Problem error analysis method based on cognitive dimension

Abstract

The invention relates to the field of education, and particularly discloses a problem error analysis method based on cognitive dimension, which comprises the following steps: a) a problem identification stage: identifying a specific problem with an error from a to-be-analyzed problem set through a natural language processing technology and a machine learning algorithm, the problem set covers problems in learning, testing, evaluation and knowledge application scenes, and an average error rate Er (P) in the problem set is calculated; b) an error classification stage: classifying the identified problem errors according to the cognitive dimension; through natural language processing and machine learning technologies, errors can be accurately recognized from a large number of problems, the average error rate is calculated, a solid foundation is provided for subsequent analysis, meanwhile, the errors are classified carefully according to the cognitive dimension, the accuracy and comprehensiveness of classification are ensured in combination with multiple technical means, and the classification accuracy and comprehensiveness are improved. And deep analysis of a cognitive mechanism behind an error is facilitated.

Description

Technical Field

[0001] The invention belongs to the field of pedagogy, and specifically is a problem error analysis method based on cognitive dimension. Background Art

[0002] In the fields of intelligent question-answering systems, educational psychology, and cognitive science research, error analysis technology is widely used to analyze the error patterns of individuals in cognitive tasks, reveal their thinking characteristics, and provide guidance for subsequent teaching or system optimization. The error analysis method based on cognitive dimensions is to conduct an in-depth analysis of the errors generated in the problem-solving process from a cognitive perspective, in order to find the root cause of the error and propose corresponding improvement measures.

[0003] In the existing error analysis process, when dealing with a large number of problems, it is often difficult to quickly and accurately identify the errors. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a problem error analysis method based on cognitive dimensions to solve the problem in the prior art that it is often difficult to quickly and accurately identify errors when dealing with a large number of problems.

[0005] A problem error analysis method based on cognitive dimension includes the following steps:

[0006] a) Problem identification stage: From the problem set to be analyzed, specific problems with errors are identified through natural language processing technology and machine learning algorithms. The problem set covers problems in learning, testing, evaluation and knowledge application scenarios, and the average error rate E in the problem set is calculated. r (P);

[0007] b) Error classification stage: classifying the identified problem errors according to cognitive dimensions, including knowledge comprehension errors, memory failures, logical reasoning errors, distraction, fixed thinking, improper strategy application, and metacognitive monitoring failure; and,

[0008] Establish a cognitive dimension error classification framework, combining expert review, historical data analysis, machine learning algorithm optimization, and real-time cognitive load monitoring based on electroencephalogram (EEG) technology to ensure the accuracy and comprehensiveness of classification;

[0009] Calculate the weight W of the cognitive dimension d , weight W d Determined by classification confidence based on expert and historical data and a cognitive load adjustment factor based on EEG data;

[0010] Use EEG technology to monitor learners' cognitive load in real time, and judge learners' cognitive effort and fatigue status in different tasks by analyzing specific frequency bands and features in EEG signals;

[0011] c) Error analysis stage: For each type of error, we deeply analyze the cognitive mechanism behind it, including the specific reasons for the error, the knowledge points involved, skill deficiencies, learning, and deviations in problem-solving strategies; we use a combination of qualitative and quantitative methods, including case analysis, statistical analysis, cognitive load measurement, eye tracking analysis, and real-time cognitive load and fatigue state analysis based on EEG data, to analyze the cognitive process of error occurrence in multiple dimensions; we calculate the correlation between cognitive load and error, R cl (E), correlation R cl (E) Determined by analyzing event-related potentials and brain network connectivity characteristics in EEG signals;

[0012] d) Error mapping stage: Mapping the analyzed error causes to the learners’ individual cognitive characteristics to identify the learners’ weaknesses and development barriers in specific cognitive dimensions;

[0013] e) Feedback and intervention design phase: Based on the error analysis results and cognitive feature mapping, as well as real-time cognitive load and fatigue status monitoring based on EEG data, design personalized feedback mechanisms and intervention strategies to strengthen learners’ weak links and improve their abilities in relevant cognitive dimensions; also includes:

[0014] Dynamically adjust learning content and pace based on learners’ real-time learning data and EEG data to provide customized learning resources and activities;

[0015] Designing a personalized learning path p (t), this path adjusts learning resources and activities in real time based on learners’ learning progress, error history, cognitive development trajectory, and EEG data feedback, combined with optimization algorithms, to promote learners’ self-correction and growth;

[0016] f) Effect evaluation and iteration: After implementing the intervention strategy, the effect of error correction is verified through re-testing and evaluation, and the analysis method and intervention strategy are adjusted according to the evaluation results to form an iterative cycle until the problem errors are effectively reduced and eliminated. At the same time, EEG data is used to monitor the changes in learners' cognitive load and fatigue status during the iteration process to evaluate the effectiveness and sustainability of the intervention strategy.

[0017] Preferably, in step a), the error rate calculation E in the problem identification stage is r (P) uses the following formula:

[0018]

[0019] E r (P) is the average error rate in the problem set P;

[0020] P i is the i-th question;

[0021] E i is the error mark of the i-th question (1 means wrong, 0 means correct);

[0022] n is the total number of questions in the question set;

[0023] t is the current time;

[0024] T is the total time;

[0025] α is the time decay factor, which indicates the speed at which the error rate decays over time;

[0026] δ(Pi,Ei) is the Dirac function, which takes 1 when Pi is an error and 0 otherwise;

[0027] Er(P)∈[0,1], the closer the value is to 1, the higher the error rate in the problem set.

[0028] Preferably, in step b), the cognitive dimension weight calculation W in the error classification stage is d Use the following formula:

[0029]

[0030] W d is the weight of cognitive dimension d;

[0031] C j (d) is the classification confidence of the jth expert and historical data on dimension d;

[0032] EEG j is the EEG data of the jth expert;

[0033] γ(EEG j ) is the cognitive load adjustment factor based on EEG data, which represents the cognitive load state of the expert when giving the classification;

[0034] m is the total number of experts and historical data involved in the classification;

[0035] W d ∈[0,1], the closer the value is to 1, the higher the importance of cognitive dimension d in misclassification.

[0036] Preferably, the error classification stage further includes utilizing real-time cognitive load monitoring technology based on electroencephalogram (EEG) signals to monitor the learner's cognitive load in real time, and adjusting the accuracy and comprehensiveness of error classification according to changes in cognitive load; and determining the learner's cognitive state by analyzing the frequency band characteristics of α, β, θ and δ waves in the EEG signals, thereby optimizing the accuracy of error classification.

[0037] Preferably, in step c), the cognitive load and error correlation calculation R in the error analysis stage cl (E) The following formula is used:

[0038]

[0039] Among them, R cl (E) is the correlation between error E and cognitive load;

[0040] ERP(t) is the event-related potential when an error occurs;

[0041] ERP base (t) is the baseline event-related potential;

[0042] σ ERP is the standard deviation of ERP;

[0043] ΔN k is the change in the number of errors in the kth cognitive dimension;

[0044] N k is the total number of errors on the kth cognitive dimension;

[0045] l is the total number of cognitive dimensions;

[0046] R cl (E)∈[0,+∞), the larger the value, the higher the correlation between the error and cognitive load.

[0047] Preferably, the error analysis stage adopts real-time cognitive load and fatigue status analysis based on EEG data to analyze the cognitive process of error occurrence in multiple dimensions; by analyzing the event-related potential (ERP) components in the EEG signal, including N100, P200, N200 and P300, as well as brain network connection characteristics, the neural mechanism of error generation is revealed.

[0048] Preferably, in step e), the personalized learning path optimization L in the feedback and intervention design phase p (t) The following algorithm is used:

[0049] L p (t) = argmin L∈L [λ1×E r(L)+λ2×CL(L,EEG(t))+λ3×F(L)];

[0050] L p (t) is the optimal personalized learning path at time t;

[0051] L is the set of all possible learning paths;

[0052] E r (L) is the expected error rate on the learning path L;

[0053] CL(L,EEG(t)) is the cognitive load of learning path L at time t;

[0054] F(L) is the fatigue degree of learning path L;

[0055] λ1, λ2, and λ3 are weight factors, indicating the relative importance of different factors in learning path optimization.

[0056] Preferably, the feedback and intervention design stage also includes real-time cognitive load and fatigue status monitoring based on EEG data to dynamically adjust the learning content and rhythm; according to the cognitive load indicators and fatigue status indicators in the EEG data, the difficulty, type of learning tasks and the presentation of learning resources are adjusted in real time to optimize the learners' learning experience and learning effects.

[0057] Preferably, it also includes using EEG technology to monitor the learner's cognitive load and fatigue status in real time, and adjusting the learning intervention strategy according to the monitoring results; by analyzing the specific frequency band characteristics, event-related potential components and brain network connection characteristics in the EEG data, the learner's cognitive state and fatigue level are evaluated, so as to design an accurate learning intervention strategy.

[0058] Compared with the prior art, the present invention has the following beneficial effects:

[0059] Through natural language processing and machine learning technology, it is possible to accurately identify errors from a large number of questions and calculate the average error rate, providing a solid foundation for subsequent analysis. At the same time, errors are carefully classified according to cognitive dimensions, and a variety of technical means are combined to ensure the accuracy and comprehensiveness of the classification, which helps to deeply analyze the cognitive mechanism behind the errors.

[0060] By real-time monitoring of learners' cognitive load and fatigue status, this method can dynamically adjust the learning content and rhythm and design personalized learning paths. This dynamic adjustment not only optimizes learners' learning experience, but also ensures the continuity and effectiveness of the learning process. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 It is a schematic diagram of the method flow of the present invention. DETAILED DESCRIPTION

[0062] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0063] like Figure 1 As shown:

[0064] Embodiment 1: The present invention provides a method for analyzing problem errors based on cognitive dimensions, comprising the following steps:

[0065] a) Problem identification stage: From the problem set to be analyzed, specific problems with errors are identified through natural language processing technology and machine learning algorithms. The problem set covers problems in learning, testing, evaluation and knowledge application scenarios. The average error rate E in the problem set is calculated. r (P);

[0066] b) Error classification stage: Classify the identified problem errors according to cognitive dimensions, including knowledge comprehension errors, memory errors, logical reasoning errors, distraction, fixed thinking, improper strategy application, and metacognitive monitoring failure; and,

[0067] Establish a cognitive dimension error classification framework, combining expert review, historical data analysis, machine learning algorithm optimization, and real-time cognitive load monitoring based on electroencephalogram (EEG) technology to ensure the accuracy and comprehensiveness of classification;

[0068] Calculate the weight W of the cognitive dimension d , weight W d Determined by classification confidence based on expert and historical data and a cognitive load adjustment factor based on EEG data;

[0069] Use EEG technology to monitor learners' cognitive load in real time, and judge learners' cognitive effort and fatigue status in different tasks by analyzing specific frequency bands and features in EEG signals;

[0070] c) Error analysis stage: For each type of error, we deeply analyze the cognitive mechanism behind it, including the specific reasons for the error, the knowledge points involved, skill deficiencies, learning, and deviations in problem-solving strategies; we use a combination of qualitative and quantitative methods, including case analysis, statistical analysis, cognitive load measurement, eye tracking analysis, and real-time cognitive load and fatigue state analysis based on EEG data, to analyze the cognitive process of error occurrence in multiple dimensions; we calculate the correlation between cognitive load and error, Rcl (E), correlation R cl (E) Determined by analyzing event-related potentials and brain network connectivity characteristics in EEG signals;

[0071] d) Error mapping stage: Mapping the analyzed error causes to the learners’ individual cognitive characteristics to identify the learners’ weaknesses and development barriers in specific cognitive dimensions;

[0072] e) Feedback and intervention design phase: Based on the error analysis results and cognitive feature mapping, as well as real-time cognitive load and fatigue status monitoring based on EEG data, design personalized feedback mechanisms and intervention strategies to strengthen learners’ weak links and improve their abilities in relevant cognitive dimensions; also includes:

[0073] Dynamically adjust learning content and pace based on learners’ real-time learning data and EEG data to provide customized learning resources and activities;

[0074] Designing a personalized learning path p (t), this path adjusts learning resources and activities in real time based on learners’ learning progress, error history, cognitive development trajectory, and EEG data feedback, combined with optimization algorithms, to promote learners’ self-correction and growth;

[0075] f) Effect evaluation and iteration: After implementing the intervention strategy, the effect of error correction is verified through re-testing and evaluation, and the analysis method and intervention strategy are adjusted according to the evaluation results to form an iterative cycle until the problem errors are effectively reduced and eliminated. At the same time, EEG data is used to monitor the changes in learners' cognitive load and fatigue status during the iteration process to evaluate the effectiveness and sustainability of the intervention strategy.

[0076] As can be seen from the above, this method systematically covers multiple key stages from problem identification to effect evaluation and iteration. In the problem identification stage, natural language processing and machine learning techniques are used to accurately locate errors in the problem set and calculate the average error rate. Subsequently, in the error classification stage, errors are carefully classified according to cognitive dimensions, and expert review, historical data analysis, machine learning algorithm optimization and EEG technology are used to ensure the accuracy and comprehensiveness of classification, and the weights of each cognitive dimension are calculated at the same time.

[0077] Entering the error analysis stage, this method deeply analyzes the cognitive mechanism behind the error, combines qualitative and quantitative methods, analyzes the cognitive process of error occurrence in multiple dimensions, and calculates the correlation between cognitive load and error. Then, in the error mapping stage, the cause of the error is mapped to the individual cognitive characteristics of the learner to identify the weak links;

[0078] Based on the above analysis, a personalized feedback mechanism and intervention strategy were designed in the feedback and intervention design phase, aiming to strengthen learners’ weak links, and dynamically adjust the learning content and rhythm according to real-time learning data and EEG data to design a personalized learning path;

[0079] Finally, in the effect evaluation and iteration stage, the intervention effect is verified by retesting and evaluating, and the learners' cognitive load and fatigue state changes are monitored based on EEG data to evaluate the effectiveness and sustainability of the intervention strategy, forming an iterative cycle until the problem errors are effectively reduced and eliminated. This method provides strong support for improving learners' cognitive abilities and learning effects.

[0080] Embodiment 2: This embodiment is basically the same as the previous embodiment, except that in step a), the error rate calculation E in the problem identification stage is r (P) uses the following formula:

[0081]

[0082] E r (P) is the average error rate in the problem set P;

[0083] P i is the i-th question;

[0084] E i is the error mark of the i-th question (1 means wrong, 0 means correct);

[0085] n is the total number of questions in the question set;

[0086] t is the current time;

[0087] T is the total time;

[0088] α is the time decay factor, which indicates the speed at which the error rate decays over time;

[0089] δ(Pi,Ei) is the Dirac function, which takes 1 when Pi is an error and 0 otherwise;

[0090] Er(P)∈[0,1], the closer the value is to 1, the higher the error rate in the problem set.

[0091] Specifically, in step b), the cognitive dimension weight calculation W in the misclassification stage is d Use the following formula:

[0092]

[0093] W d is the weight of cognitive dimension d;

[0094] C j(d) is the classification confidence of the jth expert and historical data on dimension d;

[0095] EEG j is the EEG data of the jth expert;

[0096] γ(EEG j ) is the cognitive load adjustment factor based on EEG data, which represents the cognitive load state of the expert when giving the classification;

[0097] m is the total number of experts and historical data involved in the classification;

[0098] W d ∈[0,1], the closer the value is to 1, the higher the importance of cognitive dimension d in misclassification.

[0099] Specifically, the error classification stage further includes the use of real-time cognitive load monitoring technology based on electroencephalogram (EEG) signals to monitor the learner's cognitive load in real time, and adjust the accuracy and comprehensiveness of error classification according to changes in cognitive load; by analyzing the frequency band characteristics of α, β, θ and δ waves in the EEG signal, the learner's cognitive state is judged, thereby optimizing the accuracy of error classification.

[0100] Specifically, in step c), the cognitive load and error correlation calculation R in the error analysis phase cl (E) The following formula is used:

[0101]

[0102] Among them, R cl (E) is the correlation between error E and cognitive load;

[0103] ERP(t) is the event-related potential when an error occurs;

[0104] ERP base (t) is the baseline event-related potential;

[0105] σ ERP is the standard deviation of ERP;

[0106] ΔN k is the change in the number of errors in the kth cognitive dimension;

[0107] N k is the total number of errors on the kth cognitive dimension;

[0108] l is the total number of cognitive dimensions;

[0109] R cl (E)∈[0,+∞), the larger the value, the higher the correlation between the error and cognitive load.

[0110] Specifically, the error analysis stage uses real-time cognitive load and fatigue status analysis based on EEG data to analyze the cognitive process of error occurrence in multiple dimensions; by analyzing the event-related potential (ERP) components in the EEG signal, including N100, P200, N200 and P300, as well as brain network connection characteristics, the neural mechanism of error generation is revealed.

[0111] Specifically, in step e), the personalized learning path optimization L in the feedback and intervention design phase p (t) The following algorithm is used:

[0112] L p (t) = argmin L∈L [λ1×E r (L)+λ2×CL(L,EEG(t))+λ3×F(L)];

[0113] L p (t) is the optimal personalized learning path at time t;

[0114] L is the set of all possible learning paths;

[0115] E r (L) is the expected error rate on the learning path L;

[0116] CL(L,EEG(t)) is the cognitive load of learning path L at time t;

[0117] F(L) is the fatigue degree of learning path L;

[0118] λ1, λ2, and λ3 are weight factors, indicating the relative importance of different factors in learning path optimization.

[0119] As can be seen from the above, in the problem identification stage, this embodiment realizes the dynamic calculation of the average error rate in the problem set by introducing the time decay factor and the Dirac function. In the error classification stage, the weight of the cognitive dimension is calculated by combining the cognitive load adjustment factor with the expert review, historical data analysis and EEG-based real-time cognitive load monitoring technology, thereby improving the accuracy and comprehensiveness of error classification. At the same time, by analyzing the characteristics of different frequency bands in the EEG signal, the learner's cognitive state is monitored in real time, further optimizing the accuracy of error classification.

[0120] In the error analysis phase, by calculating the correlation between errors and cognitive load, and analyzing the real-time cognitive load and fatigue status based on EEG data, the cognitive process of error occurrence was analyzed in multiple dimensions, revealing the neural mechanism of error generation. Finally, in the feedback and intervention design phase, an optimization algorithm was used to comprehensively consider factors such as the expected error rate, cognitive load, and fatigue on the learning path, and the optimal personalized learning path was designed to improve learners' cognitive ability and learning effects.

[0121] Embodiment 3: This embodiment is basically the same as the previous embodiment, except that the feedback and intervention design stage also includes real-time cognitive load and fatigue status monitoring based on EEG data to dynamically adjust the learning content and rhythm; according to the cognitive load index and fatigue status index in the EEG data, the difficulty, type of learning tasks and the presentation method of learning resources are adjusted in real time to optimize the learners' learning experience and learning effect.

[0122] Specifically, it also includes using EEG technology to monitor learners' cognitive load and fatigue status in real time, and adjusting learning intervention strategies based on the monitoring results; by analyzing specific frequency band characteristics, event-related potential components, and brain network connection characteristics in EEG data, the learners' cognitive status and fatigue level are evaluated, so as to design accurate learning intervention strategies.

[0123] As can be seen from the above, this embodiment introduces real-time cognitive load and fatigue status monitoring based on EEG data, so that the adjustment of learning content and rhythm can be carried out according to the real-time status of the learner. By analyzing the specific frequency band characteristics, event-related potential components and brain network connection characteristics in the EEG data in detail, this method can accurately evaluate the learner's cognitive state and fatigue level. Based on these evaluation results, the difficulty and type of learning tasks and the presentation of learning resources can be adjusted in real time, aiming to optimize the learner's learning experience and improve the learning effect. In addition, this method can also dynamically adjust the learning intervention strategy according to the monitoring results to ensure that the intervention measures are more accurate and effective, so as to better meet the learner's personalized needs.

[0124] The standard parts used in the present invention can all be purchased from the market, and the special-shaped parts can be customized according to the description and the drawings. The specific connection methods of each part adopt conventional means such as mature bolts, rivets, welding, etc. in the prior art. The machinery, parts and equipment all adopt conventional models in the prior art, and the circuit connection adopts the conventional connection method in the prior art, which will not be described in detail here. The contents not described in detail in this specification belong to the prior art known to professional and technical personnel in this field.

[0125] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. "Multiple" means two or more, unless otherwise clearly and specifically defined.

[0126] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0127] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0128] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0129] In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other.

[0130] Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A problem error analysis method based on cognitive dimension, characterized in that: The following steps are involved: a) Problem identification stage: From the problem set to be analyzed, specific problems with errors are identified through natural language processing technology and machine learning algorithms. The problem set covers problems in learning, testing, evaluation and knowledge application scenarios, and the average error rate E in the problem set is calculated. r (P); b) Error classification stage: classifying the identified problem errors according to cognitive dimensions, including knowledge comprehension errors, memory failures, logical reasoning errors, distraction, fixed thinking, improper strategy application, and metacognitive monitoring failure; and, Establish a cognitive dimension error classification framework, combining expert review, historical data analysis, machine learning algorithm optimization, and real-time cognitive load monitoring based on electroencephalogram (EEG) technology to ensure the accuracy and comprehensiveness of classification; Calculate the weight W of the cognitive dimension d , weight W d Determined by classification confidence based on expert and historical data and a cognitive load adjustment factor based on EEG data; Use EEG technology to monitor learners' cognitive load in real time, and judge learners' cognitive effort and fatigue status in different tasks by analyzing specific frequency bands and features in EEG signals; c) Error analysis stage: For each type of error, we deeply analyze the cognitive mechanism behind it, including the specific reasons for the error, the knowledge points involved, skill deficiencies, learning, and deviations in problem-solving strategies; we use a combination of qualitative and quantitative methods, including case analysis, statistical analysis, cognitive load measurement, eye tracking analysis, and real-time cognitive load and fatigue state analysis based on EEG data, to analyze the cognitive process of error occurrence in multiple dimensions; we calculate the correlation between cognitive load and error, R cl (E), correlation R cl (E) Determined by analyzing event-related potentials and brain network connectivity characteristics in EEG signals; d) Error mapping stage: Mapping the analyzed error causes to the learners’ individual cognitive characteristics to identify the learners’ weaknesses and development barriers in specific cognitive dimensions; e) Feedback and intervention design phase: Based on the error analysis results and cognitive feature mapping, as well as real-time cognitive load and fatigue status monitoring based on EEG data, design personalized feedback mechanisms and intervention strategies to strengthen learners’ weak links and improve their abilities in relevant cognitive dimensions; also includes: Dynamically adjust learning content and pace based on learners’ real-time learning data and EEG data to provide customized learning resources and activities; Designing a personalized learning path p (t), this path adjusts learning resources and activities in real time based on learners’ learning progress, error history, cognitive development trajectory, and EEG data feedback, combined with optimization algorithms, to promote learners’ self-correction and growth; f) Effect evaluation and iteration: After implementing the intervention strategy, the effect of error correction is verified through re-testing and evaluation, and the analysis method and intervention strategy are adjusted according to the evaluation results to form an iterative cycle until the problem errors are effectively reduced and eliminated. At the same time, EEG data is used to monitor the changes in learners' cognitive load and fatigue status during the iteration process to evaluate the effectiveness and sustainability of the intervention strategy.

2. A method for analyzing problem errors based on cognitive dimensions as claimed in claim 1, characterized in that: In step a), the error rate calculation E of the problem identification stage is r (P) uses the following formula: E r (P) is the average error rate in the problem set P; P i is the i-th question; E i is the error mark of the i-th question (1 means wrong, 0 means correct); n is the total number of questions in the question set; t is the current time; T is the total time; α is the time decay factor, which indicates the speed at which the error rate decays over time; δ(Pi,Ei) is the Dirac function, which takes 1 when Pi is an error and 0 otherwise; Er(P)∈[0,1], the closer the value is to 1, the higher the error rate in the problem set.

3. A method for analyzing problem errors based on cognitive dimensions as claimed in claim 2, characterized in that: In step b), the cognitive dimension weight calculation W of the error classification stage is d Use the following formula: W d is the weight of cognitive dimension d; C j (d) is the classification confidence of the jth expert and historical data on dimension d; EEG j is the EEG data of the jth expert; γ(EEG j ) is the cognitive load adjustment factor based on EEG data, which represents the cognitive load state of the expert when giving the classification; m is the total number of experts and historical data involved in the classification; W d ∈[0,1], the closer the value is to 1, the higher the importance of cognitive dimension d in misclassification.

4. A method for analyzing problem errors based on cognitive dimensions as claimed in claim 3, characterized in that: The error classification stage further includes utilizing real-time cognitive load monitoring technology based on electroencephalogram (EEG) signals to monitor the learner's cognitive load in real time, and adjusting the accuracy and comprehensiveness of error classification according to changes in cognitive load; and determining the learner's cognitive state by analyzing the frequency band characteristics of α, β, θ and δ waves in the EEG signals, thereby optimizing the accuracy of error classification.

5. A method for analyzing problem errors based on cognitive dimensions as claimed in claim 4, characterized in that: In step c), the cognitive load and error correlation of the error analysis phase are calculated as R cl (E) The following formula is used: Among them, R cl (E) is the correlation between error E and cognitive load; ERP(t) is the event-related potential when an error occurs; ERP base (t) is the baseline event-related potential; σ ERP is the standard deviation of ERP; ΔN k is the change in the number of errors in the kth cognitive dimension; N k is the total number of errors on the kth cognitive dimension; l is the total number of cognitive dimensions; R cl (E)∈[0,+∞), the larger the value, the higher the correlation between the error and cognitive load.

6. A method for analyzing problem errors based on cognitive dimensions as claimed in claim 5, characterized in that: The error analysis stage adopts real-time cognitive load and fatigue status analysis based on EEG data to analyze the cognitive process of error occurrence in multiple dimensions; by analyzing the event-related potential (ERP) components in the EEG signal, including N100, P200, N200 and P300, as well as brain network connection characteristics, the neural mechanism of error generation is revealed.

7. A method for analyzing problem errors based on cognitive dimensions as claimed in claim 6, characterized in that: In step e), the feedback is combined with the personalized learning path optimization L in the intervention design phase. p (t) The following algorithm is used: L p (t)=argmin L∈L [λ1×E r (L)+λ2×CL(L,EEG(t))+λ3×F(L)]; L p (t) is the optimal personalized learning path at time t; L is the set of all possible learning paths; E r (L) is the expected error rate on the learning path L; CL(L,EEG(t)) is the cognitive load of learning path L at time t; F(L) is the fatigue degree of learning path L; λ1, λ2, and λ3 are weight factors, indicating the relative importance of different factors in learning path optimization.

8. A method for analyzing problem errors based on cognitive dimensions as claimed in claim 7, characterized in that: The feedback and intervention design stage also includes real-time cognitive load and fatigue status monitoring based on EEG data to dynamically adjust the learning content and rhythm; based on the cognitive load indicators and fatigue status indicators in the EEG data, the difficulty, type of learning tasks and the presentation of learning resources are adjusted in real time to optimize the learners' learning experience and learning effects.

9. A method for analyzing problem errors based on cognitive dimensions as claimed in claim 1, characterized in that: It also includes using EEG technology to monitor learners' cognitive load and fatigue status in real time, and adjusting learning intervention strategies based on the monitoring results; by analyzing specific frequency band characteristics, event-related potential components, and brain network connection characteristics in EEG data, the learners' cognitive status and fatigue level are evaluated, so as to design accurate learning intervention strategies.

Images