructing the Ebbinghaus forgetting curve of the platform user, the following steps are further included: S501: Based on the knowledge mastery standard preset for the platform user by the education platform, collect the exercise data of the platform user for the preset knowledge points. Specifically, the exercise data includes the correct rate, completion time, and number of answering times. S502: Determine whether the exercise data can meet the knowledge mastery standard. S503: If not, according to the exercise data, obtain the exercise error types of the platform user, and based on the exercise error types, identify the error sources of the preset knowledge points, and divide the error area distribution corresponding to the error sources on the education platform. Specifically, the exercise error types include concept errors, calculation errors, and carelessness errors.

[0025] In this embodiment, the system collects the practice data of platform users on pre-set knowledge points based on the knowledge mastery standards pre-set for platform users by the education platform. The practice data specifically includes the correct rate, completion time, and number of answering times. Then, the system determines whether these practice data can meet the knowledge mastery standards to execute corresponding steps. For example, when the system determines that the practice data of platform users on pre-set knowledge points can meet the knowledge mastery standards, the system will consider that the user has reached the expected level in the learning of this knowledge point, showing a high correct rate, a reasonable completion time, and the number of answering times meeting the learning objectives. The system will update the status of this knowledge point to "mastered" in the user's learning profile, reduce the recommended frequency of subsequent repeated practice, allow the user to skip the basic practice of this knowledge point, and directly enter the learning of higher-order application questions or related knowledge points. At the same time, combined with the Ebbinghaus forgetting curve, the system predicts the possible future forgetting time of the user, sets appropriate review reminders, rather than repeating ineffective reviews frequently. According to the user's learning habits, the system can appropriately adjust the review content, such as using different question types or practical applications, to prevent rote memorization, and give the user incentive measures such as learning points, badges, and achievement unlocking to enhance the learning motivation, send a learning achievement report, so that the user can intuitively see their progress and improve the sense of achievement. For example, when the system determines that the practice data of platform users on pre-set knowledge points does not meet the knowledge mastery standards, at this time, the system will consider that the user's level on this knowledge point has not reached the expected level. The system will obtain the types of practice errors of platform users according to different practice data. The types of practice errors specifically include conceptual errors, calculation errors, and careless errors. Based on these types of practice errors, the system identifies the error sources of these pre-set knowledge points and divides the distribution of misunderstandings corresponding to the error sources on the education platform. By identifying the common types of errors in users' practice (such as conceptual errors, calculation errors, or careless errors), the system can accurately judge the weak links in users' understanding of knowledge points. Combined with the distribution of misunderstandings, the system can further analyze the error sources, whether it is due to unclear basic concepts, unfamiliar calculation methods, or mistakes caused by inattentiveness. At the same time, for different types of errors, the system can dynamically adjust the user's learning content. For example, in the case of conceptual errors, recommend that the user re-learn the core theory of this knowledge point and provide detailed explanations and examples. For example, in the case of calculation errors, guide the user to conduct calculation training and provide step-by-step analysis to improve the calculation accuracy. For example, in the case of careless errors, enhance the attention prompt for the user in similar problems, add verification steps or provide an error review function. Through personalized adjustment, ensure that the user strengthens in the correct knowledge direction instead of simply repeating wrong practice. And by collecting and analyzing a large amount of users' practice error data, the system can construct a knowledge point misunderstanding distribution map to help the education platform optimize the question setting and teaching content. The distribution of misunderstandings can also be used for group analysis to find the knowledge points that most users are prone to make mistakes in, so as to adjust the teaching strategy and improve the overall learning efficiency.

[0026] In this embodiment, before step S3 of detecting the learning progress gap of the platform user in the current learning quarter, the following steps are further included: S301: Based on the course content in the current learning quarter, obtain the average learning progress of all platform users for the course content. Specifically, the course content includes chapter progress, exercises and assignments, key quizzes, and expected learning duration; S302: Determine whether the platform user can complete the average learning progress; S303: If not, calculate the learning lag rate of the platform user according to the behavior information. Based on the learning lag rate, compare it with the preset lag levels of the education platform, and dynamically adjust the tutoring content of the platform user on the education platform through the lag levels. Specifically, the lag levels include slight lag, moderate lag, and severe lag, and the tutoring content includes recommended priority learning tasks, providing personalized review content, and emergency intervention contacts.

[0027] In this embodiment, the system obtains the average learning progress of all platform users on the course content based on the course content of the current learning quarter, which specifically includes chapter progress, exercises and homework, key tests and expected learning time, and then the system determines whether the platform user can complete the average learning progress of all platform users on the course content to execute the corresponding steps; for example, when the system determines that the platform user can complete the average learning progress of all platform users on the course content, the system will consider that the user's learning rhythm is in line with the group learning level, indicating that there is no obvious lag or advance in the course advancement of the current learning quarter, and the learning status is relatively stable. The system will combine the user's practice data and test results to recommend additional knowledge consolidation exercises, such as extension questions, case analysis or high-level thinking questions, to enhance the depth of knowledge mastery. If the user's performance in some key tests or homework is slightly insufficient, the system can intelligently push corresponding reinforcement exercises to help the user further improve the quality of learning. At the same time, if the user's progress is stable but slightly ahead, the system can provide advanced courses or more practical tasks to guide the user to learn in depth. , to avoid reducing learning interest due to leading progress. If the user's progress is stable but tends to the lower limit of the average, the system can provide appropriate learning reminders or time management suggestions to help them maintain long-term learning motivation, and timely recommend learning discussion groups or interactive exchanges with users with the same progress to improve learning participation and continuity, and provide data visualization feedback, such as learning progress curves, achievement badges, etc., to enhance the user's sense of achievement and self-motivation; for example, when the system determines that the platform user cannot complete the average learning progress of all platform users on the course content, the system will consider that the user's learning rhythm does not meet the group learning level, and there may be a significant lag in the advancement of the course in the current learning quarter. The system will calculate the user's learning lag rate based on the user's behavior information, and based on different learning lag rates, benchmark the lag levels pre-set by the education platform. The lag levels specifically include slight lag, moderate lag and severe lag. Through different lag levels, the platform user's tutoring content on the education platform is dynamically adjusted. The tutoring content specifically includes recommending priority learning tasks, providing personalized review content and emergency intervention contacts;The system can distinguish different situations of slight, moderate, and severe lags by calculating the learning lag rate of users and benchmarking the lag levels, avoiding a one-size-fits-all intervention method. Users with slight lags can receive appropriate learning reminders and priority task recommendations, while users with severe lags can trigger stronger intervention measures, such as arranging tutor tutoring or notifying parents. At the same time, according to the current learning progress, the system intelligently arranges the course content that users most need to make up for, ensuring efficient tutoring, rather than passively learning in a fixed order. Combining the user's past practice data and learning habits, the system pushes error-prone knowledge points, intensive exercises, or micro-courses to enhance the effect of knowledge remediation. For users with severe lags, the system will contact tutors, head teachers, or parents to ensure timely intervention and provide offline or online tutoring to prevent further backwardness. And by adaptively adjusting the tutoring plan, users can narrow the learning progress gap in the way that best suits their own situation, without generating anxiety or losing motivation due to excessive lags. Moreover, personalized task recommendations and review plans can enhance the pertinence and efficiency of learning, enabling users to improve their grades faster and catch up with the group progress again.

[0028] It should be noted that, based on the behavior information, the learning lag rate of the platform users is calculated. According to the learning lag rate, the lag levels preset by the education platform are benchmarked. Through the lag levels, the tutoring content of the platform users on the education platform is dynamically adjusted. The specific examples are as follows: Suppose Xiaoming is a junior high school student studying the "Algebra Basics" course on an online education platform. The course has a total of 10 chapters, including basic operations, equation solving, function graphs, geometric applications, etc. To help students master knowledge, the platform sets an average learning progress standard and judges their learning progress by collecting users' learning data. Currently, the average learning progress of all students is 6 chapters, but Xiaoming has only completed 4 chapters. Step 1: The system calculates the learning lag rate. The calculation formula for the learning lag rate is as follows: According to the preset lag level division, Slight lag (<10%): No intervention is required, and the system only reminds users to speed up their learning progress. Moderate lag (10%-30%): The system pushes personalized tutoring tasks and provides intelligent recommended learning content. Severe lag (>30%): The system implements a mandatory tutoring plan, notifies parents or tutors to intervene, and adjusts the learning path. Xiaoming's learning lag rate reaches 33.33%, which belongs to severe lag, and the system starts emergency remedial measures. Step 2: The system analyzes learning behavior information. The system collects Xiao Ming’s behavior information, which mainly includes the following data: Study time: The average student studied 20 minutes a day, while other students studied 45 minutes a day. The study frequency is low, only 3 days a week, while other students study 5-6 days a week on average; Practice data: Low accuracy: The accuracy of exercises in some chapters is only 50%, while the overall accuracy should reach more than 80% to meet the mastery standard; Error type analysis: Conceptual errors (60%): They have a misunderstanding of the basic concept of “factorization” and often choose the wrong method; Calculation errors (30%): Often omitting the negative sign or writing the wrong number during calculations; Careless errors (10%): skipping steps when answering questions, resulting in calculation errors; Study habits: Xiao Ming is used to studying after 10 pm, but his concentration is low at this time, which leads to a decrease in comprehension efficiency; Review too infrequently, rarely reviewing what you have learned, and only intensively studying before the exam; Step 3: The system executes targeted remedial measures. Since Xiao Ming is judged as "severely lagging behind", the system adopts the following remedial strategies: First, the priority learning tasks are pushed. The system marks Xiao Ming's factorization chapter as "priority tutoring content" and displays it at the top of the learning homepage. In the daily learning recommendations, the system automatically pushes "factorization" related exercises to Xiao Ming's task list. Since Xiao Ming is more likely to study after 10 pm, but his concentration is lower at this time, the system recommends adjusting the study time and recommends arranging review tasks between 7 and 9 pm, and setting study reminders. The next step is the personalized review content. Based on the Ebbinghaus forgetting curve, the system calculates the best review time for Xiao Ming and automatically arranges it: Day 1 Review basic concepts; On the 3rd day, carry out special exercises; On the 7th day, a simulation test was conducted to strengthen memory; The system will recommend micro-course videos on "factorization" to Xiao Ming, and provide a voice interaction function so that he can ask questions; Through intelligent detection of practice errors, special exercises are provided, such as conceptual error correction, supplementary basic knowledge points of factorization, and interactive exercises. Through calculation error exercises: "calculation reinforcement" exercises are generated to help Xiao Ming reduce low-level errors; Finally, emergency intervention measures are initiated. Since Xiaoming has a relatively high lag rate, the system automatically sends notifications to parents and tutors, reminding them to pay attention to Xiaoming's learning progress. The system provides a one-on-one online Q&A function and suggests that Xiaoming make an appointment for online tutoring with a teacher to help solve problems in concept understanding. If the learning progress has not improved after one week, the system will automatically arrange for a tutor or learning advisor to follow up on the learning and provide more detailed learning suggestions. Through continuous monitoring and adjustment, the system will continuously monitor Xiaoming's learning progress within the next week and adopt a dynamic adjustment strategy: if Xiaoming completes 6 chapters within 7 days, the system will lift the learning restrictions and continue to provide normal learning recommendations; if Xiaoming still lags behind, the system will further tighten the learning permissions, such as restricting access to new courses and increasing the priority of remedial tasks. In summary, the above example content objectively judges whether the user's learning progress meets the group standard by calculating the learning lag rate. At the same time, based on data such as the user's error type and learning habits, it provides a personalized learning path to improve the learning effect. And through intelligent exercises, review reminders, etc., it improves the user's mastery of knowledge points. For users with serious lags, a multi-party collaboration method involving teachers and parents is adopted to ensure that the learning progress is improved. That is, the system can help Xiaoming timely discover problems, adjust learning strategies, gradually keep up with the course progress, and improve the overall learning effect.

[0029] In this embodiment, in step S2 of judging whether the test score can reach the learning performance, it further includes: S21: Based on the learning performance structure preset by the education platform, identify the score weight of the test score; S22: Judge whether the score weight reaches various standards of the learning performance structure; S23: If not, then according to the score weight, collect the knowledge short-board information corresponding to the platform user, mark the knowledge sections of the knowledge short-board information, and divide the knowledge content that the platform user needs to make up for from the knowledge sections.

[0030] In this embodiment, the system identifies the score weights of test scores based on the learning performance structure preset by the education platform, and then the system determines whether the score weights meet various standards of the learning performance structure to execute corresponding steps; for example, when the system determines that the score weights of test scores can meet various standards of the learning performance structure, the system will consider that the learning performance of the platform user at the current stage has reached the expected goal, has the corresponding knowledge mastery level, 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 the learning level to encourage continuous learning. If the test score weight of the user meets the learning requirements of a higher stage, the system can recommend the user to unlock more difficult learning content, such as advanced courses, challenge tasks or advanced evaluations. At the same time, according to the user's performance, relevant knowledge points are recommended to encourage the user to expand the learning scope. For example, if the user performs excellently in a math test, the system can recommend more complex application problems or math competition content. According to the user's learning interests and test scores, high-quality learning materials are pushed, such as topic explanations, academic papers, online experiments, etc. And even if the user reaches the performance standard, the system will still analyze the user's answering characteristics, such as whether there are some knowledge points that are weakly mastered, so as to provide targeted consolidation exercises, continuously monitor the user's learning trend to ensure that the user maintains a stable performance in the subsequent learning process, and provide review reminders for possible knowledge forgetting; for example, when the system determines that the score weights of test scores cannot meet various standards of the learning performance structure, at this time the system will consider that the learning performance of the platform user at the current stage is below expectations. The system will collect the corresponding knowledge short-board information of the platform user according to the score weights, mark the knowledge sections with knowledge short-board information on the education platform, and divide the knowledge content that the platform user needs to make up for from the knowledge sections. The system can accurately locate the user's weak knowledge points based on the score weights, avoid adopting a "one-size-fits-all" review strategy, improve learning efficiency. By dividing the short-board content through knowledge sections, the system can ensure that the make-up content accurately matches the user's knowledge defects, avoid over-reviewing the content that has been mastered, and at the same time dynamically recommend make-up content according to the user's weak knowledge points, including targeted exercises, video explanations, interactive courses, etc., to make the make-up more targeted, adjust the make-up priority to ensure that the user first strengthens the core basic knowledge and then advances to improve, avoid affecting the overall learning progress due to knowledge gaps, and continuously monitor the make-up effect to ensure that the user can make up for the knowledge short-board after make-up and improve the overall learning performance. Appropriate intervention is carried out on low-performance users, such as providing learning guidance, AI intelligent question answering, one-on-one teacher tutoring, etc., to reduce the risk of unqualified knowledge mastery.

[0031] In this embodiment, in step S4 of determining whether the learning progress gap exceeds the preset threshold, it further includes: S41: Dynamically update the learning progress of the platform user after learning is completed based on the preset learning cycle of the platform user; S42: Determine whether the learning progress has reached a preset lower limit for a single progress; S43: If so, generate the learning duration of the platform user based on the learned content of the platform user, and dynamically update the learning goal of the platform user according to the learning duration, where the learned content specifically includes course chapter information, exercise information, and test information completed within the current cycle.

[0032] In this embodiment, the system dynamically updates the learning progress of platform users after they complete their learning based on the learning cycle preset by the platform users in advance. Then, the system determines whether the learning progress has reached the preset lower limit of the single - time progress to execute the corresponding steps. For example, when the system determines that the learning progress of platform users after they complete their learning has not reached the preset lower limit of the single - time progress, the system will consider that the user has not completed enough learning content during this learning process, and there may be problems such as insufficient learning time, low concentration, and low learning efficiency. The system will collect the user's learning duration, determine whether there are overly short learning periods, detect the interaction data during the learning process (such as mouse clicks, swipes, and answering frequencies), identify whether there are long - term stagnations or passive learning situations, monitor the learning concentration (such as capturing facial expressions and eye movement trajectories through a camera), analyze whether there are frequent distractions or low - investment phenomena, and at the same time remind the user to adjust the learning time arrangement, suggest appropriately increasing the daily learning duration, and according to the user's current learning situation, re - plan the learning tasks for the next stage to ensure that the overall learning progress is not affected, guide the user to conduct supplementary learning, such as adding quizzes, consolidation exercises, or knowledge point reviews, to improve the learning quality. For example, when the system determines that the learning progress of platform users after they complete their learning has reached the preset lower limit of the single - time progress, at this time, the system will consider that the user has completed the basic learning content during this learning process. The system will generate the learning duration of the platform users based on the learned content of the platform users, and the learned content specifically includes the course chapter information, exercise information, and test information completed within the current cycle. According to different learning durations, the system will dynamically update the learning goals of the platform users. By judging whether the learning progress reaches the minimum requirement, the system can ensure that users complete the basic learning tasks within each learning cycle, avoid procrastination or accumulation of unfinished content. Dynamically adjusting the learning goals according to the learning duration can make the goals more in line with the user's learning rhythm, avoid fatigue caused by over - learning or insufficient learning caused by too low goals. At the same time, based on the learned content of the platform users (course chapters, exercises, tests), comparing with the learning goals can ensure that the content learned by the user covers the necessary knowledge points and does not repeat the knowledge that has been mastered. Through the dynamic adjustment of the learning duration, the system can identify the user's learning rhythm (such as learning quickly and skipping forward or learning slowly and studying carefully) and optimize the subsequent learning arrangements accordingly to ensure that the learning rhythm matches the user's ability. And updating the learning goals in real - time can let the user clearly understand their learning progress, enhance the motivation and sense of achievement in learning. According to different learning durations, the system will intelligently recommend more suitable review times and learning methods, such as short - term and efficient learning modes or in - depth and intensive learning modes, to make the learning more in line with the user's habits.

[0033] 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 the platform users, it further includes: S101: Identify the learning interaction methods pre-selected by the platform user on the education platform, where the learning interaction methods specifically include video-based learning, text-based learning, and interactive learning; S102: Determine whether the learning interaction method conforms to the current learning quarter; S103: If not, dynamically adjust the learning path of the platform user based on the test scores, where the learning path specifically includes the course content structure and the exercise evaluation method.

[0034] In this embodiment, the system identifies the learning interaction method pre-selected by the platform user on the education platform. The learning interaction method specifically includes video-based learning, text-based learning, and interactive learning. Then, the system determines whether the learning interaction method conforms to the current learning quarter to execute corresponding steps. For example, when the system determines that the learning interaction method pre-selected by the platform user on the education platform can conform to the current learning quarter, the system will consider that the user's learning method adapts to the course characteristics and teaching requirements of the current quarter, thereby effectively improving learning efficiency and knowledge absorption effect. The system will automatically match the optimal teaching resources (such as video courses, reading materials, online interactive exercises) according to the video-based learning, text-based learning, or interactive learning selected by the user, ensuring that the learning method matches the teaching objectives. At the same time, analyze the user's past learning duration, completion progress, and understanding effect, and dynamically adjust the learning tasks. For example, for users who are accustomed to video-based learning, the system can add more efficient micro-lesson videos, reduce lengthy content, improve the learning experience, and increase real-time quizzes, interactive Q&A, and gamified learning tasks to improve user participation and ensure the maximization of learning effects. For example, when the system determines that the learning interaction method pre-selected by the platform user on the education platform cannot conform to the current learning quarter, at this time, the system will consider that the user's learning method cannot adapt to the course characteristics and teaching requirements of the current quarter. The system will dynamically adjust the learning path of the platform user based on different test scores. The learning path specifically includes the course content structure and the exercise evaluation method. The system actively adjusts the learning path to ensure that the user's learning method adapts to the teaching content. For example, if the current quarter emphasizes practical training and the user selects text-based learning, the system will guide the user to participate more in interactive exercises and case analyses to enhance practical ability. At the same time, based on the user's test scores, analyze the user's knowledge mastery situation and dynamically adjust the presentation order of the 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 on to advanced content instead of progressing in a fixed order. And different users have different adaptabilities to exercise types. The system can adjust the difficulty and feedback method of the exercises according to the user's test performance. For example, for users who are good at logical reasoning but perform poorly in application problems, 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.

[0035] Reference appendix Figure 2 , which is a learning progress monitoring system of an online education platform in an embodiment of the present invention, including: An identification module 10, configured to identify the test scores of the platform user on the education platform based on the learning performance preset for the platform user by the education platform; A judgment module 20, configured to judge whether the test scores can reach the learning performance; Execution module 30, which is used to, if not, restrict the examination permission of the platform user on the education platform, collect the behavior information of the platform user according to the multi-type learning data of the platform user, and detect the learning progress gap of the platform user in the current learning quarter based on the historical learning achievements pre-recorded by the education platform. The multi-type learning data specifically includes basic data, interaction data, and biological data, and the behavior information specifically includes active learning behavior, passive learning behavior, and non-learning behavior; The second judgment module 40 is used to judge whether the learning progress gap exceeds a preset threshold; The second execution module 50 is used to, if it exceeds, collect the learning habit data of the platform user, dynamically construct the Ebbinghaus forgetting curve of the platform user based on the learning habit data, calculate the best review period for the platform user to master knowledge points through the Ebbinghaus forgetting curve, and adaptively adjust the best review period according to the test scores. The learning habit data specifically includes the average daily learning duration, the habitual learning time period, and the mastering speed of the knowledge learned in the past.

[0036] In this embodiment, the recognition module 10 recognizes the test scores of platform users on the education platform based on the learning performance preset by the education platform for the platform users in advance, and then the judgment module 20 judges whether these test scores can reach the learning performance to execute corresponding steps; for example, when the system determines that the test scores of platform users on the education platform can reach the learning performance, the system will consider that the learning progress and knowledge mastery degree of the user meet the expected goals, which means 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 this knowledge point or course as "mastered" or "qualified", and at the same time update the user's learning achievements in the learning record, improve the integrity of the learning file, recommend higher-level learning content, such as advanced courses, case analyses, and practical training, etc., to help users deeply understand and apply knowledge, and allow users to independently choose whether to enter the next stage of learning, or give a short rest period to optimize the learning rhythm, combine the user's historical learning data, and adjust the future learning path to make it more in line with the user's learning habits and interests; for example, when the system determines that the test scores of platform users on the education platform cannot reach the learning performance, at this time the execution module 30 will consider that the learning progress and knowledge mastery speed of the user do not meet the expected goals, that is, the user may be engaged in ineffective learning. The system will temporarily restrict the examination rights of platform users on the education platform, collect the behavior information of platform users according to the multi-type learning data of platform users, and the multi-type learning data specifically includes basic data, interaction data, and biological data. The behavior information specifically includes active learning behaviors, passive learning behaviors, and non-learning behaviors, and detect the learning progress gap of platform users in the current learning quarter based on the historical learning achievements pre-recorded by the education platform; through the comparison of the test scores and the learning performance, the system can timely discover the learning deficiencies of users, prevent users from continuing to advance the course without mastering the knowledge, thereby avoiding ineffective learning. Restricting the examination rights can ensure that users will not pass by chance through repeated attempts at the examination, but guide them to first solve the learning problems and truly master the knowledge before taking the test. At the same time, based on the historical learning achievements of the education platform, detecting the progress gap of users in the current learning quarter helps to judge whether the learning effect of users is up to standard and provide a personalized learning path adjustment plan for them. For users with a large learning gap, the system can push supplementary learning resources, increase targeted exercises, and optimize the review strategy to ensure that users will not be forced to advance to a more complex learning stage before mastering the knowledge points. And through intelligent analysis of the learning progress and user behavior, the platform can provide more accurate and personalized learning support, make the learning assessment more scientific, and ensure that users truly master the knowledge through real-time monitoring and dynamic adjustment of the learning state, rather than just "passing the exam", thereby improving the overall learning quality; then the second judgment module 40 judges whether the learning progress gap of platform users in the current learning quarter exceeds the preset threshold to execute corresponding steps;For example, when the system determines that the learning progress gap of the platform user in the current learning quarter does not exceed the pre-set threshold, the system will consider that the user's learning progress basically meets the expectations. Even if the test score has not yet reached the learning performance, it may be due to short-term fluctuations, temporary poor state, or incomplete consolidation of the understanding of some knowledge points, rather than long-term learning problems. The system will appropriately increase personalized review tasks, such as inserting targeted intensive exercises into the learning plan, to help the user consolidate the knowledge points that are weak in the test. Combining the user's learning habit data (such as learning time period, learning frequency), fine-tuning the system's review recommendation strategy to make it more in line with the user's cognitive rhythm. At the same time, providing positive incentives through the learning platform, such as small rewards, medals, learning incentive notifications, etc., to maintain the user's learning motivation, generating a learning report, feedbacking the user's current learning status to the user, and providing suggestions, such as "Your learning progress basically meets the standard, but there is still room for improvement in some knowledge points. You can conduct appropriate reviews", and continuing to track the user's score changes in subsequent tests. If the test score has a significant improvement, it is confirmed that the user's learning path is effective; if it is still lower than the learning performance, further intervention is considered; For example, when the system determines that the learning progress gap of the platform user in the current learning quarter exceeds the pre-set threshold, at this time, the second execution module 50 will consider that the user's learning progress does not meet the expectations. The system will collect the learning habit data of the platform user. The learning habit data specifically includes the average daily learning duration, the habitual learning time period, and the mastery speed of the knowledge learned in the past. Based on these learning habit data, dynamically construct the Ebbinghaus forgetting curve of the platform user. Through the Ebbinghaus forgetting curve, calculate the best review time period for the platform user to master the knowledge points. According to different test scores, adaptively adjust the best review time period; By dynamically constructing the Ebbinghaus forgetting curve based on the user's individual data, the system can accurately predict the user's forgetting speed of the knowledge points, so as to push review tasks at the appropriate time, avoiding wasting time caused by premature review or excessive forgetting caused by too late review. Combining with the user's test scores for adaptive adjustment, making the review rhythm match the degree of knowledge mastery, ensuring that the learning content can be effectively consolidated, and at the same time being able to identify the user's learning mode and optimize the review arrangement accordingly. For example, for users with scattered learning time, the system can appropriately increase short-term and high-frequency review tasks, while for users with concentrated learning, the review interval can be optimized to make it more in line with the memory law. This personalized adjustment can effectively narrow the learning progress gap, help low-efficiency learners improve their learning effects, and ensure that users with different test scores can get appropriate learning suggestions, making the learning path more flexible. For example, for users with lower test scores, the system can increase the review frequency and strengthen the consolidation of key knowledge. For users with scores close to passing, the repetitive review can be appropriately reduced to avoid learning fatigue.;

[0037] In this embodiment, the execution module further includes: An acquisition unit, configured to perform learning interaction with the connected device through the education platform based on the connected device preset by the platform user, and acquire the feature information of the platform user, where the feature information specifically includes facial expressions, eye movement trajectories, head movements, and body postures; A judgment unit, configured to judge whether the feature information matches the identity features pre-entered by the platform user; An execution unit, configured to, if so, track the pupil trajectory of the platform user when facing the connected device according to the feature information, and synchronously extract the corresponding key features of the platform user during the learning process based on the pupil trajectory, where the key features specifically include intonation, speech rate, pauses, and volume changes.

[0038] In this embodiment, the system is based on the connection devices preset by the platform users. Through the education platform, the system conducts learning interactions with the connection devices, obtains the permission granted by the platform users to the education platform, and acquires the feature information of the platform users from the cameras of the connection devices. The feature information specifically includes facial expressions, eye movement trajectories, head movements, and body postures. Then, the system determines whether these feature information match the identity features pre-entered by the platform users to execute corresponding steps. For example, when the system determines that the feature information of the platform users cannot match the identity features pre-entered by the platform users, the system will consider that the user currently conducting the learning interaction may not be the platform user himself / herself, and there is a risk of illegal behaviors such as identity forgery, proxy learning, and proxy examination. The system will temporarily lock the learning permissions of the user, prevent them from performing key operations such as examinations and homework submissions, prompt the user to re-verify their identity, and require the user to adjust their posture (such as looking directly at the camera, turning the head left and right, etc.) until more complete feature information is obtained again and compared with the pre-stored identity information in the platform. At the same time, through multiple authentication methods, such as SMS verification codes, face recognition + passwords, fingerprint verification, etc., further identity confirmation is carried out. And if the user passes the secondary authentication, they are allowed to continue the learning interaction and update their feature information database to adapt to possible feature changes (such as wearing glasses, light changes, etc.). For example, when the system determines that the feature information of the platform users can match the identity features pre-entered by the platform users, at this time, the system will consider that the user currently conducting the learning interaction belongs to the platform user himself / herself. The system will track the pupil trajectory of the platform user when facing the connection device based on these feature information. According to different pupil trajectories, the system will synchronously extract the corresponding key features of the platform user during the learning process. The key features specifically include intonation, speech rate, pauses, and volume changes. Through pupil trajectory tracking, the system can determine whether the user's attention is focused on the learning content, identify whether the user has problems such as distracted attention and long-term lack of focus, so as to evaluate their concentration. Combining eye movement pattern analysis, the system can determine whether the user is quickly skimming, carefully reading, or looking back, and even detect whether there are difficulties in understanding when staring at the same content for a long time. At the same time, through voice feature analysis (intonation, speech rate, pauses, volume changes), the system can judge the emotional changes of the learner, such as anxiety, confusion, excitement, fatigue, etc. If the user suddenly slows down the speech rate, increases pauses, or decreases the volume when reading aloud or answering questions, it may indicate that the user is thinking or encountering difficulties. On the contrary, if the speech rate speeds up and the volume rises, it may represent that the user is more familiar with the content or more confident. And combining the learning state of the user, the system can provide real-time adaptive adjustments. For example, when detecting a decrease in concentration or large emotional fluctuations, a short break reminder is pushed in a timely manner or the learning rhythm is adjusted to prevent learning fatigue. If it is detected that the user's speech expression of a certain knowledge point is less fluent or the intonation is abnormal, the system can infer that the understanding of this knowledge point may be insufficient, automatically mark this content, and give personalized review recommendations later.

[0039] In this embodiment, it further includes: A collection module, configured to collect the practice data of the platform user on the preset knowledge points based on the knowledge mastery standard preset for the platform user by the education platform, where the practice data specifically includes the correct rate, the completion time, and the number of answer attempts; A third judgment module, configured to judge whether the practice data can meet the knowledge mastery standard; A third execution module, configured to, if not, obtain the practice error types of the platform user according to the practice data, identify the error sources of the preset knowledge points based on the practice error types, and divide the distribution of the misunderstandings corresponding to the error sources on the education platform, where the practice error types specifically include concept errors, calculation errors, and careless errors.

[0040] In this embodiment, the system collects the practice data of platform users on preset knowledge points based on the knowledge mastery standards preset for platform users by the education platform. The practice data specifically includes the correct rate, completion time, and number of answering questions. Then, the system determines whether these practice data can meet the knowledge mastery standards to execute corresponding steps. For example, when the system determines that the practice data of platform users on preset knowledge points can meet the knowledge mastery standards, the system will consider that the user has reached the expected level in the learning of this knowledge point, showing a high correct rate, reasonable completion time, and the number of answering questions conforming to the learning objectives. The system will update the status of this knowledge point to "mastered" in the user's learning profile, reduce the recommended frequency of subsequent repeated practice, allow the user to skip the basic practice of this knowledge point, and directly enter the learning of higher-order application questions or related knowledge points. At the same time, combined with the Ebbinghaus forgetting curve, the system predicts the possible future forgetting time of the user, sets appropriate review reminders, rather than frequently repeating ineffective reviews. According to the user's learning habits, the system can appropriately adjust the review content, such as using different question types or practical applications, to prevent rote memorization, and give the user incentives such as learning points, badges, and achievement unlocking to enhance the learning motivation, send a learning achievement report, so that the user can intuitively see their progress and improve the sense of achievement. For example, when the system determines that the practice data of platform users on preset knowledge points does not meet the knowledge mastery standards, at this time, the system will consider that the user's level in this knowledge point has not reached the expected level. The system will obtain the types of practice errors of platform users according to different practice data. The types of practice errors specifically include conceptual errors, calculation errors, and careless errors. Based on these types of practice errors, the system identifies the error sources of these preset knowledge points and divides the error area distributions corresponding to the error sources on the education platform. By identifying the common error types of users in practice (such as conceptual errors, calculation errors, or careless errors), the system can accurately judge the weak links of users in understanding knowledge points. Combined with the error area distribution, the system can further analyze the error sources, such as whether it is due to unclear basic concepts, unfamiliar calculation methods, or mistakes caused by inattentiveness. At the same time, for different types of errors, the system can dynamically adjust the learning content of users. For example, in the case of conceptual errors, recommend that the user re-learn the core theory of this knowledge point and provide detailed explanations and examples. For example, in the case of calculation errors, guide the user to carry out calculation training and provide step-by-step analysis to improve the calculation accuracy. For example, in the case of careless errors, enhance the attention prompt of the user in similar problems, add verification steps or provide an error review function. Through personalized adjustment, ensure that the user strengthens in the correct knowledge direction and does not simply repeat the wrong practice. And by collecting and analyzing a large amount of practice error data of users, the system can construct a knowledge point error area distribution map to help the education platform optimize the question setting and teaching content. The error area distribution can also be used for group analysis to find the knowledge points that most users are prone to make mistakes, so as to adjust the teaching strategy and improve the overall learning efficiency.

[0041] In this embodiment, it further includes: An acquisition module, configured to obtain the average learning progress of all platform users on the course content based on the course content of the current learning quarter, where the course content specifically includes chapter progress, exercises and assignments, key quizzes, and expected learning duration; A fourth judgment module, configured to judge whether the platform user can complete the average learning progress; A fourth execution module, configured to, if not, calculate the learning lag rate of the platform user according to the behavior information, and based on the learning lag rate, benchmark the lag levels preset by the education platform, and dynamically adjust the tutoring content of the platform user on the education platform through the lag levels, where the lag levels specifically include slight lag, moderate lag, and severe lag, and the tutoring content specifically includes recommended priority learning tasks, providing personalized review content, and emergency intervention contacts.

[0042] In this embodiment, the system obtains the average learning progress of all platform users on the course content based on the course content of the current learning quarter, which specifically includes chapter progress, exercises and homework, key tests and expected learning time, and then the system determines whether the platform user can complete the average learning progress of all platform users on the course content to execute the corresponding steps; for example, when the system determines that the platform user can complete the average learning progress of all platform users on the course content, the system will consider that the user's learning rhythm is in line with the group learning level, indicating that there is no obvious lag or advance in the course advancement of the current learning quarter, and the learning status is relatively stable. The system will combine the user's practice data and test results to recommend additional knowledge consolidation exercises, such as extension questions, case analysis or high-level thinking questions, to enhance the depth of knowledge mastery. If the user's performance in some key tests or homework is slightly insufficient, the system can intelligently push corresponding reinforcement exercises to help the user further improve the quality of learning. At the same time, if the user's progress is stable but slightly ahead, the system can provide advanced courses or more practical tasks to guide the user to learn in depth. , to avoid reducing learning interest due to leading progress. If the user's progress is stable but tends to the lower limit of the average, the system can provide appropriate learning reminders or time management suggestions to help them maintain long-term learning motivation, and timely recommend learning discussion groups or interactive exchanges with users with the same progress to improve learning participation and continuity, and provide data visualization feedback, such as learning progress curves, achievement badges, etc., to enhance the user's sense of achievement and self-motivation; for example, when the system determines that the platform user cannot complete the average learning progress of all platform users on the course content, the system will consider that the user's learning rhythm does not meet the group learning level, and there may be a significant lag in the advancement of the course in the current learning quarter. The system will calculate the user's learning lag rate based on the user's behavior information, and based on different learning lag rates, benchmark the lag levels pre-set by the education platform. The lag levels specifically include slight lag, moderate lag and severe lag. Through different lag levels, the platform user's tutoring content on the education platform is dynamically adjusted. The tutoring content specifically includes recommending priority learning tasks, providing personalized review content and emergency intervention contacts;By calculating the user's learning lag rate and comparing it with the lag levels, the system can distinguish different situations of mild, moderate, and severe lags, avoiding a one-size-fits-all intervention approach. Users with mild lags can receive appropriate learning reminders and priority task recommendations, while users with severe lags can trigger stronger intervention measures, such as arranging tutor tutoring or notifying parents. At the same time, according to the current learning progress, the system intelligently arranges the course content that the user most needs to make up, ensuring efficient tutoring instead of passively learning in a fixed order. Combining the user's past practice data and learning habits, the system pushes error-prone knowledge points, intensive exercises, or micro-courses to enhance the effect of knowledge remediation. For users with severe lags, the system will contact tutors, class teachers, or parents to ensure timely intervention and provide offline or online tutoring to prevent further backwardness. And through adaptive adjustment of the tutoring plan, users can narrow the learning progress gap in the way that best suits their own situation, without generating anxiety or losing learning motivation due to excessive lag. Moreover, personalized task recommendations and review plans can enhance the pertinence and efficiency of learning, enabling users to improve their grades faster and catch up with the group progress again.

[0043] In this embodiment, the judgment module further includes: An identification unit, configured to identify the score weight of the test score based on the learning performance structure preset by the education platform; A second judgment unit, configured to judge whether the score weight reaches various standards of the learning performance structure; A second execution unit, configured to, if not, collect the knowledge short-board information corresponding to the platform user according to the score weight, mark the knowledge block of the knowledge short-board information, and divide the knowledge content that the platform user needs to make up from the knowledge block.

[0044] In this embodiment, the system identifies the score weight of the test scores based on the learning performance structure preset by the education platform, and then the system determines whether the score weight meets various criteria of the learning performance structure to execute corresponding steps. For example, when the system determines that the score weight of the test scores can meet various criteria of the learning performance structure, the system will consider that the learning performance of the platform user at the current stage has reached the expected goal, has the corresponding knowledge mastery level, 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 the learning level to encourage continuous learning. If the test score weight of the user meets the learning requirements of a higher stage, the system can recommend that the user unlock more difficult learning content, such as advanced courses, challenge tasks, or advanced assessments. At the same time, according to the user's performance, relevant knowledge points are recommended to encourage the user to expand the learning scope. For example, if the user performs excellently in a math test, the system can recommend more complex application problems or math competition content. According to the user's learning interests and test scores, high-quality learning materials, such as topic explanations, academic papers, online experiments, etc., are pushed. And even if the user reaches the performance standard, the system will still analyze the user's answering characteristics, such as whether there are some knowledge points that are weakly mastered, so as to provide targeted consolidation exercises, continuously monitor the user's learning trend, ensure that the user maintains a stable performance in the subsequent learning process, and provide review reminders for possible knowledge forgetting. For example, when the system determines that the score weight of the test scores cannot meet various criteria of the learning performance structure, at this time, the system will consider that the learning performance of the platform user at the current stage is below expectations. The system will collect the corresponding knowledge short-board information of the platform user according to the score weight, mark the knowledge sections with knowledge short-board information on the education platform, and divide the knowledge content that the platform user needs to make up for from the knowledge sections. The system can accurately locate the user's weak knowledge points based on the score weight, avoid adopting a "one-size-fits-all" review strategy, improve learning efficiency, and ensure that the make-up content accurately matches the user's knowledge defects by dividing the short-board content through knowledge sections, avoiding over-reviewing the content that has been mastered. At the same time, according to the user's weak knowledge points, dynamic recommendations for make-up content, including targeted exercises, video explanations, interactive courses, etc., are provided to make the make-up more targeted, adjust the make-up priority, ensure that the user first strengthens the core basic knowledge and then makes progress, avoid affecting the overall learning progress due to knowledge gaps, and continuously monitor the make-up effect to ensure that the user can make up for the knowledge short-board and improve the overall learning performance after make-up. Appropriate intervention is carried out on low-performance users, such as providing learning guidance, AI intelligent question answering, one-on-one teacher tutoring, etc., to reduce the risk of failing to master knowledge up to standard.

[0045] In this embodiment, the second judgment module further includes: An update unit for dynamically updating the learning progress of the platform user after learning based on the preset learning cycle of the platform user; A third judgment unit, configured to judge whether the learning progress has reached a preset lower limit of a single progress; A third execution unit, configured to, if so, generate a learning duration of the platform user according to the learned content of the platform user, and dynamically update the learning target of the platform user according to the learning duration, where the learned content specifically includes course chapter information, exercise information, and test information completed within the current period.

[0046] In this embodiment, the system dynamically updates the learning progress of platform users after they complete their learning based on the learning cycle preset by the platform users in advance. Then, the system determines whether the learning progress has reached the preset lower limit of the single - time progress to execute corresponding steps. For example, when the system determines that the learning progress of the platform user after completing the learning has not reached the preset lower limit of the single - time progress, the system will consider that the user has not completed enough learning content during this learning process, and there may be problems such as insufficient learning time, low concentration, and low learning efficiency. The system will collect the user's learning duration, determine whether there are overly short learning periods, detect the interaction data during the learning process (such as mouse clicks, swipes, and answering frequencies), identify whether there are long - term stagnations or passive learning situations, monitor the learning concentration (such as capturing facial expressions and eye movement trajectories through the camera), analyze whether there are frequent distractions or low - investment phenomena, at the same time remind the user to adjust the learning time arrangement, suggest appropriately increasing the daily learning duration, and according to the user's current learning status, re - plan the learning tasks for the next stage to ensure that the overall learning progress is not affected, and guide the user to conduct supplementary learning, such as adding quizzes, consolidation exercises, or knowledge - point reviews to improve the learning quality. For example, when the system determines that the learning progress of the platform user after completing the learning has reached the preset lower limit of the single - time progress, at this time, the system will consider that the user has completed the basic learning content during this learning process. The system will generate the learning duration of the platform user according to the content the user has learned, and the content the user has learned specifically includes the course chapter information, exercise information, and test information completed within the current cycle. According to different learning durations, the learning goals of the platform user will be dynamically updated. By judging whether the learning progress reaches the minimum requirement, the system can ensure that users complete the basic learning tasks within each learning cycle, avoid procrastination or accumulation of unfinished content. Dynamically adjusting the learning goals according to the learning duration can make the goals more in line with the user's learning rhythm, avoid fatigue caused by over - learning or insufficient learning caused by too low goals. At the same time, based on the content the platform user has learned (course chapters, exercises, tests), comparing with the learning goals can ensure that the content the user learns covers the necessary knowledge points and does not repeat the knowledge that has been mastered. Through the dynamic adjustment of the learning duration, the system can identify the user's learning rhythm (such as learning quickly and moving forward quickly or learning slowly and studying carefully) and optimize the subsequent learning arrangements accordingly to ensure that the learning rhythm matches the user's ability. And updating the learning goals in real - time can let the user clearly understand their learning progress, enhance the motivation and sense of achievement in learning. According to different learning durations, the system will intelligently recommend more suitable review times and learning methods, such as short - time and high - efficiency learning modes or in - depth and intensive learning modes, to make learning more in line with the user's habits.

[0047] In this embodiment, it further includes: A second recognition module, configured to recognize the learning interaction method pre-selected by the platform user on the education platform, wherein the learning interaction method specifically includes video-based learning, text-based learning, and interactive learning; A fifth judgment module, configured to judge whether the learning interaction method conforms to the current learning quarter; A fifth execution module, configured to, if not, dynamically adjust the learning path of the platform user based on the test score, wherein the learning path specifically includes the course content structure and the exercise evaluation method.

[0048] In this embodiment, the system identifies the learning interaction methods pre-selected by platform users on the education platform. The learning interaction methods specifically include video-based learning, text-based learning, and interactive learning. Then, the system determines whether the learning interaction method conforms to the current learning quarter to execute corresponding steps. For example, when the system determines that the learning interaction method pre-selected by platform users on the education platform can conform to the current learning quarter, the system will consider that the users' learning methods adapt to the course characteristics and teaching requirements of the current quarter, thereby effectively improving learning efficiency and knowledge absorption effect. The system will automatically match the optimal teaching resources (such as video courses, reading materials, online interactive exercises) according to the video-based learning, text-based learning, or interactive learning selected by the users, ensuring that the learning method matches the teaching objectives. At the same time, it analyzes the users' past learning duration, completion progress, and understanding effect, and dynamically adjusts the learning tasks. For example, for users who are accustomed to video-based learning, the system can add more efficient micro-lesson videos, reduce verbose content, improve the learning experience, and increase real-time quizzes, interactive Q&A, and gamified learning tasks to improve user participation and ensure the maximization of learning effects. For example, when the system determines that the learning interaction method pre-selected by platform users on the education platform does not conform to the current learning quarter, at this time, the system will consider that the users' learning methods do not adapt to the course characteristics and teaching requirements of the current quarter. The system will dynamically adjust the learning paths of platform users based on different test scores. The learning paths specifically include the course content structure and the question evaluation method. By actively adjusting the learning paths, the system ensures that the users' learning methods are adapted to the teaching content. For example, if the current quarter emphasizes practical training and the user selects text-based learning, the system will guide the user to participate more in interactive exercises and case analyses to enhance practical abilities. At the same time, based on the users' test scores, it analyzes the users' knowledge mastery and dynamically adjusts the presentation order of the 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 on to advanced content instead of progressing in a fixed order. And different users have different adaptabilities to question types. The system can adjust the difficulty and feedback methods of the questions according to the users' test performances. For example, for users who are good at logical reasoning but perform poorly in application questions, the system can add case analysis questions and provide step-by-step problem-solving guidance to improve the users' mastery of this type of questions.

[0049] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A learning progress monitoring method for an online education platform, characterized in that, Including the following steps: Based on the learning performance preset for platform users on the education platform, identify the test scores of the platform users on the education platform; Judge whether the test scores can reach the learning performance; If not, restrict the examination rights of the platform users on the education platform. According to the multi-type learning data of the platform users, collect the behavior information of the platform users. Based on the historical learning achievements pre-recorded by the education platform, detect the learning progress gap of the platform users in the current learning quarter. Among them, the multi-type learning data specifically includes basic data, interaction data, and biological data, and the behavior information specifically includes active learning behavior, passive learning behavior, and non-learning behavior; Judge whether the learning progress gap exceeds a preset threshold; If it exceeds, collect the learning habit data of the platform users. Based on the learning habit data, dynamically construct the Ebbinghaus forgetting curve of the platform users. Through the Ebbinghaus forgetting curve, calculate the optimal review period for the platform users to master knowledge points. According to the test scores, adaptively adjust the optimal review period. Among them, the learning habit data specifically includes the average daily learning duration, the habitual learning time period, and the mastery speed of past learned knowledge.

2. The learning progress monitoring method of the online education platform according to claim 1, characterized in that In the step of collecting the behavior information of the platform users, it further includes: Based on the connection device preset for the platform users, conduct learning interaction with the connection device through the education platform to obtain the characteristic information of the platform users. Among them, the characteristic information specifically includes facial expressions, eye movement trajectories, head movements, and body postures; Judge whether the characteristic information matches the identity characteristics pre-entered by the platform users; If so, according to the characteristic information, track the pupil trajectory of the platform users when facing the connection device. Based on the pupil trajectory, synchronously extract the corresponding key characteristics of the platform users during the learning process. Among them, the key characteristics specifically include intonation, speech rate, pauses, and volume changes.

3. The learning progress monitoring method of the online education platform according to claim 1, characterized in that Before the step of dynamically constructing the Ebbinghaus forgetting curve of the platform users, it further includes: Based on the knowledge mastery standard preset for the platform users by the education platform, collect the practice data of the platform users for the preset knowledge points. Among them, the practice data specifically includes the correct rate, the completion time, and the number of answer attempts; Judge whether the practice data can reach the knowledge mastery standard; If not, according to the practice data, obtain the types of practice errors of the platform users. Based on the types of practice errors, identify the error sources of the preset knowledge points, and divide the distribution of misunderstandings corresponding to the error sources on the education platform. Among them, the types of practice errors specifically include conceptual errors, calculation errors, and careless errors.

4. The learning progress monitoring method of the online education platform according to claim 1, wherein Before the step of detecting the learning progress gap of the platform users in the current learning quarter, it further includes: Based on the course content of the current learning quarter, obtain the average learning progress of all platform users for the course content. Among them, the course content specifically includes chapter progress, exercises and assignments, key tests, and expected learning duration; Judge whether the platform users can complete the average learning progress; If not, then calculate the learning lag rate of the platform user according to the behavior information, and based on the learning lag rate, benchmark against the lag levels preset by the education platform. Through the lag levels, dynamically adjust the tutoring content of the platform user on the education platform. The lag levels specifically include slight lag, moderate lag, and severe lag, and the tutoring content specifically includes recommending priority learning tasks, providing personalized review content, and emergency intervention contacts.

5. The learning progress monitoring method of the online education platform according to claim 1, characterized in that In the step of judging whether the test score can reach the learning performance, it further includes: Based on the learning performance structure preset by the education platform, identify the score weight of the test score; Judge whether the score weight meets the various criteria of the learning performance structure; If not, then according to the score weight, collect the knowledge short-board information corresponding to the platform user, mark the knowledge sections of the knowledge short-board information, and divide the knowledge content that the platform user needs to make up for from the knowledge sections.

6. The learning progress monitoring method of the online education platform according to claim 1, characterized in that In the step of judging whether the learning progress gap exceeds the preset threshold, it further includes: Based on the learning cycle preset by the platform user, dynamically update the learning progress of the platform user after learning; Judge whether the learning progress has reached the preset single-progress lower limit; If so, then generate the learning duration of the platform user according to the content already learned by the platform user, and based on the learning duration, dynamically update the learning goal of the platform user. The content already learned specifically includes the course chapter information, exercise information, and test information completed within the current cycle.

7. The learning progress monitoring method of the online education platform according to claim 1, characterized in that, After the step of identifying the test score of the platform user on the education platform based on the learning performance preset by the education platform for the platform user, it further includes: Identify the learning interaction method pre-selected by the platform user on the education platform. The learning interaction method specifically includes video-based learning, text-based learning, and interactive learning; Judge whether the learning interaction method conforms to the current learning quarter; If not, then based on the test score, dynamically adjust the learning path of the platform user. The learning path specifically includes the course content structure and the exercise evaluation method.

8. A learning progress monitoring system for an online education platform, characterized in that, It includes: An identification module, used to identify the test score of the platform user on the education platform based on the learning performance preset by the education platform for the platform user; A judgment module, used to judge whether the test score can reach the learning performance; An execution module, used, if not, to restrict the examination permission of the platform user on the education platform, collect the behavior information of the platform user according to the multi-type learning data of the platform user, and detect the learning progress gap of the platform user in the current learning quarter based on the historical learning achievements pre-recorded by the education platform. The multi-type learning data specifically includes basic data, interaction data, and biological data, and the behavior information specifically includes active learning behavior, passive learning behavior, and non-learning behavior; A second judgment module, used to judge whether the learning progress gap exceeds the preset threshold; A second execution module, configured to collect learning habit data of the platform user if it exceeds, dynamically construct an Ebbinghaus forgetting curve of the platform user based on the learning habit data, calculate the optimal review period of the platform user for knowledge points through the Ebbinghaus forgetting curve, and adaptively adjust the optimal review period according to the test score. The learning habit data specifically includes the average daily learning duration, the habitual learning time period, and the mastery speed of past learned knowledge.

9. The learning progress monitoring system of the online education platform according to claim 8, characterized in that, The execution module further includes: An acquisition unit, configured to perform learning interaction with the connected device through the education platform based on the connected device preset by the platform user, and acquire characteristic information of the platform user. The characteristic information specifically includes facial expressions, eye movement trajectories, head movements, and body postures; A judgment unit, configured to judge whether the characteristic information matches the identity characteristics pre-entered by the platform user; An execution unit, configured to, if so, track the pupil trajectory of the platform user when facing the connected device according to the characteristic information, and synchronously extract corresponding key characteristics of the platform user during the learning process based on the pupil trajectory. The key characteristics specifically include intonation, speech rate, pauses, and volume changes.

10. The learning progress monitoring system of the online education platform according to claim 8, characterized in that, It further includes: An acquisition module, configured to collect practice data of the platform user for preset knowledge points based on the knowledge mastery standard preset for the platform user by the education platform. The practice data specifically includes the correct rate, the completion time, and the number of answer attempts; A third judgment module, configured to judge whether the practice data can reach the knowledge mastery standard; A third execution module, configured to, if not, obtain the practice error types of the platform user according to the practice data, identify the error sources of the preset knowledge points based on the practice error types, and divide the distribution of misunderstandings corresponding to the error sources on the education platform. The practice error types specifically include concept errors, calculation errors, and careless errors.

Images