A smart classroom management method and system based on artificial intelligence

Abstract

The present invention relates to the field of smart classroom technology, and in particular to a smart classroom management method and system based on artificial intelligence, including obtaining class scheduling information, obtaining target teaching information according to the class scheduling information; scheduling teacher resources, classroom resources and teaching equipment resources; determining the resource allocation of teaching according to the results of scheduling teacher resources, classroom resources and teaching equipment resources; obtaining classroom environment information in real time; analyzing student learning behavior data through data mining and machine learning, judging student learning progress in real time, and generating personalized progress reports; based on personalized progress reports and teaching content, generating personalized teaching materials, learning method suggestions and exercise homework through natural language processing and recommendation system technology. Real-time acquisition of classroom environment information can adjust teaching plans, teaching methods and teaching resource configuration according to actual conditions. The generation of personalized teaching materials, learning method suggestions and exercise homework is helpful to improve students' learning interest and enthusiasm.

Description

Technical Field

[0001] The present application relates to the technical field of smart classrooms, and in particular to a smart classroom management method and system based on artificial intelligence. Background Art

[0002] A smart classroom is a modern teaching place based on emerging information technologies such as the Internet of Things, cloud computing, and big data. It provides convenient and efficient services for teaching activities through smart devices and software, integrates modern technology into the teaching process, and aims to improve students' independent thinking and learning abilities.

[0003] Patent document (CN115662218A) discloses a smart classroom system, including a teacher end, a student end and a server end, the data transmission end of the teacher end is interconnected with the data transmission end of the student end, the data transmission end of the server end is interconnected with the data transmission end of the teacher end, and the data transmission end of the server end is also interconnected with the data transmission end of the student end, and the method of use includes teachers and students logging into the system through login module one and login module two respectively, the server end of the system will compare data and classify students into corresponding teacher classrooms, after the teacher completes the docking with the students, the student end can be remotely commanded through the remote control module, the teacher displays the teaching content on the electronic whiteboard in the display module one, and the teaching process is recorded through the screen recording of the display module one, and the teacher interacts with the students through the teaching interaction module and the students interact with the teacher through the class interaction module. In the above patent, the interaction of teaching can be realized, but the teaching management process may still rely on manual intervention, and it is difficult to generate personalized teaching materials, learning method suggestions and exercise homework according to the students' situation; and in traditional teaching management, the allocation of resources such as classrooms, teachers and equipment is often based on a fixed schedule, rather than dynamically adjusted according to actual needs. This may lead to an excess of resources at certain times and a shortage at other times, making it difficult to allocate teaching resources reasonably, which in turn affects teaching effectiveness.

[0004] Therefore, the prior art has defects and needs to be improved. Summary of the invention

[0005] In order to solve one or several problems in the prior art, the main purpose of this application is to provide a smart classroom management method and system based on artificial intelligence.

[0006] In order to achieve the above-mentioned invention object, the present application proposes a smart classroom management method based on artificial intelligence, the method comprising:

[0007] Obtaining class schedule information and teaching plans, and obtaining target teaching information according to the class schedule information;

[0008] Based on the target teaching information and teaching plan, dispatch teacher resources, classroom resources and teaching equipment resources;

[0009] Determine the resource allocation for teaching according to the result of scheduling teacher resources, classroom resources and teaching equipment resources;

[0010] Obtain classroom environment information in real time, including student learning behavior data and teacher teaching behavior data;

[0011] Analyze the student learning behavior data through data mining and machine learning, determine the student learning progress in real time, and generate personalized progress reports;

[0012] Based on the personalized progress report and teaching content, personalized teaching materials, learning method suggestions and practice assignments are generated through natural language processing and recommendation system technology.

[0013] Furthermore, the scheduling of teacher resources, classroom resources and teaching equipment resources based on the target teaching information and teaching plan includes:

[0014] Obtain target teaching information from the teacher, including course objectives, knowledge point objectives, and skill objectives;

[0015] Obtaining the teaching plan, including teaching cycle, course schedule and teaching links;

[0016] Integrate the target teaching information and the teaching plan to obtain a teaching strategy;

[0017] According to the course arrangement described in the teaching strategy, calculate the number of teachers required for each course and the professional background resource requirements of teachers;

[0018] According to the course arrangement in the teaching strategy, calculate the classroom capacity and hardware facility resource requirements for each course;

[0019] According to the teaching links in the teaching strategy, calculate the required projection equipment and experimental equipment resource requirements;

[0020] Based on the calculated teacher resource demand, classroom resource demand and teaching equipment resource demand, relevant resources are scheduled.

[0021] Furthermore, after the step of scheduling relevant resources based on the calculated teacher resource requirements, classroom resource requirements and teaching equipment resource requirements, the following steps are further included:

[0022] Check whether the allocation of teacher resources is reasonable and whether the professional background of teachers meets the course requirements;

[0023] Check whether the allocation of classroom resources is reasonable and whether the hardware facilities meet the course requirements;

[0024] Check whether the allocation of teaching equipment resources is reasonable and whether the equipment can meet the needs of teaching activities;

[0025] Based on the results of the detection and evaluation, the scheduling strategy is adjusted.

[0026] Furthermore, the student learning behavior data is analyzed through data mining and machine learning to determine the student learning progress in real time and generate a personalized progress report, including:

[0027] Collect students' clicks, browsing, questions, and homework completion behavior data during the learning process;

[0028] Clean, denoise, select features, and perform feature engineering on the collected raw behavior data to obtain a processed data set;

[0029] Using a machine learning algorithm to train a model, inputting the processed data set into the model, and outputting the student's current learning progress through the model;

[0030] Generate a personalized progress report based on the learning progress and historical learning habits.

[0031] Furthermore, the method further comprises:

[0032] Collect the student's learning behavior data, including student click rate, learning time, correct answer rate, etc.;

[0033] Based on the student learning behavior data, use time series analysis algorithm to predict students' future learning interests and needs;

[0034] Adjust instructional content, teaching strategies, and resource allocation based on said predicted student interests and needs;

[0035] Combined with student portraits, collaborative filtering algorithms are used to recommend personalized learning paths and teaching resources for students, and students’ feedback on recommended content is collected in real time to adjust recommendation strategies;

[0036] Through machine learning algorithms, cluster analysis of students’ learning progress is performed to identify students’ learning difficulties and weaknesses;

[0037] Based on the students' learning difficulties and weak links, and combining the teaching content with the students' characteristics, we generate personalized tutoring plans and teaching resources.

[0038] Furthermore, the method further comprises:

[0039] Collecting the teacher's teaching behavior data, including teaching content, teaching methods and teaching evaluation;

[0040] Based on the teacher's teaching behavior data, the teaching quality is evaluated using a teaching effectiveness evaluation model;

[0041] According to the teaching effect evaluation results, the decision tree algorithm is used to provide teachers with targeted teaching improvement suggestions;

[0042] Combined with teacher portraits, association rule mining algorithms are used to discover problems and improvement directions in the teaching process;

[0043] Provide real-time teaching support and guidance for the problems encountered by the teachers in the teaching process;

[0044] Through artificial neural network algorithms, the degree to which teachers adopt teaching improvement suggestions can be predicted, the recommendation strategy can be optimized, and the teaching effectiveness of teachers can be tracked to adjust teaching methods and strategies.

[0045] Furthermore, the method combines student portraits, uses collaborative filtering algorithms to recommend personalized learning paths and teaching resources to students, collects students’ feedback on recommended content in real time, and adjusts recommendation strategies, including:

[0046] Collect students’ basic information, learning behavior data, and learning preferences;

[0047] Constructing a student profile based on the student's basic information, learning behavior data, and learning preferences;

[0048] Based on the student portrait, the similarity between different teaching resources is calculated by the collaborative filtering algorithm, teaching resources similar to the teaching resources previously liked by the student are found, and a recommendation list is generated and sent to the student end;

[0049] Collect student feedback in real time and adjust the recommendation strategy based on the feedback information.

[0050] The embodiment of the present application also provides a smart classroom management system based on artificial intelligence, including:

[0051] A first acquisition module is used to acquire class schedule information and teaching plans, and acquire target teaching information according to the class schedule information;

[0052] A scheduling module, used for scheduling teacher resources, classroom resources and teaching equipment resources based on the target teaching information and teaching plan;

[0053] An allocation module, used to determine the resource allocation for teaching according to the result of scheduling teacher resources, classroom resources and teaching equipment resources;

[0054] The second acquisition module is used to acquire classroom environment information in real time, wherein the environment information includes students' learning behavior data and teachers' teaching behavior data;

[0055] A judgment module is used to analyze the student learning behavior data through data mining and machine learning, judge the student's learning progress in real time, and generate a personalized progress report;

[0056] A generation module is used to generate personalized teaching materials, learning method suggestions and practice assignments based on the personalized progress report and teaching content through natural language processing and recommendation system technology.

[0057] The present application also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0058] The present application also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any of the above-mentioned methods are implemented.

[0059] The intelligent classroom management method and system based on artificial intelligence of the embodiment of the present application obtains class scheduling information, target teaching information, and classroom environment information to schedule teachers, classrooms and teaching equipment. The behavior data of students and teachers are analyzed through data mining and machine learning to determine the learning progress of students and generate personalized progress reports. According to the learning progress and teaching content of students, personalized teaching materials, learning method suggestions and practice homework are generated. From the above analysis, by obtaining class scheduling information and target teaching information in real time, it can ensure that teaching resources are reasonably allocated and improve resource utilization. According to the course objectives and teaching content, suitable teachers and classrooms are provided to students, which helps to improve the teaching quality. By monitoring and analyzing the classroom environment, the comfort, safety and teaching quality of the teaching environment can be evaluated, providing a basis for improving teaching conditions, and obtaining classroom environment information in real time, which helps education managers adjust teaching plans, teaching methods and teaching resource configuration according to actual conditions. According to students' learning behavior data and teaching content, personalized teaching materials, learning method suggestions and practice homework are generated, which helps to improve students' learning interest and enthusiasm. Through the automated and intelligent teaching support system, teachers can complete teaching tasks more efficiently and reduce their workload. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 A flowchart of a smart classroom management method based on artificial intelligence according to an embodiment of the present application;

[0061] Figure 2 A flowchart of a smart classroom management method based on artificial intelligence according to an embodiment of the present application;

[0062] Figure 3 This is a schematic block diagram of the structure of a smart classroom management system based on artificial intelligence according to an embodiment of the present application;

[0063] Figure 4 A schematic block diagram of the structure of a computer device according to an embodiment of the present application.

[0064] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0066] Reference Figure 1 In an embodiment of the present application, a smart classroom management method based on artificial intelligence is provided, and the method comprises:

[0067] S1. Obtaining class schedule information and teaching plan, and obtaining target teaching information according to the class schedule information;

[0068] S2. Dispatching teacher resources, classroom resources and teaching equipment resources based on the target teaching information and teaching plan;

[0069] S3, determining the resource allocation for teaching according to the result of scheduling teacher resources, classroom resources and teaching equipment resources;

[0070] S4. Real-time acquisition of classroom environment information, where the environment information includes student learning behavior data and teacher teaching behavior data;

[0071] S5. Analyze the student learning behavior data through data mining and machine learning, determine the student learning progress in real time, and generate a personalized progress report;

[0072] S6. Based on the personalized progress report and teaching content, generate personalized teaching materials, learning method suggestions and practice assignments through natural language processing and recommendation system technology.

[0073] As described in the above steps S1-S3, the class scheduling information can be obtained from the school or the teaching system. This information usually includes the course name, course time, lecturer, classroom, etc. This data can be obtained by writing a crawler program or using an API interface. According to the class scheduling information, query the target teaching information of the relevant courses. The target teaching information usually includes course objectives, teaching content, teaching methods, etc. This information can be obtained from the teaching system, the course outline, or the teaching plan provided by the teacher. According to the target teaching information and course time, determine the appropriate teacher to teach. The teacher's expertise, teaching experience, class schedule, and other factors can be considered for scheduling. According to the target teaching information and course time, determine the appropriate classroom for teaching. The classroom capacity, equipment configuration, geographical location, and other factors can be considered for scheduling. According to the target teaching information and course requirements, determine the required teaching equipment, such as projectors, computers, experimental equipment, etc. Then, according to factors such as equipment requirements and the distance between the teacher and the classroom, reasonably allocate teaching equipment. By obtaining class scheduling information and target teaching information in real time, we can ensure that teaching resources are reasonably allocated and improve resource utilization. According to course objectives and teaching content, we can provide students with suitable teachers and classrooms, which will help improve teaching quality. Through data-driven resource scheduling methods, we can try to avoid excessive concentration of excellent teachers and high-quality classroom resources and promote fair distribution of teaching resources.

[0074] As described in step S4 above, in obtaining classroom environment information, monitoring equipment, such as cameras, sensors, etc., can be installed in the classroom to collect classroom environment information. These devices can capture images, sounds, light, temperature and other data in the classroom in real time, and transmit the data collected by the monitoring equipment to the server for storage and backup. Wireless networks or wired networks can be used to achieve data transmission to ensure the security and real-time nature of the data. Information related to student learning behavior, such as attendance, classroom interaction, note taking, etc., is extracted. Information related to teacher teaching behavior, such as teaching content, teaching methods, questions and answers, etc., is extracted. Student learning behavior data and teacher teaching behavior data are summarized and data analysis is performed to understand the impact of classroom environment on teaching effect. By monitoring and analyzing the classroom environment, the comfort, safety and teaching quality of the teaching environment can be evaluated, providing a basis for improving teaching conditions, and obtaining classroom environment information in real time, which helps education managers adjust teaching plans, teaching methods and teaching resource allocation according to actual conditions. By monitoring the classroom environment, potential safety hazards can be discovered in time, teaching accidents can be prevented, and the safety of teachers and students can be guaranteed.

[0075] As described in the above steps S5-S6, according to the characteristics of the student learning behavior data, select appropriate data mining and machine learning algorithms, such as association rule mining, classification, clustering, etc., and use the selected algorithm to mine the student learning behavior data to extract valuable information, such as student learning habits, learning preferences, etc. Through the data mining model, the student learning behavior data is analyzed in real time to judge the student's learning progress. The student's learning progress can be classified by setting the learning progress threshold. According to the classification results of the student's learning progress, a personalized progress report is generated. The report may include detailed information such as the number of students, the proportion of students in each progress category, and the subjects with leading progress. Combined with natural language processing technology, the teaching content is structured for the convenience of subsequent recommendation system use. Based on the personalized progress report, student learning behavior data and teaching content, personalized teaching materials, learning method suggestions and practice homework are generated for students through recommendation system technology. By analyzing students' learning behavior data and judging students' learning progress in real time, it helps teachers develop more targeted teaching strategies and improve teaching effectiveness. It also generates personalized progress reports, which helps teachers, students and parents understand students' learning status, thereby adjusting teaching methods and learning plans, and realizing personalized teaching. Based on students' learning behavior data and teaching content, it generates personalized teaching materials, learning method suggestions and practice homework, which helps improve students' learning interest and enthusiasm. Through automated and intelligent teaching support systems, teachers can complete teaching tasks more efficiently and reduce their workload.

[0076] As described in the above steps, the course scheduling information, target teaching information, and classroom environment information are obtained to schedule teachers, classrooms, and teaching equipment. The behavior data of students and teachers are analyzed through data mining and machine learning to determine the learning progress of students and generate personalized progress reports. According to the learning progress and teaching content of students, personalized teaching materials, learning method suggestions, and exercise homework are generated. From the above analysis, by obtaining the course scheduling information and target teaching information in real time, it can ensure that teaching resources are reasonably allocated and improve resource utilization. According to the course objectives and teaching content, suitable teachers and classrooms are provided to students, which helps to improve the teaching quality. By monitoring and analyzing the classroom environment, the comfort, safety, and teaching quality of the teaching environment can be evaluated, providing a basis for improving teaching conditions. Real-time acquisition of classroom environment information helps education managers adjust teaching plans, teaching methods, and teaching resource configuration according to actual conditions. According to the students' learning behavior data and teaching content, personalized teaching materials, learning method suggestions, and exercise homework are generated, which helps to improve students' learning interest and enthusiasm. Through the automated and intelligent teaching support system, teachers can complete teaching tasks more efficiently and reduce their workload.

[0077] In a feasible embodiment, when this method is used for teaching management in a higher education institution, before the start of the semester, the teaching management system will automatically obtain the course scheduling information of each course, including the course name, lecturer, class time, class location, etc. According to the course scheduling information, the teaching management system will further obtain information such as the target teaching content and teaching objectives of the relevant courses. The teaching management system will automatically dispatch teacher resources, classroom resources and teaching equipment resources according to the target teaching information and teaching plan to ensure the smooth progress of teaching activities. Under the premise of considering teachers, classrooms and equipment resources, the teaching management system will determine the allocation plan of various resources according to actual needs. During the teaching process, the teaching management system will obtain the classroom environment information in real time through sensors and other devices, including student learning behavior data (such as attendance, number of questions, etc.) and teacher teaching behavior data (such as teaching speed, teaching methods, etc.). The teaching management system will use data mining and machine learning technology to analyze the collected student learning behavior data to judge the student's learning progress in real time. According to the analysis results, the teaching management system will generate a personalized progress report to reflect the learning situation of each student. The teaching management system will generate personalized teaching materials, learning method suggestions and practice assignments for each student based on personalized progress reports and teaching content through natural language processing and recommendation system technology. The teaching management system will send the generated personalized progress reports and learning suggestions to students and teachers so that teachers can adjust teaching strategies and students can make learning plans according to their actual conditions.

[0078] In one embodiment, when scheduling teacher resources, classroom resources, and teaching equipment resources, including minimizing the cost of resource allocation, the steps include:

[0079] Setting a linear programming model, and scheduling the teacher resources, classroom resources and teaching equipment resources through the linear programming model;

[0080] The cost of minimizing resource allocation is calculated by the objective function of the linear programming model;

[0081] The formula of the objective function is:

[0082]

[0083] Among them, Z is the total cost, cij is the cost of assigning course i to teacher j, dik is the cost of assigning course i to classroom k, eil is the cost of assigning teaching equipment L to course i, xij, yik, zil are decision variables, taking values ​​of 0 or 1, indicating whether course i is assigned to teacher j, classroom k or teaching equipment L; the constraints are: each course must be assigned a teacher; each course must be assigned a classroom; if a course requires a certain teaching equipment, the equipment must be assigned. As mentioned above, the cost represents the time of use of teachers, classrooms or equipment, so what is minimized is the efficiency of time, ensuring the optimal use of resources. It is worth mentioning that if a teacher has the ability to teach multiple subjects at the same time, then assigning this teacher to different subjects may introduce additional costs because it will reduce the time that the teacher can use for other important tasks. Similarly, if a classroom is equipped with special equipment, then assigning this classroom to courses that do not require these equipment may result in a waste of resources. Therefore, in order to solve this problem, the goals and priorities of resource allocation can be set. In the linear programming model, we can reflect these goals and priorities by adjusting the cost coefficients cij, dik, and eil. By solving this model, we can find the resource allocation plan that minimizes the total cost while satisfying all constraints.

[0084] In one embodiment, scheduling teacher resources, classroom resources and teaching equipment resources based on the target teaching information and the teaching plan includes:

[0085] Obtain target teaching information from the teacher, including course objectives, knowledge point objectives, and skill objectives;

[0086] Obtaining the teaching plan, including teaching cycle, course schedule and teaching links;

[0087] Integrate the target teaching information and the teaching plan to obtain a teaching strategy;

[0088] According to the course arrangement described in the teaching strategy, calculate the number of teachers required for each course and the professional background resource requirements of teachers;

[0089] According to the course arrangement in the teaching strategy, calculate the classroom capacity and hardware facility resource requirements for each course;

[0090] According to the teaching links in the teaching strategy, calculate the required projection equipment and experimental equipment resource requirements;

[0091] Based on the calculated teacher resource demand, classroom resource demand and teaching equipment resource demand, relevant resources are scheduled.

[0092] As mentioned above, in obtaining the target teaching information on the teacher side, the course objectives, knowledge point objectives and skill objectives can be obtained through the syllabus, course design and other documents uploaded by the teacher, or through interviews with teachers, questionnaires and other methods. In obtaining the teaching plan, information such as the teaching cycle, course schedule and teaching links can be obtained according to the teaching arrangements of the school or educational institution. Through artificial intelligence technologies such as natural language processing and data mining, the obtained teaching information and plans are integrated to generate teaching strategies. According to the course arrangements in the teaching strategy, the number of teachers required for each course, the teacher's professional background resource requirements, classroom capacity, hardware facility resource requirements, and projection equipment and experimental equipment resource requirements are calculated through algorithms. According to the calculated resource requirements, resources such as teachers, classrooms and teaching equipment are dispatched through an information platform or manual methods. By accurately calculating and scheduling teaching resources, we can avoid waste and shortage of resources and improve resource utilization; according to teaching strategies, we can reasonably allocate teacher resources so that the professional background of teachers is adapted to teaching needs and the teaching quality is improved; by scheduling teaching resources through intelligent means, we can reduce the burden of teachers in teaching resource management and enable teachers to focus more on teaching content and methods; by scheduling teaching resources through a unified platform, it is convenient for teaching management personnel to monitor and evaluate teaching and improve teaching management efficiency.

[0093] In one embodiment, after the step of scheduling relevant resources based on the calculated teacher resource requirements, classroom resource requirements, and teaching equipment resource requirements, the following step is further included:

[0094] Check whether the allocation of teacher resources is reasonable and whether the professional background of teachers meets the course requirements;

[0095] Check whether the allocation of classroom resources is reasonable and whether the hardware facilities meet the course requirements;

[0096] Check whether the allocation of teaching equipment resources is reasonable and whether the equipment can meet the needs of teaching activities;

[0097] Based on the results of the detection and evaluation, the scheduling strategy is adjusted.

[0098] As mentioned above, first of all, it is necessary to collect relevant information about teacher resources, classroom resources and teaching equipment resources. This information includes the professional background of teachers, the hardware facilities of classrooms, the performance of teaching equipment, etc. According to the teaching plan, course schedule and other information, the demand for various resources is calculated. According to the calculated resource demand, the relevant resources are dispatched to ensure the smooth progress of teaching activities. By checking the allocation of teachers, classrooms and teaching equipment, ensure that the allocation of resources is reasonable and meets the course requirements, evaluate the resource allocation to see whether it achieves the expected effect. If there is any deficiency, it needs to be adjusted. According to the evaluation results, adjust the scheduling strategy to improve resource utilization and teaching effect. In the teaching process, continuously collect feedback information, optimize the scheduling strategy, realize the rationalization of resource allocation and the improvement of teaching effect. By reasonably allocating teachers, classrooms and teaching equipment resources, reduce resource waste and improve overall utilization. Ensuring the reasonable allocation of teachers, classrooms and teaching equipment resources is conducive to improving teaching quality and improving students' learning effects. By real-time monitoring and adjusting resource allocation, the school's teaching resource management level and decision-making efficiency can be improved.

[0099] Reference Figure 2 In one embodiment, the student learning behavior data is analyzed by data mining and machine learning to determine the student learning progress in real time and generate a personalized progress report, including:

[0100] S51. Collect students’ click, browse, ask questions, and complete homework behavior data during the learning process;

[0101] S52, cleaning, denoising, feature selection and feature engineering the collected raw behavior data to obtain a processed data set;

[0102] S53, using a machine learning algorithm to train a model, inputting the processed data set into the model, and outputting the student's current learning progress through the model;

[0103] S54: Generate a personalized progress report based on the learning progress and historical learning habits.

[0104] As mentioned above, the behavioral data of students such as clicks, browsing, asking questions, and completing homework during the learning process are collected. These data can be obtained through learning platforms, teaching systems and other channels. The collected raw behavioral data are cleaned, denoised, feature selected and feature engineered to obtain a processed data set. The purpose of this step is to simplify the data structure, improve data quality, and lay the foundation for subsequent model training. Machine learning algorithms (such as decision trees, support vector machines, neural networks, etc.) are used to train the model. The processed data set is input into the model, and the model outputs the student's current learning progress based on the data characteristics. According to the student's historical learning habits and current learning progress, a personalized progress report is generated. The report content can include the student's learning progress, weak links, learning suggestions, etc. The generated progress report is presented to teachers and students in a visual form to help them understand the learning situation more intuitively. According to the student's learning progress and habits, a personalized progress report is generated, which helps students understand their own learning status, find weak links, and develop targeted learning plans; by providing real-time feedback on the student's learning progress, students are encouraged to actively participate in learning, improve their interest and motivation in learning, and personalized progress reports help discover students' potential, provide teachers with targeted teaching guidance, and reduce the problem of unbalanced educational resources caused by individual differences among students.

[0105] In one embodiment, the method further comprises:

[0106] Collect the student's learning behavior data, including student click rate, learning time, correct answer rate, etc.;

[0107] Based on the student learning behavior data, use time series analysis algorithm to predict students' future learning interests and needs;

[0108] Adjust instructional content, teaching strategies, and resource allocation based on said predicted student interests and needs;

[0109] Combined with student portraits, collaborative filtering algorithms are used to recommend personalized learning paths and teaching resources for students, and students’ feedback on recommended content is collected in real time to adjust recommendation strategies;

[0110] Through machine learning algorithms, cluster analysis of students’ learning progress is performed to identify students’ learning difficulties and weaknesses;

[0111] Based on the students' learning difficulties and weak links, and combining the teaching content with the students' characteristics, we generate personalized tutoring plans and teaching resources.

[0112] As described in the above steps, students' learning behavior data, including student click-through rate, learning time, correct answer rate, etc., are collected through the learning platform. These data can be stored in the database for subsequent analysis. Time series analysis algorithms (such as ARIMA, LSTM, etc.) are used to analyze the preprocessed student learning behavior data to predict students' future learning interests and needs. According to the predicted student interests and needs, teachers or teaching teams can adjust the teaching content in time, provide teaching resources that better meet students' needs, and adjust teaching strategies. Combined with student portraits, collaborative filtering algorithms are used to recommend personalized learning paths and teaching resources for students. At the same time, students' feedback on recommended content is collected in real time to adjust the recommendation strategy. The learning progress of students is clustered and analyzed through machine learning algorithms (such as K-Means, DBSCAN, etc.) to find students' learning difficulties and weaknesses. Based on students' learning difficulties and weaknesses, combined with teaching content and student characteristics, the teaching team can generate personalized tutoring plans and teaching resources. Personalized recommendation of teaching resources and tutoring plans are more in line with individual differences of students, which helps to stimulate students' interest and enthusiasm in learning; teaching resources are allocated according to students' learning needs to improve the efficiency of teaching resource utilization; through cluster analysis of learning progress, students' learning difficulties and weak links are discovered, which helps teachers to provide timely and targeted tutoring and assistance. With the help of big data and artificial intelligence technology, teachers can understand students' learning status more objectively and improve the quality and level of teaching.

[0113] In one embodiment, the method further comprises:

[0114] Collecting the teacher's teaching behavior data, including teaching content, teaching methods and teaching evaluation;

[0115] Based on the teacher's teaching behavior data, the teaching quality is evaluated using a teaching effectiveness evaluation model;

[0116] According to the teaching effect evaluation results, the decision tree algorithm is used to provide teachers with targeted teaching improvement suggestions;

[0117] Combined with teacher portraits, association rule mining algorithms are used to discover problems and improvement directions in the teaching process;

[0118] Provide real-time teaching support and guidance for the problems encountered by the teachers in the teaching process;

[0119] Through artificial neural network algorithms, the degree to which teachers adopt teaching improvement suggestions can be predicted, the recommendation strategy can be optimized, and the teaching effectiveness of teachers can be tracked to adjust teaching methods and strategies.

[0120] As mentioned above, by collecting the teaching behavior data of teachers from the school or the teachers themselves, this includes teaching content, teaching methods and teaching evaluation. These data can be stored in the form of a spreadsheet or a database, and the collected teaching behavior data of teachers are evaluated using a teaching effect evaluation model. This model can be a pre-set algorithm, such as regression analysis, classifier, etc., or a machine learning model, such as a support vector machine, random forest, etc. The result of the evaluation is the teaching quality score of the teacher. According to the teaching effect evaluation result, a decision tree algorithm is used to provide targeted teaching improvement suggestions for the teacher. The algorithm can generate a tree-shaped decision model based on the teaching quality score of the teacher, so as to point out which teaching methods or content need to be improved for the teacher. Combined with the teacher portrait (such as age, teaching experience, professional background, etc.), an association rule mining algorithm is used to discover problems and improvement directions in the teaching process. This algorithm can find the association rules between the teaching quality score and the teacher portrait attributes, so as to help teachers understand which factors affect their teaching quality. Provide real-time teaching support and guidance for the problems found. This can include one-on-one tutoring, teaching training, online resources, etc. Use an artificial neural network algorithm to predict the degree of adoption of teaching improvement suggestions by teachers. According to the prediction results, the recommended strategy can be optimized and the teaching effect of teachers can be tracked to adjust the teaching methods and strategies. By real-time monitoring and evaluating teachers' teaching behaviors, this method can help teachers to timely discover and correct problems in the teaching process; combined with teacher portraits and association rule mining, this method can provide targeted teaching improvement suggestions to help teachers find teaching methods and strategies that suit them; as a continuously improving teaching management system, it helps schools and teachers to grasp the teaching situation in real time, adjust teaching strategies in time, and improve teaching effects.

[0121] In one embodiment, the method combines student portraits, uses collaborative filtering algorithms to recommend personalized learning paths and teaching resources to students, collects students' feedback on recommended content in real time, and adjusts recommendation strategies, including:

[0122] Collect students’ basic information, learning behavior data, and learning preferences;

[0123] Constructing a student profile based on the student's basic information, learning behavior data, and learning preferences;

[0124] Based on the student portrait, the similarity between different teaching resources is calculated by the collaborative filtering algorithm, teaching resources similar to the teaching resources previously liked by the student are found, and a recommendation list is generated and sent to the student end;

[0125] Collect student feedback in real time and adjust the recommendation strategy based on the feedback information.

[0126] As mentioned above, students' basic information (such as name, grade, major, etc.) is collected through the school's academic affairs system, student personal information management system, etc., students' learning behavior data (such as learning time, learning frequency, task completion status, etc.) is collected through student behavior logs, learning records, etc., and students' learning preferences (such as interests, hobbies, learning methods, etc.) are collected through questionnaires, student self-reporting, etc. Based on the collected students' basic information, learning behavior data and learning preferences, a student portrait is constructed through data mining and machine learning technology, including students' interests, hobbies, learning styles, learning progress, etc. Based on the student portrait, a collaborative filtering algorithm is used to calculate the similarity between different teaching resources (such as courses, textbooks, teaching videos, etc.). Specifically, the similarity matrix between teaching resources can be calculated, and then teaching resources similar to the teaching resources that students liked before can be found according to the similarity matrix; based on the calculated similarity, a recommendation list is generated for students, including teaching resources similar to the teaching resources that students liked before and other teaching resources that meet students' learning needs. Send the recommendation list to the student end; collect feedback information from the student end in real time (such as click-through rate, learning completion status, etc.), and adjust the recommendation strategy based on the feedback information, including adjusting the similarity calculation method, updating the student portrait, and optimizing the recommendation list. Personalized recommendations based on students' learning behavior data and learning preferences help students find learning resources and methods that suit them more quickly; by constantly adjusting the recommendation strategy and updating the student portrait, the teaching resource library can be gradually optimized and the quality and applicability of the teaching resource library can be improved.

[0127] In a feasible embodiment, after resource allocation, classroom resource allocation is usually static, that is, the classrooms used by each class are arranged in advance. However, the actual situation may need to be adjusted due to various reasons (such as equipment failure, special activities, weather changes, etc.). With dynamic resource allocation, classroom allocation can be automatically adjusted according to real-time usage needs and available resources, improving resource utilization efficiency and minimizing the impact on teaching.

[0128] Specifically, when a temporary equipment failure occurs in the classroom resource, the cause of the failure is analyzed using a preset model;

[0129] Analyze the repair time required for the cause of the fault (this can be done by collecting historical repair data, including repair type, repair time, required materials and labor, etc. Prediction model: Use machine learning algorithms to predict the repair time of the current fault based on historical data. Uncertainty assessment: The prediction model should provide a probability distribution of repair time, considering the shortest, most likely and longest repair time), and analyze the impact of the classroom scheduling plan on the course schedule, students and teachers, and whether the resources of the spare classroom meet the course requirements;

[0130] Combining the resources, impact and maintenance time of the spare classroom, the resources, impact and maintenance time of the spare classroom are input into a decision algorithm, a decision tree is established through the decision algorithm, and factors such as the urgency of maintenance, the importance of the course, and the availability of the spare classroom are inferred through the decision tree;

[0131] According to the result of decision tree reasoning, the result of reasoning is quantified to obtain the recommendation coefficient of classroom scheduling and the recommendation coefficient of classroom resource maintenance, wherein the larger the recommendation coefficient is, the higher the degree of execution of the suggestion is.

[0132] For example, suppose the cause of the failure is: projector hardware failure

[0133] Fault analysis: Through preset model analysis, it is determined that it is a hardware failure and parts need to be replaced.

[0134] Maintenance time prediction: Historical data shows that the average maintenance time for similar failures is 2 hours, with a standard deviation of 0.5 hours.

[0135] Course impact analysis: The next class in the current classroom is an important exam review class, so the impact is high.

[0136] Alternative classroom resources: There is an alternative classroom nearby that is configured to meet the course requirements, but students and teachers must be notified 15 minutes in advance.

[0137] Decision-making process

[0138] Input parameters: spare classroom resources (meets demand), impact level (high), maintenance time (2 hours, probability distribution).

[0139] Build a decision tree: Input parameters into the decision algorithm, which considers the urgency of maintenance (high), the importance of the course (high), and the availability of spare classrooms (meets the needs).

[0140] Reasoning decision: The decision tree reasoning results show that the urgency of maintenance and the importance of the course are both high, and spare classrooms are available, but the uncertainty of maintenance time needs to be considered.

[0141] Quantitative impact coefficient: According to the decision tree reasoning results, the recommendation coefficient for classroom scheduling is 0.8 (high), and the recommendation coefficient for maintenance classroom resources is 0.6 (medium).

[0142] Decision results

[0143] Comparison of impact coefficients: The recommended coefficient for classroom scheduling (0.8) is greater than the recommended coefficient for maintaining classroom resources (0.6).

[0144] Execution decision: Since the recommendation coefficient of classroom scheduling is higher, the system recommends adopting the classroom scheduling plan and moving the next class to the spare classroom.

[0145] Notify and execute: The system automatically notifies students and teachers of the change of course location and ensures that the backup classroom is ready. Repair in progress: At the same time, the maintenance team begins repairing the projector in the original classroom.

[0146] To sum up, when a temporary equipment failure occurs in classroom resources, the system analyzes the cause of the failure, predicts the maintenance time, evaluates the impact, and combines spare classroom resources to make the best decision through decision algorithms and decision trees to ensure the smooth progress of teaching activities while minimizing the impact on normal teaching.

[0147] The artificial intelligence-based smart classroom management method of this application obtains class scheduling information, target teaching information, and classroom environment information to schedule teachers, classrooms, and teaching equipment. The behavioral data of students and teachers are analyzed through data mining and machine learning to determine the learning progress of students and generate personalized progress reports. According to the students' learning progress and teaching content, personalized teaching materials, learning method suggestions, and practice homework are generated. From the above analysis, by obtaining class scheduling information and target teaching information in real time, it can ensure that teaching resources are reasonably allocated and improve resource utilization. According to the course objectives and teaching content, suitable teachers and classrooms are provided to students, which helps to improve the teaching quality. By monitoring and analyzing the classroom environment, the comfort, safety, and teaching quality of the teaching environment can be evaluated, providing a basis for improving teaching conditions. Real-time acquisition of classroom environment information helps education managers adjust teaching plans, teaching methods, and teaching resource configuration according to actual conditions. According to students' learning behavior data and teaching content, personalized teaching materials, learning method suggestions, and practice homework are generated, which helps to improve students' learning interest and enthusiasm. Through an automated and intelligent teaching support system, teachers can complete teaching tasks more efficiently and reduce their workload.

[0148] Reference Figure 3 In the embodiment of the present application, a smart classroom management system based on artificial intelligence is also provided, including:

[0149] The first acquisition module 1 is used to acquire class schedule information and teaching plans, and acquire target teaching information according to the class schedule information;

[0150] Scheduling module 2, for scheduling teacher resources, classroom resources and teaching equipment resources based on the target teaching information and teaching plan;

[0151] Allocation module 3, used to determine the resource allocation of teaching according to the results of scheduling teacher resources, classroom resources and teaching equipment resources;

[0152] The second acquisition module 4 is used to acquire classroom environment information in real time, wherein the environment information includes student learning behavior data and teacher teaching behavior data;

[0153] The judgment module 5 is used to analyze the student learning behavior data through data mining and machine learning, judge the student learning progress in real time, and generate a personalized progress report;

[0154] The generating module 6 is used to generate personalized teaching materials, learning method suggestions and practice assignments based on the personalized progress report and teaching content through natural language processing and recommendation system technology.

[0155] As described above, it can be understood that the various components of the artificial intelligence-based smart classroom management system proposed in this application can realize the functions of any of the artificial intelligence-based smart classroom management methods described above, and the specific structure will not be repeated.

[0156] Reference Figure 4 In an embodiment of the present application, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as monitoring data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a smart classroom management method based on artificial intelligence is implemented.

[0157] The processor executes the artificial intelligence-based smart classroom management method, including: obtaining class scheduling information, and obtaining target teaching information based on the class scheduling information; scheduling teacher resources, classroom resources and teaching equipment resources based on the target teaching information and the teaching plan; determining the resource allocation for teaching based on the results of scheduling teacher resources, classroom resources and teaching equipment resources; obtaining classroom environment information in real time, wherein the environment information includes student learning behavior data and teacher teaching behavior data; analyzing the student learning behavior data through data mining and machine learning, judging the student learning progress in real time, and generating a personalized progress report; based on the personalized progress report and teaching content, generating personalized teaching materials, learning method suggestions and practice assignments through natural language processing and recommendation system technology.

[0158] The above-mentioned smart classroom management method based on artificial intelligence obtains class scheduling information, target teaching information, and classroom environment information to schedule teachers, classrooms, and teaching equipment. Through data mining and machine learning, the behavior data of students and teachers are analyzed to determine the students' learning progress and generate personalized progress reports. According to the students' learning progress and teaching content, personalized teaching materials, learning method suggestions, and exercises are generated. From the above analysis, by obtaining class scheduling information and target teaching information in real time, it can ensure that teaching resources are reasonably allocated and improve resource utilization. According to the course objectives and teaching content, suitable teachers and classrooms are provided to students, which helps to improve the teaching quality. By monitoring and analyzing the classroom environment, the comfort, safety, and teaching quality of the teaching environment can be evaluated, providing a basis for improving teaching conditions. Real-time acquisition of classroom environment information helps education managers adjust teaching plans, teaching methods, and teaching resource configuration according to actual conditions. According to students' learning behavior data and teaching content, personalized teaching materials, learning method suggestions, and exercises are generated, which helps to improve students' learning interest and enthusiasm. Through an automated and intelligent teaching support system, teachers can complete teaching tasks more efficiently and reduce their workload.

[0159] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, an artificial intelligence-based smart classroom management method is implemented, comprising the following steps: obtaining class scheduling information, and obtaining target teaching information based on the class scheduling information; scheduling teacher resources, classroom resources, and teaching equipment resources based on the target teaching information and the teaching plan; determining the resource allocation for teaching based on the results of scheduling teacher resources, classroom resources, and teaching equipment resources; obtaining classroom environment information in real time, wherein the environment information includes student learning behavior data and teacher teaching behavior data; analyzing the student learning behavior data through data mining and machine learning, determining the student learning progress in real time, and generating a personalized progress report; and generating personalized teaching materials, learning method suggestions, and practice assignments based on the personalized progress report and teaching content through natural language processing and recommendation system technology.

[0160] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided in this application and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0161] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, device, article or method including the element.

[0162] The above description is only a preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made through the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A smart classroom management method based on artificial intelligence, characterized in that: The method comprises: Obtaining class schedule information and teaching plans, and obtaining target teaching information according to the class schedule information; Based on the target teaching information and teaching plan, dispatch teacher resources, classroom resources and teaching equipment resources; Determine the resource allocation for teaching according to the result of scheduling teacher resources, classroom resources and teaching equipment resources; Obtain classroom environment information in real time, including student learning behavior data and teacher teaching behavior data; Analyze the student learning behavior data through data mining and machine learning, determine the student learning progress in real time, and generate personalized progress reports; Based on the personalized progress report and teaching content, generate personalized teaching materials, learning method suggestions and practice homework through natural language processing and recommendation system technology; When scheduling teacher resources, classroom resources and teaching equipment resources, including minimizing the cost of resource allocation, the steps include: setting a linear programming model, scheduling the teacher resources, classroom resources and teaching equipment resources through the linear programming model; and minimizing the cost of resource allocation through the objective function calculation of the linear programming model; After resource allocation, when adjustments are needed due to various reasons, dynamic resource allocation is used to automatically adjust classroom allocation according to real-time usage needs and available resources to minimize the impact on teaching. Specifically, when there is a temporary equipment failure in the classroom resources, the cause of the failure is analyzed through a preset model; the repair time required for the cause of the failure is analyzed by collecting historical maintenance data, including maintenance type, maintenance time, required materials and labor; using machine learning algorithms, the repair time of the current failure is predicted based on historical data; based on uncertainty assessment, the prediction model provides a probability distribution of the repair time, considering the shortest, most likely and longest Maintenance time, and analyze the impact of the classroom scheduling plan on the course schedule, students and teachers, and whether the resources of the spare classroom meet the course requirements; combined with the resources, impact and maintenance time of the spare classroom, the resources, impact and maintenance time of the spare classroom are input into the decision algorithm, a decision tree is established through the decision algorithm, and the urgency of maintenance, the importance of the course, and the availability factors of the spare classroom are inferred through the decision tree; according to the result of the decision tree reasoning, the result of the reasoning is quantified to obtain the recommendation coefficient of classroom scheduling and the recommendation coefficient of classroom resource maintenance, wherein the larger the recommendation coefficient, the higher the degree of execution of the recommendation.

2. The method for managing a smart classroom based on artificial intelligence according to claim 1, characterized in that: The scheduling of teacher resources, classroom resources and teaching equipment resources based on the target teaching information and teaching plan includes: Obtain target teaching information from the teacher, including course objectives, knowledge point objectives, and skill objectives; Obtaining the teaching plan, including teaching cycle, course schedule and teaching links; Integrate the target teaching information and the teaching plan to obtain a teaching strategy; According to the course arrangement described in the teaching strategy, calculate the number of teachers required for each course and the professional background resource requirements of teachers; According to the course arrangement in the teaching strategy, calculate the classroom capacity and hardware facility resource requirements for each course; According to the teaching links in the teaching strategy, calculate the required projection equipment and experimental equipment resource requirements; Based on the calculated teacher resource demand, classroom resource demand and teaching equipment resource demand, relevant resources are scheduled.

3. The method for managing a smart classroom based on artificial intelligence according to claim 2, characterized in that: After the step of scheduling relevant resources based on the calculated teacher resource requirements, classroom resource requirements and teaching equipment resource requirements, the following steps are also included: Check whether the allocation of teacher resources is reasonable and whether the professional background of teachers meets the course requirements; Check whether the allocation of classroom resources is reasonable and whether the hardware facilities meet the course requirements; Check whether the allocation of teaching equipment resources is reasonable and whether the equipment can meet the needs of teaching activities; Based on the results of the above detection and evaluation, the scheduling strategy is adjusted.

4. The method for managing a smart classroom based on artificial intelligence according to claim 1, characterized in that: The method of analyzing the student learning behavior data through data mining and machine learning, determining the student learning progress in real time, and generating a personalized progress report includes: Collect students' clicks, browsing, questions, and homework completion behavior data during the learning process; Clean, denoise, select features, and perform feature engineering on the collected raw behavior data to obtain a processed data set; Using a machine learning algorithm to train a model, inputting the processed data set into the model, and outputting the student's current learning progress through the model; Generate a personalized progress report based on the learning progress and historical learning habits.

5. The method for managing a smart classroom based on artificial intelligence according to claim 1, characterized in that: The method further comprises: Collect the student's learning behavior data, including student click rate, learning time, and correct answer rate; Based on the student learning behavior data, use time series analysis algorithm to predict students' future learning interests and needs; Adjust instructional content, teaching strategies, and resource allocation based on predicted student interests and needs; Combined with student portraits, collaborative filtering algorithms are used to recommend personalized learning paths and teaching resources for students, and students’ feedback on recommended content is collected in real time to adjust recommendation strategies; Through machine learning algorithms, cluster analysis of students’ learning progress is performed to identify students’ learning difficulties and weaknesses; Based on the students' learning difficulties and weak links, and combining the teaching content with the students' characteristics, we generate personalized tutoring plans and teaching resources.

6. The method for managing a smart classroom based on artificial intelligence according to claim 1, characterized in that: The method further comprises: Collecting the teacher's teaching behavior data, including teaching content, teaching methods and teaching evaluation; Based on the teacher's teaching behavior data, the teaching quality is evaluated using a teaching effectiveness evaluation model; According to the teaching effect evaluation results, the decision tree algorithm is used to provide teachers with targeted teaching improvement suggestions; Combined with teacher portraits, association rule mining algorithms are used to discover problems and improvement directions in the teaching process; Provide real-time teaching support and guidance for the problems encountered by the teachers in the teaching process; Through artificial neural network algorithms, the degree to which teachers adopt teaching improvement suggestions can be predicted, the recommendation strategy can be optimized, and the teaching effectiveness of teachers can be tracked to adjust teaching methods and strategies.

7. The method for managing a smart classroom based on artificial intelligence according to claim 5, characterized in that: The method combines student portraits, uses collaborative filtering algorithms to recommend personalized learning paths and teaching resources to students, collects students’ feedback on recommended content in real time, and adjusts recommendation strategies, including: Collect students’ basic information, learning behavior data, and learning preferences; Constructing a student profile based on the student's basic information, learning behavior data, and learning preferences; Based on the student portrait, the similarity between different teaching resources is calculated by the collaborative filtering algorithm, teaching resources similar to the teaching resources previously liked by the student are found, and a recommendation list is generated and sent to the student end; Collect student feedback in real time and adjust the recommendation strategy based on the feedback information.

8. An artificial intelligence-based smart classroom management system, used in the method described in any one of claims 1 to 7, characterized in that: include: A first acquisition module is used to acquire class scheduling information, and acquire target teaching information according to the class scheduling information; A scheduling module, used for scheduling teacher resources, classroom resources and teaching equipment resources based on the target teaching information and teaching plan; An allocation module, used to determine the resource allocation for teaching according to the result of scheduling teacher resources, classroom resources and teaching equipment resources; The second acquisition module is used to acquire classroom environment information in real time, wherein the environment information includes students' learning behavior data and teachers' teaching behavior data; A judgment module is used to analyze the student learning behavior data through data mining and machine learning, judge the student's learning progress in real time, and generate a personalized progress report; A generation module is used to generate personalized teaching materials, learning method suggestions and practice assignments based on the personalized progress report and teaching content through natural language processing and recommendation system technology.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images