Course learning personalized adjustment method and system of enabling system

Abstract

The invention relates to the field of curriculum personalized adjustment, in particular to a curriculum learning personalized adjustment method and system of an enabling system, and the method comprises the steps: obtaining user information and historical learning data of a user when a learning instruction of the user is received, and recognizing target curriculum data of the user according to the user information and the historical learning data; acquiring historical behavior data of the user, identifying a concentration attenuation trend of the user according to the historical behavior data, and segmenting the target course data into a plurality of course segments according to the concentration attenuation trend; when the user learns the curriculum segment, behavior data of the user is acquired in real time; judging the concentration feedback state of the user according to the behavior data; when the concentration feedback state of the user is positive feedback, generating a learning efficiency enhancement strategy and a composite excitation strategy; and when the concentration feedback state of the user is negative feedback, generating a cognitive load regulation strategy and a pressure balance strategy. The learning state of the user is judged according to the behavior data, and the system can flexibly adjust the learning strategy.

Description

Technical Field

[0001] This application relates to the technical field of curriculum personalized adjustment, and particularly to a method and system for personalized adjustment of curriculum learning in an empowerment system. Background Art

[0002] An empowerment system refers to a system that helps individuals or teams enhance their capabilities by providing appropriate tools, resources, knowledge, or support. In curriculum learning, it can help users improve learning effects through personalized learning resources and paths. For example, online learning platforms, intelligent learning systems, etc. are a type of empowerment system that provides targeted learning content and strategies by analyzing students' learning behaviors.

[0003] Existing technologies usually adjust curriculum content based on users' behavioral data (such as learning duration, task completion status, click times, etc.) and historical learning data (such as exam scores, knowledge mastery, etc.). These methods are based on users' learning records and combine pre-set algorithms to push personalized learning resources for users and make certain learning strategy adjustments. However, this is likely to ignore the dynamic changes in users' concentration. Users' learning concentration may vary greatly in different learning stages. Especially when users' concentration is insufficient, recommendations and adjustments may still be made based on static labels, resulting in poor personalized learning effects. Secondly, existing personalized learning systems usually rely on static labels to classify users' learning situations, such as pushing curriculum content according to labels such as learning progress, ability level, gender, age, etc. This method can provide personalized learning paths to a certain extent, but its adaptability has certain limitations. Since these static labels cannot reflect the changes in users' concentration at different learning stages, the adaptability to the behavioral data of the same user at different learning stages is poor.

[0004] Therefore, there are defects in the existing technologies and improvements are needed. Summary of the Invention

[0005] In order to solve one or several problems in the existing technologies, the main object of this application is to provide a method and system for personalized adjustment of curriculum learning in an empowerment system.

[0006] To achieve the above-mentioned invention object, this application proposes a method for personalized adjustment of curriculum learning in an empowerment system, and the method includes:

[0007] When receiving a user's learning instruction, obtain the user's information and historical learning data, and identify the user's target curriculum data according to the user's information and historical learning data;

[0008] Obtain the historical behavior data of the user, identify the user's concentration attenuation trend according to the historical behavior data, and divide the target course data into multiple course segments according to the concentration attenuation trend;

[0009] When the user is learning a course segment, obtain the user's behavior data in real time;

[0010] Judge the user's concentration feedback status according to the behavior data;

[0011] When the user's concentration feedback status is positive feedback, generate a learning efficiency enhancement strategy and a composite incentive strategy;

[0012] When the user's concentration feedback status is negative feedback, generate a cognitive load adjustment strategy and a stress balance strategy.

[0013] The embodiment of the present application also provides a course learning personalized adjustment system for an empowerment system, including:

[0014] A receiving module, configured to obtain the user information and historical learning data of the user when receiving the user's learning instruction, and identify the target course data of the user according to the user information and historical learning data;

[0015] A first obtaining module, configured to obtain the historical behavior data of the user, identify the user's concentration attenuation trend according to the historical behavior data, and divide the target course data into multiple course segments according to the concentration attenuation trend;

[0016] A second obtaining module, configured to obtain the user's behavior data in real time when the user is learning a course segment;

[0017] A judging module, configured to judge the user's concentration feedback status according to the behavior data;

[0018] A first generating module, configured to generate a learning efficiency enhancement strategy and a composite incentive strategy when the user's concentration feedback status is positive feedback;

[0019] A second generating module, configured to generate a cognitive load adjustment strategy and a stress balance strategy when the user's concentration feedback status is negative feedback.

[0020] The present application also provides a computer device, including a memory and a processor, where the memory stores a computer program, and the processor implements the steps of the method described in any one of the above when executing the computer program.

[0021] The present application also provides a computer-readable storage medium, on which a computer program is stored, and the computer program implements the steps of the method described in any one of the above when executed by a processor.

[0022] The course learning personalized adjustment method and system of the empowerment system in the embodiments of the present application can accurately identify the learning needs and the changing trend of the user's concentration by comprehensively analyzing the user information, historical learning data, and real-time behavior data during the learning process. By dividing the course content into multiple segments to adapt to the user's concentration fluctuations and judging the user's learning state based on the real-time obtained behavior data, the system can flexibly adjust the learning strategy. Specifically, when the user's concentration is good, the system strengthens the learning efficiency and incentive mechanism; when the concentration drops, cognitive load adjustment and stress balance strategies are adopted to avoid fatigue and reduced efficiency caused by overlearning. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 is a schematic flowchart of the course learning personalized adjustment method of the empowerment system according to an embodiment of the present application;

[0024] Figure 2 is a schematic flowchart of the course learning personalized adjustment method of the empowerment system according to an embodiment of the present application;

[0025] Figure 3 is a schematic block diagram of the structure of the course learning personalized adjustment system of the empowerment system according to an embodiment of the present application;

[0026] Figure 4 is a schematic block diagram of the structure of a computer device according to an embodiment of the present application.

[0027] The realization, functional features, and advantages of the purpose of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] In order to make the purpose, technical solutions, and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0029] Refer to Figure 1 , in the embodiments of the present application, a course learning personalized adjustment method of an empowerment system is provided, and the method includes:

[0030] S1. When receiving a learning instruction from a user, obtain the user information and historical learning data of the user, and identify the target course data of the user according to the user information and historical learning data;

[0031] S2. Obtain the historical behavior data of the user, identify the concentration attenuation trend of the user according to the historical behavior data, and divide the target course data into multiple course segments according to the concentration attenuation trend;

[0032] S3. When the user is learning a course segment, obtain the user's behavior data in real time;

[0033] S4. Judge the user's concentration feedback status according to the behavior data;

[0034] S5. When the user's concentration feedback status is positive feedback, generate a learning efficiency enhancement strategy and a compound incentive strategy;

[0035] S6. When the user's concentration feedback status is negative feedback, generate a cognitive load adjustment strategy and a stress balance strategy.

[0036] As described in the above steps S1 - S3, by obtaining the user's basic information (such as age, subject preference, learning style, etc.) and historical learning data (such as academic performance, learning time, learning progress, etc.), the current learning needs and learning goals of the user are determined. By analyzing this information, the system can identify and determine the target course data most suitable for the user's current situation. Through this method, the system can provide personalized course recommendations for the user, thereby enhancing the relevance and effectiveness of learning. Different users have different learning needs. Through accurate selection of target courses, it can help users better achieve their learning goals. By analyzing the user's historical learning behavior data (such as learning duration, learning frequency, concentration, etc.), the system identifies the trend of the user's concentration changing over time. For example, users may be prone to a decline in concentration after a long period of learning. Through monitoring of these behavior data, the system can effectively judge the trend of the user's concentration decay. On this basis, the course content is split into multiple short course segments to adapt to the user's learning concentration at different time periods, thereby optimizing the learning process and avoiding a decrease in efficiency caused by overly long learning. By splitting the course into multiple segments, it can maintain the user's learning concentration and avoid fatigue and reduced efficiency caused by long - term continuous learning. Each segment is relatively short, which helps to enhance the user's learning enthusiasm and ensure that the user's concentration during the learning process is maintained at the best state. The principle of this feature is that by real - time tracking of the user's learning behavior (such as learning duration, mouse clicks, video viewing duration, question - answering progress, etc.), the system can obtain the user's immediate feedback during the learning process. These data can reflect the user's learning state and their degree of concentration. Obtaining the user's behavior data in real time enables the system to adjust the learning strategy according to the data generated during the learning process. This real - time monitoring enhances the flexibility and accuracy of personalized adjustment, enabling the system to optimize the user's learning method at the most appropriate moment.

[0037] As described in the above steps S4 - S7, based on the real - time collected behavioral data (such as the user's interaction frequency, input accuracy, page switching frequency, etc.), the current concentration state of the user is judged. The concentration feedback state can be positive feedback (indicating that the user's concentration remains good) or negative feedback (indicating that the user may start to be distracted or fatigued). Through accurate judgment of behavioral data, the system can understand in real - time whether the user is in a good learning state. If the concentration is low, the system can timely adjust the learning strategy or recommend appropriate intervention measures to improve learning efficiency. When the user's concentration is in a positive feedback state, it means that the user's learning state is good and can withstand more challenges or tasks. At this time, the system further improves the user's learning effect by generating learning efficiency reinforcement strategies (such as increasing learning difficulty, extending learning time, etc.) and compound incentive strategies (such as adding reward mechanisms, providing progress prompts, etc.). The reinforcement strategy in the positive feedback state can effectively improve the user's learning motivation and efficiency. For example, by increasing the task difficulty, providing advanced content, etc., it can prompt the user to further improve the learning level. The compound incentive strategy maintains the user's motivation in various ways to ensure that the user's learning process is not easily interrupted or fatigued. If the user's concentration state is in negative feedback, it means that the user may have problems such as fatigue, distraction, and excessive cognitive load. At this time, the system generates a cognitive load adjustment strategy (such as reducing task difficulty, providing rest time, etc.) and a stress balance strategy (such as psychological counseling, reducing learning intensity, etc.) by analyzing the trend of concentration decay to help the user restore concentration and reduce the stress during the learning process. Through this adjustment in the negative feedback state, the system can prevent the user's learning effect from decreasing due to over - learning. The cognitive load adjustment and stress balance strategies can effectively reduce the stress during the learning process and ensure that the user can maintain an efficient learning state after restoring concentration.

[0038] As described above, through the comprehensive analysis of user information, historical learning data, and real - time behavioral data during the learning process, the learning needs and the changing trend of concentration of the user can be accurately identified. By dividing the course content into multiple segments to adapt to the user's concentration fluctuations and judging the user's learning state based on the real - time obtained behavioral data, the system can flexibly adjust the learning strategy. Specifically, when the user's concentration is good, the system strengthens the learning efficiency and incentive mechanism; when the concentration drops, it adopts the cognitive load adjustment and stress balance strategies to avoid fatigue and reduced efficiency caused by over - learning.

[0039] Refer to Figure 2 , in one embodiment, the steps of generating the learning efficiency reinforcement strategy and the compound incentive strategy include:

[0040] S51. Analyze the current concentration decay trend and eye movement focusing rate of the user according to the behavioral data;

[0041] S52. Build a prediction model, input the attention decay trend and the eye movement focusing rate into the prediction model, and predict the duration of the current attention peak through the prediction model;

[0042] S53. Infer the time compression ratio parameter based on the predicted duration of the attention peak;

[0043] S54. Adjust the learning duration of the current course data based on the time compression ratio parameter;

[0044] S55. Determine the composite incentive strategy based on the adjusted learning duration;

[0045] S56. Build a knowledge association model according to the target course data and historical learning data, input the current knowledge point into the knowledge association degree model, identify the corresponding high-order knowledge nodes through the knowledge association model, and generate interdisciplinary association learning content;

[0046] S57. Determine the learning efficiency enhancement strategy based on the interdisciplinary association learning content.

[0047] As described in the above steps, behavioral data includes users' learning behaviors (such as clicks, dwell time, mouse clicks, etc.) and physiological data (such as eye movement data, brain waves, etc.). These data can reveal the fluctuations in users' concentration. In particular, the eye movement focusing rate (the percentage of time the eyes focus on the course content) can reflect the degree of concentration of users on the current learning content. By analyzing these data, the system can judge the attenuation trend of users' concentration in real time and understand the changes in their attention during the learning process. The attenuation trend of concentration is usually related to factors such as fatigue, learning difficulty, or information overload. For example, if it is found that the concentration drops rapidly, the system can adopt adjustment strategies (such as adjusting the learning rhythm, content, or incentive strategies) to prevent users from being affected by fatigue and thus affecting their learning efficiency. The prediction model uses machine learning techniques and combines factors such as the attenuation trend of concentration and the eye movement focusing rate to establish a dynamic model to predict the change trajectory of users' concentration. Through training with a large amount of historical data, the model can identify the fluctuation patterns of concentration and predict the peak concentration value (i.e., the longest time users can concentrate) in the current state of users, and predict the duration for which the peak concentration value of users is maintained, helping the system to dynamically adjust the presentation time of learning content and avoid content overload or inappropriate learning arrangements before the concentration declines. The core idea of this speculation step is to estimate the optimal learning time arrangement for users based on the predicted peak concentration duration. The time compression ratio is an efficiency optimization parameter for completing learning content within the optimal concentration maintenance duration, and the system can adjust the learning duration of course content through this parameter. For example, if a user's concentration is most concentrated within 30 minutes, then the time compression ratio parameter can adapt to the density and display method of the course content according to this duration, compress unnecessary lengthy content, and highlight key knowledge points. This method can intelligently adjust the learning progress according to the concentration characteristics of users, prevent users from getting fatigued due to excessive learning time, and ensure the maximization of learning efficiency. Through the application of the time compression ratio, the learning content can be completed within the optimal concentration range of users, enhancing the sense of engagement and efficiency of learning. Adjust the duration of the current learning module according to the time compression ratio calculated previously. This means that if the concentration maintenance time of a user is short, the system can shorten the course time and focus on learning key content; if the concentration is long, the learning duration can be appropriately extended or the depth of the course can be increased. Through time adjustment, the learning time can be matched with the concentration of users, avoiding both learning burnout of users and information indigestion caused by learning too quickly, thereby improving the learning effect and learning experience. The compound incentive strategy refers to adjusting suitable incentive methods according to multi-dimensional factors such as learning progress, concentration status, and learning goals. This includes various means such as rewards, feedback, and interactivity, aiming to improve the motivation and participation of learners. If the system detects that a user has completed the expected learning tasks within a certain period of time, the system will give rewards or positive feedback (such as points, progress bars, challenge prompts, etc.) in a timely manner according to the learning duration and progress, enhancing the sense of achievement of learners.The composite incentive strategy can enhance users' learning enthusiasm while they maintain good concentration. By adjusting the incentive means, it can promote users' active learning and improve the motivation and engagement in continuous learning. The knowledge association model analyzes the internal relationships between knowledge points based on course data and historical learning records. Through this model, the relationships between the current knowledge point and higher-order knowledge nodes can be identified, and interdisciplinary associated learning content can be recommended. For example, when learning mathematics, there may be certain knowledge intersections with fields such as physics and computer science. The system can analyze these relationships through the model and suggest interdisciplinary learning paths. This model helps to achieve the integration and learning of interdisciplinary knowledge, enhancing the coherence and depth of knowledge. Users can obtain a more comprehensive learning experience, strengthen their comprehensive abilities by connecting knowledge points in multiple disciplines, and thus improve the learning effect. The learning efficiency enhancement strategy adjusts the learning methods, rhythms, and content display methods targeted based on the user's knowledge structure and interdisciplinary learning content to improve learning efficiency. The system may adjust the learning strategy according to the difficulty of the interdisciplinary content, the user's current knowledge mastery, and historical learning data, and select the most suitable enhancement methods, such as reinforcement memory, problem-solving exercises, interdisciplinary thinking training, etc. This strategy can customize learning methods according to the specific situation of users, thus effectively improving learning efficiency. By dynamically optimizing the learning strategy, it helps users improve their comprehension and application abilities in interdisciplinary learning and achieve more efficient learning goals.

[0048] In one embodiment, the steps of generating the cognitive load regulation strategy and the stress balance strategy include:

[0049] According to the behavioral data, analyze the current focus decay trend of the user, and predict the cognitive load threshold of the user based on the focus decay trend;

[0050] According to the target course data and historical learning data, disassemble the knowledge points of the current learning course segment into the smallest logical units;

[0051] Based on the disassembly results, determine the stress balance strategy;

[0052] When it is detected that the user's cognition reaches the cognitive load threshold, activate the multimodal guidance mechanism to reduce the learning difficulty;

[0053] Based on the multimodal guidance mechanism, determine the load regulation strategy.

[0054] As mentioned above, during the learning process, the user's concentration gradually decays over time, and this decay trend can be identified by analyzing behavioral data (such as eye movement data, mouse click frequency, learning duration, pause time, etc.). Behavioral data reflects the user's learning activities. Combining certain pattern recognition or machine learning algorithms, the decay of the user's concentration can be inferred. The cognitive load threshold refers to the maximum cognitive load that a user can bear. When the concentration decays to a certain extent, the user's cognitive load will reach the threshold, which may lead to a decrease in learning effectiveness or a sense of fatigue. Therefore, predicting the cognitive load threshold based on the decay trend of concentration can help the system timely adjust the learning content or strategy to prevent the user from overworking. By predicting the user's cognitive load threshold, the system can make adjustments in advance to prevent the user from experiencing cognitive overload and ensure that the learning process remains within the optimal efficiency range, improving the user's learning experience. Breaking down the course content into the smallest logical units is to decompose the knowledge points from the macroscopic overall content into small pieces that are easy to understand and remember, avoiding information overload. Historical learning data can provide feedback on the user's learning effectiveness for certain knowledge points. These data can help identify which content is more difficult and which is easier for the user, so as to carry out personalized decomposition. The smallest logical unit refers to a knowledge unit that can be independently understood and is relatively simple, such as a concept, a formula, or an operation step. This decomposition method makes the learning process more operable and modular, facilitating user understanding. According to the decomposed smallest logical units, the system can adjust the learning strategy by evaluating the difficulty of each unit, the user's learning progress, and the cognitive load situation, forming a "pressure balance strategy". If a certain knowledge point is too complex or exceeds the user's current cognitive load threshold, the system can recommend segmented learning, increase demonstrations, or provide tutoring to reduce stress. The pressure balance strategy may involve adjustments to the learning content, such as simplifying information, providing auxiliary materials, or adjusting the learning pace. The aim is to reduce the pressure during the user's learning process and prevent them from having negative emotions or giving up learning due to excessive pressure. Ensure that the learning content matches the user's cognitive load, avoiding overly complex content from causing pressure to the user, thereby reducing learning efficiency or experience. Through the pressure balance strategy, help the user learn in the best learning state. When the system monitors through behavioral data that the user's cognitive load is approaching or reaching its threshold, activate the multimodal guidance mechanism. The multimodal guidance mechanism includes various sensory inputs such as vision, hearing, and touch. In this way, the user can receive more intuitive guidance, such as through diagrams, animations, or voice prompts to help the user reduce the burden. Through multimodal feedback, the system can provide a more vivid and vivid way of helping, enhancing the learning experience while reducing the information complexity in a single mode. Reduce the user's cognitive load and make the learning process more relaxed and intuitive. Multimodal guidance can effectively reduce the cognitive pressure of information, improve the acceptability of learning, and enhance the learning effect.After enabling the multi-modal guidance mechanism, the system adjusts the load regulation strategy in real time according to the current learning progress, the user's response, and the cognitive load level. This may include adjusting the complexity of the learning content, the learning rhythm, or providing rest prompts or guiding curriculum design changes when necessary. The load regulation strategy needs to monitor the user's response in real time and dynamically adjust the learning method based on changes in learning effects and load levels. For example, if a certain knowledge point makes the user overly anxious or fatigued, the system may postpone the learning of that knowledge point, switch to reviewing previous content, or provide more auxiliary information.

[0055] In one embodiment, the step of judging the user's concentration feedback state according to the behavior data includes:

[0056] Analyze the user's current eye movement focusing rate and page scrolling frequency according to the behavior data;

[0057] Obtain the concentration decay trend in the historical behavior data, and determine the concentration feedback threshold according to the concentration decay trend;

[0058] Calculate the user's current concentration index according to the eye movement focusing rate and page scrolling frequency;

[0059] When the concentration index continuously exceeds the concentration feedback threshold, it is determined as a positive feedback state;

[0060] When the concentration index continuously is less than or equal to the concentration feedback threshold, it is determined as a negative feedback state.

[0061] As mentioned above, eye-tracking technology can detect the user's eye fixation points and analyze their attention to different areas on the page. The eye fixation rate represents the ratio of the time the user's eyes are fixed on the learning content to the total time within a certain period. If the user's eyes stay on a certain part for a long time, it indicates that they have a high level of concentration on that part of the content. The page scrolling frequency refers to the speed and frequency at which the user scrolls the page during the learning process. Frequent scrolling may mean that the user is quickly skimming or skipping over content that they are not interested in, while less scrolling may mean that the user is reading or thinking about the content in depth. By analyzing the eye fixation rate and the page scrolling frequency, the user's concentration level can be identified. If the user's eyes move or scroll frequently on the page, it may indicate a lack of concentration; if the eye movements are more concentrated and the scrolling is less, it usually means that the user is focused on the current learning content. Through the analysis of the eye fixation rate and the page scrolling frequency, the user's concentration state can be monitored in real time, helping the system to dynamically determine whether the user is in a state of concentrated attention, and then making adjustments to the learning content. This analysis can provide a reliable basis for subsequent feedback judgments. The trend of concentration decay in historical behavior data: By analyzing the user's historical learning behavior, the system can identify the trend of concentration decay. As the learning time increases or the complexity of the content rises, the user's concentration usually gradually weakens. Historical data can provide a trend analysis model to predict the concentration decay of the user during the current learning process. Based on the trend analyzed from the historical behavior data, the system can determine a concentration feedback threshold, which represents the critical point of the user's concentration. When the user's concentration is below this threshold, the system considers that their attention is not concentrated and feedback or adjustment of the learning strategy is required. By determining the concentration feedback threshold, the system can real-time judge whether the user's concentration is within an acceptable range. The setting of this threshold is based on the historical behavior data of individual users, ensuring that the judgment of the concentration state is personalized and accurate, and helping to give feedback in a timely manner when the concentration is insufficient. The concentration index is an indicator calculated based on the comprehensive calculation of the eye fixation rate and the page scrolling frequency. Generally, when the eye fixation rate is high and the page scrolling frequency is low, it indicates that the user is concentrating and the concentration index is high. On the contrary, if the eye fixation rate is low and the page scrolling is frequent, it indicates that the user's attention is scattered and the concentration index is low. The calculation of the concentration index can combine various algorithms, such as weighted average, machine learning models, etc., to comprehensively evaluate the user's current concentration state. This index will change dynamically according to the user's behavior data, reflecting their concentration level. The calculation of the concentration index can provide a quantitative basis for subsequent feedback judgments, enabling the system to more accurately identify the user's concentration state. Through the dynamic concentration index, the system can adjust the learning strategy in real time to maintain the user's optimal learning state. When the concentration index continuously exceeds the feedback threshold, it indicates that the user is in a focused and efficient learning state.In this case, the system does not need to intervene too much and can maintain the current learning strategy or continue to advance the learning content. The positive feedback state means that the user is learning at an ideal level of concentration. When the system determines that it is in a positive feedback state, it may continue to provide appropriate learning content, maintain the current learning rhythm, and avoid unnecessary interruptions or adjustments. By determining that it is in a positive feedback state, the system can confirm that the user's learning progress and concentration are in an ideal state, so there is no need to adjust the learning content or strategy, ensuring that the user's learning efficiency is not disturbed. When the concentration index is lower than or equal to the concentration feedback threshold, it indicates that the user's concentration is insufficient and may not be able to effectively absorb the current learning content. At this time, the system will determine it as a negative feedback state and prompt the user that there may be problems with the current learning method and adjustments are needed. In the negative feedback state, the system can activate adjustment mechanisms, such as reducing the difficulty of the learning content, providing more visual or auditory feedback, guiding the user to rest or switch the learning content, etc., to help the user restore concentration and improve learning efficiency.

[0062] In one embodiment, the method further includes:

[0063] Obtaining the user's behavior data in real time and identifying the learning stage corresponding to the behavior data;

[0064] Predicting the user's future concentration feedback state based on the learning stage and the behavior data;

[0065] When the predicted result is that the future concentration feedback state is negative feedback, generating an early adjustment strategy based on the judgment result, which is used to generate the cognitive load adjustment strategy and stress balance strategy in advance before the negative feedback state occurs.

[0066] As described above, by obtaining the user's real-time behavior data, behavioral metrics such as their learning status, attention changes, and mood fluctuations are monitored. This data can come from various sensors, monitoring systems, or user interaction behaviors (such as mouse clicks, keyboard inputs, eye trackers, etc.). The real-time acquisition of this data is for dynamically adjusting strategies during the learning process, rather than relying on static or post hoc analysis. Being able to capture the user's changes in real time ensures that timely responses can be made. This enables subsequent feedback mechanisms and adjustment strategies to be more precise, maximizing the user's learning efficiency. The user's learning process is divided into different stages, such as the beginner stage, the mastery stage, the review stage, etc. The cognitive load, concentration level, and behavior patterns are different in each stage. By identifying patterns in the behavior data, it can be determined which learning stage the user is in. This identification can be carried out through machine learning algorithms, pattern recognition techniques, etc. Adjust corresponding strategies according to the user's learning stage. For example, in the beginner stage, more guidance and support may be needed, while in the review stage, it may focus on automated feedback and knowledge reinforcement. This feature helps personalize the learning path and improve learning efficiency. During the learning process, the user's concentration often fluctuates over time, and this fluctuation may be related to various factors, such as task difficulty, fatigue, environmental impact, etc. By combining the learning stage and behavior data, predictive algorithms (such as time series prediction, regression analysis, or machine learning methods) can be used to predict the future concentration state. This process is based on the analysis of the user's past behavior data to speculate on the concentration feedback of the user at a future time point. Being able to predict the user's concentration state in advance, especially predicting the negative feedback state. This provides a basis for early intervention and avoids the user falling into a state of inefficient learning or excessive fatigue. The negative feedback state usually refers to situations such as the user's concentration decreasing, learning efficiency being low, or having negative emotions. Through the prediction of the concentration state, if the system detects a possible downward or unstable trend in future concentration, it can make a timely response. Signs of negative feedback may be the user's slow response, increased error rate, extended interaction time, etc. Timely detecting the downward trend of concentration prevents the user from entering an inefficient state and reduces the decrease in learning efficiency caused by lack of concentration. This feature can effectively avoid problems such as the user having too high a cognitive load or emotional breakdown. After predicting the user's future negative concentration state, the system will automatically generate adjustment strategies to ensure that measures are taken before the problem occurs. These strategies may include cognitive load regulation, task difficulty adjustment, rest time arrangement, environmental optimization, etc. This process takes proactive measures by analyzing the user's needs and behavior patterns in advance, rather than waiting passively for problems to occur. Cognitive load and stress level are closely related during the learning process. When the cognitive load is too high, learning efficiency will decline, and the user's concentration is also easily distracted. By real-time monitoring the user's cognitive load and stress level, adjustment can be made before negative feedback occurs to ensure that the user remains in the best learning state.For example, appropriate rest, task assignment, and adjustment can effectively reduce the user's cognitive burden.

[0067] In one embodiment, after the step of generating an early adjustment strategy based on the judgment result, the method further includes:

[0068] Real-time monitoring of the user's behavior data and emotional state after the execution of the strategy;

[0069] Based on the behavior data and emotional state, determine whether the early adjustment strategy meets the user's expectations;

[0070] When the strategy effect does not meet the expectations, trigger a backup strategy.

[0071] As mentioned above, real-time monitoring of user behavior data and emotional states is to ensure the effectiveness of the generated adjustment strategies. By monitoring behavior data (such as the frequency, duration, and task completion of user operations) and emotional states (such as mood swings, heart rate, facial expressions, and intonation), the system can accurately obtain the user's immediate feedback. This process is similar to the "closed-loop feedback" mechanism for observing the effects after the implementation of strategies. The adjustment of strategies during the learning process not only depends on static data but also needs to combine the user's immediate reactions. The user's behavior and emotional states directly reflect their acceptance and effectiveness of the strategies. If the strategies fail to effectively improve the user's learning state after implementation, then real-time monitoring can help the system capture this and further adjust or replace the strategies. Through real-time monitoring, the system can timely detect changes in the user's behavior after the implementation of strategies and further verify whether the user feels happy or has reduced stress through emotional state feedback. This helps to dynamically adjust strategies during the learning process to improve learning effects and avoid user frustration or inefficient learning caused by ineffective strategies. This part evaluates the effectiveness of strategies by comprehensively analyzing the user's behavior data and emotional states. Behavior data may include task completion, error rate, task completion time, etc., and emotional states may be detected through physiological sensors or facial recognition technology. The system will judge the user's concentration, emotional stability, etc. based on this data and then evaluate whether the pre-adjusted strategies have achieved the expected goals, such as improving concentration and reducing anxiety. The "expected" goals during the learning process are not only to improve knowledge mastery but also to improve emotional states, reduce stress, and avoid fatigue. The monitoring of behavior data and emotional states enables the system to not only evaluate the cognitive effects of strategies but also evaluate the adaptability and comfort of strategies at the emotional level. Through this comprehensive evaluation, it is ensured that users are not only efficient during the learning process but also maintain a pleasant mood and a healthy cognitive load. If the monitoring data shows that the user's behavior or emotional state has not achieved the expected effect after the implementation of the strategies, the system will trigger alternative strategies according to the judgment results. Alternative strategies can be different learning methods, adjust the difficulty of tasks, provide more support or feedback, arrange rest times, change the learning method, etc. The design of alternative strategies needs to be adjusted according to the user's personalized needs and data feedback. For example, if the user shows fatigue or anxiety at a certain learning stage, alternative strategies can be short breaks, mood soothing activities, or adjusting the difficulty of learning content. In the process of personalized learning, not every adjustment strategy can adapt to every user. Especially when faced with changing emotional states and complex behavior patterns, a single strategy may not fully meet the user's needs. Therefore, introducing alternative strategies can prevent users from falling into inefficient learning or negative emotions due to ineffective strategies and improve the adaptability and fault tolerance of the entire learning process.

[0072] In one embodiment, the trigger backup strategy includes: converting text content into visual charts and providing a progressive hint chain. Converting plain text information into a more intuitive chart or visual form. For example, a data table can be converted into a bar chart, line chart, pie chart, etc., or a conceptual description can be converted into a mind map, flowchart, etc. Visual charts can help users more intuitively understand abstract information and improve the acceptability and memorability of information. Plain text may be difficult for some users to digest, especially when dealing with complex data or concepts, and the textual information is prone to causing confusion. Converting information into charts or visual elements can help users quickly grasp key information and reduce the cognitive burden. This method is particularly effective for visual learners (i.e., learners who like to obtain information through visual perception). Through this strategy, the learning content becomes more operable and can effectively improve users' comprehension and learning motivation. The progressive hint chain means providing hint information step by step according to the user's needs and learning progress, rather than presenting all information at once. Such a strategy can help users better understand the learning content through step-by-step guidance and avoid information overload. The hint chain can gradually reveal the methods, steps, or knowledge points for solving problems in stages, encouraging users to gradually explore and solve problems independently.

[0073] Referring to Figure 3 , in the embodiment of the present application, a personalized adjustment system for course learning of an empowerment system is further provided, including:

[0074] A receiving module 1, configured to obtain the user information and historical learning data of the user when receiving the user's learning instruction, and identify the target course data of the user according to the user information and historical learning data;

[0075] A first acquisition module 2, configured to obtain the historical behavior data of the user, identify the attention decay trend of the user according to the historical behavior data, and divide the target course data into multiple course segments according to the attention decay trend;

[0076] A second acquisition module 3, configured to obtain the behavior data of the user in real time when the user learns a course segment;

[0077] A judgment module 4, configured to judge the attention feedback state of the user according to the behavior data;

[0078] A first generation module 5, configured to generate a learning efficiency enhancement strategy and a composite incentive strategy when the attention feedback state of the user is positive feedback;

[0079] A second generation module 6, configured to generate a cognitive load adjustment strategy and a stress balance strategy when the attention feedback state of the user is negative feedback.

[0080] As described above, it can be understood that each component of the course learning personalized adjustment system of the empowerment system proposed in this application can implement the functions of any of the course learning personalized adjustment methods of the empowerment system described above, and the specific structure will not be elaborated.

[0081] Referring to Figure 4 , an embodiment of the present application also provides a computer device, which may be a server, and its internal structure may be as Figure 4 shown. The computer device includes a processor, a memory, a network interface, and a database connected through a system bus. Among them, the processor of the computer design 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, a computer program, and a database. The memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store data such as monitoring data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a course learning personalized adjustment method of an empowerment system.

[0082] The above-mentioned processor executes the above-mentioned course learning personalized adjustment method of the empowerment system, including: when receiving a learning instruction from a user, obtaining the user information and historical learning data of the user, and identifying the target course data of the user according to the user information and historical learning data; obtaining the historical behavior data of the user, identifying the concentration attenuation trend of the user according to the historical behavior data, and dividing the target course data into multiple course segments according to the concentration attenuation trend; when the user is learning a course segment, obtaining the behavior data of the user in real time; judging the concentration feedback state of the user according to the behavior data; when the concentration feedback state of the user is positive feedback, generating a learning efficiency enhancement strategy and a composite incentive strategy; when the concentration feedback state of the user is negative feedback, generating a cognitive load adjustment strategy and a stress balance strategy.

[0083] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, a method for personalized adjustment of course learning of an empowerment system is implemented, including the steps of: when a learning instruction of a user is received, obtaining user information and historical learning data of the user, and identifying target course data of the user according to the user information and historical learning data; obtaining historical behavior data of the user, identifying a focus decay trend of the user according to the historical behavior data, and dividing the target course data into multiple course segments according to the focus decay trend; when the user learns a course segment, obtaining the behavior data of the user in real time; judging a focus feedback state of the user according to the behavior data; when the focus feedback state of the user is a positive feedback, generating a learning efficiency enhancement strategy and a composite incentive strategy; and when the focus feedback state of the user is a negative feedback, generating a cognitive load adjustment strategy and a stress balance strategy.

[0084] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium provided in the present application and used in the embodiments can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or an external cache. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0085] It should be noted that in this text, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, such that a process, apparatus, article or method comprising a series of elements not only includes those elements but also other elements not expressly listed, or elements inherent to such process, apparatus, article or method. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, apparatus, article or method comprising such element.

[0086] The above are only the preferred embodiments of the present application, and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present application.

Claims

1. A method for personalized adjustment of course learning in an empowerment system, characterized in that, The method includes: When receiving a learning instruction from a user, obtaining the user information and historical learning data of the user, and identifying the target course data of the user according to the user information and historical learning data; Obtaining the historical behavior data of the user, identifying the concentration attenuation trend of the user according to the historical behavior data, and dividing the target course data into multiple course segments according to the concentration attenuation trend; When the user is learning a course segment, obtaining the behavior data of the user in real time; Judging the concentration feedback state of the user according to the behavior data; When the concentration feedback state of the user is positive feedback, generating a learning efficiency enhancement strategy and a composite incentive strategy; When the concentration feedback state of the user is negative feedback, generating a cognitive load adjustment strategy and a stress balance strategy.

2. The method for personalized adjustment of course learning of the empowerment system according to claim 1, characterized in that, The steps of generating the learning efficiency enhancement strategy and the composite incentive strategy include: Analyzing the current concentration attenuation trend and eye movement focusing rate of the user according to the behavior data; Constructing a prediction model, inputting the concentration attenuation trend and eye movement focusing rate into the prediction model, and predicting the duration of maintaining the current concentration peak through the prediction model; Speculating the time compression ratio parameter according to the predicted duration of maintaining the concentration peak; Based on the time compression ratio parameter, adjusting the learning duration of the current course data; Based on the adjusted learning duration, determining the composite incentive strategy; According to the target course data and historical learning data, constructing a knowledge association model, inputting the current knowledge point into the knowledge association degree model, identifying the corresponding high-order knowledge nodes through the knowledge association model, and generating interdisciplinary association learning content; Determining the learning efficiency enhancement strategy based on the interdisciplinary association learning content.

3. The method for personalized adjustment of course learning of the empowerment system according to claim 2, characterized in that, The steps of generating the cognitive load adjustment strategy and the stress balance strategy include: Analyzing the current concentration attenuation trend of the user according to the behavior data, and predicting the cognitive load threshold of the user according to the concentration attenuation trend; Decomposing the knowledge points of the current learning course segment into the smallest logical units according to the target course data and historical learning data; Determining the stress balance strategy based on the decomposition result; When it is detected that the user's cognition reaches the cognitive load threshold, activating a multimodal guidance mechanism for reducing the learning difficulty; Determining the load adjustment strategy based on the multimodal guidance mechanism.

4. The method for personalized adjustment of course learning of the empowerment system according to claim 1, characterized in that The steps of judging the concentration feedback state of the user according to the behavior data include: Analyzing the current eye movement focusing rate and page scrolling frequency of the user according to the behavior data; Obtaining the concentration attenuation trend in the historical behavior data, and determining the concentration feedback threshold according to the concentration attenuation trend; Calculating the current concentration index of the user according to the eye movement focusing rate and page scrolling frequency; When the concentration index continuously is greater than the concentration feedback threshold, determining it as a positive feedback state; When the concentration index continuously is less than or equal to the concentration feedback threshold, determining it as a negative feedback state.

5. The method for personalized adjustment of course learning of the empowerment system according to claim 2, characterized in that, The method further includes: Obtaining the behavior data of the user in real time, and identifying the learning stage corresponding to the behavior data. Predict the user's future focus feedback status based on the learning stage and the behavioral data; When the predicted result is that the future focus feedback status is negative feedback, generate an early adjustment strategy based on the judgment result, which is used to generate the cognitive load adjustment strategy and the stress balance strategy in advance before the negative feedback status occurs.

6. The method for personalized adjustment of course learning of the empowerment system according to claim 5, characterized in that After the step of generating the early adjustment strategy based on the judgment result, the method further includes: Real-time monitor the user's behavioral data and emotional state after the strategy is executed; Judge whether the early adjustment strategy meets the user's expectations according to the behavioral data and emotional state; When the strategy effect does not meet the expectations, trigger a backup strategy.

7. The method for personalized adjustment of course learning of the empowerment system according to claim 1, characterized in that, The triggering of the backup strategy includes: converting the text content into a visual chart and providing a progressive hint chain.

8. A personalized adjustment system for course learning of an empowerment system, characterized in that, Include: A receiving module, which is used to obtain the user's user information and historical learning data when receiving the user's learning instruction, and identify the user's target course data according to the user information and historical learning data; A first acquisition module, which is used to obtain the user's historical behavioral data, identify the user's focus attenuation trend according to the historical behavioral data, and divide the target course data into multiple course segments according to the focus attenuation trend; A second acquisition module, which is used to obtain the user's behavioral data in real time when the user is learning a course segment; A judgment module, which is used to judge the user's focus feedback status according to the behavioral data; A first generation module, which is used to generate a learning efficiency enhancement strategy and a composite incentive strategy when the user's focus feedback status is positive feedback; A second generation module, which is used to generate a cognitive load adjustment strategy and a stress balance strategy when the user's focus feedback status is negative feedback.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor implements the steps of the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer program implements the steps of the method according to any one of claims 1 to 7 when executed by the processor.

Images