Self-adaptive education system based on artificial intelligence

Abstract

The invention, which relates to the technical field of the adaptive education system, discloses an artificial intelligence-based adaptive education system comprising a data collection module, a path generation module, a recommendation module, a monitoring feedback module, an adjustment module and an optimization module. The data collection module is used for collecting learning behaviors, hobbies and interests and score performance information of students by adopting a multi-modal data fusion technology to obtain student learning data; the path generation module is used for processing the obtained student learning data by adopting a machine learning algorithm and dynamically generating a personalized learning path; the recommendation module is used for recognizing demands and preferences of students by utilizing collaborative filtering, sentiment analysis and natural language processing technologies according to the personalized learning path and the current learning state so as to obtain optimal learning resources; and the monitoring feedback module is used for collecting the use condition of the optimal learning resource and generating an evaluation result by establishing an evaluation model.

Description

Technical Field

[0001] The present invention relates to the technical field of adaptive education systems, and in particular, to an adaptive education system based on artificial intelligence. Background Art

[0002] An adaptive education system is an education system that uses artificial intelligence technology to dynamically adjust teaching content, methods, and resources to meet the unique learning needs of each student. Its core goal is to improve students' learning efficiency and satisfaction and promote their all-round development through personalized learning paths, accurate resource recommendations, and real-time feedback mechanisms.

[0003] In the field of adaptive education systems, existing education systems usually rely only on a single type of data to evaluate students' learning status, ignoring multi-dimensional information such as learning behaviors and hobbies, resulting in an inability to comprehensively understand students' actual learning status and needs, making it difficult to develop personalized education programs. Moreover, existing learning resource recommendation systems are usually based on simple rules or user ratings, failing to fully consider students' personalized needs and preferences, reducing learning enthusiasm and efficiency. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an adaptive education system based on artificial intelligence to solve the problem that existing education systems usually rely only on a single type of data to evaluate students' learning status, ignoring multi-dimensional information such as learning behaviors and hobbies, resulting in an inability to comprehensively understand students' actual learning status and needs, making it difficult to develop personalized education programs.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides an adaptive education system based on artificial intelligence, which includes:

[0008] A data collection module, a path generation module, a recommendation module, a monitoring and feedback module, an adjustment module, and an optimization module;

[0009] The data collection module is used to collect students' learning behavior, hobbies, and performance information by using multi-modal data fusion technology to obtain students' learning data;

[0010] The path generation module is used to process the obtained students' learning data by using machine learning algorithms and dynamically generate personalized learning paths;

[0011] The recommendation module is used to identify the needs and preferences of students based on the personalized learning path and the current learning status, and utilize collaborative filtering, sentiment analysis, and natural language processing technologies to obtain the optimal learning resources;

[0012] The monitoring and feedback module is used to collect the usage situation of the optimal learning resources, generate an evaluation result by establishing an evaluation model, and adjust the learning plan based on the evaluation result to obtain an adjusted plan;

[0013] The adjustment module is used to adjust the teaching strategy according to the adjusted plan to obtain a learning report;

[0014] The optimization module is used to obtain the student performance data from the learning report and update the learning path using an evolutionary algorithm to obtain the final personalized learning path.

[0015] As a preferred solution of the artificial intelligence-based adaptive education system of the present invention, wherein: the multi-modal data fusion technology is adopted to collect the learning behavior, hobbies, and academic performance information of students to obtain student learning data, and the specific steps are as follows:

[0016] Adopt a multi-modal data processing method based on weighted feature fusion to extract key features from multiple data sources;

[0017] The multiple data sources include learning behavior data, hobby data, and academic performance data;

[0018] The key features include the homework completion situation, class participation, and online learning duration in the learning behavior data, the interaction records in the learning platform in the hobby data, and the exam scores and test results in the academic performance data;

[0019] Integrate the multiple data sources into a unified student learning data S.

[0020] As a preferred solution of the artificial intelligence-based adaptive education system of the present invention, wherein: the machine learning algorithm is adopted to process the obtained student learning data and dynamically generate a personalized learning path, and the specific steps are as follows:

[0021] According to the student learning data S, calculate the scores of the student in each dimension;

[0022] Let S B 、S I and S P respectively represent the learning behavior score, hobby index, and academic performance value of the student;

[0023] Construct a student portrait PprofilePprofile, and the portrait synthesizes the multi-faceted information of the student;

[0024] Based on student profile P profile , combined with the curriculum outline and teaching objectives, set short-term and long-term learning goals G;

[0025] Use the Dijkstra algorithm to generate the optimal learning path L according to the current student knowledge state and short-term and long-term learning goals G;

[0026] During the learning process, continuously monitor the student's performance and adjust the learning path according to the feedback;

[0027] Through continuous iterative optimization, generate the final personalized learning path.

[0028] As a preferred solution of the artificial intelligence-based adaptive education system described in the present invention, wherein: according to the personalized learning path and the current learning state, using collaborative filtering, sentiment analysis and natural language processing technologies to identify the needs and preferences of students, and obtain the optimal learning resources, the specific steps are as follows:

[0029] Based on the behavioral similarity in the student learning data, use the collaborative filtering algorithm to predict the learning resources that the student is interested in, and obtain the interest score R CF ;

[0030] Perform sentiment analysis on the text generated by the student during the learning process to obtain the sentiment analysis result S SA ;

[0031] Use NLP technology to parse the student's queries, comments and feedback, understand the student's real needs, and obtain the analysis result N NLP ;

[0032] According to the results of collaborative filtering, sentiment analysis and NLP, combined with the personalized learning path L final , screen out the learning resources that best meet the needs and preferences of students from the database, and mark them as the resource collection R selected ;

[0033] Based on the quality, applicability and historical evaluation factors of the learning resources, optimize and sort the selected learning resources R selected to obtain the sorted resource list R optimal ;

[0034] Based on the sorted resource list R optimal , generate a personalized learning resource recommendation list R for this student l .

[0035] As a preferred solution of the artificial intelligence-based adaptive education system described in the present invention, wherein: collect the usage of the optimal learning resources, generate an evaluation result through the establishment of an evaluation model, and adjust the learning plan based on the evaluation result to obtain an adjusted plan, the specific steps are as follows:

[0036] Track and record the usage of the recommended learning resource R l by students to obtain a dataset on the usage of learning resources;

[0037] Based on the dataset D of the usage of learning resources usage construct an evaluation model to quantify the utilization effect of learning resources by students and obtain an evaluation score E;

[0038] Based on the evaluation score, calculate a specific evaluation value e i ;

[0039] According to the evaluation result e i adjust the original personalized learning path L final .

[0040] As a preferred solution of the artificial intelligence-based adaptive education system described in the present invention, wherein: the adjustment of the original personalized learning path L final is carried out according to the following specific steps:

[0041] According to the evaluation result e i decide how to modify the learning plan and define an adjustment strategy;

[0042] When the effect of a certain resource is not good, replace or remove the resource;

[0043] When it is found that a student lacks knowledge in a certain aspect, add corresponding supplementary materials;

[0044] After implementing the adjustment strategy, obtain an adjusted learning plan L adjusted ;

[0045] Feed the adjusted learning plan L adjusted back to the students and teachers.

[0046] As a preferred solution of the artificial intelligence-based adaptive education system described in the present invention, wherein: according to the adjustment plan, adjust the teaching strategy to obtain a learning report, and the specific steps are as follows:

[0047] Check the learning progress, understanding level of students and their reactions to different teaching methods, and analyze whether the current teaching strategy is effective;

[0048] According to the analysis result, adjust the teaching strategy to better meet the personalized needs of students;

[0049] When it is found that a student has a low mastery level of a certain knowledge point, increase interactive teaching and obtain an adjusted teaching strategy;

[0050] Based on the adjusted teaching strategy T new, reallocate learning resource R allocated ;

[0051] Generate a learning report based on the above information;

[0052] The learning report includes an overview of learning progress, an assessment of knowledge mastery, improvement suggestions, and future learning plans.

[0053] As a preferred solution of the artificial intelligence-based adaptive education system described in the present invention, wherein: obtaining student performance data from the learning report and using an evolutionary algorithm to update the learning path to obtain the final personalized learning path, the specific steps are as follows:

[0054] Extract key student performance data from the learning report.

[0055] The student performance data includes knowledge point mastery, learning progress, assessment scores, and teacher feedback;

[0056] According to the adjusted learning plan L adjusted and student performance data D pf , initialize the population P0, each individual represents a learning path plan, and use the evolutionary algorithm EA to optimize the learning path;

[0057] Define a fitness function F to evaluate the effect of each learning path;

[0058] According to the results of the fitness function F, perform selection, crossover, and mutation operations on the individuals in the population P0 to generate a new generation of population P t+1 ;

[0059] When the maximum number of iterations is reached , select the individual with the highest fitness from the final population as the final personalized learning path

[0060] In a second aspect, the present invention provides a computer device, including a memory and a processor, where the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the artificial intelligence-based adaptive education system described in the first aspect of the present invention.

[0061] In a third aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, wherein: when the computer program is executed by the processor, it implements any step of the artificial intelligence-based adaptive education system described in the first aspect of the present invention.

[0062] The beneficial effects of the present invention are as follows: By adopting a multimodal data processing method based on weighted feature fusion to collect students' learning behaviors, hobbies, and academic performance information, the construction of a comprehensive learning portrait of students is realized. It can not only more accurately reflect the actual learning status of students, but also identify the advantages and disadvantages of students in different dimensions, thus providing a solid foundation for the design of subsequent personalized education paths. By calculating the scores of students in each dimension and dynamically generating personalized learning paths, the setting and optimization of students' short-term and long-term learning goals are realized, ensuring that each student has a tailor-made learning path that not only conforms to their current knowledge state but also stimulates their learning interest. By using collaborative filtering, sentiment analysis, and natural language processing technologies to identify students' needs and preferences, the optimal learning resources are obtained, which not only improves the relevance and attractiveness of the recommended resources but also ensures that the provided learning materials are most suitable for the students' current level and interests, helping to enhance students' learning motivation, promote their active participation in learning activities, and effectively improve learning effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0064] Figure 1 It is a flowchart of an adaptive education system based on artificial intelligence in Embodiment 1.

[0065] Figure 2 It is a flowchart of students' learning data in Embodiment 1.

[0066] Figure 3 It is a flowchart of a learning report in Embodiment 1. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0067] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will make a detailed description of the specific embodiments of the present invention in conjunction with the drawings of the specification.

[0068] In the following description, many specific details are set forth to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar generalizations without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0069] Second, the "one embodiment" or "embodiment" referred to herein means a specific feature, structure, or characteristic that may be included in at least one implementation manner of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or alternative embodiments that are mutually exclusive with other embodiments.

[0070] Embodiment 1, referring to Figure 1 , Figure 2 and Figure 3 , is the first embodiment of the present invention, which provides an artificial intelligence-based adaptive education system, including:

[0071] A data collection module, a path generation module, a recommendation module, a monitoring and feedback module, an adjustment module, and an optimization module;

[0072] The data collection module is used to collect students' learning behaviors, hobbies, and performance information by using multi-modal data fusion technology to obtain students' learning data;

[0073] Adopt a multi-modal data processing method based on weighted feature fusion to extract key features from multiple data sources;

[0074] The multiple data sources include learning behavior data, hobby data, and performance data;

[0075] The key features include the completion of homework, classroom participation, and online learning duration in learning behavior data, interaction records in the learning platform in hobby data, and exam scores and test results in performance data;

[0076] Integrate multiple data sources into a unified student learning data S, and the expression is:

[0077]

[0078] where B is the normalized learning behavior score, I is the normalized hobby index, P is the normalized performance value, α, γ, δ are the weight coefficients of learning behavior, hobby, and performance respectively, and e -β·(1-B) is a non-linear function, ln(1 + I) is a non-linear transformation of the hobby index, and arctan(P) is a smoothing process of the performance value;

[0079] It should be noted that the non-linear function and transformation function used in the expression not only enhance the expression ability of the model, but also effectively avoid the influence of extreme values on the final result. Through the weighted feature fusion method, the system can more comprehensively and accurately reflect the comprehensive situation of students in terms of learning behavior, hobby, and performance, providing a solid data basis for the design of subsequent personalized education paths.

[0080] A path generation module, which is used to process the obtained student learning data by using a machine learning algorithm and dynamically generate a personalized learning path;

[0081] Calculate the scores of the student in each dimension according to the student learning data S;

[0082] Let S B 、S I and S P respectively represent the learning behavior score, interest and hobby index, and performance value of the student;

[0083] Construct a student portrait PprofilePprofile, which comprehensively combines various aspects of the student's information, and the expression is:

[0084]

[0085] Among them, P profile is the student portrait, S B 、S I and S P respectively represent the learning behavior score, interest and hobby index, and performance value of the student;

[0086] Based on the student portrait P profile , combined with the curriculum syllabus and teaching objectives, set short-term and long-term learning goals G;

[0087] Use the Dijkstra algorithm to generate an optimal learning path L according to the current student knowledge state and short-term and long-term learning goals G, and the expression is:

[0088] L = Dj(K,G);

[0089] Among them, Dj(K,G) represents the shortest path between the student's current knowledge state and the target state;

[0090] During the learning process, continuously monitor the student's performance and adjust the learning path according to the feedback, and the expression is:

[0091] L′ = L + η·ΔL;

[0092] Among them, η is the adjustment factor, and ΔL is the path adjustment amount calculated based on the real-time feedback;

[0093] Through continuous iterative optimization, generate the final personalized learning path, and the expression is:

[0094]

[0095] Among them, L (n) represents the learning path after the nth iteration.

[0096] It should be noted that during the process of generating personalized learning paths, the application of Dijkstra's algorithm ensures that the path from the student's current knowledge state to the target state is optimal. In addition, the real-time monitoring and feedback mechanism enables the learning path to be flexibly adjusted according to the student's latest performance through the dynamic adjustment of the adjustment factor and path adjustment amount, thereby maximizing the learning effect. This method not only improves the accuracy of path planning but also enhances the self-adaptability of the system.

[0097] A recommendation module for identifying students' needs and preferences based on the personalized learning path and current learning state, using collaborative filtering, sentiment analysis, and natural language processing technologies to obtain the optimal learning resources;

[0098] Based on the behavioral similarity in students' learning data, use collaborative filtering algorithm to predict the learning resources that students are interested in and obtain the interest score R CF , and the expression is:

[0099] R CF = CF(L final );

[0100] Where CF(L final ) represents the collaborative filtering calculation based on the personalized learning path and current learning state;

[0101] Perform sentiment analysis on the text generated by students during the learning process to obtain the sentiment analysis result S SA ;

[0102] Use NLP technology to analyze students' queries, comments, and feedback, understand students' real needs, and obtain the analysis result N NLP ;

[0103] According to the results of collaborative filtering, sentiment analysis, and NLP, combined with the personalized learning path L final , screen out the learning resources that best meet the needs and preferences of students from the database and mark them as the resource collection R selected , and the expression is:

[0104] R selected = M(R CF , S SA , N NLP , L final );

[0105] Where M(.) represents the process of combining the three analysis results with the personalized learning path to match the most suitable learning resources;

[0106] Based on factors such as the quality, applicability of learning resources, and students' historical evaluations, for the screened learning resources R selectedPerform an optimized sorting to obtain the sorted resource list R optimal ;

[0107] Based on the sorted resource list R optimal , generate a personalized learning resource recommendation list R for this student l ;

[0108] It should be noted that the combination of collaborative filtering, sentiment analysis, and natural language processing technologies not only improves the relevance and attractiveness of the recommended resources but also better understands the real needs and preferences of students. By combining these analysis results with the personalized learning path, the system can screen out high-quality learning resources that are most suitable for students, and further optimize the sorting to ensure that each resource in the recommendation list can maximize the learning needs of students and promote their enthusiasm for active learning.

[0109] The monitoring and feedback module is used to collect the usage situation of the optimal learning resources, generate an evaluation result by establishing an evaluation model, and adjust the learning plan based on the evaluation result to obtain an adjusted plan;

[0110] Track and record the usage situation of the recommended learning resources R l for the student to obtain a dataset of the learning resource usage situation;

[0111] Based on the dataset D of the learning resource usage situation usage , construct an evaluation model to quantify the utilization effect of students on learning resources and obtain an evaluation score E;

[0112] Based on the evaluation score, calculate the specific evaluation value e i , and the expression is:

[0113] e i = El(r i , D usage );

[0114] where El(.) is a function for evaluating the effect of a single resource;

[0115] According to the evaluation result e i , adjust the original personalized learning path L final , and the specific steps are as follows:

[0116] According to the evaluation result e i decide how to modify the learning plan and define the adjustment strategy;

[0117] When the effect of a certain resource is not good, replace or remove the resource;

[0118] When it is found that the student lacks knowledge in a certain aspect, add corresponding supplementary materials;

[0119] After implementing the adjustment strategy, the adjusted learning plan L is obtained adjusted , and the expression is:

[0120] L adjusted = AP(L final , Strategy);

[0121] where AP(.) is the process of adjusting the learning path according to the evaluation results and predefined strategies;

[0122] The adjusted learning plan L adjusted is fed back to the students and teachers;

[0123] It should be noted that the construction of the evaluation model and the calculation of the evaluation scores are based on the comprehensive consideration of multi-dimensional data, including learning duration, completion rate, and accuracy rate. By quantifying the utilization effect of learning resources by students, the system can timely discover and correct problem resources, and at the same time dynamically adjust the learning plan according to the evaluation results. The continuous feedback mechanism not only improves the utilization efficiency of educational resources but also promotes the improvement of students' learning effects, ensuring that the teaching strategies always meet the actual needs and development directions of students.

[0124] Adjustment module, used to adjust the teaching strategy according to the adjustment plan to obtain a learning report;

[0125] Check the learning progress, understanding level of students, and their responses to different teaching methods, and analyze whether the current teaching strategy is effective;

[0126] Adjust the teaching strategy according to the analysis results to better meet the personalized needs of students;

[0127] When it is found that students have a low mastery of a certain knowledge point, increase interactive teaching and obtain the adjusted teaching strategy;

[0128] Based on the adjusted teaching strategy T new , reallocate the learning resources R allocated , and the expression is:

[0129] R allocated = AR(T new , L adjusted );

[0130] where AR(.) represents the process of reallocating learning resources according to the new teaching strategy and the adjusted learning plan;

[0131] Generate a learning report based on the above information;

[0132] The learning report includes an overview of learning progress, knowledge mastery assessment, improvement suggestions, and future learning plans;

[0133] It should be noted that in the process of adjusting teaching strategies, not only the learning progress and comprehension level of students are considered, but also the feedback on the effectiveness of different teaching methods for students is incorporated. By means of increasing interactive teaching or supplementary materials, etc., the system can better support students in overcoming learning obstacles, improving the mastery of knowledge points, and the process of reallocating learning resources ensures that each student can obtain the support most suitable for their own needs, further promoting the effective implementation of personalized education.

[0134] An optimization module, which is used to obtain student performance data from the learning report and update the learning path using an evolutionary algorithm to obtain the final personalized learning path;

[0135] Extract key student performance data from the learning report.

[0136] Student performance data includes the mastery of knowledge points, learning progress, assessment scores, and teacher feedback;

[0137] According to the adjusted learning plan L adjusted and student performance data D pf , initialize the population P0, where each individual represents a learning path plan, and use the evolutionary algorithm EA to optimize the learning path. The expression is:

[0138] P0 = IP(L jt , D pf , N);

[0139] where IP(.) is the process of generating the initial population according to the existing path and student performance data;

[0140] Define a fitness function F to evaluate the effectiveness of each learning path;

[0141] According to the results of the fitness function F, perform selection, crossover, and mutation operations on the individuals in the population P0 to generate a new generation of population P t+1 ;

[0142] When the maximum number of iterations is reached , select the individual with the highest fitness from the final population as the final personalized learning path.

[0143] It should be noted that the application of the evolutionary algorithm EA enables the system to find the optimal solution among a large number of possible learning paths. By defining the fitness function to evaluate the effectiveness of each path and continuously iterating and optimizing according to selection, crossover, and mutation operations, the finally generated personalized learning path can not only meet the needs of students to the greatest extent, but also be dynamically updated with the changes in student performance. This method not only improves the flexibility and accuracy of path planning, but also provides a more personalized learning experience for students, helping them achieve long-term development goals.

[0144] This embodiment also provides a computer device, which is applicable to the case of an adaptive education system based on artificial intelligence, and includes: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the adaptive education system based on artificial intelligence proposed in the above embodiment.

[0145] This computer device can be a terminal, and this computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of this computer device is used to provide computing and control capabilities. The memory of this computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of this computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through Wi-Fi, a carrier network, NFC (Near Field Communication), or other technologies. The display screen of this computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of this computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad set on the housing of the computer device, or an external keyboard, a touchpad, or a mouse, etc.

[0146] This embodiment also provides a storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the adaptive education system based on artificial intelligence proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disc.

[0147] In summary, the present invention collects students' learning behaviors, hobbies, and academic performance information by adopting a multimodal data processing method based on weighted feature fusion, realizing the construction of a comprehensive learning portrait of students. It can not only more accurately reflect the actual learning status of students but also identify their advantages and deficiencies in different dimensions, thus providing a solid foundation for the design of subsequent personalized education paths. By calculating students' scores in each dimension and dynamically generating personalized learning paths, the setting and optimization of students' short-term and long-term learning goals are achieved. It can ensure that each student has a tailor-made learning path that not only conforms to their current knowledge state but also stimulates their learning interest. By using collaborative filtering, sentiment analysis, and natural language processing technologies to identify students' needs and preferences, the optimal learning resources are obtained, which not only improves the relevance and attractiveness of the recommended resources but also ensures that the provided learning materials are most suitable for the students' current level and interests, helping to enhance students' learning motivation, promote their active participation in learning activities, and effectively improve learning effects.

[0148] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. An artificial intelligence-based adaptive education system, characterized in that: Including: A data collection module, a path generation module, a recommendation module, a monitoring and feedback module, an adjustment module, and an optimization module; The data collection module is used to collect the learning behavior, interests and hobbies, and academic performance information of students by using multi-modal data fusion technology to obtain student learning data; The path generation module is used to process the obtained student learning data by using machine learning algorithms and dynamically generate personalized learning paths; The recommendation module is used to identify the needs and preferences of students based on the personalized learning path and the current learning status, and utilize collaborative filtering, sentiment analysis, and natural language processing technologies to obtain the optimal learning resources; The monitoring and feedback module is used to collect the usage situation of the optimal learning resources, generate an evaluation result by establishing an evaluation model, and adjust the learning plan based on the evaluation result to obtain an adjusted plan; The adjustment module is used to adjust the teaching strategy according to the adjusted plan to obtain a learning report; The optimization module is used to obtain student performance data from the learning report and update the learning path by using an evolutionary algorithm to obtain the final personalized learning path.

2. The adaptive education system based on artificial intelligence according to claim 1, characterized in that: The specific steps for collecting the learning behavior, interests and hobbies, and academic performance information of students by using multi-modal data fusion technology to obtain student learning data are as follows: Adopt a multi-modal data processing method based on weighted feature fusion to extract key features from multiple data sources; The multiple data sources include learning behavior data, interests and hobbies data, and academic performance data; The key features include the completion situation of homework, classroom participation, and online learning duration in the learning behavior data, the interaction records in the learning platform in the interests and hobbies data, and the exam scores and test results in the academic performance data; Integrate the multi-data sources into a unified student learning data S.

3. The adaptive education system based on artificial intelligence according to claim 2, wherein: The specific steps for processing the obtained student learning data by using machine learning algorithms and dynamically generating personalized learning paths are as follows: According to the student learning data S, calculate the scores of students in each dimension; Let S B , S I and S P represent the learning behavior score, the interest index, and the performance value of the student respectively; Construct a student portrait PprofilePprofile, which comprehensively integrates the information of students in multiple aspects; Based on the student portrait P profile , combined with the curriculum syllabus and teaching objectives, set short-term and long-term learning goals G; Use the Dijkstra algorithm to generate an optimal learning path L according to the current student knowledge state and short-term and long-term learning goals G; During the learning process, continuously monitor the performance of students and adjust the learning path according to the feedback; Generate the final personalized learning path through continuous iterative optimization.

4. The adaptive education system based on artificial intelligence according to claim 3, wherein: The specific steps for identifying the needs and preferences of students based on the personalized learning path and the current learning status, and utilizing collaborative filtering, sentiment analysis, and natural language processing technologies to obtain the optimal learning resources are as follows: Based on the behavioral similarity in students' learning data, the collaborative filtering algorithm is used to predict the learning resources that students are interested in, and the interest score R is obtained CF ; Perform sentiment analysis on the text generated by students during the learning process to obtain the sentiment analysis result S SA ; Use NLP technology to parse students' queries, comments, and feedback, understand students' real needs, and obtain analysis result N NLP ; Based on the results of collaborative filtering, sentiment analysis, and NLP, combined with the personalized learning path L final , the learning resources that best meet the needs and preferences of students are screened from the database and marked as the resource collection R selected ; Based on the quality, applicability of learning resources, and the historical evaluation factors of students, the selected learning resources R selected are optimized and sorted to obtain the sorted resource list R optimal ; Based on the sorted resource list R optimal , generate a personalized learning resource recommendation list R for this student l .

5. The adaptive education system based on artificial intelligence according to claim 4, wherein: The specific steps for collecting the usage situation of the optimal learning resources, generating an evaluation result by establishing an evaluation model, and adjusting the learning plan based on the evaluation result to obtain an adjusted plan are as follows: Tracking and recording students' usage of the recommended learning resource R l to obtain a dataset on the usage of learning resources; Dataset D based on the usage of learning resources usage , construct an evaluation model to quantify the utilization effect of students on learning resources and obtain an evaluation score E; Based on the evaluation score, calculate the specific evaluation value e i ; According to the evaluation result e i , adjust the original personalized learning path L final .

6. The adaptive education system based on artificial intelligence according to claim 5, characterized in that: The adjustment of the original personalized learning path L final is carried out as follows: According to the evaluation result e i Decide how to modify the learning plan and define the adjustment strategy; When the effect of a certain resource is not good, replace or remove the resource; When it is found that a student lacks knowledge in a certain aspect, add corresponding supplementary materials; After implementing the adjustment strategy, the adjusted learning plan L is obtained adjusted ; Feed the adjusted learning plan L adjusted back to the students and teachers.

7. The artificial intelligence-based adaptive education system according to claim 6, characterized in that: The specific steps for adjusting the teaching strategy according to the adjusted plan to obtain a learning report are as follows: Check the learning progress, understanding level of students, and their responses to different teaching methods, and analyze whether the current teaching strategies are effective; Adjust the teaching strategies according to the analysis results to better meet the personalized needs of students; When it is found that students have a low mastery of a certain knowledge point, increase interactive teaching and obtain the adjusted teaching strategy; Based on the adjusted teaching strategy T new , reallocate the learning resources R allocated ; Generate a learning report based on the above information; The learning report includes an overview of learning progress, assessment of knowledge mastery, improvement suggestions, and future learning plans.

8. The adaptive education system based on artificial intelligence according to claim 7, characterized in that: Obtain student performance data from the learning report and use an evolutionary algorithm to update the learning path to obtain the final personalized learning path. The specific steps are as follows: Extract key student performance data from the learning report. The student performance data includes the mastery of knowledge points, learning progress, assessment scores, and teacher feedback; According to the adjusted learning plan L adjusted and the student performance data D pf , initialize the population P0, where each individual represents a learning path plan, and use the evolutionary algorithm EA to optimize the learning path; Define a fitness function F to evaluate the effectiveness of each learning path; According to the results of the fitness function F, individuals in the population P0 are selected, crossed, and mutated to generate a new generation of population P t+1 ; When the maximum number of iterations is reached After that, the individual with the highest fitness is selected from the final population as the final personalized learning path.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the artificial intelligence-based adaptive education system according to any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the artificial intelligence-based adaptive education system according to any one of claims 1 to 8.

Images