Course management-based interactive processing method and apparatus

Abstract

The invention discloses an interactive processing method and device based on course management, and relates to the technical field of intelligent education, and the method comprises the steps: collecting student information, carrying out the preprocessing of the student information, and generating an initial learning path according to the preprocessed student information; in the process that the student learns according to the initial learning path, learning behavior data of the student is monitored, and a personalized learning path is generated according to the learning behavior data of the student; monitoring emotion change data, cognitive load data and attention level data of the trainee in the personalized learning path in real time, constructing a learning state evaluation model, and evaluating the current learning state of the trainee; and dynamically generating an immersive learning situation according to the current learning state of the student. According to the invention, the pertinence and utilization efficiency of educational resources are improved, and the enthusiasm and effect of learning are enhanced.

Description

Technical Field

[0001] The present invention relates to the field of intelligent education technology, and in particular to an interactive processing method and device based on course management. Background Art

[0002] With the development of information technology and the popularization of the Internet, the field of education has also ushered in unprecedented changes. The traditional course management model mainly relies on fixed textbooks and syllabi, which is difficult to meet the differentiated needs of individual learners. In recent years, online education platforms based on advanced technologies such as big data analysis and artificial intelligence have gradually emerged. They can provide a certain degree of personalized services based on the basic information and historical learning data of students. For example, by analyzing the learning progress and test scores of students to adjust the course content, a certain degree of adaptive learning path planning is achieved. However, most of these methods are limited to the application of surface data and lack the ability to accurately evaluate and dynamically adjust the deep learning status of students. This not only limits the effectiveness of personalized learning programs, but also fails to fully stimulate students' learning interest and potential.

[0003] Although current technology has improved the utilization efficiency of educational resources and teaching effectiveness to a certain extent, it still has obvious shortcomings. First, existing technologies often ignore factors such as students' emotional changes, cognitive load, and attention levels during the learning process, resulting in the generated learning path not fully meeting the actual needs of students. Secondly, the existing adaptive learning path adjustment mechanism is relatively simple, and is usually only adjusted based on academic performance or simple learning behaviors (such as answer accuracy, learning time), without considering learners' emotional fluctuations and changes in psychological state. These problems make the optimization of the learning path less accurate, affecting the improvement of learning effects. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an interactive processing method based on course management to solve the problem in the prior art that factors such as students' emotional changes, cognitive load and attention level are ignored, resulting in inaccurate learning path optimization.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides an interactive processing method based on course management, which includes collecting student information and preprocessing the student information, generating an initial learning path based on the preprocessed student information; monitoring the student's learning behavior data during the student's learning according to the initial learning path, and generating a personalized learning path based on the student's learning behavior data; real-time monitoring of the student's emotion change data, cognitive load data and attention level data in the personalized learning path, constructing a learning status evaluation model, and evaluating the student's current learning status; and dynamically generating an immersive learning scenario based on the student's current learning status.

[0008] As a preferred solution of the interactive processing method based on course management of the present invention, wherein: the student information includes name, age, education background, available learning time, learning goals and existing knowledge reserves;

[0009] The preprocessing includes data cleaning, data standardization and outlier detection.

[0010] As a preferred solution of the interactive processing method based on course management of the present invention, the specific steps of generating the initial learning path according to the pre-processed student information are as follows:

[0011] Based on the pre-processed student information, the test scope is defined through the knowledge point screening method, and the Bayesian knowledge tracking method is used to preliminarily predict the student's knowledge point mastery probability P(k);

[0012] Adaptive Testing is used to dynamically adjust the difficulty of questions based on the probability of mastering knowledge points, and ultimately generate a preliminary intelligent test;

[0013] During the test, the students' answer time and accuracy rate for each knowledge point are recorded in real time;

[0014] Based on the students’ answering time and accuracy rate for each knowledge point, the collaborative filtering algorithm is used to match students to courses in the course database;

[0015] Based on the courses matched to the students and their available learning time, the courses are divided into multiple learning units through hierarchical clustering method, and the initial learning path is generated in combination with MDP.

[0016] As a preferred solution of the interactive processing method based on course management of the present invention, wherein: in the process of students learning according to the initial learning path, the learning behavior data of the students is monitored, and a personalized learning path is generated according to the learning behavior data of the students. The specific steps are as follows:

[0017] Students start learning the course based on the initial learning path, and their learning behavior data is monitored during the learning process;

[0018] The learning behavior data includes learning progress, test answer accuracy, answer time, learning frequency and eye concentration;

[0019] Input the students' emotional change data, cognitive load data and attention level data into the learning state evaluation model to predict the students' current learning state index P'(K);

[0020] Based on historical learning data and mastery distribution, define a low mastery threshold P1 and a high mastery threshold P2;

[0021] When P'(K)≤P1, the learners' mastery is poor, and additional basic courses in the initial learning path are recommended, and targeted exercises are recommended;

[0022] When P1<P'(K)≤P2, the learner's mastery is average, and consolidation exercises are recommended based on the initial learning path, combined with new knowledge points;

[0023] When P'(K)>P2, the learner has a good grasp of the subject, and advanced courses are recommended based on the initial learning path;

[0024] Generate a personalized learning path based on the comparison results of P'(K) with P1 and P2.

[0025] As a preferred solution of the interactive processing method based on course management of the present invention, wherein: the emotional change data includes frown frequency, voice tone fluctuation, speech speed change and heart rate fluctuation;

[0026] The cognitive load data includes eye movement trajectory, number of repeated learning, information dwell time, and distribution of eye movement dwell points;

[0027] The attention level data includes eye movement focus duration, blink frequency, head posture changes and body forward leaning angle.

[0028] As a preferred solution of the interactive processing method based on course management described in the present invention, wherein: the learning state evaluation model is constructed, and the student's emotional change data, cognitive load data and attention level data are input into the learning state evaluation model to evaluate the student's current learning state. The specific steps are as follows:

[0029] Build a data input layer through time synchronization mechanism to integrate students' emotional change data, cognitive load data and attention level data;

[0030] Construct a feature extraction layer based on CNN and statistical analysis to obtain multi-level learning state feature vectors;

[0031] Through time series alignment, feature normalization and multimodal attention mechanism, a data fusion layer is constructed to fuse learning state features;

[0032] Based on Bayesian knowledge tracking and HMM, a learning status recognition layer is constructed to identify the student’s current learning status index;

[0033] Based on the data input layer, feature extraction layer, data fusion layer and learning state recognition layer, a learning state evaluation model is constructed;

[0034] Input the students' emotional change data, cognitive load data and attention level data into the learning status assessment model to predict the students' current learning status index;

[0035] According to the students' learning status index S t , marking the students’ learning status as focused, confused and tired.

[0036] As a preferred solution of the interactive processing method based on course management of the present invention, wherein: the immersive learning scenario is dynamically generated according to the current learning status of the students, and the specific steps are as follows:

[0037] When students are in a focused state, an exploratory learning situation is generated;

[0038] When students are confused, generate guided learning situations;

[0039] When students are in a state of fatigue, a relaxing learning situation is created.

[0040] In a second aspect, the present invention provides an interactive processing device based on course management, including an initial path generation module, a personalized path generation module, a learning status evaluation module and a situation generation module; the initial path generation module is used to collect student information, pre-process the student information, and generate an initial learning path based on the pre-processed student information; the personalized path generation module is used to monitor the student's learning behavior data during the student's learning process according to the initial learning path, and to generate a personalized learning path based on the student's learning behavior data; the learning status evaluation module is used to monitor the student's emotion change data, cognitive load data and attention level data in real time in the personalized learning path, construct a learning status evaluation model, and evaluate the student's current learning status; the situation generation module is used to dynamically generate an immersive learning situation based on the student's current learning status.

[0041] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the interactive processing method based on course management as described in the first aspect of the present invention is implemented.

[0042] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the interactive processing method based on course management as described in the first aspect of the present invention is implemented.

[0043] The beneficial effects of the present invention are: by collecting and preprocessing student information to generate a personalized initial learning path, combining factors such as the student's learning goals, existing knowledge, and available time, accurately matching learning resources, effectively improving the pertinence and utilization efficiency of educational resources, and enhancing the enthusiasm and effect of learning. At the same time, based on real-time monitoring of students' emotional changes, cognitive load, and attention level data, dynamically adjust teaching strategies and generate immersive learning situations, not only focusing on the improvement of academic performance, but also paying special attention to students' emotional experience and psychological state, thereby effectively improving students' learning motivation and interest, reducing learning fatigue, and achieving the goal of comprehensively improving learning experience and effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0045] Figure 1 This is a flow chart of the interactive processing method based on course management in Example 1.

[0046] Figure 2 Schematic diagram of an interactive processing device based on course management in Example 1. DETAILED DESCRIPTION

[0047] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0048] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0049] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0050] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides an interactive processing method based on course management, comprising the following steps:

[0051] S1. Collect and preprocess student information, and generate an initial learning path based on the preprocessed student information.

[0052] The student information includes name, age, education background, available study time, learning goals and existing knowledge reserves;

[0053] It should be noted that the above content has been obtained with the user's consent and is used for legitimate purposes.

[0054] Preprocessing includes data cleaning, data standardization, and outlier detection.

[0055] It should be noted that missing values ​​in student information are removed through data cleaning. The specific process involves identifying whether there are blank or unfilled fields in the student information, and adopting appropriate filling strategies for missing values ​​of key attributes such as name and age, such as using default values ​​or estimating based on other relevant information; for non-key attributes, records with missing values ​​may be directly deleted.

[0056] Through data standardization, the numerical data in the student information is normalized. First, the range of numerical data to be processed is determined, such as available learning time and existing knowledge reserves. Then, a specific mathematical formula is used to map these values ​​to a common interval, usually between [0,1], to eliminate the differences between different magnitudes and make each feature have the same scale.

[0057] Outlier detection is used to identify and correct outlier data in student information. First, we define what an outlier is, which is usually based on statistical principles. For example, data points that are more than three standard deviations from the mean are considered outliers. After identifying these outliers, different correction measures are taken according to the specific situation. For example, if the outlier is caused by an input error, it can be adjusted according to the known reasonable range.

[0058] According to the preprocessed student information, the test scope is defined by the knowledge point screening method, and the Bayesian knowledge tracking method is combined to preliminarily predict the student's knowledge point mastery probability P(k), which is expressed as:

[0059]

[0060] Among them, P(k) represents the initial mastery of knowledge point k by the students, P 0 (k) represents the estimated value of the student's mastery of knowledge point k, λ1 is the weight coefficient of the student's existing knowledge reserve, λ 2 is the weight coefficient of the student's available learning time, B represents the student's existing knowledge reserve, T represents the student's available learning time, β represents the test difficulty attenuation coefficient, and G is the test difficulty;

[0061] It should be noted that first, the knowledge points that need to be taken into consideration are determined based on the students' existing knowledge reserves and available learning time, ensuring that the test content is both in line with the students' current knowledge level and can effectively promote their further learning and development. Next, the students' initial mastery of each knowledge point is calculated based on their historical learning data and specific algorithms. This process fully considers the students' background information and their learning potential, so as to tailor an initial learning path that best suits each student's personal situation.

[0062] It should also be noted that P 0 (k) is determined based on the student’s historical learning data. Specifically, this estimate is made by analyzing the student’s past performance on relevant knowledge points, including test scores, homework completion, and other evaluation indicators, to determine their initial mastery of a certain knowledge point.

[0063] The student's existing knowledge reserve B is obtained through a comprehensive analysis of the student's past learning experience, completed courses, grades obtained, and performance in related tests, and is quantified based on the proportion of the analysis results in the current course and the courses not yet studied.

[0064] The test difficulty G is determined by analyzing the average accuracy of knowledge points in previous tests, the average time required to complete related questions, and the conceptual levels involved in the questions.

[0065] Adaptive Testing is used to dynamically adjust the difficulty of questions based on the probability of mastering knowledge points, and ultimately generate a preliminary intelligent test;

[0066] It should be noted that the difficulty of the questions at the beginning of the test is determined based on the students' initial mastery of each knowledge point. During the test, the students' actual mastery of the current knowledge point is evaluated in real time based on the accuracy and speed of their answers. If the students can answer the questions quickly and accurately, the difficulty of the subsequent questions will be automatically increased; otherwise, the difficulty of the questions will be reduced to ensure the effectiveness and adaptability of the test. In this way, the understanding of the students' knowledge level is gradually refined, and finally a preliminary intelligence test is generated that can accurately reflect the students' true ability and improve their weak links in a targeted manner. Suppose a student is initially provided with a medium-difficulty algebra question based on the evaluation results of the probability of mastering the knowledge point of basic algebra in the study of mathematics. The student quickly and accurately answers this question, indicating that he has a good grasp of this knowledge point. Next, based on the students' answers, the Adaptive Testing mechanism automatically provides questions of higher difficulty levels, such as word problems involving complex equations or inequalities. However, if the students make mistakes in their answers to these high-difficulty questions and spend a long time on them, the difficulty of the subsequent questions will be reduced accordingly, and some questions between basic and medium difficulty will be provided to help consolidate related concepts. By dynamically adjusting the difficulty of questions based on students' performance, a preliminary intelligence test is ultimately generated for students that not only reflects their true ability level but also helps improve their weak links in a targeted manner.

[0067] During the test, the students' answer time and accuracy rate for each knowledge point are recorded in real time;

[0068] Based on the students’ answering time and accuracy rate for each knowledge point, the collaborative filtering algorithm is used to match students to courses in the course database;

[0069] It should be noted that the course database is derived from long-term accumulated teaching resources and student learning data, and contains a large number of detailed records on course content, knowledge point distribution and student learning behavior. First, the student's performance in the test is analyzed, including indicators such as answering time and accuracy, to evaluate their mastery of different knowledge points. Then, using collaborative filtering algorithms, historical student data with similar learning patterns and needs are searched in the course database, and the course content that best suits the current student is recommended based on these data.

[0070] Based on the courses matched to the students and their available learning time, the courses are divided into multiple learning units through hierarchical clustering method, and the initial learning path is generated in combination with MDP.

[0071] It should be noted that the matched course content is first planned reasonably according to the students' available learning time. Using the hierarchical clustering method, the course is divided into several learning units suitable for gradual learning according to the relevance and difficulty level of the knowledge points, ensuring that each unit is neither too complex nor too simple, in line with the students' learning rhythm. Subsequently, the Markov decision process (MDP) is applied to optimize the order and combination of these learning units, generating a personalized initial learning path with the goal of maximizing learning efficiency and effect.

[0072] S2. During the process of students learning according to the initial learning path, the learning behavior data of the students is monitored, and a personalized learning path is generated based on the learning behavior data of the students.

[0073] Students start learning the course based on the initial learning path, and their learning behavior data is monitored during the learning process;

[0074] Learning behavior data includes learning progress, test answer accuracy, answering time, learning frequency and eye focus;

[0075] Based on the students’ learning behavior data, the probability of students mastering knowledge points in the initial learning path is updated through the Bayesian knowledge tracking method combined with exponential decay and nonlinear activation function. The expression is:

[0076]

[0077] Among them, P'(K) represents the updated students' mastery of knowledge point k, γ 1 represents the weight coefficient of the correct answer rate, δ represents the time deviation attenuation coefficient, η represents the learning frequency attenuation coefficient, Q represents the correct answer rate of the students, T 2 represents the standard answering time, F represents the learning frequency of the students, E represents the students’ eye concentration during the answering process, and γ 2 Indicates the weight coefficient of answering time, the actual answering time of T1 students;

[0078] It should be noted that the standard answering time refers to the average time required to complete a specific question, which is pre-set based on the course content and the difficulty of the knowledge points. It is calculated by analyzing the answering time data of a large number of students on the same questions, and combining factors such as the difficulty of the question and the complexity of the knowledge points.

[0079] It should also be explained that, first of all, according to the correct Q of the answers generated by the students during the learning process, the actual answering time T1 and the standard answering time T 2The deviation between the two is used to calculate the influence of the time deviation attenuation coefficient δ. Then, the learning frequency F and eye concentration E of the students are used to adjust the learning frequency attenuation coefficient η and the corresponding nonlinear activation function to ensure that the contribution of these factors to the mastery of the knowledge point is accurately reflected. Where P(k) is the estimated value of the student's initial mastery of knowledge point k obtained based on the Bayesian knowledge tracking method. By combining γ 1 The weight coefficient and γ representing the correct answer rate 2 Represents the weight coefficient of answering time, accurately adjusting the student's probability of mastering the knowledge point P'(K).

[0080] Based on historical learning data and mastery distribution, define a low mastery threshold P1 and a high mastery threshold P2;

[0081] When P'(K)≤P1, the learners' mastery is poor, and additional basic courses in the initial learning path are recommended, and targeted exercises are recommended;

[0082] When P1<P'(K)≤P2, the learner's mastery is average, and consolidation exercises are recommended based on the initial learning path, combined with new knowledge points;

[0083] When P'(K)>P2, the learner has a good grasp of the subject, and advanced courses are recommended based on the initial learning path;

[0084] It should be noted that when P'(K)≤P1, for example, the probability of a student mastering the knowledge points in the elementary mathematics course is only 0.3, which is lower than the low mastery threshold P1, indicating that the student has a poor grasp of the current knowledge points. Therefore, basic courses in the preliminary learning path are added, and exercises specifically targeting these weak knowledge points are recommended to enhance understanding.

[0085] When P1<P'(K)≤P2, assuming that a student has a knowledge point mastery probability of 0.6 in the intermediate programming course, which is between P1 and P2, indicating that his mastery is average. At this time, consolidation exercises are added to the original learning path, and an appropriate amount of new knowledge points are introduced to help students smoothly transition to more complex topics.

[0086] When P'(K)>P2, if a student's probability of mastering knowledge points in the advanced physics course reaches 0.9, exceeding the high mastery threshold P2, it shows that he has a good grasp of the relevant knowledge points. Therefore, more challenging advanced courses are recommended based on the initial learning path to further deepen and expand his knowledge system.

[0087] Generate a personalized learning path based on the comparison results of P'(K) with P1 and P2.

[0088] S3. Real-time monitoring of students’ emotional change data, cognitive load data, and attention level data in the personalized learning path, building a learning status assessment model, and evaluating students’ current learning status.

[0089] Emotional change data include frown frequency, voice tone fluctuations, speech speed changes, and heart rate fluctuations.

[0090] Cognitive load data include eye movement trajectories, number of repeated learning, information dwell time, and distribution of eye movement dwell points.

[0091] Attention level data include eye movement focus duration, blink frequency, head posture changes and body leaning angle.

[0092] Build a data input layer through time synchronization mechanism to integrate students' emotional change data, cognitive load data and attention level data;

[0093] It should be noted that in order to build a data input layer through a time synchronization mechanism and integrate students' emotional change data, cognitive load data, and attention level data, it is first necessary to ensure that all collected data (such as frown frequency, voice tone fluctuations, eye movement trajectories, etc.) can be accurately aligned to the same time point.

[0094] Construct a feature extraction layer based on CNN and statistical analysis to obtain multi-level learning state feature vectors;

[0095] It should be noted that convolutional neural networks are used to automatically identify complex patterns, such as extracting specific patterns that represent high cognitive load from eye movement trajectory data. CNN processes input data through multiple convolutional layers and pooling layers to capture local dependencies and high-level abstract features. At the same time, statistical analysis methods are used to further process the data, such as calculating the mean and variance of eye movement focus duration, or analyzing the changing trend of blink frequency. These statistical indicators can provide important information about the students' attention level. Then, the high-level features extracted by the deep learning model are combined with the features obtained by statistical analysis to form a comprehensive feature vector set, which contains multi-dimensional information reflecting the students' current learning status. For example, when evaluating the students' cognitive load, not only the eye movement trajectory features identified by CNN are considered, but also the statistical analysis results of blink frequency are combined to ensure the comprehensiveness and accuracy of the features. Through this comprehensive method, the deep mining and precise expression of the students' learning status features are achieved, and the feature extraction layer is constructed. .

[0096] Through time series alignment, feature normalization and multimodal attention mechanism, a data fusion layer is constructed to fuse learning state features;

[0097] It should be noted that, firstly, for data from different sources (such as emotion change data, cognitive load data, and attention level data), accurate time series alignment is performed according to their respective timestamps to ensure the consistency of all information in the time dimension. For example, the eye movement trajectory data is synchronized with the emotion change data (such as frown frequency) at the corresponding moment so that the correlation of these data can be analyzed at the same time point. Then, the feature normalization technology is used to adjust the scale of each feature to eliminate the deviation caused by the magnitude difference between different data types, such as unifying the movement speed of the eye movement trajectory and the blinking frequency to the same numerical range. Finally, the multimodal attention mechanism is applied to dynamically adjust the weight according to the importance of each modal data, so that more attention is paid to certain types of data in specific situations, such as when analyzing the concentration of students, more consideration is given to eye concentration rather than the body forward leaning angle. Through this comprehensive processing method, efficient and accurate data fusion is achieved, and a data fusion layer is constructed.

[0098] Based on Bayesian knowledge tracking and HMM, a learning status recognition layer is constructed to identify the student’s current learning status index;

[0099] It should be noted that the Bayesian knowledge tracking method is used to continuously track and update the students' knowledge mastery, and adjust the mastery probability according to the students' performance on different knowledge points. For example, by analyzing the accuracy and reaction time of students when answering specific questions, their mastery of a certain knowledge point is dynamically updated. Then, combined with the hidden Markov model, historical learning behavior data is used to predict the students' learning state transition sequence, such as the possibility of changing from a focused state to a confused state. HMM establishes a series of hidden states (such as focus, confusion, fatigue) and the transition probabilities between them, and combines the observed learning behavior characteristics (such as answering speed, eye movement trajectory, etc.) to infer the most likely learning state path, thereby constructing a learning state recognition layer.

[0100] Based on the data input layer, feature extraction layer, data fusion layer and learning state recognition layer, a learning state evaluation model is constructed;

[0101] It should be noted that by integrating the above layers, a complete chain from raw data collection to final learning status evaluation is realized. Each step focuses on solving specific problems, such as data synchronization, feature extraction, data fusion and status identification, which work together to achieve a comprehensive understanding and accurate quantification of the students' learning status.

[0102] The students’ emotional change data, cognitive load data, and attention level data are input into the learning state evaluation model to predict the students’ current learning state index. The expression is:

[0103]

[0104] Among them, St is the learning status index of the student at time t, X t is the data input to the input layer at time t, M is the total number of input data, and f i (X t ) is the i-th learning state feature extracted by the feature extraction layer, α i is the attention weight of the i-th learning state feature, v 1 is the updated weight coefficient of the probability that the student has mastered the knowledge point k, H t is the learning state hidden variable obtained by HMM, N is the window length of the past moment, and v 2 is the learning state hidden variable H t The weight coefficient, g j (X j ) is the learning state feature extracted by the feature extraction layer at the past time j, β j is the learning state feature g at past time j j (X j ) weight coefficient, ψ(H t ) is the hidden variable H of the student in the learning state t The sensitivity coefficient to past learning experience, o i represents the standard deviation of the i-th learning state feature, μ i represents the mean of the i-th learning state feature, σ represents the activation function, P' min The minimum probability that students master all knowledge points, P' max Indicates the maximum probability of all students mastering the knowledge point;

[0105] It should be noted that, first, the data X at time t is obtained from the input layer t , and calculate M learning state features f at the feature extraction layer i (X t ), each feature is assigned different attention weights α according to its importance i , forming a weighted product. Then, combining the updated student's mastery of knowledge point K P'(K) with the corresponding weight coefficient v 1 This part reflects the influence of students’ knowledge mastery on the current learning state. At the same time, the hidden variable H of the learning state obtained by the hidden Markov model (HMM) t and its weight coefficient v 2 , considering the impact of past learning experience on the current state, through the features g of N time points in the historical data j X j and its weight coefficient β j Quantized, these features are also based on the learning state hidden variable H t The sensitivity coefficient ψ(H t) adjusts the weights to reflect the impact of long-term learning trends on the current state. Finally, all these factors are integrated through nonlinear transformation σ to obtain the student’s learning state index S at time t t .

[0106] According to the students' learning status index S t , marking the students’ learning status as focused, confused and tired.

[0107] It should be noted that first, based on the calculated S t The value is used to judge the student’s current psychological and cognitive state. For example, if a student’s learning state index S at a certain moment t If the score falls within the preset concentration state range, such as between 0.8 and 1.0, the student is marked as being in a concentration state, indicating that he or she currently has a high level of attention and a low cognitive load, which is suitable for in-depth learning or exploring new knowledge. t If the score is in the range of confusion, such as 0.4 to 0.7, it means that the learner may be experiencing some degree of difficulty in understanding or cognitive overload and needs additional guidance and support to help overcome the obstacle. t Below a certain threshold, assuming it is between 0 and 0.3, the learner is marked as fatigued, which means that their attention is significantly reduced and cognitive load is increased. At this time, it is recommended to provide rest or light activities to restore energy. In this way, based on the learning state index S t The specific numerical range of the data can accurately identify and mark the learning status of students, so as to take appropriate educational intervention measures to optimize the learning effect.

[0108] S4. Dynamically generate immersive learning scenarios based on students’ current learning status.

[0109] When students are in a focused state, an exploratory learning situation is generated;

[0110] It should be noted that it first relies on an accurate assessment of the student's current learning status index, which is based on the emotional change data, cognitive load data, and attention level data collected and analyzed previously. After determining that the student is in a focused state based on these data, the next step is to deeply analyze the student's learning path and knowledge point mastery. By comparing the knowledge points that the student has mastered with other untouched knowledge points in the course outline, identify those contents that are both challenging and in line with the student's interests and development direction. For example, in a history course, if the student is particularly interested in ancient civilizations and has mastered the basic background knowledge, then recommend articles and videos on the latest research results or archaeological discoveries about a specific civilization. In addition, algorithms are used to screen out suitable resources from the course database, and combined with interactive elements such as virtual reality experiences or online discussion groups to further enhance the learning experience.

[0111] When students are confused, generate guided learning situations;

[0112] It should be noted that the wrong answers, answering time, eye movement trajectory and other multi-dimensional data generated by the students during the learning process are analyzed in detail to determine which specific knowledge points the students have difficulty with. For example, in a physics course, if a student is confused about the application of Newton's third law, relevant teaching materials will be selected based on this information, including detailed explanation videos, workshops that step by step demonstrate how to apply the law to solve practical problems, and quiz sets containing similar questions but with increasing difficulty. All of these resources are carefully selected and sorted to help students gradually build their understanding of the knowledge point. At the same time, a feedback mechanism will be provided to allow students to submit questions and receive targeted answers. This will not only directly solve the students' confusion, but also enhance their self-confidence.

[0113] When students are in a state of fatigue, a relaxing learning situation is created.

[0114] It should be noted that the assessment of the students' physical and mental fatigue depends on the analysis of data such as eye concentration, blinking frequency, and changes in head posture. Once it is confirmed that the students are in a state of fatigue, the next task is to design a series of activities that help to restore energy. For example, after a long period of reading and technical learning, recommend a 5-minute natural landscape meditation video or play a piece of soft classical music as a short break for students. In addition, some relaxing and interesting learning content can be provided, such as stories or anecdotes related to the professional field but not so tense, such as introducing some interesting historical fragments of the early development of computers in programming courses. These contents are designed to reduce the stress of students and enable them to relax and recover effectively in a short period of time. In this way, students can avoid excessive fatigue while maintaining learning continuity.

[0115] The present embodiment also provides an interactive processing device based on course management, including: an initial path generation module, a personalized path generation module, a learning status evaluation module and a situation generation module; the initial path generation module is used to collect student information, pre-process the student information, and generate an initial learning path according to the pre-processed student information; the personalized path generation module is used to monitor the student's learning behavior data during the student's learning process according to the initial learning path, and to generate a personalized learning path according to the student's learning behavior data; the learning status evaluation module is used to monitor the student's emotion change data, cognitive load data and attention level data in real time in the personalized learning path, construct a learning status evaluation model, and evaluate the student's current learning status; the situation generation module is used to dynamically generate an immersive learning situation according to the student's current learning status.

[0116] This embodiment also provides a computer device, which is suitable for the interactive processing method based on course management, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the interactive processing method based on course management proposed in the above embodiment.

[0117] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0118] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the interactive processing method based on course management as proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination of them, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0119] In summary, the present invention collects and pre-processes student information to generate a personalized initial learning path, combines student learning goals, existing knowledge, available time and other factors, accurately matches learning resources, effectively improves the pertinence and utilization efficiency of educational resources, and enhances the enthusiasm and effect of learning. At the same time, based on real-time monitoring of students' emotional changes, cognitive load and attention level data, dynamically adjusts teaching strategies and generates immersive learning situations, not only focusing on the improvement of academic performance, but also paying special attention to students' emotional experience and psychological state, thereby effectively improving students' learning motivation and interest, reducing learning fatigue, and achieving the goal of comprehensively improving learning experience and effect.

[0120] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An interactive processing method based on course management, characterized in that: include, Collect and pre-process student information, and generate an initial learning path based on the pre-processed student information; In the process of students learning according to the initial learning path, the learning behavior data of the students is monitored, and a personalized learning path is generated according to the learning behavior data of the students; Real-time monitoring of students' emotional changes, cognitive load and attention level data in personalized learning paths, building a learning status evaluation model, and evaluating students' current learning status; Dynamically generate immersive learning scenarios based on students’ current learning status.

2. The interactive processing method based on course management as claimed in claim 1, characterized in that: The student information includes name, age, education background, available study time, learning goals and existing knowledge reserves; The preprocessing includes data cleaning, data standardization and outlier detection.

3. The interactive processing method based on course management as claimed in claim 2, characterized in that: The specific steps of generating the initial learning path according to the preprocessed student information are as follows: Based on the pre-processed student information, the test scope is defined through the knowledge point screening method, and the Bayesian knowledge tracking method is used to preliminarily predict the student's knowledge point mastery probability P(k); Adaptive Testing is used to dynamically adjust the difficulty of questions based on the probability of mastering knowledge points, and ultimately generate a preliminary intelligent test; During the test, the students' answer time and accuracy rate for each knowledge point are recorded in real time; Based on the students’ answering time and accuracy rate for each knowledge point, the collaborative filtering algorithm is used to match students to courses in the course database; Based on the courses matched to the students and their available learning time, the courses are divided into multiple learning units through hierarchical clustering method, and the initial learning path is generated in combination with MDP.

4. The interactive processing method based on course management as claimed in claim 3, characterized in that: In the process of students learning according to the initial learning path, the learning behavior data of the students is monitored, and a personalized learning path is generated according to the learning behavior data of the students. The specific steps are as follows: Students start learning the course based on the initial learning path, and their learning behavior data is monitored during the learning process; The learning behavior data includes learning progress, test answer accuracy, answer time, learning frequency and eye concentration; Based on the students’ learning behavior data, the probability of students mastering knowledge points in the initial learning path P'(K) is updated through the Bayesian knowledge tracking method combined with exponential decay and nonlinear activation function; Based on historical learning data and mastery distribution, define a low mastery threshold P1 and a high mastery threshold P2; When P'(K)≤P1, the learners' mastery is poor, and additional basic courses in the initial learning path are recommended, and targeted exercises are recommended; When P1<P'(K)≤P2, the learner's mastery is average, and consolidation exercises are recommended based on the initial learning path, combined with new knowledge points; When P'(K)>P2, the learner has a good grasp of the subject, and advanced courses are recommended based on the initial learning path; Based on the comparison results of P'(K) with P1 and P2, a personalized learning path is generated.

5. The interactive processing method based on course management as claimed in claim 4, characterized in that: The emotion change data include frown frequency, voice tone fluctuation, speech speed change and heart rate fluctuation; The cognitive load data includes eye movement trajectory, number of repeated learning, information dwell time, and distribution of eye movement dwell points; The attention level data includes eye movement focus duration, blink frequency, head posture changes and body forward leaning angle.

6. The interactive processing method based on course management as claimed in claim 5, characterized in that: The learning status evaluation model is constructed by inputting the student's emotion change data, cognitive load data and attention level data into the learning status evaluation model to evaluate the student's current learning status. The specific steps are as follows: Build a data input layer through time synchronization mechanism to integrate students' emotional change data, cognitive load data and attention level data; Construct a feature extraction layer based on CNN and statistical analysis to obtain multi-level learning state feature vectors; Through time series alignment, feature normalization and multimodal attention mechanism, a data fusion layer is constructed to fuse learning state features; Based on Bayesian knowledge tracking and HMM, a learning status recognition layer is constructed to identify the student’s current learning status index; Based on the data input layer, feature extraction layer, data fusion layer and learning state recognition layer, a learning state evaluation model is constructed; Input the students' emotional change data, cognitive load data and attention level data into the learning status assessment model to predict the students' current learning status index; According to the students' learning status index S t , marking the students’ learning status as focused, confused and tired.

7. The interactive processing method based on course management according to claim 6, characterized in that: The immersive learning scenario is dynamically generated according to the current learning status of the students. The specific steps are as follows: When students are in a focused state, an exploratory learning situation is generated; When students are confused, generate guided learning situations; When students are in a state of fatigue, a relaxing learning situation is created.

8. An interactive processing device based on course management, based on the interactive processing method based on course management according to any one of claims 1 to 7, characterized in that: Including, initial path generation module, personalized path generation module, learning status evaluation module and situation generation module; The initial path generation module is used to collect and preprocess student information and generate an initial learning path based on the preprocessed student information; A personalized path generation module is used to monitor the learning behavior data of the students during the process of the students learning according to the initial learning path, and to generate a personalized learning path according to the learning behavior data of the students; The learning status assessment module is used to monitor the students' emotional change data, cognitive load data and attention level data in real time during the personalized learning path, build a learning status assessment model, and assess the students' current learning status; The scenario generation module is used to dynamically generate immersive learning scenarios based on the students' current learning status.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the interactive processing method based on course management described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the interactive processing method based on course management described in any one of claims 1 to 7 are implemented.

Images