Online ideological and political course management system based on big data

Abstract

The invention belongs to the technical field of internet online education, and discloses an online ideological and political course management system based on big data. Comprising the steps of collecting emotional behavior data and cognitive behavior data in a user learning period based on a preset learning period; analyzing to obtain a standardized parameter value; calculating to obtain a cognitive toughness index of the user; generating a datum line, determining upper and lower boundaries, and forming a dynamic safety area of the learning cycle; continuously comparing the cognitive toughness index with the dynamic safety area of the learning cycle, and calculating a cognitive load factor, an emotion blocking factor and a method mismatch factor when the cognitive toughness index is located outside the dynamic safety area; based on the preset main cause judgment rule, the main cause of the user cognitive toughness index outside the dynamic safety area is judged, and the care strategy is distributed according to the main cause, so that coupling evaluation of the emotion behavior and the cognitive behavior of the user on-line ideological and political courses is realized, and an achievement incentive mechanism is configured to improve the learning enthusiasm of the user.

Description

Technical Field

[0001] This invention relates to the field of online education technology, and more specifically, to an online ideological and political education course management system based on big data. Background Technology

[0002] Online ideological and political education course management refers to the detailed data recording and efficiency analysis of users' online learning of ideological and political courses, and the use of big data technology to monitor users' course learning. With the development of internet technology, more and more universities are focusing on the teaching and supervision of online ideological and political courses. To adapt to the teaching needs of the information age, online ideological and political education course management has undergone continuous improvement and optimization, and the platform's functions and practicality are increasingly suited to market demands. However, existing online ideological and political education course management has the following shortcomings: Traditional online course management typically focuses on evaluating users' learning time, course progress, and assignment completion. It only comprehensively assesses users' learning progress by statistically analyzing total learning time and course evaluation scores, failing to accurately capture users' emotional and cognitive behaviors during course learning. Consequently, online course user management is not suitable for the current ideological and political education plans of universities. Furthermore, traditional online course management only monitors whether users have completed the assigned tasks. When users complete course tasks and tests, they do not gain sufficient sense of accomplishment, which leads to users no longer using online courses to explore topics in the course comment section, failing to meet the actual teaching guidance and self-improvement needs.

[0003] In view of this, the present invention proposes an online ideological and political education course management system based on big data to solve the above problems. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art and to achieve the above objectives, in a first aspect, the present invention provides an online ideological and political education course management system based on big data, including: a data acquisition module, used to collect emotional behavior data and cognitive behavior data of users in real time within a preset learning cycle.

[0005] The data standardization module is used to analyze emotional and cognitive behavioral data to obtain standardized parameter values ​​for these data.

[0006] The Emotional Coupling Module is used to calculate the user's cognitive resilience index based on standardized parameter values ​​of emotional and cognitive behavioral data.

[0007] The safe zone generation module is used to generate a baseline and determine the upper and lower boundaries based on the cognitive resilience index of the user's historical learning cycle, forming a dynamic safe zone for the learning cycle.

[0008] The safe zone comparison module is used to continuously compare the cognitive resilience index with the dynamic safe zone of the learning cycle to determine whether the cognitive resilience index is within the dynamic safe zone, and to calculate the cognitive load factor, emotional barrier factor and method mismatch factor when the cognitive resilience index is outside the dynamic safe zone.

[0009] The strategy generation module is used to determine the main reason why a user's cognitive resilience index is outside the dynamic safety zone based on cognitive load factor, emotional barrier factor, method mismatch factor and preset main reason judgment rules, and to allocate care strategies according to the main reason.

[0010] The technical effects and advantages of this invention, an online ideological and political education course management system based on big data, are as follows: This invention collects users' emotional and cognitive behavioral data in parallel within a preset learning cycle, cleans and standardizes them, and calculates a cognitive resilience index reflecting the coupling state of cognition and emotion. A baseline is generated using the cognitive resilience index of historical learning cycles, and upper and lower boundaries are adaptively determined to construct a dynamic safety zone. The cognitive resilience index of the current cycle is continuously compared to determine in real time whether the user has learning deviations. When the main cause of the learning deviation is identified, cognitive load factor, emotional barrier factor, and method mismatch factor are calculated. Based on preset main cause judgment rules, the main cause is determined and corresponding care strategies are matched. Furthermore, by adopting a segmented achievement incentive mechanism, the user's phased learning cycle improvements are transformed into accumulative achievement values ​​to enhance input and self-regulation, achieving refined monitoring, personalized correction, and positive feedback-driven online ideological and political education, improving identification accuracy, intervention timeliness, and teaching collaboration efficiency. Attached Figure Description

[0011] Figure 1 This is a schematic diagram of an online ideological and political education course management system based on big data according to the present invention. Detailed Implementation

[0012] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. Example

[0013] Please see Figure 1 As shown in this embodiment, an online ideological and political education course management system based on big data includes: a data acquisition module, used to collect emotional behavior data and cognitive behavior data of users in real time within a preset learning cycle.

[0014] The data standardization module is used to analyze emotional and cognitive behavioral data to obtain standardized parameter values ​​for these data.

[0015] The Emotional Coupling Module is used to calculate the user's cognitive resilience index based on standardized parameter values ​​of emotional and cognitive behavioral data.

[0016] The safe zone generation module is used to generate a baseline and determine the upper and lower boundaries based on the cognitive resilience index of the user's historical learning cycle, forming a dynamic safe zone for the real-time learning cycle.

[0017] The safe zone comparison module is used to continuously compare the cognitive resilience index with the dynamic safe zone of the real-time learning cycle to determine whether the cognitive resilience index is within the dynamic safe zone, and to calculate the cognitive load factor, emotional barrier factor and method mismatch factor when the cognitive resilience index is outside the dynamic safe zone.

[0018] The strategy generation module is used to determine the main reason why a user's cognitive resilience index is outside the dynamic safety zone based on cognitive load factor, emotional barrier factor, method mismatch factor and preset main reason judgment rules, and to allocate care strategies according to the main reason.

[0019] According to an embodiment of the present invention, the preset learning period is adjusted by the system based on the total duration of ideological and political courses on the platform and according to actual needs; in this embodiment, it is set to one month. During the preset learning period, the system obtains the user's emotional and cognitive behavioral data through the user's operational behavior logs on the platform. The emotional behavioral data specifically includes a case resonance value obtained by multiplying the complete viewing rate of case videos by the proportion of emotional words in notes (such as inspiration, agreement, etc.). The collaboration temperature index is calculated by dividing the number of adopted suggestions by the total number of times the group discussion was held. Cognitive behavioral data specifically includes the number of course interactions for each lesson's ideological and political analysis. The number of independent viewpoints (such as dialectical unity, historical materialism, etc.) in posts in the discussion forum The number of logical connectors (such as therefore, thus, it can be seen, etc.) in the discussion thread By emotionally coupling emotional and cognitive behavioral data, a user's cognitive resilience index can be calculated. A baseline is generated based on the cognitive resilience index of the user's historical learning cycle, and upper and lower boundaries are determined to define the dynamic safety zone of the learning cycle.

[0020] After calculating the user's cognitive resilience index and generating a dynamic safe zone for real-time learning cycles, it is necessary to continuously compare the cognitive resilience index with the dynamic safe zone to determine in real time whether the user has learning biases. When the user's cognitive resilience index falls below the lower limit of the dynamic safe zone for two consecutive learning cycles, it is determined that the user has learning biases. At this point, cognitive load factor, emotional barrier factor, and method mismatch factor are calculated. According to the preset root cause judgment rules, the calculated cognitive load factor, emotional barrier factor, and method mismatch factor are weighted and sorted according to their corresponding weights. The root cause of learning bias is identified based on the cause corresponding to the highest-ranking factor. After identifying the root cause, personalized learning guidance is provided to the user based on the care strategy.

[0021] Additionally, it can be based on predefined achievement trigger conditions and their corresponding achievement values. It calculates the cumulative achievement value a user gains after adjusting their learning after experiencing a learning deviation, and then fulfilling any achievement trigger condition in subsequent learning cycles. Users can increase their learning motivation for online courses based on their cumulative achievement ranking in the class. At the same time, course instructors can also adjust their teaching methods or provide personalized teaching guidance to students in the class based on their cumulative achievement ranking.

[0022] According to an embodiment of the present invention, analysis is performed on emotional behavior data and cognitive behavior data to obtain standardized parameter values ​​for the emotional behavior data and cognitive behavior data, including: data preprocessing of the emotional behavior data and cognitive behavior data to obtain preprocessed data; data preprocessing includes data cleaning and data transformation; Standardized parameter values ​​for emotional and cognitive behavioral data are extracted from the preprocessed data.

[0023] It should be noted that the emotional behavior data specifically includes the case resonance value, which is calculated by multiplying the complete viewing rate of the case video by the proportion of emotional words in the notes (such as inspiration, agreement, etc.). The collaboration temperature index is calculated by dividing the number of adopted suggestions by the total number of times the group discussion was held. Cognitive behavioral data specifically includes the number of course interactions in the analysis of ideological and political education in each lesson. The number of independent viewpoints (such as dialectical unity, historical materialism, etc.) in posts in the discussion forum The number of logical connectors (such as therefore, thus, it can be seen, etc.) in the discussion thread Emotional and cognitive behavioral data were extracted from the platform's operation logs, and outliers were removed. Percentile normalization was used to map the parameter values ​​to the [0,1] interval, thus determining the standardized parameter values ​​for the emotional and cognitive behavioral data.

[0024] According to an embodiment of the present invention, calculating a user's cognitive resilience index includes: calculating the cognitive resilience index for a real-time learning cycle based on standardized parameter values ​​of emotional behavior data and cognitive behavior data. To comprehensively assess the user's overall cognitive and emotional state and resilience; The computational structure embodies an innovative design for cognitive-emotional coupling, that is, it integrates cognitive and emotional behavioral indicators into a single index to reflect their coupled influence. In a preferred embodiment, It can be represented as:

[0025] in, This is a cognitive resilience index within a real-time learning cycle. This represents the average number of course interactions for each lesson's ideological and political education analysis. To the resonance value of the case, For the temperature index of cooperation, The number of independent opinion words in posts on the discussion forum. To discuss the number of logical connectors within a post, , and The corresponding weights are set based on experimental calibration or expert experience to ensure a balance between the contributions of cognitive behavioral data and emotional behavioral data to the cognitive resilience index. In this implementation, the preferred approach is... , , .

[0026] It should be noted that the number of course interactions... Using logarithmic transformation This is to reduce the impact of potential value skewness on the results; the number of independent opinion words in the discussion forum posts. The number of logical connectors within the discussion thread Using square root transformation This is to appropriately compress the differences in larger complexity values; the case resonance value is selected. and cooperation temperature index The mean of the sum of the two, This is to prevent a single indicator from dominating emotional identification.

[0027] According to an embodiment of the present invention, the step of obtaining a dynamic security zone includes: obtaining history. A sequence of cognitive resilience indices for each learning cycle.

[0028] According to history The average value of the cognitive resilience index sequence over a learning cycle is calculated. and standard deviation .

[0029] average As a baseline for the cognitive resilience index during real-time learning cycles, and based on the cognitive resilience index baseline and standard deviation The upper limit of the dynamic safe zone for the real-time learning cycle is calculated respectively. and the lower limit of the dynamic safe zone ;

[0030] in, This is the upper limit of the dynamic security zone. This is the lower limit of the dynamic safety zone. This is the average value. Standard deviation, and These are the preset upper and lower tolerance coefficients, This is a stage coefficient, set according to the start time of the current learning stage, used to dynamically adjust the width of the safety zone.

[0031] The dynamic safe zone of the real-time learning cycle is determined based on the upper and lower limits of the dynamic safe zone. .

[0032] It should be noted that the dynamic safety zone refers to setting an upper and lower tolerance range for the cognitive resilience index of the real-time learning cycle based on the user's cognitive resilience index over multiple historical learning cycles. This range is used to determine normal fluctuations and abnormal deviations in the learning state. First, historical data is obtained. Learning cycles (e.g.) A cognitive resilience index sequence (which can be 5 or 10, depending on implementation needs) is used to calculate historical data. Average of learning cycles and standard deviation Then with As a baseline, pre-set upper and lower tolerance coefficients are introduced. and and stage coefficient To determine the upper and lower limits of the safe zone.

[0033] It should be noted that, according to embodiments of the present invention, the stage coefficient... The schedule will be dynamically adjusted according to the course start time, within one month of the new course start date. Taking the larger value increases the dynamic safety zone interval length by 15%, allowing for a certain range of fluctuations; while during the review period (within one month after the course ends). A smaller value can be used to shorten the dynamic safety zone interval length to 50%, thereby more rigorously monitoring subtle deviations. By constructing upper and lower boundaries based on the adjustment of upper and lower tolerance coefficients combined with stage coefficients, personalized learning can be adaptively generated for different users at different learning stages. Safe zone. Within the dynamic safe zone, Changes are considered normal learning fluctuations; once... Beyond this range, especially if it falls below the lower limit. If this occurs, it can be considered a significant decline in learning status, requiring further analysis and processing.

[0034] According to an embodiment of the present invention, calculating the cognitive load factor, emotional barrier factor, and method mismatch factor when the cognitive resilience index is outside the dynamic safe zone includes: continuously comparing the cognitive resilience index with the upper and lower limits of the dynamic safe zone of the real-time learning cycle to determine whether the cognitive resilience index is within the dynamic safe zone.

[0035] When monitoring users' cognitive resilience index If the user's learning progress falls below the lower limit of the dynamic safe zone for two consecutive learning cycles, it is determined that the user has a learning bias.

[0036] It should be noted that continuously monitoring the user's cognitive resilience index and comparing it with the lower limit of the dynamic safe zone within a real-time learning cycle is to determine whether the user currently has a learning bias. If the user's cognitive resilience index is not lower than the lower limit of the dynamic safe zone, it indicates that the user does not have a learning bias, and no action is taken. If the user's cognitive resilience index is lower than the lower limit of the dynamic safe zone for one learning cycle, the user is reminded to pay attention to their learning progress and is marked. If the user's cognitive resilience index is lower than the lower limit of the dynamic safe zone for two consecutive learning cycles, it is determined that the user currently has a learning bias, and further assistance is needed to help the user find the root cause of the learning bias.

[0037] Calculate the cognitive load factor of the real-time learning cycle when learning bias exists. Emotional barrier factors Method mismatch factor ;

[0038] in, Cognitive load factor, This represents the maximum number of course interactions for each lesson's ideological and political education analysis. This represents the maximum number of independent opinion terms in posts across multiple learning cycles. This represents the maximum number of logical connectors in discussion posts across multiple learning cycles. This is a collaborative temperature index for the real-time learning cycle. The number of independent opinion words in posts on the discussion forum during the real-time learning cycle. The number of logical connectors within discussion posts during the real-time learning cycle.

[0039] Cognitive Load Factor This method is used to measure whether a user's performance has declined due to excessively heavy or difficult cognitive tasks. It compares cognitive behavior data from the most recent learning cycle with historical averages, such as the number of course interactions. Whether there is a significant decline, and whether the difficulty of the course content in this learning cycle is significantly higher than in previous learning cycles. If it is found that the user's performance has significantly decreased and the difficulty of the content has increased significantly during abnormal periods, the cognitive load factor is set to a high value, indicating that there may be a decline in performance due to excessive learning load.

[0040]

[0041] in, As an emotional barrier factor, The case resonance value is the real-time learning cycle. Collaboration temperature index for real-time learning cycles. Emotional barrier factor. This is used to assess whether users' emotional factors (motivation, empathy, collaboration, etc.) are experiencing problems such as insufficient learning motivation or negative emotional interference. It analyzes abnormal changes in emotional behavior data, such as whether the case resonance value and collaboration temperature index are significantly lower than normal. If a lack of recent resonance with the teaching case is detected (case resonance value...), it indicates a potential issue. (Significantly low) and a lack of willingness to participate in collaboration (collaboration temperature index) If the value decreases, the emotional barrier factor will be high, indicating that emotional participation barriers may be the main reason.

[0042]

[0043] in, The method mismatch factor, This refers to the number of times that incorrect assignments were redone without improvement. The total number of redo attempts is used to measure the inefficiency of repetitive practice. Both data can be obtained from the user's assignment submission and correction records on the platform.

[0044] Method mismatch factor This tool is used to determine if a user is using an unsuitable learning method or strategy. It checks the degree of deviation between the user's learning strategy and the system's recommended strategy. For example, it checks whether the user is not learning content in the recommended order, skipping important parts, or using inefficient learning methods. This can be assessed by allocating learning time and the time spent in each lesson to determine if excessive time is spent in a single lesson. If it is significantly higher than the average of other users, it is considered a problem with the learning method. It also considers the user's course assignment redoing frequency. Frequent invalid redos indicate low learning efficiency, leading to more redoing behavior; this is set as a method mismatch factor. If the ratio of invalid course redo attempts to total redos by a user is found to be large, then the corresponding method mismatch factor is indicated. Increase.

[0045] According to this embodiment, the main reason why the user's cognitive resilience index is outside the dynamic safety zone is determined, and the care strategy is allocated according to the main reason, including: performing deviation attribution analysis, weighting the cognitive load factor, emotional barrier factor and method mismatch factor according to the preset main reason judgment rules, and ranking them according to size, taking the first one in the size ranking as the main reason for the occurrence of learning deviation.

[0046] It should be noted that the calculation results of the cognitive load factor, emotional barrier factor, and method mismatch factor are normalized and then multiplied by preset weighting coefficients. , , (This weight can be set based on experience, representing the impact of various factors on the overall learning effect, and is preferred in this implementation.) , , The weighted attribution factor values ​​are compared, and when the weighted value of one factor is significantly higher than the others, the corresponding cause is determined to be the primary cause. For example, if the cognitive load factor score is the highest, the primary cause is determined to be cognitive overload caused by excessively difficult learning content or tasks; if the emotional barrier factor score is the highest, the primary cause is that the user lacks emotional motivation or is affected by psychological factors; if the method mismatch factor is the highest, the primary cause is determined to be inappropriate learning methods.

[0047] After identifying the primary cause, appropriate care strategies are matched from a pre-defined care strategy library based on the primary cause of the learning bias, and intervention operations are performed.

[0048] It should be noted that after identifying the primary cause, if the primary cause is excessive cognitive load, strategies will be adopted to reduce the learning difficulty or workload. This includes providing users with step-by-step explanations of difficult content, recommending supplementary materials, or adjusting the learning pace to alleviate the excessive cognitive load. If the primary cause is emotional barrier, encouraging feedback will be sent, visual results of learning progress will be displayed, and encouraging interactions from mentors will be provided to enhance the user's confidence and emotional investment. If the primary cause is method mismatch, guidance on learning methods will be provided, such as suggesting more effective learning strategies, recommending a revised learning plan, or providing targeted learning skills training. Based on this, the care strategy library configuration is set as follows:

[0049] By generating deviation attribution analysis and matching care strategies, this invention can promptly diagnose the causes of a user's continuous abnormal decline and provide customized support interventions to help the user correct deviations and return to a safe zone.

[0050] According to an embodiment of the present invention, it further includes establishing a positive feedback achievement reward mechanism: pre-defining the user's achievement trigger conditions and corresponding achievement values. The predefined conditions for triggering user achievements are as follows.

[0051] Condition 1: Cognitive resilience index during real-time learning cycles If there is improvement compared to the previous learning cycle and the student remains within their comfort zone, it is considered to have achieved basic progress, and a small achievement increment is assigned. .

[0052] Condition 2: Cognitive resilience index during real-time learning cycles An improvement exceeding the safe zone limit is considered a significant advancement and is awarded a substantial achievement value. .

[0053] Condition 3: Continuous Learning cycles (e.g.) Cognitive resilience index If all scores are maintained within or above the safe zone limit, the player is considered to be consistently excellent and will be awarded a higher achievement score. .

[0054] When a user meets any achievement trigger condition within the real-time learning cycle, the corresponding achievement value is calculated. The system then accumulates the real-time achievement values ​​to generate the user's cumulative achievement value. .

[0055] Achievement Points The calculation can be represented as a piecewise function:

[0056] in, Achievement values ​​adjusted for user learning This represents the upper limit of the safe zone for the cognitive resilience index. This represents the lower limit of the safe zone for the cognitive resilience index. For real-time learning cycles Cognitive resilience index, These are experience coefficients, set by the system based on historical experience or by the instructor according to the actual needs of the class users. In this embodiment, the preferred coefficient is... , , .

[0057] It should be noted that establishing a positive feedback achievement reward mechanism involves calculating achievement values. It also sets achievement trigger conditions to convert users' recent good performance into incentive feedback, encouraging users to maintain a positive attitude. Achievement Value The calculation employs a piecewise function, assigning different reward values ​​based on different levels of achievement conditions. The positive feedback achievement reward mechanism transforms abstract achievement values ​​into concrete forms of positive feedback, such as awarding digital badges, points rewards, or unlocking permissions. When accumulated achievement values ​​reach a specific threshold, special titles or badges can be awarded and displayed on the user interface to enhance the user's sense of accomplishment. Simultaneously, course instructors can monitor and accurately identify classes based on the cumulative achievement value ranking of users, encouraging users with higher cumulative achievement value rankings and providing guidance to those with lower rankings.

[0058] This invention collects users' emotional and cognitive behavioral data in parallel within a preset learning cycle, cleans and standardizes them, and calculates a cognitive resilience index that reflects the coupling state of cognition and emotion. A baseline is generated using the cognitive resilience index from historical learning cycles, and upper and lower boundaries are adaptively determined to construct a dynamic safety zone. The cognitive resilience index of the current cycle is continuously compared to determine in real time whether the user has learning deviations. When the main cause of the learning deviation is identified, cognitive load factor, emotional barrier factor, and method mismatch factor are calculated. Based on preset main cause judgment rules, the main cause is determined and corresponding care strategies are matched. Furthermore, by adopting a segmented achievement incentive mechanism, the user's phased learning cycle improvements are transformed into accumulative achievement values ​​to enhance input and self-regulation. This achieves refined monitoring, personalized correction, and positive feedback-driven online ideological and political learning, improving identification accuracy, intervention timeliness, and teaching collaboration efficiency.

[0059] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0060] It should be noted that all formulas in this manual are calculated by removing dimensions and taking their numerical values. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters and thresholds in the formulas are set by those skilled in the art according to the actual situation.

[0061] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

Claims

1. A big data-based online ideological and political education course management system, characterized in that, include: The data acquisition module is used to collect emotional and cognitive behavioral data of users in real time within a preset learning period; The data standardization module is used to analyze emotional and cognitive behavioral data to obtain standardized parameter values ​​for these data. The emotional coupling module is used to calculate the user's cognitive resilience index based on standardized parameter values ​​of emotional and cognitive behavioral data. The safe zone generation module is used to generate a baseline and determine the upper and lower boundaries based on the cognitive resilience index of the user's historical learning cycle, forming a dynamic safe zone for the real-time learning cycle. The safe zone comparison module is used to continuously compare the cognitive resilience index with the dynamic safe zone of the real-time learning cycle, determine whether the cognitive resilience index is within the dynamic safe zone, and calculate the cognitive load factor, emotional barrier factor and method mismatch factor when the cognitive resilience index is outside the dynamic safe zone. The strategy generation module is used to determine the main reason why a user's cognitive resilience index is outside the dynamic safety zone based on cognitive load factor, emotional barrier factor, method mismatch factor and preset main reason judgment rules, and to allocate care strategies according to the main reason.

2. The online ideological and political education course management system based on big data according to claim 1, characterized in that, The analysis based on emotional and cognitive behavioral data yields standardized parameter values ​​for these data, including: Emotional and cognitive behavioral data are preprocessed to obtain preprocessed data; data preprocessing includes data cleaning and data transformation. Standardized parameter values ​​for emotional and cognitive behavioral data are extracted from the preprocessed data.

3. The online ideological and political education course management system based on big data according to claim 2, characterized in that, The emotional behavior data includes the case resonance value. and cooperation temperature index Cognitive behavioral data includes the number of course interactions for each lesson's ideological and political analysis. The number of independent opinion words in discussion forum posts The number of logical connectors in the discussion thread .

4. The online ideological and political education course management system based on big data according to claim 1, characterized in that, The calculation yields the user's cognitive resilience index, including: Number of course interactions Logarithmic transformation was used to analyze the number of independent opinion words in posts on the discussion forum. The number of logical connectors in the discussion thread Using square root transformation, the resonance value of the case is... and cooperation temperature index The cognitive resilience index for a user's real-time learning cycle is calculated by weighting standardized parameter values ​​based on the mean of emotional and cognitive behavioral data. .

5. The online ideological and political education course management system based on big data according to claim 1, characterized in that, The system also includes: Get History A sequence of cognitive resilience indices for each learning cycle; According to history The average value of the cognitive resilience index sequence over a learning cycle is calculated. and standard deviation ; average As a baseline for the cognitive resilience index during real-time learning cycles, and based on the cognitive resilience index baseline and standard deviation The upper limit of the dynamic safe zone for the real-time learning cycle is calculated respectively. and the lower limit of the dynamic safe zone ; The dynamic safe zone of the real-time learning cycle is determined based on the upper and lower limits of the dynamic safe zone. .

6. The online ideological and political education course management system based on big data according to claim 1, characterized in that, The cognitive load factor, emotional barrier factor, and method mismatch factor for calculating the cognitive resilience index when it is outside the dynamic safety zone include: The cognitive resilience index is continuously compared with the upper and lower limits of the dynamic safe zone of the real-time learning cycle to determine whether the cognitive resilience index is within the dynamic safe zone. When monitoring users' cognitive resilience index If the user's learning rate falls below the lower limit of the dynamic safety zone for two consecutive learning cycles, it is determined that the user has a learning bias. Calculate the cognitive load factor of the real-time learning cycle when learning bias exists. Emotional barrier factors Method mismatch factor .

7. The online ideological and political education course management system based on big data according to claim 1, characterized in that, The main reasons for determining that the user's cognitive resilience index is outside the dynamic safety zone, and the allocation of care strategies based on the main reasons, include: To conduct bias attribution analysis, cognitive load factor, emotional barrier factor and method mismatch factor are weighted and calculated according to the preset main cause judgment rules, and ranked by size. The first one in the size ranking is taken as the main cause of learning bias. After identifying the primary cause, appropriate care strategies are matched from a pre-defined care strategy library based on the primary cause of the learning deviation and intervention operations are performed.

8. The online ideological and political education course management system based on big data according to claim 1, characterized in that, The system also includes: Predefine the user's achievement trigger conditions and corresponding achievement values. ; When a user meets any achievement trigger condition within the real-time learning cycle, the corresponding achievement value is calculated. The system then accumulates the real-time achievement values ​​to generate the user's cumulative achievement value. .

9. The online ideological and political education course management system based on big data according to claim 8, characterized in that, The predefined achievement trigger conditions for users include: Cognitive resilience index of real-time learning cycle Improvement from the previous learning cycle and remaining within the comfort zone warrants a smaller increment in achievement. ; Cognitive resilience index of real-time learning cycle Exceeding the safe zone limit grants a significant achievement value. ; continuous Cognitive resilience index per learning cycle All achievements are awarded if they remain within or above the safe zone limit. .

Images