Personalized learning monitoring system based on user behavior data

Abstract

The invention relates to the technical field of personalized education, and discloses a personalized learning monitoring system based on user behavior data, and the system comprises a data collection module which is used for collecting the learning behavior data and physiological data of a target user, and integrating the interaction log data in a learning platform; the learning target formulating module is used for formulating a personalized learning target system containing short-term and long-term learning; the self-evaluation and feedback module is used for guiding the target user to perform self-evaluation regularly and assisting the target user in knowing the current learning progress; the emotion monitoring module identifies the current emotion fluctuation of the target user; and the dynamic task adjustment module is used for dynamically adjusting the difficulty, the content and the rhythm of the learning task based on the personalized learning target system, the current learning progress and the current emotion fluctuation, and generating a real-time adaptive learning task flow. The state change is automatically identified, the matching task is pushed, and the cognitive burden and the management cost are greatly reduced.

Description

Technical Field

[0001] This application relates to the technical field of personalized education, and in particular to a personalized learning monitoring system based on user behavior data. Background Technology

[0002] Personalized education is a teaching model that customizes educational content, teaching methods, and assessment methods based on learners' needs, interests, abilities, and learning pace. With the development of information technology, especially the advancement of big data, artificial intelligence, and educational technology, personalized education has gradually become an important direction for modern education reform. Its core concept is "student-centered," emphasizing providing a tailored learning experience based on each student's unique characteristics to maximize learning outcomes and promote students' all-round development.

[0003] In practical applications, personalized education often relies on advanced technologies such as learning analytics, artificial intelligence, and big data analytics. By tracking students' learning behavior data, interaction logs, and physiological data, it dynamically adjusts learning tasks and goals to make the learning process more efficient and tailored to individual characteristics. Its ultimate goal is to cultivate students' self-learning ability, critical thinking, and problem-solving skills, while stimulating their learning interest and intrinsic motivation. With the continuous development of educational technology, personalized education is gradually breaking through the limitations of traditional education models, providing students with more precise and diverse learning support.

[0004] However, in the implementation of personalized education, existing technologies generally suffer from problems such as lagging learning path updates, limited recommendation strategies, and inadequate feedback mechanisms, making it difficult to provide accurate and dynamic personalized learning support. In addition, personalized education lacks structured feedback and self-reflection guidance, making it difficult to form a complete and effective closed-loop learning process. Summary of the Invention

[0005] To address the shortcomings of existing technologies, such as lagging learning path updates, limited recommendation strategies, and weak feedback mechanisms, which make it difficult to achieve accurate and dynamic personalized learning support, this application provides a personalized learning monitoring system based on user behavior data.

[0006] A personalized learning monitoring system based on user behavior data, the personalized learning monitoring system comprising: The data acquisition module is used to collect learning behavior data and physiological data of target users, and integrate the interaction log data in the learning platform; The learning goal setting module, based on learning behavior data and interaction log data, sets up a personalized learning goal system that includes both short-term and long-term goals. The self-assessment and feedback module guides target users to conduct regular self-assessments through periodic online tests and provides targeted feedback based on the assessment results to help target users understand their current learning progress. The emotion monitoring module monitors the target user's emotional state in real time through interaction log data and physiological data, and identifies the target user's current emotional fluctuations; The dynamic task adjustment module dynamically adjusts the difficulty, content, and pace of learning tasks based on a personalized learning goal system, current learning progress, and current emotional fluctuations, generating a real-time adapted learning task flow.

[0007] Optionally, the learning objective setting module includes: The learning behavior and interaction data analysis module is used to analyze learning behavior data and interaction log data to extract the target user's comprehensive learning preferences, learning habits, knowledge mastery and weaknesses. Learning level and ability baseline modeling, based on knowledge mastery and weaknesses, combined with learning habits and comprehensive learning preferences, determines the learning level and ability baseline of the target users; The personalized learning goal system generation module formulates personalized short-term and long-term learning goals based on the learning level and ability baseline, and maintains the correlation between short-term and long-term learning goals to form a complete personalized learning goal system.

[0008] Optionally, the expression for the target user's learning level and ability baseline is: ; ; In the formula, , , and They represent knowledge mastery respectively. Weak links Study habits and comprehensive learning preferences The weights; Indicates mastery of knowledge; Indicates the weak link; express; Indicates overall learning preferences; , and These represent the weights of preference consistency (A), preference diversity (B), and preference matching (C), respectively; A represents preference consistency; B represents preference diversity; and C represents preference matching. This represents the baseline of the target user's learning level and ability.

[0009] Optionally, through regular online tests, target users are guided to conduct self-assessments periodically, and targeted feedback is provided based on the assessment results to help them understand their current learning progress, including: Based on the learning goals and phased plans of the target users, regularly push online tests related to the current learning stage to the target users; After the online test is completed, the test results are used as feedback signals and substituted into the learning attraction update formula to adjust the learning attraction concentration of relevant knowledge units on the learning path, thereby obtaining the optimized learning path. Based on the target user's knowledge domain, knowledge level, test scores, and optimized learning path, the similarity between the target user and each reference learner is calculated. Each reference learner is sorted in descending order according to the similarity score, and parameter learners that meet the preset requirements are selected to construct a reference learning group. Based on the target user's current learning status, combined with the learning paths and test scores of reference learners in the reference learning group, the recommendation probability of the learning unit is calculated using the recommendation strategy formula, and personalized learning suggestions are generated for the target user. Based on personalized learning suggestions, structured feedback reports are generated for target users, and after the target users read the feedback reports, they are guided to conduct self-reflection.

[0010] Optionally, the expression for the learning attraction update formula is: ; In the formula, This represents the concentration of learning attraction along the path at time S+1; The volatility coefficient, representing the attractiveness of learning; This represents the concentration of learning attraction along the path at time S; Indicates the learning rate; This represents the change in reward along the learning path from time S to time S+1.

[0011] Optionally, based on the target user's knowledge domain, knowledge level, test scores, and optimized learning path, the similarity between the target user and each reference learner is calculated. Each reference learner is then sorted in descending order according to their similarity score. Reference learners meeting preset requirements are selected to construct a reference learning group, including: Extract feature data for the target user and each reference learner, including knowledge domain, knowledge level, test scores, and optimized learning path, and perform normalization processing. Based on the normalized feature data, the differences in knowledge domain, knowledge level, test scores, and learning paths between the target user and each reference learner are calculated. The differences in each dimension are weighted and fused according to preset weights to calculate the total difference index. The total difference is mapped to a similarity score to measure the degree of similarity between the target user and each reference learner; All reference learners are sorted in descending order of similarity score, and those who meet the preset requirements are selected to construct reference learning groups.

[0012] Optionally, based on the target user's current learning status, combined with the learning paths and test scores of reference learners in the reference learning group, the recommendation probability of the learning unit is calculated using the recommendation strategy formula, and personalized learning suggestions are generated for the target user, including: Identify the target user's current learning state as the adaptive state, and simultaneously obtain the most recently completed learning unit L from the target user. i Learning Unit L i As the starting point of the current learning path, find all available candidate learning units L. j ; Calculate sequentially from the current learning unit L i Jump to each candidate learning unit L j heuristic value W ij ; Initialize the learning unit L based on the learning behavior paths and test scores of users in the reference learning group. i To candidate learning unit L j Learning attraction concentration S ij ; Based on heuristic W ij and learning attraction concentration S ij The learning unit L is calculated using the recommendation strategy formula. i Jump to learning unit L j Recommendation probability U ij ; The learning unit with the highest recommendation probability is selected, and personalized learning suggestions are generated for each recommendation result.

[0013] Optionally, the learning unit L is calculated using the recommendation strategy formula. i Jump to learning unit L j Recommendation probability U ij The expression is: ; In the formula, Indicates starting from the current learning unit L i To candidate learning unit L j Recommendation summary; Indicates starting from the current learning unit L i Jump to each candidate learning unit L j heuristic value; Indicates starting from the current learning unit L i To candidate learning unit L j The concentration of learning attraction; Indicates starting from the current learning unit L i To candidate learning unit L k The concentration of learning attraction; Indicates heuristic information factor; This represents the learning attraction factor; Indicates starting from the current learning unit L i Starting from the point, all jumpable candidate learning units L k A set of.

[0014] Optionally, based on a personalized learning goal system, current learning progress, and current emotional fluctuations, the difficulty, content, and pace of learning tasks are dynamically adjusted to generate a real-time adapted learning task flow, including: Obtain a personalized learning goal system, current learning progress, and current emotional fluctuations; Based on the personalized learning objective system, select task units that match content themes, ability requirements, and personalized learning objectives. Based on the current learning progress and current emotional fluctuations, assess the target user's knowledge level, cognitive load, and psychological fluctuations, and infer the target user's current capacity to handle and comprehension of the learning task. Based on the predicted results, the complexity, content granularity, and time allocation of task units are dynamically adjusted to identify the learning content most suitable for the current state. The learning content is arranged into task paths according to cognitive rhythm and logical order, forming a learning task flow that adapts to the current state, and then pushed to the learner.

[0015] In summary, this application includes at least one of the following beneficial technical effects: (1) This application integrates learning behavior data, physiological feedback, interaction logs and stage assessments to build a complete closed-loop process from data collection, goal setting, emotion perception to task push; dynamically perceives the learner's cognitive and emotional state, and adjusts the learning content and path accordingly, realizing highly intelligent and personalized learning support; users do not need to actively manage the learning pace, automatically identify state changes and push matching tasks, which greatly reduces cognitive burden and management cost.

[0016] (2) This application guides users to actively conduct periodic self-assessment through regular online tests, and uses test results as feedback signals to dynamically optimize their learning path; it uses a learning attraction update mechanism to adjust the weight concentration of knowledge units, thereby reflecting the changes in users' mastery of each knowledge point and generating more accurate learning path suggestions. At the same time, it also introduces similar learner modeling, combines the target user's knowledge domain, ability level and test data to screen out a group of reference learners with high similarity, and calculates the jump probability of learning tasks through the recommendation strategy formula to select the optimal task unit and generate personalized learning suggestion paths for users. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the system in this application. Detailed Implementation

[0018] The embodiments of this application are described in detail below, and examples of the embodiments are shown in the accompanying drawings.

[0019] In the description of this specification, the references to "certain embodiments," "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples" refer to specific features, structures, materials, or characteristics described in connection with the described embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0020] This application discloses a personalized learning monitoring system based on user behavior data, referring to... Figure 1 This personalized learning monitoring system includes: The data acquisition module is used to collect learning behavior data and physiological data of target users, and integrate the interaction log data in the learning platform.

[0021] It should be explained that learning behavior data includes the target user's operation trajectory, learning path, task completion time, answering process, error rate, click behavior, page dwell time, note-taking and discussion behavior, etc., which are used to analyze learning habits, learning strategies, mastery and cognitive load, etc. Physiological data (wearable devices / sensors) such as electroencephalogram (EEG), heart rate, skin conductance, eye movement, facial expression, and body movement amplitude can help infer the target user's emotional state, focus level, stress index, and fatigue level. The interaction log data in the learning platform includes records of interactions between learners and the learning terminal, such as interface click streams, video playback behavior, exercise feedback, message reply records, and voice interaction content.

[0022] The learning goal setting module, based on learning behavior data and interaction log data, formulates a personalized learning goal system that includes both short-term and long-term goals.

[0023] Preferably, the learning objective setting module includes: The learning behavior and interaction data analysis module is used to analyze learning behavior data and interaction log data to extract the target user's comprehensive learning preferences, learning habits, knowledge mastery, and weaknesses.

[0024] It should be explained that the learning behavior data and interaction log data collected from the learning platform are analyzed to extract multiple dimensions of user characteristics in the learning process. These multiple dimensions include comprehensive learning, learning habits, knowledge mastery, and identification of weak points. Among them, comprehensive learning preferences include: such as content preferences (videos / text / questions), learning time preferences, and learning formats (passive learning / active exploration); Study habits: such as task completion pace, amount of learning per unit of time, review frequency, skipping content, etc. Knowledge mastery status: The degree of mastery is analyzed through indicators such as accuracy, frequency of repeated learning, and test performance; Identify weaknesses: Find knowledge points that are repeatedly missed, not mastered for a long time, or frequently skipped.

[0025] Learning level and ability baseline modeling, based on knowledge mastery and weaknesses, combined with learning habits and comprehensive learning preferences, determines the learning level and ability baseline of the target users.

[0026] Preferably, the expression for the learning level and ability baseline of the target user is: ; ; In the formula, , , and They represent knowledge mastery respectively. Weak links Study habits and comprehensive learning preferences The weights; Indicates mastery of knowledge; Indicates the weak link; express; Indicates overall learning preferences; , and These represent the weights of preference consistency (A), preference diversity (B), and preference matching (C), respectively; A represents preference consistency; B represents preference diversity; and C represents preference matching. This represents the baseline of the target user's learning level and ability.

[0027] The personalized learning goal system generation module formulates personalized short-term and long-term learning goals based on the learning level and ability baseline, and maintains the correlation between short-term and long-term learning goals to form a complete personalized learning goal system.

[0028] It should be explained that after the learning level and ability baseline are established, personalized short-term and long-term learning goals are formulated. Short-term learning goals are primarily aimed at specific tasks at the current stage (such as mastering a certain knowledge point or improving a certain skill), and are closely matched with the baseline ability to avoid being too difficult or too easy. Long-term learning goals are primarily geared towards a longer-term growth path (such as completing a course or obtaining a certification). Short-term goals should serve long-term goals. The achievement of each short-term goal should be quantifiable in advancing the progress of long-term goals. A capability development trajectory should be established through the hierarchical relationship of goals to support phased assessments and dynamic adjustments.

[0029] The self-assessment and feedback module guides target users to conduct regular self-assessments through periodic online tests and provides targeted feedback based on the assessment results to help target users understand their current learning progress.

[0030] Specific examples are as follows: The target user is a university math student whose goal is to improve their math scores within 6 months, with a focus on functions and geometry. (1) Learning behavior data: Students study math for 1.5 hours daily, preferring illustrated textbooks (60%) and interactive question banks (40%). They have a high error rate in function graph transformation problems (65%), but perform well in algebraic operations (85% accuracy).

[0031] (2) Interaction log data: I frequently consult function-related analyses, but skip geometric proofs; my average problem-solving time is relatively long (especially for geometry problems), but I solve algebra problems faster.

[0032] (3) Study habits: They are accustomed to studying in the morning and can focus for about 40 minutes; they review infrequently and tend to do new problems directly rather than reviewing wrong ones.

[0033] The analysis results are as follows: (1) Overall learning preferences ( They prefer structured knowledge (text and images) and immediate feedback (question banks), but have a low acceptance of abstract content (such as geometric proofs). (2) Knowledge mastery ( ): Algebraic operations (0.85), Function fundamentals (0.5), Geometric proofs (0.3); (3) Weak links ( ): Function graph transformation (0.65), geometric proof (0.7); (4) Study habits : Moderate focus (0.6), weak review behavior (0.2).

[0034] Substitute the above content into the expression for the target user's learning level and ability baseline, and set... , , and The baseline learning level and ability of the target user were calculated using values ​​of 0.4, 0.3, 0.2, and 0.1, respectively. The score is approximately 0.46, which is below average. The focus should be on improving weaknesses in functions and geometry, and optimizing study habits.

[0035] Preferably, the specific steps for guiding target users to conduct regular self-assessments through periodic online tests and providing targeted feedback based on the assessment results to help target users understand their current learning progress are as follows: Based on the learning goals and phased plans of the target users, online tests related to their current learning stage will be pushed to them regularly.

[0036] After the online test is completed, the test results are used as feedback signals and substituted into the learning attraction update formula to adjust the learning attraction concentration of relevant knowledge units on the learning path, thereby obtaining the optimized learning path.

[0037] Preferably, the expression for the learning attraction update formula is: ; In the formula, This represents the concentration of learning attraction along the path at time S+1; The volatility coefficient, representing the attractiveness of learning; This represents the concentration of learning attraction along the path at time S; Indicates the learning rate; This represents the change in reward along the learning path from time S to time S+1.

[0038] It should be explained that, based on the target user's learning goals and phased plans, online tests corresponding to the current stage are pushed regularly to evaluate learning effectiveness. After the test, the score is used as a quantitative feedback signal and substituted into the learning attraction update formula for calculation. The weight of the old path is gradually reduced by the learning attraction evaporation factor. At the same time, the learning attraction concentration of relevant knowledge units is enhanced or weakened by the test reward signal, thereby dynamically adjusting the priority and recommendation direction of the learning path. The learning path can continuously self-optimize according to the user's actual learning performance, avoiding over-reliance on already mastered content and highlighting weak links, so as to achieve personalized guidance and continuous adaptation of the learning process.

[0039] Based on the target user's knowledge domain, knowledge level, test scores, and optimized learning path, the similarity between the target user and each reference learner is calculated. Each reference learner is sorted in descending order according to the similarity score, and parameter learners that meet the preset requirements are selected to construct a reference learning group.

[0040] Preferably, based on the target user's knowledge domain, knowledge level, test scores, and optimized learning path, the similarity between the target user and each reference learner is calculated. Each reference learner is then sorted in descending order according to their similarity score. The specific steps for constructing a reference learning group by selecting learners who meet the preset requirements are as follows: Extract feature data for the target user and each reference learner, including knowledge domain, knowledge level, test scores, and optimized learning path, and perform normalization processing. Based on the normalized feature data, the differences in knowledge domain, knowledge level, test scores, and learning paths between the target user and each reference learner are calculated. The differences in each dimension are weighted and fused according to preset weights to calculate the total difference index. The total difference is mapped to a similarity score to measure the degree of similarity between the target user and each reference learner; All reference learners are sorted in descending order of similarity score, and those who meet the preset requirements are selected to construct reference learning groups.

[0041] It should be explained that by extracting feature data from the target user and other reference learners across multiple dimensions such as knowledge domain, knowledge level, test scores, and optimized learning paths, and after uniform normalization, the difference between each dimension is calculated and weighted to form a total difference index. This index is then mapped to a similarity score, and all learners are ranked according to their similarity. Finally, a group of reference learners most similar to the target user is selected to construct a personalized reference learning group, providing support for path recommendation, strategy transfer, and learning resource adaptation.

[0042] Based on the target user's current learning status, combined with the learning paths and test scores of reference learners in the reference learning group, the recommendation probability of the learning unit is calculated using the recommendation strategy formula, and personalized learning suggestions are generated for the target user.

[0043] Preferably, the specific steps for calculating the recommendation probability of a learning unit and generating personalized learning suggestions for the target user based on the target user's current learning status, combined with the learning paths and test scores of reference learners in the reference learning group, using the recommendation strategy formula are as follows: Identify the target user's current learning state as the adaptive state, and simultaneously obtain the most recently completed learning unit L from the target user. i Learning Unit L i As the starting point of the current learning path, find all available candidate learning units L. j ; Calculate sequentially from the current learning unit L i Jump to each candidate learning unit L j heuristic value W ij ; Initialize the learning unit L based on the learning behavior paths and test scores of users in the reference learning group. i To candidate learning unit L j Learning attraction concentration S ij ; Based on heuristic W ij and learning attraction concentration S ij The learning unit L is calculated using the recommendation strategy formula. i Jump to learning unit L j Recommendation probability U ij ; The learning unit with the highest recommendation probability is selected, and personalized learning suggestions are generated for each recommendation result.

[0044] Preferably, the learning unit L is calculated using the recommended strategy formula. i Jump to learning unit L j Recommendation probability U ij The expression is: ; In the formula, Indicates starting from the current learning unit L i To candidate learning unit L j Recommendation summary; Indicates starting from the current learning unit L i Jump to each candidate learning unit L j heuristic value; Indicates starting from the current learning unit L i To candidate learning unit L j The concentration of learning attraction; Indicates starting from the current learning unit L i To candidate learning unit L k The concentration of learning attraction; Indicates heuristic information factor; This represents the learning attraction factor; Indicates starting from the current learning unit L i Starting from the point, all jumpable candidate learning units L k A set of.

[0045] Based on personalized learning suggestions, structured feedback reports are generated for target users, and after the target users read the feedback reports, they are guided to conduct self-reflection.

[0046] It should be explained that by analyzing the target user's current learning behavior and test scores, their learning state is identified, which is usually divided into adaptive state, transitional state, and consolidation state. Here, the target user is in the adaptive state, which means that the user is learning new or relatively unfamiliar knowledge points, and a suitable learning path needs to be recommended based on the performance of the reference learning group. Extract the most recently completed learning unit (such as a chapter, module, or knowledge point) from the target user's learning record. i This serves as a recommended starting point; by analyzing the knowledge graph or course structure, it automatically lists resources related to the current learning unit L. i Related candidate learning units L j These units can be related to L j It can be at the same level, or it can be a subsequent knowledge point, or it can be a review unit; For each candidate learning unit L j The heuristic value W is calculated using heuristic rules (such as knowledge difficulty, learning time, and historical learner performance). ij (Heuristic value W) ij Typically based on candidate learning units L j (A comprehensive calculation is performed on the relevance of the current learning objectives, the difficulty of the content, and the degree of matching between the learner's current ability). Heuristic values ​​represent the values ​​derived from learning unit L. i To L j The expected effectiveness is usually related to factors such as the similarity of learning content and the suitability of difficulty; combined with user data (learning paths and test scores) from the reference learning group, the initial learning attraction concentration S is determined. ij ; The magnitude of learning attraction concentration reflects the historical success of this path among similar learners; if many reference learners perform well on similar learning paths, the learning attraction concentration of that path is high. The recommendation probability formula combines the two, and by adjusting the weights m and n, it achieves flexible adjustment and provides personalized recommendations based on different user needs and learning stages. Once the recommended path is selected, personalized learning suggestions are provided to the target users: Specifically, we recommend the next learning unit; we recommend learning methods (such as videos, exercises, reading materials, etc.); and we recommend suitable learning time and pace based on your learning progress.

[0047] The target user background is as follows: Identity: University mathematics student; Learning objectives: Improve math scores within 6 months, with a focus on mastering the "functions" and "geometry" modules; The baseline ability score is approximately 0.46, which is below average. Weaknesses: Function graph transformation (error rate 65%), geometric proof (error rate 70%); Habitual preferences: Images and text + question bank, focus in the morning, weak review behavior; The phased online test design is as follows: Testing frequency: One phase test every two weeks (12 times in total); Weeks 4, 8, and 12 are designated as key testing nodes, and the learning path is updated accordingly. First test task (Week 2): The test content is divided into: function graph transformation (4 questions), application of function properties (2 questions), simple geometric reasoning (2 questions), and basic algebra test (2 questions). Test platform: Text and image questions combined with interactive answer boxes; instant feedback after submission + answer explanation; allows one pause during the test. Example test scores (hypothetical results) are shown in the table below: Table 1 Test Score Table Knowledge Points Score rate Error type description Function graph transformation 25% Misunderstanding of coordinate transformation, unable to draw the image Application of function properties 50% I can apply the formula but I can't reverse-engineer the graph. Simple geometric reasoning 0% Skip directly, no answer. Algebra Fundamentals Test 90% High accuracy and fast calculation speed Using the performance score as a feedback signal ΔR, the test results are substituted into the learning attraction update formula: For the "image transformation" path diagram L 图 ΔR = −0.4 → Learning engagement decreases → Basic practice units will be prioritized in subsequent recommendations; For the path of "geometric proof" L 几 ΔR = −0.7 → Learning attraction evaporates rapidly → Recommend reducing depth geometry content; Algebraic path L 代ΔR = +0.8 → Increased learning appeal → Recommendation of more challenging algebra content; Based on the test results and the updated learning attraction concentration, the recommendation probability is calculated using the recommendation formula, combined with the knowledge graph and historical learning data, and the recommended path is output.

[0048] Table 2 Recommended Path Table Candidate learning units <![CDATA[Heuristic value W ij > <![CDATA[Learning attraction concentration S ij > <![CDATA[Recommended probability U ij > Suggestions Image Transformation Fundamentals Review 0.7 0.5 0.34 Using image-based examples, we can start with "translation" and "symmetry". Function symmetry and parity 0.6 0.4 0.25 Illustrated Explanation + Quick Quiz Questions Advanced Algebraic Transformation 0.8 0.7 0.41 Includes comprehensive solution problems, offering a medium level of challenge. Based on the learning suggestions above, generate structured feedback reports for target users, and guide them to reflect on their own behavior after reading the reports.

[0049] The emotion monitoring module monitors the target user's emotional state in real time through interaction log data and physiological data, and identifies the target user's current emotional fluctuations.

[0050] It's important to explain that by combining interaction log data and physiological data, the system tracks the target user's emotional state in real time and identifies their emotional fluctuations. Specifically, interaction log data provides information about the user's behavior during the interaction process, such as learning time, frequently queried knowledge points, and task completion time, thereby inferring the user's emotional tendencies (e.g., anxiety, confusion, or pleasure). Physiological data includes indicators such as heart rate, skin conductance, and eye movement, which directly reflect the user's physiological state and emotional responses. By fusing and analyzing these two types of data, emotional fluctuations can be identified, helping to adjust learning suggestions or provide emotional regulation support in a timely manner.

[0051] The dynamic task adjustment module dynamically adjusts the difficulty, content, and pace of learning tasks based on a personalized learning goal system, current learning progress, and current emotional fluctuations, generating a real-time adapted learning task flow.

[0052] Preferably, based on a personalized learning goal system, current learning progress, and current emotional fluctuations, the difficulty, content, and pace of learning tasks are dynamically adjusted to generate a real-time adapted learning task flow, including: Obtain a personalized learning goal system, current learning progress, and current emotional fluctuations; Based on the personalized learning objective system, select task units that match content themes, ability requirements, and personalized learning objectives. Based on the current learning progress and current emotional fluctuations, assess the target user's knowledge level, cognitive load, and psychological fluctuations, and infer the target user's current capacity to handle and comprehension of the learning task. Based on the predicted results, the complexity, content granularity, and time allocation of task units are dynamically adjusted to identify the learning content most suitable for the current state. The learning content is arranged into task paths according to cognitive rhythm and logical order, forming a learning task flow that adapts to the current state, and then pushed to the learner.

[0053] It needs to be explained that three types of core input information are obtained. (1) Personalized learning objective system: including the learner's overall goal (such as "mastering functions and geometry in six months"), ability dimensions (logical reasoning, spatial perception, etc.) and priority improvement content; (2) Current learning progress: The degree of knowledge mastery and progress are judged by learning records, test results, etc.; (3) Current emotional fluctuations: Based on the results of the emotion monitoring module, identify the learner's current emotional state (such as anxiety, fatigue, calmness, focus, etc.).

[0054] Based on the thematic dimensions and ability requirements in the learning objectives, suitable task units (e.g., image transformation, geometric construction, etc.) are matched from the knowledge graph or course base. Assess the learner's current state: knowledge acquisition, cognitive load, and psychological fluctuations; In terms of knowledge acquisition, is the level at the stage of understanding, application, or transfer? In terms of cognitive load, are the tasks too complex or repetitive, causing psychological burden? In terms of psychological fluctuations, are the emotions stable, are they suitable for entering new content, or do they need to practice easily to relieve stress?

[0055] Based on the above analysis, adjust the parameters of the task unit (complexity, content granularity, allocation time, and feedback mechanism): Among these, complexity refers to simplifying or increasing the difficulty of the questions; content granularity refers to selecting micro-tasks or comprehensive exercises; time allocation refers to adjusting the learning pace according to concentration; and feedback mechanism refers to adapting to instant prompts or delayed assessments. The selected learning tasks are arranged according to cognitive order and logical rhythm (e.g., basic questions first, then advanced questions), and the difficulty is "interspersed" according to emotional fluctuations (e.g., easy practice is arranged when you are tired); a learning task flow adapted to the current state is generated and pushed to the learning interface.

[0056] It should be noted that the calculation formulas and all parameters involved in the calculations in this application have been dimensionless beforehand. The process of dimensionless processing is well known in the industry and will not be described here.

[0057] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A personalized learning monitoring system based on user behavior data, characterized in that, This personalized learning monitoring system includes: The data acquisition module is used to collect learning behavior data and physiological data of target users, and integrate the interaction log data in the learning platform; The learning goal setting module, based on the learning behavior data and the interaction log data, sets up a personalized learning goal system that includes short-term and long-term goals; The self-assessment and feedback module guides target users to conduct regular self-assessments through periodic online tests and provides targeted feedback based on the assessment results to help target users understand their current learning progress. The emotion monitoring module monitors the target user's emotional state in real time through the interaction log data and the physiological data, and identifies the target user's current emotional fluctuations. The dynamic task adjustment module dynamically adjusts the difficulty, content, and pace of learning tasks based on the personalized learning goal system, the current learning progress, and the current emotional fluctuations, generating a real-time adapted learning task flow.

2. The personalized learning monitoring system based on user behavior data according to claim 1, characterized in that, The learning objective setting module includes: The learning behavior and interaction data analysis module is used to analyze learning behavior data and interaction log data to extract the target user's comprehensive learning preferences, learning habits, knowledge mastery and weaknesses. Learning level and ability baseline modeling, based on knowledge mastery and weaknesses, combined with learning habits and comprehensive learning preferences, determines the learning level and ability baseline of the target users; The personalized learning goal system generation module formulates personalized short-term and long-term learning goals based on the learning level and ability baseline, and maintains the correlation between short-term and long-term learning goals to form a complete personalized learning goal system.

3. The personalized learning monitoring system based on user behavior data according to claim 2, characterized in that, The expression for the learning level and ability baseline of the target user is: ； ； In the formula, , , and They represent knowledge mastery respectively. Weak links Study habits and comprehensive learning preferences The weights; Indicates mastery of knowledge; Indicates the weak link; express; Indicates overall learning preferences; , and These represent the weights of preference consistency (A), preference diversity (B), and preference matching (C), respectively; A represents preference consistency; B represents preference diversity; and C represents preference matching. This represents the baseline of the target user's learning level and ability.

4. The personalized learning monitoring system based on user behavior data according to claim 1, characterized in that, The method involves guiding target users to conduct regular self-assessments through periodic online tests, and providing targeted feedback based on the assessment results to help target users understand their current learning progress. Based on the learning goals and phased plans of the target users, regularly push online tests related to the current learning stage to the target users; After the online test is completed, the test results are used as feedback signals and substituted into the learning attraction update formula to adjust the learning attraction concentration of relevant knowledge units on the learning path, thereby obtaining the optimized learning path. Based on the target user's knowledge domain, knowledge level, test scores, and optimized learning path, the similarity between the target user and each reference learner is calculated. Each reference learner is sorted in descending order according to the similarity score, and parameter learners that meet the preset requirements are selected to construct a reference learning group. Based on the target user's current learning status, combined with the learning paths and test scores of reference learners in the reference learning group, the recommendation probability of the learning unit is calculated using the recommendation strategy formula, and personalized learning suggestions are generated for the target user. Based on personalized learning suggestions, structured feedback reports are generated for target users, and after the target users read the feedback reports, they are guided to conduct self-reflection.

5. The personalized learning monitoring system based on user behavior data according to claim 4, characterized in that, The expression for the learning attraction update formula is: ； In the formula, This represents the concentration of learning attraction along the path at time S+1; The volatility coefficient, representing the attractiveness of learning; This represents the concentration of learning attraction along the path at time S; Indicates the learning rate; This represents the change in reward along the learning path from time S to time S+1.

6. The personalized learning monitoring system based on user behavior data according to claim 5, characterized in that, Based on the target user's knowledge domain, knowledge level, test scores, and optimized learning path, the similarity between the target user and each reference learner is calculated. Each reference learner is then sorted in descending order according to their similarity score. Reference learning groups are constructed by selecting learners who meet preset requirements. Extract feature data for the target user and each reference learner, including knowledge domain, knowledge level, test scores, and optimized learning path, and perform normalization processing. Based on the normalized feature data, the differences in knowledge domain, knowledge level, test scores, and learning paths between the target user and each reference learner are calculated. The differences in each dimension are weighted and fused according to preset weights to calculate the total difference index. The total difference is mapped to a similarity score to measure the degree of similarity between the target user and each reference learner; All reference learners are sorted in descending order of similarity score, and those who meet the preset requirements are selected to construct reference learning groups.

7. The personalized learning monitoring system based on user behavior data according to claim 6, characterized in that, The step of calculating the recommendation probability of learning units based on the target user's current learning status, combined with the learning paths and test scores of reference learners in the reference learning group, and generating personalized learning suggestions for the target user using the recommendation strategy formula includes: Identify the target user's current learning state as the adaptive state, and simultaneously obtain the most recently completed learning unit L from the target user. i Learning Unit L i As the starting point of the current learning path, find all available candidate learning units L. j ; Calculate sequentially from the current learning unit L i Jump to each candidate learning unit L j heuristic value W ij ; Initialize the learning unit L based on the learning behavior paths and test scores of users in the reference learning group. i To candidate learning unit L j Learning attraction concentration S ij ; Based on heuristic value W ij and learning attraction concentration S ij The learning unit L is calculated using the recommendation strategy formula. i Jump to learning unit L j Recommendation probability U ij ; The learning unit with the highest recommendation probability is selected, and personalized learning suggestions are generated for each recommendation result.

8. The personalized learning monitoring system based on user behavior data according to claim 7, characterized in that, The learning unit L is calculated using the recommendation strategy formula. i Jump to learning unit L j Recommendation probability U ij The expression is: ； In the formula, Indicates starting from the current learning unit L i To candidate learning unit L j Recommendation summary; Indicates starting from the current learning unit L i Jump to each candidate learning unit L j heuristic value; Indicates starting from the current learning unit L i To candidate learning unit L j The concentration of learning attraction; Indicates starting from the current learning unit L i To candidate learning unit L k The concentration of learning attraction; Indicates heuristic information factor; This represents the learning attraction factor; Indicates starting from the current learning unit L i Starting from the point, navigate to all available candidate learning units L. k A set of.

9. The personalized learning monitoring system based on user behavior data according to claim 1, characterized in that, The process of dynamically adjusting the difficulty, content, and pace of learning tasks based on the personalized learning goal system, the current learning progress, and the current emotional fluctuations to generate a real-time adapted learning task flow includes: Obtain a personalized learning goal system, current learning progress, and current emotional fluctuations; Based on the personalized learning objective system, select task units that match content themes, ability requirements, and personalized learning objectives. Based on the current learning progress and current emotional fluctuations, assess the target user's knowledge level, cognitive load, and psychological fluctuations, and infer the target user's current capacity to handle and comprehension of the learning task. Based on the predicted results, the complexity, content granularity, and time allocation of task units are dynamically adjusted to identify the learning content most suitable for the current state. The learning content is arranged into task paths according to cognitive rhythm and logical order, forming a learning task flow that adapts to the current state, and then pushed to the learner.

Images