Personalized course teaching auxiliary management system based on AI

Abstract

The invention relates to the technical field of education, and particularly discloses an AI-based personalized course teaching auxiliary management system, and the system is characterized in that a personalized learning path selection module sets different teaching paths according to different teaching contents, and a student user can select different teaching paths for learning according to needs; the data acquisition module acquires learning data of each student user under different teaching paths, and the AI intelligent analysis module analyzes learning results of each student user under different teaching paths according to the learning data and makes a subsequent learning plan for each student according to the learning results. And meanwhile, the data acquisition module also acquires user parameters of each learning path, and the upgrading resource allocation module allocates upgrading resources to each teaching path according to the user parameters, so that the learning characteristics and requirements of each student can be accurately known, and the learning efficiency and learning experience of the student are greatly improved.

Description

Technical Field

[0001] The present invention relates to the field of educational technology, and specifically to a personalized course teaching assistant management system based on AI. Background Art

[0002] With the continuous advancement of educational informatization, the traditional teaching management mode has been difficult to meet the increasingly diverse learning needs of students.

[0003] The existing teaching assistant management systems only focus on simple teaching and examinations, with limited data processing capabilities. They are unable to comprehensively evaluate students' learning performance based on their learning situations, provide suggestions for students' subsequent learning and review of different learning contents according to the evaluation results, and at the same time, when the system upgrade resources are limited, upgrade different teaching paths of the system according to the learning situations of student users to ensure students' learning efficiency and learning experience. Summary of the Invention

[0004] The purpose of the present invention is to provide a personalized course teaching assistant management system based on AI to solve the above technical problems: The purpose of the present invention can be achieved through the following technical solutions: A personalized course teaching assistant management system based on AI, the system includes: a personalized learning path selection module, a data collection module, an AI intelligent analysis module, and an upgrade resource allocation module; The personalized teaching path selection module sets different teaching paths for different teaching contents, and is used for each student to select different teaching paths according to learning needs, and assign homework and tests to each student; The data collection module is used to collect multi-source data of each student during the learning process and simultaneously collect user parameters of each teaching path; The AI intelligent analysis module uses artificial intelligence algorithms to analyze the collected student learning data, and evaluates the learning achievements of students under each teaching path according to the analysis results; The upgrade resource allocation module uses artificial intelligence algorithms to analyze the collected user parameters of each teaching path, and allocates upgrade resources according to the analysis results.

[0005] As a further description of the solution of the present invention, the working process of the personalized teaching path selection module includes: Dividing the teaching content of the system into n teaching paths based on different teaching contents, and numbering each teaching path, the numbers are in sequence: 1, 2,..., n; The working process of the data collection module includes: Collect multi-source learning data of student users under different teaching paths, where the multi-source learning data includes live learning performance data, online learning performance data, and exam performance data; The live learning performance data includes attendance rate, the number of interactions per class, and the frequency of questions asked per class. The online learning performance data includes online learning duration, the completion rate of each online learning video, and the completion rate of each online learning video assignment. The exam performance data includes exam completion time and the score of each question.

[0006] As a further description of the solution of the present invention, the working process of the AI intelligent analysis module includes: Obtain the live learning performance data of student user A under the i-th teaching path. The live learning performance data includes: attendance rate , the number of interactions in the j-th class and the frequency of questions asked in the j-th class ; Construct a mathematical model of the live learning performance coefficient of student user A under the i-th teaching path based on the obtained live learning performance data of student user A under the i-th teaching path. The expression is: ; In the formula, is the minimum attendance rate required by the system under the i-th teaching path, m is the total number of live classes under the i-th teaching path, where j belongs to m, and are the weight coefficients corresponding to the number of interactions and the frequency of questions asked respectively, and are the standard number of interactions and the frequency of questions asked in the j-th class under the i-th teaching path preset by the system; Compare the live learning performance coefficient of student user A under the i-th teaching path with the threshold of the live learning performance coefficient set by the system under the i-th teaching path. If the live learning performance coefficient of student user A under the i-th teaching path is lower than the corresponding threshold set by the system, it means that the live learning performance of student user A under the i-th teaching path is unqualified.

[0007] As a further description of the solution of the present invention, the working process of the AI intelligent analysis module further includes: Obtain the online learning performance data of student user A under the i-th teaching path. The online learning performance data includes: Online learning duration , the completion rate of the x-th online learning video and the completion rate of the assignment of the x-th online learning video ; Construct a mathematical model of the online learning performance coefficient of student user A under the i-th teaching path based on the obtained online learning performance data of student user A under the i-th teaching path. The expression is: ; In the formula, is the minimum learning duration required by the system under the i-th teaching path, is the number of online learning videos under the i-th teaching path, where x belongs to y, and are the weight coefficients corresponding to the learning completeness and the homework completion rate respectively, and are the standard learning completeness and homework completion rate of the x-th online learning video under the i-th teaching path preset by the system; Compare the online learning performance coefficient of student user A under the i-th teaching path with the threshold of the online learning performance coefficient set by the system under the i-th teaching path. If the online learning performance coefficient of student user A under the i-th teaching path is lower than the corresponding threshold set by the system, it indicates that the online learning performance of student user A under the i-th teaching path is unqualified.

[0008] As a further description of the solution of the present invention, the working process of the AI intelligent analysis module further includes: Obtain the exam performance data of student user A under the i-th teaching path. The exam performance data includes: the exam completion time and the score of the p-th question ; Construct a mathematical model of the exam performance coefficient of student user A under the i-th teaching path based on the obtained exam performance data of student user A under the i-th teaching path. The expression is: ; In the formula, is the maximum exam duration required by the system under the i-th teaching path, is the number of questions in the exam under the i-th teaching path, where p belongs to q, is the set score of the p-th exam question under the i-th teaching path, is the weight coefficient of the p-th exam question under the i-th teaching path, The difficulty coefficient of the p-th exam question under the i-th teaching path; Compare the exam performance coefficient Compare with the threshold of the examination performance coefficient under the i-th teaching path set by the system. If the examination performance coefficient of student user A under the i-th teaching path is lower than the corresponding threshold set by the system, it indicates that the examination performance of student user A under the i-th teaching path is unqualified.

[0009] As a further description of the solution of the present invention, the working process of the AI intelligent analysis module further includes evaluating the overall performance of student user A under the i-th teaching path: Construct a mathematical model of the overall performance coefficient of student user A under the i-th teaching path, and the expression is: ; In the formula, , and respectively represent the weight coefficients corresponding to the live learning performance, online learning performance and examination performance, , and respectively represent the threshold of the live learning performance coefficient, the threshold of the online learning performance coefficient and the threshold of the examination performance coefficient under the i-th teaching path; Compare the overall performance coefficient of student user A under the i-th teaching path with different threshold intervals of the overall performance coefficient of the i-th teaching path set by the system. If belongs to the corresponding unqualified threshold interval, it indicates that student user A fails to learn the teaching content under the i-th teaching path. If belongs to the corresponding qualified threshold interval, it indicates that student user A passes the learning of the teaching content under the i-th teaching path. If belongs to the corresponding excellent threshold interval, it indicates that student user A is excellent in learning the teaching content under the i-th teaching path, and student user A formulates corresponding subsequent learning plans according to the corresponding learning results.

[0010] As a further description of the solution of the present invention, the working process of the upgraded resource allocation module includes: Obtain the user parameters of the h-th teaching path, and the user parameters include: the unqualified rate , the qualified rate and the excellent rate under the h-th teaching path, and construct a mathematical model of the upgrade coefficient of the h-th teaching path, and the expression is: ; Calculate the upgrade coefficients of n teaching paths in sequence, arrange them in descending order, and preferentially allocate the upgraded resources to the teaching paths with higher ranks.

[0011] As a further description of the solution of the present invention, the system further includes an interactive communication module for students to communicate with each other at any time during the learning process.

[0012] Advantages of the present invention: The personalized learning path selection module of the present invention sets different teaching paths for different teaching contents. Student users can select different teaching paths for learning according to their needs. The data collection module collects the learning data of each student user under different teaching paths. The AI intelligent analysis module analyzes the learning achievements of each student user under different teaching paths based on the learning data, and formulates subsequent learning plans for each student according to the learning achievements. At the same time, the data collection module also collects the user parameters of each learning path, and the upgraded resource allocation module performs upgraded resource allocation for each teaching path according to the user parameters, which can accurately understand the learning characteristics and needs of each student, and greatly improve the learning efficiency and learning experience of students. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The present invention will be further described below with reference to the accompanying drawings.

[0014] Figure 1 is a schematic structural diagram of the personalized course teaching auxiliary management system based on AI of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0015] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to 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 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 shall fall within the protection scope of the present invention.

[0016] Please refer to Figure 1 As shown, the present invention provides a personalized course teaching auxiliary management system based on AI, and the system includes: a personalized learning path selection module, a data collection module, an AI intelligent analysis module, and an upgraded resource allocation module; The personalized teaching path selection module sets different teaching paths for different teaching contents, and is used for each student to select different teaching paths according to learning needs, and assigns homework and tests to each student; The data collection module is used to collect multi-source data of each student during the learning process and simultaneously collect the user parameters of each teaching path; The AI intelligent analysis module uses artificial intelligence algorithms to analyze the collected student learning data and evaluate the learning achievements of students under each teaching path according to the analysis results; The upgrade resource allocation module uses artificial intelligence algorithms to analyze the user parameters of each teaching path collected and allocate upgrade resources according to the analysis results.

[0017] Through the above technical solution, the personalized learning path selection module of the present invention sets different teaching paths for different teaching contents. Student users can choose different teaching paths for learning according to their needs. The data collection module collects the learning data of each student user under different teaching paths. The AI intelligent analysis module analyzes the learning achievements of each student user under different teaching paths based on the learning data, and formulates subsequent learning plans for each student according to the learning achievements. At the same time, the data collection module also collects the user parameters of each learning path. The upgrade resource allocation module allocates upgrade resources to each teaching path according to the user parameters, can accurately understand the learning characteristics and needs of each student, and greatly improves the learning efficiency and learning experience of students.

[0018] As a further description of the solution of the present invention, the working process of the personalized teaching path selection module includes: Divide the teaching content of the system into n teaching paths based on different teaching contents, and number each teaching path. The numbers are in turn: 1, 2,..., n; The working process of the data collection module includes: Collect multi-source learning data of student users under different teaching paths. The multi-source learning data includes live learning performance data, online learning performance data, and exam performance data; The live learning performance data includes attendance rate, the number of classroom interactions per class, and the frequency of questions asked per class. The online learning performance data includes online learning duration, the completion rate of each online learning video, and the completion rate of each online learning video assignment. The exam performance data includes exam completion time and the score of each question.

[0019] As a further description of the solution of the present invention, the working process of the AI intelligent analysis module includes: Obtain the live learning performance data of student user A under the i-th teaching path. The live learning performance data includes: attendance rate , the number of classroom interactions in the j-th class and the frequency of questions asked in the j-th class ; Construct a mathematical model of the live learning performance coefficient of student user A under the i-th teaching path according to the obtained live learning performance data of student user A under the i-th teaching path. The expression is: ; In the formula, The minimum attendance rate under the i-th teaching path required by the system, where m is the total number of live classes under the i-th teaching path, and j belongs to m. and are the weight coefficients corresponding to the number of classroom interactions and the frequency of classroom questions respectively. and are the standard number of interactions and the frequency of questions in the j-th class under the i-th teaching path preset by the system. Compare the live learning performance coefficient of student user A under the i-th teaching path with the threshold of the live learning performance coefficient under the i-th teaching path set by the system. If the live learning performance coefficient of student user A under the i-th teaching path is lower than the corresponding threshold set by the system, it means that the live learning performance of student user A under the i-th teaching path is unqualified.

[0020] Through the above technical solution, this embodiment provides an evaluation method for live learning performance, obtaining the attendance rate of student user A under the i-th teaching path, the number of interactions in the j-th class and the frequency of questions in the j-th class , calculating the live learning performance coefficient through the formula . represents the ratio of the actual attendance rate to the minimum attendance rate, which is proportional to the live learning performance coefficient. represents the ratio of the actual number of interactions to the standard number of interactions. represents the ratio of the actual question frequency to the standard question frequency, which is proportional to the live learning performance coefficient. Finally, compare the live learning performance coefficient of student user A under the i-th teaching path with the threshold of the live learning performance coefficient under the i-th teaching path set by the system. If the live learning performance coefficient of student user A under the i-th teaching path is lower than the corresponding threshold set by the system, it means that the live learning performance of student user A under the i-th teaching path is unqualified.

[0021] It should be noted that the minimum attendance rate, the standard number of interactions, and the standard question frequency are all empirical data obtained based on the historical data of student users with qualified live learning performance.

[0022] As a further description of the solution of the present invention, the working process of the AI intelligent analysis module further includes: Obtain the online learning performance data of student user A under the i-th teaching path, and the online learning performance data includes: Online learning duration , the learning completeness of the x-th online learning video and the completion rate of the x-th online learning video assignment ; Construct a mathematical model of the online learning performance coefficient of student user A under the i-th teaching path based on the obtained online learning performance data of student user A under the i-th teaching path. The expression is: ; In the formula, is the minimum learning duration required by the system under the i-th teaching path, is the number of online learning videos in the i-th teaching path. Among them, x belongs to y, and are the weight coefficients corresponding to the learning completion rate and the assignment completion rate respectively, and are the standard learning completion rate and assignment completion rate of the x-th online learning video under the i-th teaching path preset by the system; Compare the online learning performance coefficient of student user A under the i-th teaching path with the threshold of the online learning performance coefficient set by the system under the i-th teaching path. If the online learning performance coefficient of student user A under the i-th teaching path is lower than the corresponding threshold set by the system, it means that the online learning performance of student user A under the i-th teaching path is unqualified.

[0023] Through the above technical solution, this embodiment provides an evaluation method for online learning performance, which obtains the online learning duration of student user A, the learning completion rate of the x-th online learning video, and the completion rate of the x-th online learning video assignment, calculate the live learning performance coefficient through the formula. represents the ratio of the actual learning duration to the minimum learning duration and is proportional to the online learning performance coefficient. represents the ratio of the actual learning completion rate to the standard learning completion rate. represents the ratio of the actual learning video assignment completion rate to the standard learning video assignment completion rate and is proportional to the live learning performance coefficient. Finally, compare the online learning performance coefficient of student user A under the i-th teaching path with the threshold of the online learning performance coefficient set by the system under the i-th teaching path. If the online learning performance coefficient of student user A under the i-th teaching path is lower than the corresponding threshold set by the system, it means that the online learning performance of student user A under the i-th teaching path is unqualified.

[0024] It should be noted that the minimum learning duration, the standard learning completion rate, and the standard homework completion rate are all empirical data obtained based on the historical data of student users who have passed the live learning performance assessment.

[0025] As a further description of the solution of the present invention, the working process of the AI intelligent analysis module further includes: Obtain the exam performance data of student user A under the i-th teaching path. The exam performance data includes: the exam completion time and the score of the p-th question ; Construct a mathematical model of the exam performance coefficient of student user A under the i-th teaching path according to the obtained exam performance data of student user A under the i-th teaching path. The expression is: ; In the formula, is the maximum exam duration required by the system under the i-th teaching path, is the number of questions in the exam under the i-th teaching path, where p belongs to q, is the set score of the p-th exam question under the i-th teaching path, is the weight coefficient of the p-th exam question under the i-th teaching path, the difficulty coefficient of the p-th exam question under the i-th teaching path; Compare the exam performance coefficient of student user A under the i-th teaching path with the threshold of the exam performance coefficient set by the system. If the exam performance coefficient of student user A under the i-th teaching path is lower than the corresponding threshold set by the system, it indicates that the exam performance of student user A under the i-th teaching path is unqualified.

[0026] Through the above technical solution, this embodiment provides a method for evaluating exam performance, which obtains the exam performance data of student user A under the i-th teaching path. The exam performance data includes: the exam completion time and the score of the p-th question , calculates the live learning performance coefficient through the formula , represents the ratio of the actual exam duration to the maximum exam duration, which is inversely proportional to the exam performance coefficient, represents the ratio of the actual score to the set score, which is directly proportional to the live learning performance coefficient. Finally, compare the exam performance coefficient of student user A under the i-th teaching path with the threshold of the exam performance coefficient set by the system. If the exam performance coefficient If it is lower than the corresponding threshold set by the system, it indicates that the exam performance of student user A under the i-th teaching path is unqualified.

[0027] It should be noted that the maximum exam duration and the set score are both system-set data and are related to the actual difficulty of the exam paper.

[0028] As a further description of the solution of the present invention, the working process of the AI intelligent analysis module further includes evaluating the overall performance of student user A under the i-th teaching path: Construct a mathematical model of the overall performance coefficient of student user A under the i-th teaching path, and the expression is: ; In the formula, , and respectively represent the weight coefficients corresponding to the live learning performance, online learning performance, and exam performance, , and respectively represent the threshold values of the live learning performance coefficient, online learning performance coefficient, and exam performance coefficient under the i-th teaching path; Compare the overall performance coefficient of student user A under the i-th teaching path with different threshold intervals of the overall performance coefficient set by the system for the i-th teaching path. If belongs to the corresponding unqualified threshold interval, it indicates that student user A fails to learn the teaching content under the i-th teaching path. If belongs to the corresponding qualified threshold interval, it indicates that student user A passes the learning of the teaching content under the i-th teaching path. If belongs to the corresponding excellent threshold interval, it indicates that student user A excels in learning the teaching content under the i-th teaching path, and student user A formulates corresponding subsequent learning plans according to the corresponding learning results.

[0029] Through the above technical solution, the present invention provides a method for formulating corresponding subsequent learning plans. First, calculate the overall performance coefficient through the formula , compare the live learning performance, online learning performance, and exam performance with the set threshold values respectively, and then obtain the overall performance coefficient by weighted summation. Compare the overall performance coefficient of student user A under the i-th teaching path with different threshold intervals of the overall performance coefficient set by the system for the i-th teaching path. If belongs to the corresponding unqualified threshold interval, it indicates that student user A fails to learn the teaching content under the i-th teaching path, and the learning cycle of the i-th teaching path needs to be increased in subsequent learning. If If it belongs to the corresponding qualified threshold range, it indicates that the student user A has passed the learning of the teaching content under the i-th teaching path, and the learning cycle of the i-th teaching path can be maintained in subsequent learning. If it belongs to the corresponding excellent threshold range, it indicates that the student user A has excelled in the learning of the teaching content under the i-th teaching path, and the learning cycle of the i-th teaching path can be reduced in subsequent learning. Moreover, during the subsequent learning process, corresponding adjustments can be made based on the live learning performance, online learning performance, and combined with the exam performance.

[0030] It should be noted that > > and 、 and are empirical data.

[0031] As a further description of the solution of the present invention, the working process of the upgrade resource allocation module includes: Obtain the user parameters of the h-th teaching path, and the user parameters include: the unqualified rate 、qualified rate and excellent rate under the h-th teaching path, and construct a mathematical model for the upgrade coefficient of the h-th teaching path, and the expression is: ; Calculate the upgrade coefficients of the n teaching paths in sequence, and arrange them in descending order, and preferentially allocate the upgrade resources to the teaching paths with higher order.

[0032] Through the above technical solution, this embodiment provides a solution for upgrade resource allocation, obtains the unqualified rate 、qualified rate and excellent rate under the h-th teaching path, and then based on the formula obtain the upgrade coefficient of the h-th teaching path, which is proportional to and inversely proportional to . Calculate the upgrade coefficients of the n teaching paths in sequence, and arrange them in descending order, and preferentially allocate the upgrade resources to the teaching paths with higher order.

[0033] As a further description of the solution of the present invention, the system further includes an interactive communication module for students to communicate with each other at any time during the learning process.

[0034] It should be noted that the calculations in the present invention are all simple numerical calculations, which have been dimensionless processed, and the standard data, threshold ranges, and weight coefficients set in the present invention are all empirical data and will not be elaborated.

[0035] The above has described in detail an embodiment of the present invention, but the above content is only a preferred embodiment of the present invention and cannot be considered as limiting the scope of implementation of the present invention. All equivalent changes and improvements made according to the scope of the application of the present invention shall still fall within the scope covered by the patent of the present invention.

Claims

1. An AI-based personalized curriculum teaching assistance management system, characterized in that The system includes: a personalized learning path selection module, a data collection module, an AI intelligent analysis module, and an upgraded resource allocation module; The personalized teaching path selection module sets different teaching paths for different teaching contents, and is used for each student to select different teaching paths according to learning needs, and assign homework and conduct tests for each student; The data collection module is used to collect multi-source data of each student during the learning process and simultaneously collect user parameters of each teaching path; The AI intelligent analysis module uses artificial intelligence algorithms to analyze the collected student learning data, and evaluates the learning achievements of students under each teaching path according to the analysis results; The upgraded resource allocation module uses artificial intelligence algorithms to analyze the user parameters of each teaching path collected, and allocates upgraded resources according to the analysis results.

2. The personalized curriculum teaching assistance management system based on AI according to claim 1, characterized in that, The working process of the personalized teaching path selection module includes: Dividing the teaching contents of the system into n teaching paths based on different teaching contents, and numbering each teaching path, and the numbers are in sequence: 1, 2,..., n; The working process of the data collection module includes: Collecting multi-source learning data of student users under different teaching paths, and the multi-source learning data includes live learning performance data, online learning performance data, and exam performance data; The live learning performance data includes attendance rate, the number of classroom interactions per class, and the frequency of questions asked per class. The online learning performance data includes online learning duration, the completion rate of each online learning video, and the completion rate of each online learning video assignment. The exam performance data includes exam completion time and the score of each question.

3. The personalized curriculum teaching assistance management system based on AI according to claim 2, wherein, The working process of the AI intelligent analysis module includes: Obtain the live learning performance data of student user A under the i-th teaching path, where the live learning performance data includes: attendance rate , the number of classroom interactions in the j-th class and the classroom question-asking frequency in the j-th class ; Constructing a live learning performance coefficient mathematical model of student user A under the i-th teaching path according to the obtained live learning performance data of student user A under the i-th teaching path, and the expression is: ; Wherein, is the minimum attendance rate under the i-th teaching path required by the system, m is the total number of live classes under the i-th teaching path, where j belongs to m, and are the weight coefficients corresponding to the number of classroom interactions and the frequency of classroom questions respectively, and are the standard number of classroom interactions and the question frequency of the j-th class under the i-th teaching path preset by the system; Compare the live learning performance coefficient of student user A under the i-th teaching path with the threshold of the live learning performance coefficient under the i-th teaching path set by the system. If the live learning performance coefficient of student user A under the i-th teaching path is lower than the corresponding threshold set by the system, it indicates that the live learning performance of student user A under the i-th teaching path is unqualified.

4. The personalized curriculum teaching assistance management system based on AI according to claim 3, characterized in that The working process of the AI intelligent analysis module also includes: Obtaining the online learning performance data of student user A under the i-th teaching path, and the online learning performance data includes: Online learning duration 、Degree of completion of learning the x-th online learning video and Degree of completion of the assignment of the x-th online learning video ; Constructing an online learning performance coefficient mathematical model of student user A under the i-th teaching path according to the obtained online learning performance data of student user A under the i-th teaching path, and the expression is: ; Wherein, is the minimum learning duration under the i-th teaching path required by the system, is the number of online learning videos under the i-th teaching path. Among them, x belongs to y, and are the weight coefficients corresponding to the learning completeness and the homework completion degree respectively, and are the standard learning completeness and homework completion degree of the x-th online learning video under the i-th teaching path preset by the system; Compare the online learning performance coefficient of student user A under the i-th teaching path with the threshold of the online learning performance coefficient under the i-th teaching path set by the system. If the online learning performance coefficient of student user A under the i-th teaching path is lower than the corresponding threshold set by the system, it indicates that the online learning performance of student user A under the i-th teaching path is unqualified.

5. An AI-based personalized curriculum teaching assistance management system according to claim 4, characterized in that, The working process of the AI intelligent analysis module also includes: Obtain the exam performance data of student user A under the i-th teaching path, where the exam performance data includes: exam completion time and the score of the p-th question ; Constructing an exam performance coefficient mathematical model of student user A under the i-th teaching path according to the obtained exam performance data of student user A under the i-th teaching path, and the expression is: ; Wherein, is the maximum exam duration under the i-th teaching path required by the system, is the number of exam questions under the i-th teaching path, where p belongs to q, is the set score of the p-th exam question under the i-th teaching path, is the weight coefficient of the p-th exam question under the i-th teaching path, the difficulty coefficient of the p-th exam question under the i-th teaching path; Compare the exam performance coefficient of student user A under the i-th teaching path with the threshold of the exam performance coefficient under the i-th teaching path set by the system. If the exam performance coefficient of student user A under the i-th teaching path is lower than the corresponding threshold set by the system, it indicates that the exam performance of student user A under the i-th teaching path is unqualified.

6. The personalized curriculum teaching assistance management system based on AI according to claim 5, characterized in that, The working process of the AI intelligent analysis module also includes evaluating the overall performance of student user A under the i-th teaching path: Constructing an overall performance coefficient mathematical model of student user A under the i-th teaching path, and the expression is: ； Wherein, , and respectively represent the weight coefficients corresponding to the live learning performance, online learning performance, and exam performance, , and respectively represent the threshold values of the live learning performance coefficient, online learning performance coefficient, and exam performance coefficient under the i-th teaching path; Compare the overall performance coefficient of student user A under the i-th teaching path with different threshold intervals of the overall performance coefficient set by the system under the i-th teaching path. If belongs to the corresponding unqualified threshold interval, it indicates that student user A fails to learn the teaching content under the i-th teaching path. If belongs to the corresponding qualified threshold interval, it indicates that student user A passes the learning of the teaching content under the i-th teaching path. If belongs to the corresponding excellent threshold interval, it indicates that student user A excels in learning the teaching content under the i-th teaching path. Student user A formulates corresponding subsequent learning plans according to the corresponding learning outcomes.

7. The personalized curriculum teaching assistance management system based on AI according to claim 2, characterized in that, The working process of the upgraded resource allocation module includes: Obtain the user parameters of the h-th teaching path, where the user parameters include: the unqualified rate, the qualified rate, and the excellent rate under the h-th teaching path, and construct a mathematical model for the upgrade coefficient of the h-th teaching path, with the expression: and the qualified rate and the excellent rate , and construct a mathematical model for the upgrade coefficient of the h-th teaching path, with the expression: ； Calculating the upgrade coefficients of n teaching paths in sequence, arranging them in descending order, and preferentially allocating upgraded resources to the teaching paths with higher rankings.

8. An AI-based personalized curriculum teaching assistance management system according to claim 2, characterized in that The system also includes an interactive communication module, which is used for students to communicate with each other at any time during the learning process.

Images