An education effect evaluation method and system based on artificial intelligence

Abstract

The present invention discloses an educational effect evaluation method and system based on artificial intelligence. The method includes multi-modal data preparation, dynamic cognitive modeling, multi-dimensional effect evaluation, adaptive result optimization, and educational effect evaluation. The present invention relates to the technical field of educational effect evaluation. By using integrated analysis of multi-modal data and combining the fusion method of generative adversarial network and time series model, comprehensive evaluation of immediate, long-term, and transfer educational effects is carried out, which can more comprehensively and meticulously evaluate the performance of students at different learning stages and provide accurate evaluation results. By combining cognitive network analysis with improved dynamic Bayesian network, and using dynamic Bayesian inference and reinforcement learning optimization, accurate modeling of the cognitive process of students is carried out based on the learning history and real-time feedback of students. By adopting a hybrid recommendation improvement method combined with clustering of group learning characteristics, dynamic learning content and strategy recommendations are made for students.

Description

Technical Field

[0001] The present invention relates to the technical field of educational effect evaluation, and specifically refers to an educational effect evaluation method and system based on artificial intelligence. Background Art

[0002] The educational effect evaluation method based on artificial intelligence is an innovative way that uses technologies such as machine learning, natural language processing, and data mining to intelligently analyze and evaluate students' learning behaviors, cognitive processes, and knowledge mastery. It collects multi-dimensional data (such as classroom performance, homework completion, interactive feedback, etc.), constructs personalized learning models, and monitors learning progress in real time and predicts future performance. This method can not only accurately identify students' knowledge blind spots and learning preferences, but also provide scientific teaching optimization suggestions for teachers, so as to achieve individualized teaching and comprehensive improvement of teaching quality. Its core role is to transform the traditional result-oriented evaluation into a process-oriented and dynamic intelligent evaluation, providing a data-driven scientific basis for educational decision-making.

[0003] However, in the existing educational effect evaluation process, there are technical problems where many traditional evaluation methods only focus on a certain dimension (such as exam scores or classroom interaction) to evaluate students' learning effects, and the existing evaluation methods often only focus on students' short-term effects, ignoring the changes in long-term learning achievements and in-depth knowledge mastery; in the existing dynamic cognitive modeling methods, there are technical problems where the existing cognitive modeling methods are difficult to adapt to the dynamic changes in students' cognitive structures and strategies during the learning process, and the knowledge mastery of students in learning is constantly changing, and traditional models cannot reflect these changes in real time; in the existing multi-dimensional effect evaluation methods, there are technical problems where traditional evaluation dimensions often focus on one aspect (such as grades or participation), ignoring other key factors in the learning process, and existing evaluation methods also tend to be short-term instant evaluations, making it difficult to effectively capture students' knowledge accumulation, thinking transfer ability, and interdisciplinary comprehensive qualities over a long period of time, resulting in single evaluation dimensions and unable to comprehensively reflect students' comprehensive learning abilities; in the existing adaptive result optimization methods, there are technical problems where the existing optimization methods usually lack learning content recommendations for students' individual differences, unable to provide accurate learning resources or strategies according to students' cognitive processes, learning states, and behavioral characteristics, and traditional methods mostly only consider the learning processes of individual students, ignoring the potential of group learning characteristics, lacking personalized recommendations and consideration of group learning characteristics. Summary of the Invention

[0004] In view of the above situation, to overcome the defects of the existing technology, the present invention provides an education effect evaluation method and system based on artificial intelligence. In the existing education effect evaluation process, there are many traditional evaluation methods that only focus on a certain dimension (such as exam scores or classroom interaction) to evaluate the learning effect of students. Moreover, the existing evaluation methods often only focus on the short-term effect of students, ignoring the changes in long-term learning achievements and in-depth knowledge mastery. The present solution creatively adopts multi-modal data integration analysis, combines the fusion method of generative adversarial network and time series model, and conducts comprehensive evaluation of immediate, long-term and transfer education effects, which can more comprehensively and meticulously evaluate the performance of students at different learning stages and provide accurate evaluation results. In the existing dynamic cognitive modeling methods, there is a technical problem that the existing cognitive modeling methods are difficult to adapt to the dynamic changes of students' cognitive structures and strategies during the learning process, and the knowledge mastery of students in learning is constantly changing, and traditional models cannot reflect these changes in real time. The present solution creatively adopts the method of combining cognitive network analysis and improved dynamic Bayesian network, uses dynamic Bayesian inference and reinforcement learning optimization, and accurately models the cognitive process of students based on their learning history and real-time feedback. At the same time, the metacognitive adjustment module further improves the personalization and accuracy of the model through adaptive learning strategy optimization. In the existing multi-dimensional effect evaluation methods, there is a technical problem that traditional evaluation dimensions often focus on one aspect (such as grades or participation), ignoring other key factors in the learning process. Existing evaluation methods also tend to focus on short-term immediate evaluation, making it difficult to effectively capture students' knowledge accumulation, thinking transfer ability and interdisciplinary comprehensive qualities over a long period of time, resulting in a single evaluation dimension and unable to comprehensively reflect students' comprehensive learning ability. The present solution creatively adopts an innovative method combining generative adversarial network and variable pressure time series network, considers immediate feedback, long-term learning effect and interdisciplinary transfer ability during the evaluation process, ensures that the learning effect of students can be comprehensively evaluated from multiple dimensions, and provides more accurate education effect evaluation results. In the existing adaptive result optimization methods, there is a technical problem that the existing optimization methods usually lack learning content recommendations for students' individual differences, cannot provide accurate learning resources or strategies according to students' cognitive processes, learning states and behavioral characteristics, and traditional methods mostly only consider the learning processes of individual students, ignoring the potential of group learning characteristics and lacking personalized recommendations and consideration of group learning characteristics. The present solution creatively adopts a hybrid recommendation improvement method combining group learning characteristic clustering, dynamically recommends learning content and strategies for students, and provides a personalized and flexible dynamic optimization plan for the learning process by analyzing students' cognitive process characteristics and group similarity data, realizing continuous improvement and optimization of education effects.

[0005] The technical solution adopted by the present invention is as follows: An education effect evaluation method based on artificial intelligence provided by the present invention includes the following steps:

[0006] Step S1: Multi-modal data preparation;

[0007] Step S2: Dynamic cognitive modeling;

[0008] Step S3: Multi-dimensional effect evaluation;

[0009] Step S4: Adaptive result optimization;

[0010] Step S5: Education effect evaluation.

[0011] Further, in step S1, the multi-modal data preparation is used to collect the learning process data of students. Specifically, through the collection of learning process data, the original learning process data of students is collected, and through knowledge construction analysis and data optimization, the optimized multi-modal education effect evaluation data is obtained;

[0012] The original learning process data of students specifically includes classroom interaction record data, homework and quiz data, classroom feedback data, student status evaluation data, classroom note data, and extracurricular learning situation data;

[0013] The optimized multi-modal education effect evaluation data specifically includes optimized classroom interaction data, optimized student status data, and optimized learning process data.

[0014] Further, in step S2, the dynamic cognitive modeling is used to optimize the cognitive process of students through a dynamic modeling method. Specifically, based on the optimized multi-modal education effect evaluation data, a dynamic Bayesian network improved by combining cognitive network analysis and cognitive ability modeling is adopted for dynamic cognitive modeling and prediction, and the cognitive process feature data is obtained, including the following steps:

[0015] Step S21: Construct the original data input, specifically using the optimized multi-modal education effect evaluation data as the original data input sample;

[0016] Step S22: Cognitive network analysis, specifically using the standard cognitive network analysis method to construct knowledge nodes and learning relationship paths, and based on the historical learning situation of students in the original data input sample, conduct an association analysis of the students' mastery of knowledge points to obtain the reference data of knowledge point association degree;

[0017] Step S23: Construct an improved dynamic Bayesian network, specifically constructing a standard dynamic Bayesian network and using the reference data of knowledge point association degree as state variables for improved dynamic Bayesian inference to obtain the basic cognitive modeling model of students' knowledge points;

[0018] Step S24: Meta - cognitive adjustment, specifically by constructing a student cognitive reward function, performing knowledge - point cognitive adjustment based on reinforcement learning, constructing a meta - cognitive ability model, simulating students' learning strategy adjustment, and obtaining a meta - cognitive corrected student dynamic cognitive modeling model through iterative training of reinforcement learning;

[0019] The student cognitive reward function is specifically weighted and composed of a classroom interaction reward term, a homework and quiz reward term, a classroom feedback reward term, a learning state reward term, and an in - class and out - of - class learning reward term;

[0020] Step S25: Dynamic cognitive modeling, specifically by the above - mentioned construction of raw data input, cognitive network analysis, construction of an improved dynamic Bayesian network, and meta - cognitive adjustment, performing dynamic cognitive modeling to obtain cognitive process feature data;

[0021] The cognitive process feature data specifically includes knowledge - point mastery situation data, learning strategy behavior data, learning emotion state change data, learning process prediction and optimization data, and meta - cognitive data;

[0022] The meta - cognitive data is used to represent students' ability to monitor, evaluate, and regulate their own learning processes.

[0023] Furthermore, in step S3, the multi - dimensional effect evaluation is used to evaluate the learning effect in multiple dimensions. Specifically, based on the cognitive process feature data, a variable - pressure time - series network combined with generative adversarial transfer knowledge is used to perform immediate, long - cycle, and transfer three - dimensional education effect evaluations to obtain multi - dimensional education effect evaluation reference data, including the following steps:

[0024] Step S31: Immediate education effect evaluation, specifically by constructing a generative adversarial network with improved feedback rewards for immediate education effect generation and evaluation to obtain immediate education effect evaluation reference data;

[0025] The improvement of the feedback reward is specifically achieved by generating the learning progress data of students through a generator and designing the improvement of the feedback reward by calculating the expected decision probability;

[0026] Step S32: Long - cycle education effect evaluation, specifically by using a variable - pressure time - series network to perform long - cycle education effect evaluation modeling and obtaining long - cycle education effect evaluation data through time - series modeling;

[0027] Step S33: Transfer education effect evaluation, specifically by combining the results of the immediate education effect evaluation and transferring them to interdisciplinary content for cross - disciplinary transfer effect evaluation to obtain transfer education effect evaluation data;

[0028] Step S34: Training of the multi-dimensional effect evaluation model. Specifically, through the instant education effect evaluation, the long-term education effect evaluation, and the transfer education effect evaluation, the multi-dimensional effect evaluation model is trained to obtain the multi-dimensional effect evaluation model;

[0029] Step S35: Multi-dimensional effect evaluation. Specifically, based on the cognitive process characteristic data, the multi-dimensional effect evaluation model is used to conduct multi-dimensional effect evaluation to obtain multi-dimensional education effect evaluation reference data.

[0030] Furthermore, in Step S4, the adaptive result optimization is used to dynamically optimize the learning process according to the evaluation results. Specifically, based on the cognitive process characteristic data and the multi-dimensional education effect evaluation reference data, a hybrid recommendation improvement method combining group learning feature clustering is adopted to dynamically optimize the adaptive learning process, and reference learning plan data for dynamic optimization of the learning process is obtained, including the following steps:

[0031] Step S41: Group learning feature clustering. Specifically, through a clustering algorithm, based on the cognitive process characteristic data and the multi-dimensional education effect evaluation reference data, student similarity calculation is performed to obtain similarity clustering learning feature data;

[0032] Step S42: Learning content recommendation. Specifically, based on the cognitive process data of students and the similarity clustering learning feature data, learning content recommendation is performed to obtain learning content recommendation data;

[0033] Step S43: Collaborative filtering recommendation. Specifically, based on the multi-dimensional education effect evaluation reference data and the similarity clustering learning feature data, learning strategy recommendation within the student group is performed to obtain in-group recommendation data;

[0034] Step S44: Integration of learning content recommendations. Specifically, the learning content recommendation data and the in-group recommendation data are weighted and integrated to obtain balanced learning content recommendation reference data;

[0035] Step S45: Adaptive result optimization. Specifically, by testing and adjusting the weights of the integrated learning content recommendations, reference learning plan data for dynamic optimization of the learning process is obtained.

[0036] Furthermore, in Step S5, the education effect evaluation is used to integrate the processes of cognitive modeling, effect evaluation, and result optimization and conduct comprehensive education effect evaluation. Specifically, by combining the reference learning plan data for dynamic optimization of the learning process and the multi-dimensional education effect evaluation reference data, student education effect evaluation and personalized learning plan optimization are performed to obtain comprehensive reference data for education effect evaluation.

[0037] An education effect evaluation system based on artificial intelligence provided by the present invention includes a multi-modal data preparation module, a dynamic cognitive modeling module, a multi-dimensional effect evaluation module, an adaptive result optimization module, and an education effect evaluation module;

[0038] The multi-modal data preparation module is used for multi-modal data preparation. Through multi-modal data preparation, multi-modal education effect evaluation and optimization data are obtained, and the multi-modal education effect evaluation and optimization data are sent to the dynamic cognitive modeling module;

[0039] The dynamic cognitive modeling module is used for dynamic cognitive modeling. Through dynamic cognitive modeling, cognitive process feature data are obtained, and the cognitive process feature data are sent to the multi-dimensional effect evaluation module and the adaptive result optimization module;

[0040] The multi-dimensional effect evaluation module is used for multi-dimensional effect evaluation. Through multi-dimensional effect evaluation, multi-dimensional education effect evaluation reference data are obtained, and the multi-dimensional education effect evaluation reference data are sent to the adaptive result optimization module and the education effect evaluation module;

[0041] The adaptive result optimization module is used for adaptive result optimization. Through adaptive result optimization, dynamic optimization reference learning plan data for the learning process are obtained, and the dynamic optimization reference learning plan data for the learning process are sent to the education effect evaluation module;

[0042] The education effect evaluation module is used for education effect evaluation. Through education effect evaluation, comprehensive reference data for education effect evaluation are obtained.

[0043] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0044] (1) Aiming at the technical problems existing in the existing education effect evaluation process, where many traditional evaluation methods only focus on a certain dimension (such as exam scores or classroom interaction) to evaluate students' learning effects, and the existing evaluation methods often only focus on students' short-term effects, ignoring the changes in long-term learning achievements and in-depth knowledge mastery. This scheme creatively adopts multi-modal data integrated analysis, combines the fusion method of generative adversarial network and time series model, and conducts comprehensive evaluation of immediate, long-term and transfer education effects, which can more comprehensively and meticulously evaluate students' performance at different learning stages and provide accurate evaluation results;

[0045] (2)Regarding the technical problem that in existing dynamic cognitive modeling methods, the existing cognitive modeling methods are difficult to adapt to the dynamic changes in students' cognitive structures and strategies during the learning process, and the degree of knowledge mastery of students during learning is constantly changing, and traditional models cannot reflect these changes in real time, this solution creatively adopts a method combining cognitive network analysis and improved dynamic Bayesian networks, uses dynamic Bayesian inference and reinforcement learning optimization, and accurately models the students' cognitive processes based on the students' learning history and real-time feedback. At the same time, the metacognitive adjustment module further improves the personalization and accuracy of the model through adaptive learning strategy optimization;

[0046] (3)Regarding the technical problem that in existing multi-dimensional effect evaluation methods, traditional evaluation dimensions often focus on one aspect (such as grades or participation), ignoring other key factors in the learning process, and existing evaluation methods also tend to be short-term immediate evaluations, making it difficult to effectively capture the students' knowledge accumulation, thinking transfer ability, and comprehensive inter-disciplinary qualities over a long period of time, resulting in a single evaluation dimension and an inability to comprehensively reflect the students' comprehensive learning abilities, this solution creatively adopts an innovative method combining a generative adversarial network and a transformer time series network, considers immediate feedback, long-cycle learning effects, and inter-disciplinary transfer ability during the evaluation process, ensures that the learning effects of students can be comprehensively evaluated from multiple dimensions, and provides more accurate evaluation results of educational effects;

[0047] (4)Regarding the technical problem that in existing adaptive result optimization methods, the existing optimization methods usually lack personalized learning content recommendations for students' individual differences, cannot provide accurate learning resources or strategies according to the students' cognitive processes, learning states, and behavioral characteristics, and traditional methods mostly only consider the learning processes of individual students while ignoring the potential of group learning characteristics, lacking personalized recommendations and consideration of group learning characteristics, this solution creatively adopts a hybrid recommendation improvement method combining group learning characteristic clustering, makes dynamic learning content and strategy recommendations for students, and provides a personalized and flexible dynamic optimization plan for the learning process by analyzing the students' cognitive process characteristics and group similarity data, realizing the continuous improvement and optimization of educational effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a schematic flow chart of an artificial intelligence-based educational effect evaluation method provided by the present invention;

[0049] Figure 2 It is a schematic diagram of an artificial intelligence-based educational effect evaluation system provided by the present invention;

[0050] Figure 3 It is a schematic flow chart of step S2 for dynamic cognitive modeling;

[0051] Figure 4 It is a schematic flowchart of the multi-dimensional effect evaluation in step S3;

[0052] Figure 5 It is a schematic flowchart of the adaptive result optimization in step S4.

[0053] The accompanying drawings are used to provide a further understanding of the present invention and form a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation to the present invention. Detailed implementation manners

[0054] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0055] In the description of the present invention, it should be understood that the terms "upper", "lower", "front", "rear", "left", "right", "top", "bottom", "inner", "outer", etc. indicating the orientation or positional relationship are based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention.

[0056] Embodiment 1, referring to Figure 1 , an education effect evaluation method based on artificial intelligence provided by the present invention includes the following steps:

[0057] Step S1: Preparation of multi-modal data;

[0058] Step S2: Dynamic cognitive modeling;

[0059] Step S3: Multi-dimensional effect evaluation;

[0060] Step S4: Adaptive result optimization;

[0061] Step S5: Education effect evaluation.

[0062] By performing the above operations, in view of the technical problem that in the existing educational effect evaluation process, many traditional evaluation methods only focus on a certain dimension (such as exam scores or classroom interaction) to evaluate students' learning effects, and the existing evaluation methods often only focus on students' short-term effects, ignoring the changes in long-term learning achievements and in-depth knowledge mastery, this solution creatively adopts multi-modal data integration analysis, combines the fusion method of generative adversarial network and time series model, conducts comprehensive evaluation of immediate, long-term and transfer educational effects, can more comprehensively and meticulously evaluate students' performance at different learning stages, and provides accurate evaluation results.

[0063] Example 2, refer to Figure 1 and Figure 2 In step S1, the multi-modal data preparation is used to collect students' learning process data. Specifically, through the collection of learning process data, the original data of students' learning process is collected, and through knowledge construction analysis and data optimization, the optimized data for multi-modal educational effect evaluation is obtained;

[0064] The original data of students' learning process specifically includes classroom interaction record data, homework and test data, classroom feedback data, student status evaluation data, classroom note data, and extracurricular learning situation data;

[0065] The classroom interaction record data is collected through manual recording, including the number of students' questions, students' answering situations, and classroom performance record data; the classroom performance record data includes the number of times of active speaking, the answering correct rate, and the artificial evaluation data of classroom concentration;

[0066] The homework and test data is collected through manual recording, including the completion situation of homework and the test score situation data;

[0067] The classroom feedback data is collected through students' questionnaire filling, including students' self-feedback data and students' emotional feedback data;

[0068] The student status evaluation data is collected through manual recording, including the artificial evaluation status data and the artificial evaluation of students' emotions data;

[0069] The classroom note data is collected through manual recording and questionnaire filling, including whether students take notes and whether there is classroom discussion data;

[0070] The extracurricular learning situation data is collected through questionnaire filling, including extracurricular learning record data and students' self-study record data

[0071] The knowledge construction analysis and data optimization specifically perform labeled analysis and data optimization on the original data of students' learning process to obtain knowledge construction analysis data;

[0072] The multi-modal education effect evaluation and optimization data specifically include optimized classroom interaction data, optimized student status data, and optimized learning process data.

[0073] Example 3. Refer to Figure 1 , Figure 2 and Figure 3 . Based on the above example, in step S2, the dynamic cognitive modeling is used to optimize the cognitive process of students through a dynamic modeling method. Specifically, according to the multi-modal education effect evaluation and optimization data, a dynamic Bayesian network improved by combining cognitive network analysis and cognitive ability modeling is adopted for dynamic cognitive modeling and prediction to obtain cognitive process characteristic data, including the following steps:

[0074] Step S21: Construct the original data input, specifically taking the multi-modal education effect evaluation and optimization data as the original data input sample;

[0075] Step S22: Cognitive network analysis, specifically using the standard cognitive network analysis method to construct knowledge nodes and learning relationship paths, and performing correlation analysis on the student's mastery of knowledge points based on the student's historical learning situation in the original data input sample to obtain knowledge point correlation reference data;

[0076] Step S23: Construct an improved dynamic Bayesian network, specifically constructing a standard dynamic Bayesian network and performing improved dynamic Bayesian inference with the knowledge point correlation reference data as the state variable to obtain a basic cognitive modeling model of the student's knowledge points;

[0077] The calculation formula for constructing a standard dynamic Bayesian network and performing improved dynamic Bayesian inference with the knowledge point correlation reference data as the state variable is:

[0078] ;

[0079] In the formula, P(c t |c t-1 ,X t ) as a whole is the cognitive state dynamic Bayesian inference probability, which is used to represent the student's cognitive degree of the current knowledge point. c t is the cognitive state variable, X t is the student's cognitive behavior data, which is used to represent the knowledge point correlation reference data. a is the normalization constant. P(c t |c t-1 ) as a whole is the cognitive state influence probability, which is used to represent the influence degree of the student's cognitive state of the knowledge point at time t-1 on the current time t. P(X t |c t)The whole is the probability of influencing students' cognitive behavior, which is used to represent the degree to which students' cognitive behavior is affected by cognitive state variables;

[0080] Step S24: Meta-cognitive adjustment, specifically, by constructing a student cognitive reward function, performing knowledge point cognitive adjustment based on reinforcement learning, and by constructing a meta-cognitive ability model, simulating students' adjustment of learning strategies, and through iterative training of reinforcement learning, obtaining a meta-cognitive corrected student dynamic cognitive modeling model;

[0081] Through the iterative training of reinforcement learning, an improved meta-cognitive correction factor is adopted to optimize the basic modeling model of the students' knowledge point cognition, obtaining a student knowledge point meta-cognitive adjustment model, and constructing the student cognitive reward function to perform reinforcement learning;

[0082] The calculation formula of the student knowledge point meta-cognitive adjustment model is:

[0083] ;

[0084] In the formula, The whole is the dynamic Bayesian inference probability of the cognitive state after the meta-cognitive adjustment of the students' knowledge points, is the meta-cognitive adjustment factor, which is used to represent the students' self-adjustment and feedback on the learning situation;

[0085] The student cognitive reward function is specifically composed of a weighted sum of a classroom interaction reward term, a homework and test reward term, a classroom feedback reward term, a learning state reward term, and an in-class and out-of-class learning reward term. The calculation formula is:

[0086] ;

[0087] In the formula, R(t) is the student cognitive reward function, w1 is the classroom interaction reward weight, R inter (t) is the classroom interaction reward sub-function, w2 is the homework and test reward weight, R test (t) is the homework and test reward sub-function, w3 is the classroom feedback reward weight, R febk (t) is the classroom feedback reward sub-function, w4 is the learning state reward weight, R notes (t) is the learning state reward sub-function, w5 is the in-class and out-of-class learning reward weight, R extra (t) is the in-class and out-of-class learning reward sub-function;

[0088] Table 1 is the composition table of the sub-reward functions of the student cognitive reward function. As shown in the table, the classroom interaction reward sub-function R interIn (t), a1 is the weight of the number of questions asked, Q(t) is the item of the number of questions asked by the student, a2 is the weight of the correct rate of the student's answers, P(t) is the item of the correct rate of the student's answers, a3 is the weight of the student's classroom concentration, and C(t) is the item of classroom concentration;

[0089] The sub - function of the assignment and quiz reward R test In (t), b1 is the weight of the assignment completion situation, A(t) is the item of the assignment completion situation, b2 is the weight of the test score situation, and S(t) is the item of the test score situation

[0090] The sub - function of the classroom feedback reward R febk In (t), c1 is the weight of the self - feedback score, F s (t) is the item of the self - feedback score, c2 is the weight of the emotional feedback score, F e (t) is the item of the emotional feedback score;

[0091] The sub - function of the learning state reward R notes In (t), d1 is the weight of whether the student takes notes, E N (t) is the item of whether the student takes notes, d2 is the weight of whether there is a classroom discussion, E D (t) is the item of whether there is a classroom discussion;

[0092] The sub - function of the in - class and out - of - class learning reward R extra In (t), e1 is the weight of the out - of - class learning duration, L ss (t) is the item of the out - of - class learning duration, e2 is the weight of the in - class self - study duration, L ex (t) is the item of the in - class self - study duration;

[0093] Table 1 Composition table of sub - reward functions of the student cognitive reward function

[0094]

[0095] Step S25: Dynamic cognitive modeling, specifically, through the construction of the original data input, the cognitive network analysis, the construction of the improved dynamic Bayesian network, and the metacognitive adjustment, dynamic cognitive modeling is carried out to obtain cognitive process characteristic data;

[0096] The cognitive process characteristic data specifically includes knowledge point mastery data, learning strategy behavior data, learning emotion state change data, learning process prediction and optimization data, and metacognitive data;

[0097] The metacognitive data is used to represent the student's ability to monitor, evaluate, and adjust their own learning process.

[0098] By performing the above operations, in view of the technical problem that in the existing dynamic cognitive modeling methods, the existing cognitive modeling methods are difficult to adapt to the dynamic changes in the cognitive structure and strategies of students during the learning process, and the knowledge mastery of students in learning is constantly changing, and the traditional models cannot reflect these changes in real time, this solution creatively adopts a method of combining cognitive network analysis and improved dynamic Bayesian network, uses dynamic Bayesian inference and reinforcement learning optimization, and accurately models the cognitive process of students based on the learning history and real-time feedback of students. At the same time, the metacognitive adjustment module further improves the personalization and accuracy of the model through adaptive learning strategy optimization.

[0099] Example 4, refer to Figure 1 、 Figure 2 and Figure 4 and

[0100] Step S31: Immediate education effect evaluation, specifically constructing a generative adversarial network with feedback reward improvement for immediate education effect generation and evaluation to obtain reference data for immediate education effect evaluation;

[0101] The feedback reward improvement is specifically designed by generating the learning progress data of students through the generator and calculating the decision probability expectation for feedback reward improvement;

[0102] The calculation formula for the feedback reward improvement design is:

[0103] ;

[0104] In the formula, R instant (t) is the feedback reward improvement function, used to calculate the decision probability expectation of the generated learning progress data. By maximizing the feedback reward improvement function, it is used as the optimization goal for immediate education effect evaluation. E real [·] is the decision probability expectation of being judged as true, E fake [·] is the decision probability expectation of being judged as false, x t is the actual learning progress data, is the generated predicted learning progress data, D real (·) is the decision probability of the discriminator for real data, D fake (·) is the decision probability of the discriminator for generated data;

[0105] Step S32: Long-term education effect evaluation. Specifically, a variable voltage time series network is used to model the long-term education effect evaluation, and through time series modeling, long-term education effect evaluation data is obtained;

[0106] The calculation formula for the long-term education effect evaluation is as follows:

[0107] ;

[0108] In the formula, R long (t) is the long-term learning reward function, which is used to calculate the learning gain over time t and serves as the optimization goal for the long-term education effect evaluation. T is the total time, t is the time index, is the non-linear transformation function, n is the total number of long-term education effect evaluation tasks, i is the long-term education effect evaluation task index, is the weight of the i-th education effect evaluation task, S test (·) is the long-term education effect evaluation function, which is used to represent the learning effect of students in long-term learning, The overall is the time decay factor, is the time decay coefficient;

[0109] Step S33: Transfer education effect evaluation. Specifically, by combining the results of the immediate education effect evaluation and transferring them to interdisciplinary content, an interdisciplinary transfer effect evaluation is carried out to obtain transfer education effect evaluation data;

[0110] The interdisciplinary transfer effect evaluation is combined with the feedback improvement of the immediate education effect evaluation for transfer and construction. The calculation formula is as follows:

[0111] ;

[0112] In the formula, R transfer (t) is the interdisciplinary transfer effect evaluation reward function, which is used to calculate the adversarial loss between the source domain and the target domain. By minimizing the feedback reward improvement function, it serves as the optimization goal for the interdisciplinary transfer effect evaluation reward function. E source [·] is the adversarial loss of the source domain, E target [·] is the target domain, X s is the source domain data, which is used to represent the original data before interdisciplinary transfer, is the target domain data, which is used to represent the data after source transfer, D source (·) is the source domain output, D target (·) is the target domain output;

[0113] Step S34: multidimensional effect evaluation model training, specifically, performing multidimensional effect evaluation model training through the instant education effect evaluation, the long-term education effect evaluation and the transfer education effect evaluation to obtain a multidimensional effect evaluation model;

[0114] Step S35: multidimensional effect evaluation, specifically, based on the cognitive process characteristic data, using the multidimensional effect evaluation model, to perform multidimensional effect evaluation to obtain multidimensional education effect evaluation reference data.

[0115] By performing the above operations, in view of the fact that in the existing multi-dimensional effect evaluation methods, traditional evaluation dimensions often focus on one aspect (such as grades or participation), ignoring other key factors in the learning process, and the existing evaluation methods are also biased towards short-term instant evaluation, which is difficult to effectively capture students' knowledge accumulation, thinking transfer ability and interdisciplinary comprehensive quality over a long period of time, resulting in a single evaluation dimension and the inability to fully reflect the technical problem of students' comprehensive learning ability. This solution creatively adopts an innovative method based on the combination of generative adversarial networks and transformer timing networks. In the evaluation process, instant feedback, long-term learning effects and interdisciplinary transfer capabilities are taken into account to ensure that students' learning effects can be comprehensively evaluated from multiple dimensions, providing more accurate education effect evaluation results.

[0116] Example 5, see Figure 1 , Figure 2 and Figure 5 This embodiment is based on the above embodiment. In step S4, the adaptive result optimization is used to dynamically optimize the learning process according to the evaluation results. Specifically, based on the cognitive process feature data and the multi-dimensional education effect evaluation reference data, a hybrid recommendation improvement method combined with group learning feature clustering is adopted to dynamically optimize the adaptive learning process to obtain reference learning plan data for dynamic optimization of the learning process, including the following steps:

[0117] Step S41: group learning feature clustering, specifically, using a clustering algorithm to calculate student similarity based on the cognitive process feature data and the multi-dimensional education effect evaluation reference data to obtain similarity clustering learning feature data;

[0118] The student similarity calculation specifically uses K-means clustering algorithm to perform similarity calculation;

[0119] Step S42: Recommending learning content, specifically, recommending learning content based on the student's cognitive process data and the similarity clustering learning feature data to obtain learning content recommendation data, and the calculation formula is:

[0120] ;

[0121] In the formula, is the learning content recommendation data, used to represent the scoring value for recommending learning content c to students where is the student index, c is the learning content index, K is the total number of similarity clustering learning features, k is the similarity clustering learning feature index, w k is the weight of the similarity clustering learning feature, and sim(·) is the similarity function. is the value of the student on the similarity clustering learning feature, and is the value of the learning content on the similarity clustering learning feature;

[0122] Step S43: Collaborative filtering recommendation, specifically, based on the multi-dimensional education effect evaluation reference data and the similarity clustering learning feature data, perform learning strategy recommendation within the student group to obtain the in-group recommendation data. The calculation formula is:

[0123] ;

[0124] In the formula, is the in-group recommendation data, used to represent the collaborative filtering score value for recommending learning content c to students where is the total number of neighboring students of student is the neighboring student index, is the historical reference score value of neighboring student for learning content c, and sim(·) is the similarity function. is the similarity between student and neighboring student ; and neighboring student

[0125] Step S44: Learning content recommendation integration, specifically, perform weighted integration on the learning content recommendation data and the in-group recommendation data to obtain the balanced learning content recommendation reference data. The calculation formula is:

[0126] ;

[0127] In the formula, R is the balanced learning content recommendation reference data, is the learning content recommendation weight, is the learning content recommendation data, is the in-group recommendation data;

[0128] Step S45: Adaptive result optimization, specifically, obtain the dynamic optimization reference learning plan data for the learning process by testing and adjusting the weights of the learning content recommendation integration.

[0129] ​By performing the above operations, in the existing adaptive result optimization methods, there are technical problems that the existing optimization methods usually lack learning content recommendations for individual student differences, cannot provide accurate learning resources or strategies according to the cognitive process, learning status and behavioral characteristics of students, and most traditional methods only consider the learning process of individual students while ignoring the potential of group learning characteristics, lacking personalized recommendations and consideration of group learning characteristics. This solution creatively adopts a hybrid recommendation improvement method combining group learning feature clustering to recommend dynamic learning content and strategies for students, and provides a personalized and flexible dynamic optimization plan for the learning process by analyzing the cognitive process characteristics and group similarity data of students, achieving continuous improvement and optimization of educational effects.

[0130] Example 6, refer to Figure 1 and Figure 2 In this example, based on the above example, in step S5, the educational effect evaluation is used to integrate the processes of cognitive modeling, effect evaluation and result optimization and conduct a comprehensive evaluation of educational effects. Specifically, by combining the dynamic optimization reference learning plan data of the learning process and the multi-dimensional educational effect evaluation reference data, the educational effect evaluation of students and the optimization of personalized learning plans are carried out to obtain comprehensive reference data for educational effect evaluation.

[0131] Example 7, refer to Figure 1 and Figure 2 In this example, based on the above example, an educational effect evaluation system based on artificial intelligence provided by the present invention includes a multi-modal data preparation module, a dynamic cognitive modeling module, a multi-dimensional effect evaluation module, an adaptive result optimization module and an educational effect evaluation module;

[0132] The multi-modal data preparation module is used for multi-modal data preparation. Through multi-modal data preparation, multi-modal educational effect evaluation and optimization data are obtained, and the multi-modal educational effect evaluation and optimization data are sent to the dynamic cognitive modeling module;

[0133] The dynamic cognitive modeling module is used for dynamic cognitive modeling. Through dynamic cognitive modeling, cognitive process characteristic data are obtained, and the cognitive process characteristic data are sent to the multi-dimensional effect evaluation module and the adaptive result optimization module;

[0134] The multi-dimensional effect evaluation module is used for multi-dimensional effect evaluation. Through multi-dimensional effect evaluation, multi-dimensional educational effect evaluation reference data are obtained, and the multi-dimensional educational effect evaluation reference data are sent to the adaptive result optimization module and the educational effect evaluation module;

[0135] The adaptive result optimization module is used for adaptive result optimization. Through adaptive result optimization, the dynamic optimization reference learning plan data for the learning process is obtained, and the dynamic optimization reference learning plan data for the learning process is sent to the education effect evaluation module;

[0136] The education effect evaluation module is used for education effect evaluation. Through education effect evaluation, the comprehensive reference data for education effect evaluation is obtained.

[0137] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device.

[0138] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention.

[0139] The above description of the present invention and its embodiments is not restrictive. What is shown in the drawings is only one of the embodiments of the present invention, and the actual structure is not limited thereto. All in all, if those of ordinary skill in the art are inspired by it and design similar structural modes and embodiments without creative efforts without departing from the purpose of the present invention, they should fall within the protection scope of the present invention.

Claims

1. An education effect evaluation method based on artificial intelligence, characterized in that: The method includes the following steps: Step S1: Multimodal data preparation to obtain optimized data for multimodal education effect evaluation; Step S2: Dynamic cognitive modeling. Use a dynamic Bayesian network improved by combining cognitive network analysis and cognitive ability modeling to perform dynamic cognitive modeling and prediction to obtain cognitive process characteristic data; The improved dynamic Bayesian network for cognitive modeling is specifically to construct a standard dynamic Bayesian network and perform improved dynamic Bayesian inference with the knowledge point correlation reference data as state variables to obtain a basic cognitive modeling model for students' knowledge points; For the dynamic cognitive modeling and prediction, adjust the knowledge point cognition based on reinforcement learning by constructing a student cognitive reward function. The student cognitive reward function is specifically composed of a weighted sum of a classroom interaction reward term, a homework and quiz reward term, a classroom feedback reward term, a learning state reward term, and an in-class and out-of-class learning reward term. The calculation formula is: R(t) = w1R inter (t) + w2R test (t) + w3R febk (t) + w4R notes (t) + w5R extra (t); where \(R(t)\) is the student cognitive reward function, \(w_1\) is the classroom interaction reward weight, \(R\) inter (t) is the classroom interaction reward sub - function, \(w_2\) is the homework and quiz reward weight, \(R\) test (t) is the homework and quiz reward sub - function, \(w_3\) is the classroom feedback reward weight, \(R\) febk (t) is the classroom feedback reward sub - function, \(w_4\) is the learning state reward weight, \(R\) notes (t) is the learning state reward sub - function, \(w_5\) is the in - class and out - of - class learning reward weight, \(R\) extra (t) is the in - class and out - of - class learning reward sub - function; Step S3: Multidimensional effect evaluation. Use a variable-pressure time-series network combined with generative adversarial transfer knowledge to perform three-dimensional education effect evaluation in terms of immediate, long-term, and transfer dimensions to obtain multidimensional education effect evaluation reference data, including the following steps: Step S31: Immediate education effect evaluation. Specifically, construct a generative adversarial network improved by feedback rewards to generate and evaluate the immediate education effect to obtain reference data for immediate education effect evaluation. The improvement of the feedback rewards is specifically to generate the learning progress data of students through the generator and perform feedback reward improvement design by calculating the expected value of the decision probability; Step S32: Long-term education effect evaluation. Specifically, use a variable-pressure time-series network to perform long-term education effect evaluation modeling and obtain long-term education effect evaluation data through time-series modeling; The calculation formula for the long-term education effect evaluation is: where, R long (t) is the long-term learning reward function, which is used to calculate the learning gain over time t and serves as the optimization goal for the long-term education effect evaluation. T is the total time, t is the time index, is the non-linear conversion function, n is the total number of long-term education effect evaluation tasks, i is the long-term education effect evaluation task index, α i is the weight of the i-th education effect evaluation task, S test (·) is the long-term education effect evaluation function, which is used to represent the learning effect of students in long-term learning. exp(-ρt) as a whole is the time decay factor, and ρ is the time decay coefficient; Step S33: Transfer education effect evaluation. Specifically, combine the results of the immediate education effect evaluation and transfer them to interdisciplinary content to perform interdisciplinary transfer effect evaluation to obtain transfer education effect evaluation data. Step S34: Multidimensional effect evaluation model training. Step S35: Multidimensional effect evaluation; Step S4: Adaptive result optimization. Use a hybrid recommendation improvement method combined with group learning feature clustering to perform dynamic optimization of the adaptive learning process to obtain reference learning plan data for dynamic optimization of the learning process; Step S5: Education effect evaluation to obtain comprehensive reference data for education effect evaluation.

2. The educational effect evaluation method based on artificial intelligence according to claim 1, characterized in that: In step S1, the multimodal data preparation is used to collect students' learning process data. Specifically, through the collection of learning process data, the original data of students' learning process is collected, and through knowledge construction analysis and data optimization, optimized data for multimodal education effect evaluation is obtained; The original data of students' learning process specifically includes classroom interaction record data, homework and quiz data, classroom feedback data, student status evaluation data, classroom note data, and out-of-class learning situation data; The optimized data for multimodal education effect evaluation specifically includes optimized classroom interaction data, optimized student status data, and optimized learning process data.

3. The educational effect evaluation method based on artificial intelligence according to claim 2, characterized in that: In step S2, the dynamic cognitive modeling is used to optimize the cognitive process of students through a dynamic modeling method. Specifically, based on the optimized data of multimodal education effect assessment, a dynamic Bayesian network improved by combining cognitive network analysis and cognitive ability modeling is adopted to perform dynamic cognitive modeling and prediction, and obtain cognitive process characteristic data, including the following steps: Step S21: Construct the original data input, specifically using the optimized data of multimodal education effect assessment as the original data input sample; Step S22: Cognitive network analysis, specifically using the standard cognitive network analysis method to construct knowledge nodes and learning relationship paths, and based on the historical learning situation of students in the original data input sample, conduct an association analysis of students' mastery of knowledge points to obtain reference data on knowledge point association degree; Step S23: Construct an improved dynamic Bayesian network, specifically constructing a standard dynamic Bayesian network and using the reference data on knowledge point association degree as state variables to perform improved dynamic Bayesian inference to obtain a basic modeling model for students' knowledge point cognition; Step S24: Meta-cognitive adjustment, specifically constructing a student cognitive reward function to perform knowledge point cognition adjustment based on reinforcement learning, constructing a meta-cognitive ability model to simulate students' adjustment of learning strategies, and through iterative training of reinforcement learning, obtaining a meta-cognitive corrected student dynamic cognitive modeling model; In the iterative training through reinforcement learning, an improved meta-cognitive correction factor is used to optimize the basic modeling model for students' knowledge point cognition, obtain a student knowledge point meta-cognitive adjustment model, construct the student cognitive reward function, and execute reinforcement learning; The student cognitive reward function is specifically composed of a weighted sum of a classroom interaction reward term, a homework and quiz reward term, a classroom feedback reward term, a learning state reward term, and an in-class and out-of-class learning reward term; Step S25: Dynamic cognitive modeling, specifically through the construction of the original data input, the cognitive network analysis, the construction of the improved dynamic Bayesian network, and the meta-cognitive adjustment, perform dynamic cognitive modeling to obtain cognitive process characteristic data.

4. The educational effect evaluation method based on artificial intelligence according to claim 3, characterized in that: In step S2, the cognitive process characteristic data specifically includes data on knowledge point mastery, learning strategy behavior data, learning emotion state change data, learning process prediction optimization data, and meta-cognitive data; the meta-cognitive data is used to represent students' ability to monitor, evaluate, and adjust their own learning processes.

5. The educational effect evaluation method based on artificial intelligence according to claim 4, characterized in that: In step S3, the multi-dimensional effect evaluation is used to evaluate the learning effect from multiple dimensions. Specifically, based on the cognitive process characteristic data, a variable-pressure time-series network combined with generative adversarial transfer knowledge is adopted to conduct three-dimensional education effect evaluations in real-time, long-term, and transfer dimensions, and obtain reference data on multi-dimensional education effect evaluation, including the following steps: Step S31: Real-time education effect evaluation, specifically constructing a generative adversarial network improved by feedback reward to generate and evaluate the real-time education effect, and obtaining reference data on real-time education effect evaluation; The feedback reward improvement is specifically achieved by generating the learning progress data of students through a generator and designing the feedback reward improvement by calculating the expected value of the judgment probability. The calculation formula for the improved design of the feedback reward is as follows: Ri nstant (t) = E real [logD real (x t )] + E fake [log D fake (x′ t )]; Wherein, R instant (t) is a feedback reward improvement function for calculating the expected probability of generating judgment of learning progress data. By maximizing the feedback reward improvement function, it is used as the optimization goal for immediate education effect evaluation. E real [·] is the expected probability of judgment being true. E fake [·] is the expected probability of judgment being false. x t is the actual learning progress data, and x′ t is the generated predicted learning progress data. D real (·) is the judgment probability of the discriminator for real data. D fake (·) is the judgment probability of the discriminator for generated data; Step S32: Long-term education effect evaluation. Specifically, a variable voltage timing network is used to model the long-term education effect evaluation, and through timing modeling, long-term education effect evaluation data is obtained. Step S33: Transfer education effect evaluation. Specifically, by combining the results of the immediate education effect evaluation and transferring them to interdisciplinary content, an interdisciplinary transfer effect evaluation is carried out to obtain transfer education effect evaluation data. The interdisciplinary transfer effect evaluation is combined with the feedback improvement of the immediate education effect evaluation for transfer and construction. The calculation formula is as follows: R transfer R(t) = -E source [log D source (X s )] - E target [log D target (X′ t )]; Wherein, R transfer (t) is an interdisciplinary transfer effect evaluation reward function, which is used to calculate the adversarial loss between the source domain and the target domain. By minimizing the feedback reward improvement function, as the optimization objective of the interdisciplinary transfer effect evaluation reward function, E source [·] is the adversarial loss of the source domain, E target [·] is the target domain, X s is the source domain data, which is used to represent the original data before interdisciplinary transfer, X′ t is the target domain data, which is used to represent the data after source transfer, D source (·) is the source domain output, D target (·) is the target domain output; Step S34: Multi-dimensional effect evaluation model training. Specifically, through the immediate education effect evaluation, the long-term education effect evaluation, and the transfer education effect evaluation, multi-dimensional effect evaluation model training is carried out to obtain a multi-dimensional effect evaluation model. Step S35: Multi-dimensional effect evaluation. Specifically, based on the cognitive process characteristic data, the multi-dimensional effect evaluation model is used to carry out multi-dimensional effect evaluation to obtain multi-dimensional education effect evaluation reference data.

6. The educational effect evaluation method based on artificial intelligence according to claim 5, wherein: In step S4, the adaptive result optimization is used to dynamically optimize the learning process according to the evaluation result. Specifically, based on the cognitive process characteristic data and the multi-dimensional education effect evaluation reference data, a hybrid recommendation improvement method combining group learning feature clustering is adopted to dynamically optimize the adaptive learning process, and dynamic optimization reference learning plan data for the learning process is obtained, including the following steps: Step S41: Group learning feature clustering. Specifically, through a clustering algorithm, student similarity calculation is carried out according to the cognitive process characteristic data and the multi-dimensional education effect evaluation reference data to obtain similarity clustering learning feature data. Step S42: Learning content recommendation. Specifically, based on the cognitive process data of students and the similarity clustering learning feature data, learning content recommendation is carried out to obtain learning content recommendation data. Step S43: Collaborative filtering recommendation. Specifically, based on the multi-dimensional education effect evaluation reference data and the similarity clustering learning feature data, learning strategy recommendation within the student group is carried out to obtain in-group recommendation data. Step S44: Integration of learning content recommendations. Specifically, the learning content recommendation data and the in-group recommendation data are weighted and integrated to obtain balanced learning content recommendation reference data. The calculation formula is: R = α · R content (i′, c) + (1 - α) · R collab (i′, c); Wherein, R is the reference data for recommending balanced learning content, α is the weight for recommending learning content, and R content (i′, c) is the learning content recommendation data, and R collab (i′, c) is the in-group recommendation data; Step S45: Adaptive result optimization. Specifically, by testing and adjusting the weights integrated in the learning content recommendation, dynamic optimization reference learning plan data for the learning process is obtained.

7. The educational effect evaluation method based on artificial intelligence according to claim 6, characterized in that: In step S5, the education effect evaluation is used to integrate the processes of cognitive modeling, effect evaluation, and result optimization and carry out comprehensive education effect evaluation. Specifically, by combining the dynamic optimization reference learning plan data for the learning process and the multi-dimensional education effect evaluation reference data, student education effect evaluation and personalized learning plan optimization are carried out to obtain comprehensive reference data for education effect evaluation.

8. An education effect evaluation system based on artificial intelligence, which is used to implement an education effect evaluation method based on artificial intelligence as described in any one of claims 1-7, and is characterized in that: It includes a multi-modal data preparation module, a dynamic cognitive modeling module, a multi-dimensional effect evaluation module, an adaptive result optimization module, and an education effect evaluation module. The multi-modal data preparation module is used for multi-modal data preparation. Through multi-modal data preparation, multi-modal education effect evaluation and optimization data is obtained, and the multi-modal education effect evaluation and optimization data is sent to the dynamic cognitive modeling module. The dynamic cognitive modeling module is used for dynamic cognitive modeling. Through dynamic cognitive modeling, characteristic data of the cognitive process is obtained, and the characteristic data of the cognitive process is sent to the multi-dimensional effect evaluation module and the adaptive result optimization module; The multi-dimensional effect evaluation module is used for multi-dimensional effect evaluation. Through multi-dimensional effect evaluation, reference data for multi-dimensional education effect evaluation is obtained, and the reference data for multi-dimensional education effect evaluation is sent to the adaptive result optimization module and the education effect evaluation module; The adaptive result optimization module is used for adaptive result optimization. Through adaptive result optimization, reference learning plan data for dynamic optimization of the learning process is obtained, and the reference learning plan data for dynamic optimization of the learning process is sent to the education effect evaluation module; The education effect evaluation module is used for education effect evaluation. Through education effect evaluation, comprehensive reference data for education effect evaluation is obtained.

Images