An automatic teaching and course scheduling system based on artificial intelligence

Abstract

The present invention relates to the field of educational information technology, and specifically to an automatic teaching affairs scheduling system based on artificial intelligence, including a student learning path optimization module, a multi-party interest balancing module based on game theory, an intelligent conflict resolution module, a dynamic demand adjustment module, and a resource optimization allocation module, wherein: the student learning path optimization module analyzes students' historical data; the multi-party interest balancing module based on game theory balances the interests of teachers, students and school managers; the intelligent conflict resolution module detects conflict problems in the preliminary scheduling plan; the dynamic demand adjustment module dynamically adjusts the scheduling plan according to real-time changing needs; and the resource optimization allocation module monitors and optimizes the school's teaching resources in real time after the scheduling plan is determined. The present invention improves the overall teaching efficiency and education quality, and achieves the harmonious unity of the interests of multiple parties.

Description

Technical Field

[0001] The present invention relates to the field of educational information technology, and in particular to an automatic teaching and class scheduling system based on artificial intelligence. Background Art

[0002] With the continuous development of the education system and the increasing abundance of educational resources, colleges and educational institutions are facing increasingly complex challenges in course scheduling and resource management. Traditional academic scheduling systems often rely on manual experience and simple rule settings to formulate course schedules. This approach has obvious limitations in dealing with complex teaching needs, dynamically changing student and teacher needs, and efficient use of resources. At the same time, with the increasing demand for personalized education, how to meet students' personalized learning paths while taking into account teachers' teaching time preferences and efficient use of school resources has become a problem that needs to be solved urgently.

[0003] Existing academic scheduling systems generally lack intelligence and dynamic adjustment capabilities, and are unable to effectively deal with the balance between the interests of multiple parties. Traditional systems usually only consider simple factors such as time and space, lack in-depth analysis of students' personalized needs and reasonable allocation of teachers and resources. In addition, existing technologies are often unable to respond quickly to temporary changes in demand (such as adding new courses or adjusting teacher time), resulting in rigid scheduling plans, insufficient resource utilization, and even possible resource conflicts. This scheduling method that lacks intelligence and dynamic adaptability not only affects teaching quality and management efficiency, but also reduces student and teacher satisfaction.

[0004] The present invention aims to provide an automatic teaching and class scheduling system based on artificial intelligence, which improves the overall efficiency and quality of teaching management and meets the requirements of modern education management for flexibility and efficiency. Summary of the invention

[0005] The invention provides an automatic teaching affairs and class scheduling system based on artificial intelligence.

[0006] An automatic teaching and course scheduling system based on artificial intelligence includes a student learning path optimization module, a multi-party interest balancing module based on game theory, an intelligent conflict resolution module, a dynamic demand adjustment module and a resource optimization allocation module, wherein;

[0007] The student learning path optimization module analyzes the student's historical data, including grades, interests and hobbies, and career planning, and generates optimized learning path suggestions;

[0008] The multi-party interest balancing module based on game theory balances the interests of teachers, students and school administrators through the game theory model, and generates a preliminary course scheduling plan in combination with the optimized learning path suggestions, which specifically includes:

[0009] Collecting interests and demands: Collecting the interests and demands of teachers, students, and school administrators, including teachers' teaching time preferences, students' course selection requirements, and the school's resource utilization priorities, and quantifying the interests and demands of all parties to generate a set of strategies in the game theory model;

[0010] Strategy analysis and balance optimization: Based on the generated strategy set, the game theory algorithm is used to perform strategy analysis, simulate the gains and losses of each party under different plans, and optimize and generate a class scheduling plan that balances the interests of multiple parties;

[0011] The intelligent conflict resolution module detects conflict problems in the preliminary course scheduling plan, including course time conflicts, teacher time conflicts and resource conflicts. After detecting the conflict problems, the course scheduling plan is adjusted in real time by simulating multiple solutions;

[0012] The dynamic demand adjustment module dynamically adjusts the class scheduling plan according to real-time changing needs (such as adding new courses or adjusting teacher schedules in the middle of a semester);

[0013] After the class schedule is determined, the resource optimization allocation module conducts real-time monitoring and optimization allocation of the school's teaching resources, which include classrooms, laboratories, sports facilities, library learning spaces, professional workshops, computing resources, and multi-purpose halls.

[0014] Optionally, the student learning path optimization module includes:

[0015] Data collection and preprocessing: Collect students' historical data, including grades (such as GPA, grades in various subjects, etc.), interests and hobbies (obtained through questionnaires or analysis of historical course selection records), and career plans (such as career goals and relevant course requirements filled in by students), and standardize the historical data;

[0016] Multi-objective optimization model construction: We use weighted linear combination to conduct comprehensive analysis on different historical data and construct a multi-objective optimization model, which is expressed as:

[0017] ;

[0018] in, is the comprehensive score, Scoring students' grades, Score the relevance of student interests to the course, Score the match between the course and career plan, , , are the weights of each factor respectively;

[0019] Course matching: Based on the multi-objective optimization model, calculate the comprehensive score of each course , expressed as:

[0020] ;

[0021] in, , , Courses Scores on grades, interests and career plans, , , are the corresponding weights respectively;

[0022] Path generation: All courses are sorted according to the comprehensive score of each course, and a dynamic programming algorithm is used to generate an optimized learning path based on the student's semester credit limit and course prerequisite constraints.

[0023] Optionally, the dynamic programming algorithm includes:

[0024] Collect course information: Collect information for each course Comprehensive score , each course Credits , each course Prerequisite courses ;

[0025] Define state variables: Before Among the courses, the total credits should not exceed The maximum combined score for a course combination that meets the prerequisites is ;

[0026] Initialization state: If you have not selected any courses, initialize , indicating that the score is 0 if no course is selected;

[0027] Go through each course : For each course , from the total number of credits Start traversing downwards, making sure each course is considered only once. There are prerequisite courses , then you are allowed to take the course only if you meet the prerequisites;

[0028] State Transfer Equation: If you do not choose this course , then the state transfer equation is:

[0029] If you choose a course , and meet the prerequisites , then the total number of credits is guaranteed Greater than or equal to the course credits Under the premise of , the state transfer equation is:

[0030] ;

[0031] The final state transfer equation is:

[0032] ;

[0033] Prerequisite course constraint: When calculating state transitions, add a prerequisite course check. If the course Prerequisite courses ,but Updates where prerequisite courses have been taken;

[0034] Determine the optimal solution: traverse all courses Total credits And the total score , the comprehensive score of the optimal learning path is expressed as:

[0035] dp n [ max _ credits ] k ;

[0036] in, is the total number of courses, For semester credit limit, final selection The largest path;

[0037] Tracing the path backwards: From the state matrix The last item dp n [ max _ credits ] k First, trace back the choices made at each step to determine the courses selected into the optimal learning path;

[0038] Output optimal learning path: Output the generated learning path, including the selected courses and their sequence, and verify whether it meets all prerequisites and credit limits;

[0039] Credit and score verification: Verify that the total number of credits in the path does not exceed the semester credit limit, and check whether the total score is consistent with the semester credit limit. dp n [ max _ credits ] k Consistent.

[0040] Optionally, the interest demand collection includes:

[0041] Collection and quantification of teachers’ teaching time preferences: Through data questionnaires and historical teaching records, we collect each teacher’s teaching time preference data, including available time periods, priority time periods, and unavailable time periods. We also quantify the collected teaching time preference data, perform weighted processing based on the importance of the time periods, and generate a set of teacher teaching time preference strategies. , expressed as:

[0042] ;

[0043] in, For every teacher Teaching time Quantitative rating of For Teachers For time period preference scores (e.g., priority time periods have higher scores, non-priority time periods have lower scores, and unavailable time periods have a score of 0), is the importance weight of the time period;

[0044] ;

[0045] in, The total number of time slots available for teachers;

[0046] Collection and quantification of students’ course selection needs: Through the student course selection platform, interest surveys, and career planning, students’ course selection demand data is collected, including priority elective courses, required courses, and elective courses. The collected course selection demand data is quantified, and the demand priority and interest score of each course are weighted to generate a set of student course selection demand strategies. , expressed as:

[0047] ;

[0048] in, For each student Courses Quantitative rating of and are the weights of course priority and interest, For Courses For students Prioritize the needs of students (e.g., required courses have the highest scores, and elective courses have lower scores based on student interests), For Students About Courses interest score (e.g. determined through a questionnaire or historical data);

[0049] ;

[0050] in, The total number of courses available to students;

[0051] Collection and quantification of school resource utilization priorities: Through the school resource management platform, the school's resource utilization data, including the utilization and priority information of classrooms, laboratories, and equipment, is collected and quantified. By weighting the utilization and availability of resources in different time periods, a set of school resource utilization priority strategies is generated. , expressed as:

[0052] ;

[0053] in, Resources for every school In time period Quantitative scoring of utilization priority, For resources In time period utilization of the classroom or laboratory, for example, For resources In time period availability (e.g. whether the classroom is vacant), and are the weights of resource utilization and availability, respectively;

[0054] ;

[0055] in, is the total number of time periods for resource utilization;

[0056] Generating a strategy set: Comprehensive teacher teaching time preference strategy set , Student course selection demand strategy set , School resource utilization priority strategy set , forming a set of strategies in the game theory model.

[0057] Optionally, the generation strategy set includes:

[0058] Basic construction of strategy set: teachers’ teaching time preference strategy set , Student course selection demand strategy set , School resource utilization priority strategy set The sets are combined into a global strategy set, expressed as:

[0059] ;

[0060] Weight allocation and strategy combination: Assign a weight to each strategy set to indicate the relative importance of the interests of all parties, and generate a comprehensive strategy set while balancing the interests of all parties, expressed as:

[0061] ;

[0062] in, is the weight of the teacher's strategy set, is the weight of the student strategy set, is the weight of the set of school resource strategies;

[0063] Strategy set in game theory model: The generated comprehensive strategy set is used as the input of the game theory model, and the equilibrium point is found through simulation and optimization, which is expressed as:

[0064] ;

[0065] in, is the utility function of each strategy set in the game theory model;

[0066] Equilibrium solution in the game theory model: By analyzing the comprehensive strategy set, the optimal solution that balances the interests of all parties is found, which is expressed as:

[0067] ;

[0068] in, Represents the set of equilibrium strategies reached in the game theory model.

[0069] Optionally, the strategy analysis and balance optimization include:

[0070] Strategy analysis and simulation: In the game theory model, by simulating different strategy combinations (in Represents different strategy choices) to analyze the changes in the utility values ​​of each party under different strategy combinations and evaluate the gains and losses of each party, expressed as:

[0071] ;

[0072] in, For Teachers In the The choice under the strategy, For Students In the The choice under the strategy, For school administrators or school resources In the The choice under the strategy, For the strategy combination The utility value or benefit of the following participants (teachers, students or school administrators), For the strategy combination The sum of the overall utility values ​​of all participants (teachers, students and school administrators);

[0073] ;

[0074] in, Indicates the participants In the strategy portfolio Relative to the benchmark strategy portfolio changes in utility;

[0075] ;

[0076] in, The total benefits and losses of all parties involved;

[0077] Generation of optimization and equilibrium solutions: All strategy combinations are optimized through the Nash equilibrium algorithm, and a strategy combination is selected that balances the utility of all parties and has the highest overall utility value.

[0078] Optionally, the Nash equilibrium algorithm includes:

[0079] Construct all strategy combinations: Consider all the strategy combinations of the participating parties ,in , , An index representing different strategy choices;

[0080] Calculate the total utility value of each strategy combination: For each strategy combination , calculate the total utility value , expressed as:

[0081] ;

[0082] in, Indicates the parties involved;

[0083] Finding Nash equilibrium: For each participant Find the optimal strategy when the strategies of other participants remain unchanged , Nash equilibrium point The conditions for satisfying are:

[0084] ;

[0085] in, For any other strategy, The first The optimal strategy for each participant is For the The strategy combination of the remaining participants other than the participants;

[0086] Select the strategy combination that makes the overall utility value the highest: After finding all Nash equilibrium points, select the strategy combination with the highest total utility value as the final optimal strategy, expressed as:

[0087] ;

[0088] in, represents the optimal strategy combination selected by optimization.

[0089] Optionally, the intelligent conflict resolution module includes:

[0090] Conflict detection: Conflict detection is performed on the preliminary course scheduling plan, including course time conflict detection, teacher time conflict detection and resource conflict detection;

[0091] The course time conflict detection is defined as when multiple courses are scheduled in the same time slot and have at least one common student;

[0092] The teacher time conflict detection is defined as when the same teacher is scheduled to teach multiple courses in the same time period;

[0093] The resource conflict is defined as when multiple courses have a demand for the same teaching resource in the same time period;

[0094] Simulate multiple solutions: After a conflict is detected, multiple solutions are simulated to resolve the conflict, including modifying the time slot of the conflicting course, reallocating the teacher's teaching time, and reallocating teaching resources;

[0095] Adjust the class scheduling plan in real time: Based on the simulated solutions, select the solution with the least conflict and the highest overall utility value, and adjust the preliminary class scheduling plan in real time.

[0096] Optionally, the dynamic demand adjustment module includes:

[0097] Real-time demand monitoring: Real-time monitoring of demand changes that occur during the teaching process, including new courses, cancelled courses, teacher schedule adjustments, student course selection changes, and emergency resource deployment;

[0098] Evaluate the impact of adjustments: After detecting changes in demand, evaluate the impact of changes in demand on the existing scheduling plan, including the impact on course schedules, teacher schedules, and resource allocation, expressed as:

[0099] ;

[0100] in, is a comprehensive score of the overall adjustment impact. To understand the impact of changing demand on course schedules, To understand the impact of changing demand on teachers’ schedules, The impact of demand changes on resource allocation, are the weights of time impact, teacher impact, and resource impact respectively;

[0101] Dynamically adjust the class schedule: Based on the evaluation results, dynamically generate adjustment plans, giving priority to adjustments that have the least impact on the existing plan and meet new needs.

[0102] Optionally, the resource optimization allocation module includes:

[0103] Real-time monitoring: Real-time monitoring of all teaching resources to obtain the current usage status, occupancy time, and idle time periods of resources. The monitoring content includes the utilization of classrooms, laboratories, sports facilities, library learning spaces, professional workshops, computing resources, and multi-purpose halls;

[0104] Resource utilization evaluation: Based on real-time monitoring data, the utilization of various teaching resources is evaluated and the efficiency of current resource utilization is calculated. The evaluation content includes resource idle rate, occupation conflict rate and resource scheduling flexibility;

[0105] Generation of optimal allocation strategy: Generate optimal resource allocation strategy based on the evaluation results. The optimal allocation strategy includes adjusting the resource allocation of courses, changing the time period for resource use, or reallocating resources.

[0106] Beneficial effects of the present invention:

[0107] The present invention, through the student learning path optimization module, combines the student's historical data, interests and hobbies, and career planning to intelligently generate optimized learning path suggestions, and through the multi-party interest balancing module based on game theory, balances the interests of teachers, students, and school administrators to ensure that the generated preliminary class scheduling plan meets the personalized needs of students while reasonably considering the interests of all parties. This intelligent path planning and interest balancing mechanism improves the overall teaching efficiency and education quality, and achieves the harmonious unity of the interests of multiple parties.

[0108] The present invention can monitor and respond to various conflicts and demand changes that occur in the teaching process in real time through an intelligent conflict resolution module and a dynamic demand adjustment module. The intelligent conflict resolution module detects conflicts among course time, teacher time and resource allocation, simulates and selects the optimal adjustment plan to ensure the rationality and feasibility of the class scheduling plan. The dynamic demand adjustment module monitors changes in teaching demand in real time and dynamically adjusts the class scheduling plan according to the impact assessment results to ensure that the plan has the least impact on the existing arrangements and can quickly respond to sudden demands, thereby enhancing the flexibility and adaptability of the system.

[0109] The present invention ensures that various resources (including classrooms, laboratories, sports facilities, etc.) are utilized to the maximum extent by monitoring the utilization of the school's teaching resources in real time, evaluating the utilization efficiency of resources, and generating an optimized allocation strategy. It can reduce resource conflicts, improve the flexibility of resource scheduling, and optimize the overall teaching arrangement, thereby ensuring the smooth progress of teaching activities and improving the school's resource utilization efficiency and user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0110] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0111] Figure 1 A schematic diagram of system function modules according to an embodiment of the present invention;

[0112] Figure 2 Schematic diagram of a multi-party interest balancing module based on game theory in an embodiment of the present invention. DETAILED DESCRIPTION

[0113] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0114] It should be noted that the references to "one embodiment", "embodiment", "exemplary embodiments", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0115] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0116] like Figure 1-Figure 2 As shown, an automatic teaching and course scheduling system based on artificial intelligence includes a student learning path optimization module, a multi-party interest balancing module based on game theory, an intelligent conflict resolution module, a dynamic demand adjustment module and a resource optimization allocation module, wherein;

[0117] The student learning path optimization module analyzes students' historical data, including grades, interests and hobbies, and career plans, and generates optimized learning path suggestions;

[0118] The multi-party interest balance module based on game theory balances the interests of teachers, students and school administrators through the game theory model, and generates a preliminary class scheduling plan based on the optimized learning path suggestions to ensure that the interests of all parties are reasonably considered under the premise of satisfying the optimization of students' learning paths. Specifically, it includes:

[0119] Collecting interests and demands: Collecting the interests and demands of teachers, students, and school administrators, including teachers' teaching time preferences, students' course selection requirements, and the school's resource utilization priorities, and quantifying the interests and demands of all parties to generate a set of strategies in the game theory model;

[0120] Strategy analysis and balance optimization: Based on the generated strategy set, the game theory algorithm is used to perform strategy analysis, simulate the gains and losses of each party under different plans, and optimize and generate a class scheduling plan that balances the interests of multiple parties;

[0121] The intelligent conflict resolution module detects conflict issues in the preliminary class scheduling plan, including course time conflicts, teacher time conflicts and resource conflicts. After detecting the conflict issues, it simulates multiple solutions and adjusts the class scheduling plan in real time to ensure its rationality and feasibility.

[0122] The dynamic demand adjustment module dynamically adjusts the class schedule according to real-time changing needs (such as adding new courses or adjusting teacher schedules in the middle of a semester);

[0123] After the class schedule is determined, the resource optimization allocation module monitors and optimizes the allocation of the school's teaching resources in real time. Teaching resources include classrooms, laboratories, sports facilities, library learning spaces, professional workshops, computing resources, and multi-functional halls. Through dynamic analysis of the use of teaching resources, resource utilization can be maximized.

[0124] Through the above content, the whole process of automated academic scheduling is realized, from optimization of students' personalized learning paths to balancing the interests of multiple parties, conflict resolution, real-time adjustment and resource optimization. It can dynamically adapt to complex teaching needs and conflicts of interest among multiple parties, ensure the rationality, flexibility and efficient resource utilization of the scheduling plan, and provide a highly intelligent and optimized solution for the school's academic management.

[0125] The student learning path optimization module includes:

[0126] Data collection and preprocessing: Collect students' historical data, including grades (such as GPA, grades in various subjects, etc.), interests and hobbies (obtained through questionnaires or analysis of historical course selection records), and career plans (such as career goals and relevant course requirements filled in by students), and standardize the historical data to ensure that the dimensions of each data item are consistent, and improve data quality by filling in missing values ​​and processing outliers;

[0127] Multi-objective optimization model construction: We use weighted linear combination to conduct comprehensive analysis on different historical data and construct a multi-objective optimization model, which is expressed as:

[0128] ;

[0129] in, is the comprehensive score, is the student's score, obtained by normalizing the historical scores. Score the relevance of student interests to courses, calculated based on the cosine similarity between interest data and course content. The score for the matching between the course and career planning is calculated by analyzing the correlation between the skills required for career planning and the course content. , , are the weights of each factor respectively;

[0130] Course matching: Based on the multi-objective optimization model, calculate the comprehensive score of each course , expressed as:

[0131] ;

[0132] in, , , Courses Scores on grades, interests and career plans, , , are the corresponding weights respectively;

[0133] Path generation: All courses are sorted according to the comprehensive score of each course, and the dynamic programming algorithm is used to generate an optimized learning path based on the student's semester credit limit and course prerequisite constraints;

[0134] Student's grade score The calculation formula is:

[0135] ;

[0136] in, represents the average score of students, and are the lowest and highest values ​​of all students in the system. , through normalization, the performance scores are converted to the range of 0 to 1;

[0137] Student interest and course relevance score The calculation formula is:

[0138] ;

[0139] in, To rate students' areas of interest, Ratings for the course content in the corresponding areas, is the total number of matches between interest areas and course content, cosine similarity The value of is between 0 and 1, indicating the matching degree between interest and course content;

[0140] Course and career planning matching score The calculation formula is:

[0141] ;

[0142] in, Score the skills needed for career planning, Score the skills match of the course content, The number of skills required for the student's career planning goals.

[0143] course Scores for academic performance, interests, and career plans , , The calculation formula is:

[0144] ;

[0145] in, is the student's grade in the course, after normalization. and The lowest and highest ;

[0146] ;

[0147] in, For students in areas of interest Interest score, For Courses In the field of interest The matching score on

[0148] ;

[0149] in, For career planning The demand score of each skill, For Courses In the field of professional skills The matching score of .

[0150] Weight , , The setting basis and range are expressed as:

[0151] The setting of is based on the importance that the school places on students’ academic performance. For courses or education systems with a strong academic orientation, performance may account for a higher proportion. The value range is: , the specific value is 0.5;

[0152] The setting basis is the importance of students' personal interests in the learning path. Personalized learning often pays more attention to students' interests and elective intentions. Especially in elective courses or diversified course systems, the weight of interest may be relatively high. The value range is: , the specific value is 0.3;

[0153] The basis for setting is the importance of career planning in students' future development. Especially in career-oriented education, the matching degree of relevant courses in career planning is particularly critical. The value range is: , the specific value is 0.2.

[0154] Weight , , The setting basis and range are expressed as:

[0155] The basis for setting is to measure the importance of student grades in course matching. In some course systems or educational environments, students' academic grades may be an important basis for class scheduling and course matching, so they will be given a higher weight. Especially for academic-oriented courses, the weight of grades is usually higher. The value range is: , the specific value is 0.5;

[0156] The setting basis is to reflect the importance of students' personal interests in course matching. The personalized learning system pays more attention to recommending courses based on students' interests, so it will assign a higher weight to students' interests. Especially in the elective course system, interest orientation is the key factor in course recommendation. The value range is: , the specific value is 0.3;

[0157] The basis for setting is to reflect the correlation between students' future career development plans and course matching. In a career-oriented education environment, the school hopes to help students choose courses that are closely related to their career plans. Therefore, a certain weight will be given to the matching degree of career planning. The value range is: , the specific value is 0.2.

[0158] Through the above content, it is possible to intelligently balance grades, interests and career planning, and provide personalized, data-driven learning suggestions, so that students can obtain the best learning experience and results within limited credits, thereby improving overall teaching efficiency and education quality.

[0159] Dynamic programming algorithms include:

[0160] Collect course information: Collect information for each course Comprehensive score , each course Credits , each course Prerequisite courses ;

[0161] Define state variables: Before Among the courses, the total credits should not exceed The maximum combined score for a course combination that meets the prerequisites is ;

[0162] Initialization state: If you have not selected any courses, initialize , indicating that the score is 0 if no course is selected;

[0163] Go through each course : For each course , from the total number of credits Start traversing downwards, making sure each course is considered only once. There are prerequisite courses , then you are allowed to take the course only if you meet the prerequisites;

[0164] State Transfer Equation: If you do not choose this course , then the state transfer equation is:

[0165] If you choose a course , and meet the prerequisites , then the total number of credits is guaranteed Greater than or equal to the course credits Under the premise of , the state transfer equation is:

[0166] ;

[0167] The final state transfer equation is:

[0168] ;

[0169] Prerequisite course constraint: When calculating state transitions, add a prerequisite course check. If the course Prerequisite courses ,but Updates where prerequisite courses have been taken;

[0170] Determine the optimal solution: traverse all courses Total credits And the total score , the comprehensive score of the optimal learning path is expressed as:

[0171] dp n [ max _ credits ] k ;

[0172] in, is the total number of courses, For semester credit limit, final selection The largest path;

[0173] Tracing the path backwards: From the state matrix The last item dp n [ max _ credits ] k First, trace back the choices made at each step to determine the courses selected into the optimal learning path;

[0174] Output optimal learning path: Output the generated learning path, including the selected courses and their sequence, and verify whether it meets all prerequisites and credit limits;

[0175] Credit and score verification: Verify that the total number of credits in the path does not exceed the semester credit limit, and check whether the total score is consistent with the semester credit limit. dp n [ max _ credits ] k Consistency;

[0176] The prerequisite course relationship is Boolean quantified and is determined based on whether the prerequisite conditions are met, expressed as:

[0177] If the student has completed the prerequisite courses, the prerequisite relationship If the student has not completed the required prerequisite courses, the prerequisite relationship ;

[0178] Through the above content, it is more efficient and applicable when dealing with complex course prerequisite relationships and credit restrictions, and can dynamically generate the optimal learning path to maximize students' comprehensive scores while ensuring the legitimacy and rationality of the path.

[0179] Benefit demand collection includes:

[0180] Collection and quantification of teachers’ teaching time preferences: Through data questionnaires and historical teaching records, we collect each teacher’s teaching time preference data, including available time periods, priority time periods, and unavailable time periods. We also quantify the collected teaching time preference data, perform weighted processing based on the importance of the time periods, and generate a set of teacher teaching time preference strategies. , expressed as:

[0181] ;

[0182] in, For every teacher Teaching time Quantitative rating of For Teachers For time period preference scores (e.g., priority time periods have higher scores, non-priority time periods have lower scores, and unavailable time periods have a score of 0), is the importance weight of the time period;

[0183] ;

[0184] in, The total number of time slots available for teachers;

[0185] Collection and quantification of students’ course selection needs: Through the student course selection platform, interest surveys, and career planning, students’ course selection demand data is collected, including priority elective courses, required courses, and elective courses. The collected course selection demand data is quantified, and the demand priority and interest score of each course are weighted to generate a set of student course selection demand strategies. , expressed as:

[0186] ;

[0187] in, For each student Courses Quantitative rating of and are the weights of course priority and interest, For Courses For students Prioritize the needs of students (e.g., required courses have the highest scores, and elective courses have lower scores based on student interests), For Students About Courses interest score (e.g. determined through a questionnaire or historical data);

[0188] ;

[0189] in, The total number of courses available to students;

[0190] Collection and quantification of school resource utilization priorities: Through the school resource management platform, the school's resource utilization data, including the utilization and priority information of classrooms, laboratories, and equipment, is collected and quantified. By weighting the utilization and availability of resources in different time periods, a set of school resource utilization priority strategies is generated. , expressed as:

[0191] ;

[0192] in, Resources for every school In time period Quantitative scoring of utilization priority. For resources In time period utilization of the classroom or laboratory, for example, For resources In time period availability (e.g. whether the classroom is vacant), and are the weights of resource utilization and availability, respectively;

[0193] ;

[0194] in, is the total number of time periods for resource utilization;

[0195] Generating a strategy set: Comprehensive teacher teaching time preference strategy set , Student course selection demand strategy set , School resource utilization priority strategy set , forming a set of strategies in the game theory model;

[0196] Importance weight of time period The setting basis is to reflect the preferences of teachers or students for different time periods. Teachers or students may have preferences for certain time periods (such as giving priority to morning classes and avoiding afternoon classes). These preferences may be related to their habits, course effects, etc. The value range is The larger the weight value, the higher the priority of the time period. The value for the morning time period is 0.8, the value for the afternoon time period is 0.5, and the value for the evening time period is 0.2.

[0197] Course Priority Weight The setting basis is to reflect the priority of certain courses, mainly considering the different importance of required courses, elective courses and interest courses. For example, required courses may have a higher priority, while elective courses have a lower priority. The value range is , the value of required courses is 0.7, the value of elective courses is 0.3, and the value of interest-driven courses is 0.6;

[0198] Course interest weight The setting basis is the importance of students' personal interests in course selection. Personalized education often gives higher weight to interests to help students choose courses that are more in line with their personal interests. The value range is , the value of required courses is 0.7, the value of elective courses is 0.3, and the value of interest-driven courses is 0.6;

[0199] Resource utilization weight The setting of is based on the frequency and demand of a certain teaching resource (such as classrooms, laboratories, etc.). Frequently used resources are usually more popular, so higher weights are assigned to ensure efficient use of these resources. The value range is , the value of high-usage resources is 0.7, and the value of low-usage resources is 0.3;

[0200] Resource availability weight The setting basis is to reflect the flexibility of whether the resource is available. For example, some classrooms may be relatively idle during a specific time period, so the availability weight is higher. The value range is , the value for high availability resources is 0.8, and the value for low availability resources is 0.2.

[0201] Through the above content, we quantify teachers' teaching time preferences, students' course selection needs and the school's resource utilization priorities, and generate a set of strategies in the game theory model, ensuring that the interests of multiple parties are reasonably reflected in the scheduling plan, providing a solid foundation for the final optimization of scheduling.

[0202] The set of generation strategies includes:

[0203] Basic construction of strategy set: teachers’ teaching time preference strategy set , Student course selection demand strategy set , School resource utilization priority strategy set The sets are combined into a global strategy set, expressed as:

[0204] ;

[0205] Weight allocation and strategy combination: Assign a weight to each strategy set to indicate the relative importance of the interests of all parties, and generate a comprehensive strategy set while balancing the interests of all parties, expressed as:

[0206] ;

[0207] in, is the weight of the teacher's strategy set, reflecting the importance of the teacher's time preference in the overall strategy, is the weight of the student strategy set, reflecting the relative importance of the student's course selection needs, is the weight of the school resource strategy set, reflecting the importance of resource utilization priority in the class scheduling plan;

[0208] Strategy set in game theory model: The generated comprehensive strategy set is used as the input of the game theory model. Through simulation and optimization, the equilibrium point is found to ensure that the interests of all parties are reasonably balanced, which is expressed as:

[0209] ;

[0210] in, is the utility function of each strategy set in the game theory model. By maximizing the overall utility, the model finds the optimal strategy combination;

[0211] Equilibrium solution in the game theory model: By analyzing the comprehensive strategy set, the optimal solution that balances the interests of all parties is found, which is expressed as:

[0212] ;

[0213] in, It represents the set of equilibrium strategies reached in the game theory model, representing the optimal strategies of teachers, students and school administrators in scheduling classes;

[0214] Weight The setting basis and value range include:

[0215] Weight The basis for setting is to reflect the relative importance of teachers in the class scheduling plan. For example, if the school pays more attention to the teacher's teaching time preference or the teacher's teaching needs, a higher weight can be set. The teacher's time arrangement often has a greater impact on the class scheduling, especially when teacher resources are tight. The value range is , the value is 0.5;

[0216] Weight The setting basis is to reflect the priority of students' needs and interests in the course scheduling plan. In personalized education, students' course selection and interests are often the core, so the system with higher student weights can better support personalized path planning. The value range is , the value is 0.3;

[0217] Weight The setting basis is the degree to which the school attaches importance to the efficiency of resource utilization when scheduling classes. When school resources (such as classrooms, laboratories, libraries, etc.) are limited, the system needs to balance the utilization rate and availability of these resources. The value range is , the value is 0.2;

[0218] Through the above content, we ensure that the class scheduling plan can not only meet the personalized needs of teachers and students, but also optimize the utilization rate of school resources. We can generate a class scheduling plan that achieves the best balance between the interests of multiple parties, improve the efficiency and satisfaction of overall teaching management, and take into account the core needs of all parties.

[0219] Utility Function By calculating the weighted scores in the strategy sets of all parties, the comprehensive utility of the strategy combination on the interests of all parties is reflected, which is expressed as:

[0220] ;

[0221] ;

[0222] ;

[0223] ;

[0224] in, Strategy Collection for Teachers The utility reflects the teacher's satisfaction with this strategy combination. Policy Collection for Students The utility reflects the students’ satisfaction with this strategy combination. Resource Policy Collection for Schools The utility reflects the school administrators’ satisfaction with the strategy combination. are the weights of teacher, student and school resource utility respectively.

[0225] Strategy analysis and balance optimization include:

[0226] Strategy analysis and simulation: In the game theory model, by simulating different strategy combinations (in Represents different strategy choices) to analyze the changes in the utility values ​​of each party under different strategy combinations and evaluate the gains and losses of each party, expressed as:

[0227] ;

[0228] in, For Teachers In the The choice under the strategy, For Students In the The choice under the strategy, For school administrators or school resources In the The choice under the strategy, For the strategy combination The utility value or benefit of the following participants (teachers, students or school administrators), For the strategy combination The sum of the overall utility values ​​of all participants (teachers, students and school administrators);

[0229] ;

[0230] in, Indicates the participants In the strategy portfolio Relative to the benchmark strategy portfolio The utility change, that is, the gain or loss of its benefits, is positive. Indicates that this strategy combination enables the participants The utility of is increased, while negative values ​​indicate a decrease in utility;

[0231] ;

[0232] in, The total benefits and losses of all parties involved;

[0233] Generation of optimization and equilibrium solutions: All strategy combinations are optimized through the Nash equilibrium algorithm, and a strategy combination is selected that balances the utilities of all parties and has the highest overall utility value;

[0234] Through the above content, we can find the best balance point among the interests of multiple parties and generate an optimal class scheduling plan that balances the interests of multiple parties. This not only improves the fairness and rationality of the class scheduling plan, but also optimizes the utilization rate of teaching resources and maximizes the overall teaching efficiency and satisfaction.

[0235] Nash equilibrium algorithms include:

[0236] Construct all strategy combinations: Consider all the strategy combinations of the participating parties ,in , , An index representing different strategy choices;

[0237] Calculate the total utility value of each strategy combination: For each strategy combination , calculate the total utility value , expressed as:

[0238] ;

[0239] in, Indicates the parties involved;

[0240] Finding the Nash equilibrium point: For each participant Find the optimal strategy when the strategies of other participants remain unchanged , Nash equilibrium point The conditions for satisfying are:

[0241] ;

[0242] in, For any other strategy, The first The optimal strategy for each participant is For the The strategy combination of the remaining participants other than the participants, for each participant , the strategy it chooses The strategies of other participants The strategy that maximizes its utility when things remain unchanged;

[0243] Select the strategy combination that makes the overall utility value the highest: After finding all Nash equilibrium points, select the strategy combination with the highest total utility value as the final optimal strategy, expressed as:

[0244] ;

[0245] in, represents the optimal strategy combination selected by optimization;

[0246] Through the above content, not only the utilization of teaching resources is optimized, but also the satisfaction and fairness of all parties are improved. The class scheduling plan generated by the system can find the best balance between the complex interests of multiple parties and realize efficient and reasonable academic management.

[0247] The intelligent conflict resolution module includes:

[0248] Conflict detection: Conflict detection is performed on the preliminary course scheduling plan, including course time conflict detection, teacher time conflict detection and resource conflict detection;

[0249] Course time conflict detection is defined as when multiple courses are scheduled in the same time slot and have at least one common student;

[0250] Teacher schedule conflict detection is defined as when the same teacher is scheduled to teach multiple courses in the same time slot;

[0251] Resource conflict is defined as when multiple courses have demands for the same instructional resources in the same time period;

[0252] Simulate multiple solutions: After a conflict is detected, multiple solutions are simulated to resolve the conflict, including modifying the time slot of the conflicting course, reallocating the teacher's teaching time, and reallocating teaching resources;

[0253] Adjust the class scheduling plan in real time: According to the simulated solutions, select the solution with the least conflict and the highest overall utility value, and adjust the preliminary class scheduling plan in real time;

[0254] Through the above content, not only various conflicts in teaching are effectively avoided, but also the rationality and execution efficiency of the plan are ensured. By selecting the adjustment plan with the least conflict and the highest overall utility value, the utilization of teaching resources can be maximized, and the overall effect of scheduling and the satisfaction of all parties can be improved.

[0255] The dynamic demand adjustment module includes:

[0256] Real-time demand monitoring: Real-time monitoring of demand changes that occur during the teaching process, including new courses, cancelled courses, teacher schedule adjustments, student course selection changes, and emergency resource deployment;

[0257] Evaluate the impact of adjustments: After detecting changes in demand, evaluate the impact of changes in demand on the existing scheduling plan, including the impact on course schedules, teacher schedules, and resource allocation, expressed as:

[0258] ;

[0259] in, is a comprehensive score of the overall adjustment impact. To understand the impact of changing demand on course schedules, To understand the impact of changing demand on teachers’ schedules, The impact of demand changes on resource allocation, are the weights of time impact, teacher impact, and resource impact respectively;

[0260] Dynamically adjust the class schedule: Based on the evaluation results, dynamically generate adjustment plans, giving priority to those that have the least impact on the existing plan and meet new needs;

[0261] The impact of changing demand on course schedules , the impact of changing demand on teachers’ schedules , the impact of demand changes on resource allocation The quantitative representation of is:

[0262] ;

[0263] in, Indicates the change in the course time period after the class schedule is adjusted (usually in hours);

[0264] ;

[0265] in, Indicates teacher The offset (in hours) of the teaching time of a course relative to its ideal teaching time;

[0266] ;

[0267] in, Indicates the resources after the course adjustment The amount of change in resource usage (e.g., changes in resource usage time or reallocation of resources);

[0268] Weight The setting basis and value range include:

[0269] Weight The setting basis is that if the time period has a greater impact on the class schedule, especially in high-demand time periods (such as mornings), the weight of time impact should be higher, and the value range is , the value is 0.4;

[0270] Weight The setting basis is the teacher's time preference and the impact of the class schedule on the overall plan. If the teacher's schedule is tight or difficult to adjust, the weight of the teacher's influence should be higher. The value range is , the value is 0.5;

[0271] Weight The basis for setting is that the efficiency of resource use has a significant impact on the course scheduling plan, especially the limited nature of popular resources (such as laboratories). If resource utilization has a great impact on the overall course scheduling, the resource weight should be high, and the value range is , the value is 0.4;

[0272] Through the above, by ensuring that the adjusted plan has minimal impact on the existing arrangements and meets new needs, it not only improves the efficiency and rationality of the teaching plan, but also enhances the robustness and responsiveness of the system in dealing with emergencies and changing needs.

[0273] The resource optimization allocation module includes:

[0274] Real-time monitoring: Real-time monitoring of all teaching resources to obtain the current usage status, occupancy time, and idle time periods of resources. The monitoring content includes the utilization of classrooms, laboratories, sports facilities, library learning spaces, professional workshops, computing resources, and multi-purpose halls;

[0275] Resource utilization evaluation: Based on real-time monitoring data, the utilization of various teaching resources is evaluated to calculate the current resource utilization efficiency. The evaluation content includes resource idle rate, occupation conflict rate and resource scheduling flexibility, which is expressed as:

[0276] ;

[0277] in, Indicates the total time the resource is actually used. Indicates the total time that the resource is available;

[0278] Optimization allocation strategy generation: Generate resource optimization allocation strategy based on the evaluation results, giving priority to resources with low utilization or conflicts. The optimization allocation strategy includes adjusting the resource allocation of courses, changing the time period for resource use, or reallocating resources to eliminate conflicts and improve utilization;

[0279] Through the above content, we can maximize resource utilization, reduce resource conflicts, adapt to changing teaching needs, and optimize the overall teaching arrangements. This not only improves the school's resource utilization efficiency, but also ensures the smooth progress of teaching activities and improves user experience.

[0280] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0281] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An automatic teaching and course scheduling system based on artificial intelligence, characterized in that: It includes student learning path optimization module, multi-party interest balance module based on game theory, intelligent conflict resolution module, dynamic demand adjustment module and resource optimization allocation module, among which; The student learning path optimization module analyzes the student's historical data, including grades, interests and hobbies, and career planning, and generates optimized learning path suggestions; The multi-party interest balancing module based on game theory balances the interests of teachers, students and school administrators through the game theory model, and generates a preliminary course scheduling plan in combination with the optimized learning path suggestions, which specifically includes: Collecting interests and demands: Collecting the interests and demands of teachers, students, and school administrators, including teachers' teaching time preferences, students' course selection requirements, and the school's resource utilization priorities, and quantifying the interests and demands of all parties to generate a set of strategies in the game theory model; Strategy analysis and balance optimization: Based on the generated strategy set, the game theory algorithm is used to perform strategy analysis, simulate the gains and losses of each party under different plans, and optimize and generate a class scheduling plan that balances the interests of multiple parties; The intelligent conflict resolution module detects conflict problems in the preliminary course scheduling plan, including course time conflicts, teacher time conflicts and resource conflicts. After detecting the conflict problems, the course scheduling plan is adjusted in real time by simulating multiple solutions; The dynamic demand adjustment module dynamically adjusts the course scheduling plan according to the real-time changing demand; After the class schedule is determined, the resource optimization allocation module monitors and optimizes the allocation of the school's teaching resources in real time. The teaching resources include classrooms, laboratories, sports facilities, library learning spaces, professional workshops, computing resources, and multi-purpose halls. The student learning path optimization module includes: Data collection and preprocessing: Collect students’ historical data, including grades, interests, hobbies, and career plans, and standardize the historical data; Multi-objective optimization model construction: We use weighted linear combination to conduct comprehensive analysis on different historical data and construct a multi-objective optimization model, which is expressed as: S=w1·S 成绩 +w2·S 兴趣 +w3·S 职业规划 ; Among them, S is the comprehensive score, S 成绩 S is the student's performance score, 兴趣 S is the score for the relevance of student interests to the course, 职业规划 is the score of the matching degree between the course and career planning, w1, w2, and w3 are the weights of each factor; Course matching: Based on the multi-objective optimization model, calculate the comprehensive score C of each course i , expressed as: C i =w7·C i,成绩 +w8·C i,兴趣 +w9·C i,职业规划 ; Among them, C i,成绩 , C i,兴趣 , C i,职业规划 are the scores of course i in terms of grades, interests and career planning, and w7, w8 and w9 are the corresponding weights; Path generation: All courses are sorted according to the comprehensive score of each course, and the dynamic programming algorithm is used to generate an optimized learning path based on the student's semester credit limit and course prerequisite constraints; The dynamic programming algorithm includes: Collect course information: collect the comprehensive score scores[i] of each course i, the credits[i] of each course i, and the prerequisite course relationship prereq[i] of each course i; Define state variables: define dp[i][j][k] to represent the maximum comprehensive score of a course combination with a total credit score not exceeding j and meeting the prerequisites among the first i courses. Initialization state: If no course is selected, initialize dp[0][j][0] = 0, indicating that the score is 0 if no course is selected; Traverse each course i: For each course i, traverse downward from the total number of credits j = max_credits, ensuring that each course is only considered once. If course i has a prerequisite course requirement prereq[i], then the course is only allowed to be selected if the prerequisite is met; State transfer equation: If course i is not selected, the state transfer equation is: dp[i][j][k] = dp[i-1][j][k]. If course i is selected and the prerequisite prereq[i] is met, then the state transition equation is: dp[i][j][k]=max(dp[i-1][j][k],dp[i-1][j-credits[i]][k+score[i]]); The final state transfer equation is: dp[i][j][k]=max(dp[i-1][j][k],dp[i-1][j-credits[i]][k+scores[i]]); Prerequisite course constraint: When calculating state transitions, add a prerequisite course check. If course i has a prerequisite course prereq[i], then dp[i][j][k] is updated if the prerequisite course has been taken. Determine the optimal solution: Traverse all courses i, total credits j, and total scores k. The comprehensive score of the optimal learning path is expressed as: dp[n][max_credits][k]where k is maximum; Among them, n is the total number of courses, max_credits is the semester credit limit, and finally the path with the largest k is selected; Backward tracing path: Starting from the last item dp[n][max_credits][k of the state matrix dp, reversely trace the selection of each step to determine the course selected into the optimal learning path; Output optimal learning path: Output the generated learning path, including the selected courses and their sequence, and verify whether it meets all prerequisites and credit limits; Credit and score verification: Verify that the total number of credits in the path does not exceed the semester credit limit, and check whether the total score is consistent with dp[n][max_credits][k].

2. According to the artificial intelligence-based automatic teaching and course scheduling system of claim 1, it is characterized in that: The collection of interest requirements includes: Collection and quantification of teachers’ teaching time preferences: Through data questionnaires and historical teaching records, we collect each teacher’s teaching time preference data, including available time periods, priority time periods, and unavailable time periods. We also quantify the collected teaching time preference data and perform weighted processing based on the importance of the time periods to generate a teacher’s teaching time preference strategy set T. i , expressed as: T ij =w time ×P ij ; Among them, T ij is the quantitative score of each teacher i’s teaching period j, P ij is the preference score of teacher i for time period j, w time is the importance weight of the time period; Among them, z1 is the total number of optional time periods for teachers; Collection and quantification of students’ course selection needs: Through the student course selection platform, interest surveys, and career planning, students’ course selection demand data is collected, including priority elective courses, required courses, and elective courses. The collected course selection demand data is quantified, and the student course selection demand strategy set S is generated by weighting the demand priority and interest score of each course. m , expressed as: S mn =w priority ×C mn +w interest ×I mn ; Among them, S mn is the quantitative score of each student m in course n, w priority and w interest are the weights of course priority and interest, respectively, and C mn is the demand priority of course n for student m, I mn Score student m's interest in course n; Among them, z2 is the total number of courses that students can choose; Collection and quantification of school resource utilization priorities: Through the school resource management platform, the school's resource utilization data, including the utilization and priority information of classrooms, laboratories, and equipment, is collected and quantified. By weighting the utilization and availability of resources in different time periods, a school resource utilization priority strategy set R is generated. k , expressed as: R kl =w utilization ×U kl +w availability ×A kl ; Among them, R kl To quantitatively score the utilization priority of each school resource k in time period l, U kl is the utilization rate of resource k in time period l, A kl is the availability of resource k in time period l, w utilization and w availability are the weights of resource utilization and availability, respectively; Among them, z3 is the total number of time periods for resource utilization; Generating strategy set: Comprehensive teacher teaching time preference strategy set T i , student course selection demand strategy set S m , school resource utilization priority strategy set R k , forming a set of strategies in the game theory model.

3. The automatic teaching and course scheduling system based on artificial intelligence according to claim 2 is characterized in that: The generation strategy set includes: Basic construction of strategy set: teachers’ teaching time preference strategy set T i , student course selection demand strategy set S m , school resource utilization priority strategy set R k The sets are combined into a global strategy set, expressed as: Global Strategt Set={T i ,S m ,R k }; Weight allocation and strategy combination: Assign a weight to each strategy set to indicate the relative importance of the interests of all parties, and generate a comprehensive strategy set while balancing the interests of all parties, expressed as: Weighted Strategy Set=α×T i +β×S m +γ×R k ; Among them, α is the weight of the teacher strategy set, β is the weight of the student strategy set, and γ is the weight of the school resource strategy set; Strategy set in game theory model: The generated comprehensive strategy set is used as the input of the game theory model, and the equilibrium point is found through simulation and optimization, which is expressed as: Optimal Strategy=argmax(∑Utility(T i ,S m ,R k )); Among them, Utility(T i ,S m ,R k ) is the utility function of each strategy set in the game theory model; Equilibrium solution in the game theory model: By analyzing the comprehensive strategy set, the optimal solution that balances the interests of all parties is found, which is expressed as: in, Represents the set of equilibrium strategies reached in the game theory model.

4. The automatic teaching and course scheduling system based on artificial intelligence according to claim 3 is characterized in that: The strategy analysis and balance optimization include: Strategy analysis and simulation: In the game theory model, by simulating different strategy combinations To analyze the changes in the utility values ​​of each party under different strategy combinations and evaluate the gains and losses of each party, expressed as: in, is the choice of teacher i under the ath strategy, is the choice of student m under the bth strategy, is the choice of school managers or school resources k under the cth strategy, For the strategy combination The utility value or benefit of the participants, For the strategy combination The sum of the overall utility values ​​of all participants; Among them, ΔUtility p Indicates that the participant p has a strategy combination Relative to the benchmark strategy portfolio changes in utility; Total Gain / Loss=∑ p∈participants ΔUtility p ; Among them, Total Gain / Loss is the total gain / loss of all participants; Generation of optimization and equilibrium solutions: All strategy combinations are optimized through the Nash equilibrium algorithm, and a strategy combination is selected that balances the utility of all parties and has the highest overall utility value.

5. The automatic teaching and course scheduling system based on artificial intelligence according to claim 4 is characterized in that: The Nash equilibrium algorithm includes: Construct all strategy combinations: Consider all the strategy combinations of the participating parties Where a, b, and c represent the indexes of different strategy choices; Calculate the total utility value of each strategy combination: For each strategy combination Calculate the total utility value TotalUtility, expressed as: Among them, p represents the participating party; Find the Nash equilibrium point: For each participant p, find its optimal strategy when the strategies of other participants remain unchanged. Nash equilibrium The conditions for satisfying are: Among them, S p 'For any other strategy, is the optimal strategy of the pth participant in the strategy combination, is the strategy combination of the remaining participants except the pth participant; Select the strategy combination that makes the overall utility value the highest: After finding all Nash equilibrium points, select the strategy combination with the highest total utility value as the final optimal strategy, expressed as: Among them, {T' i ,S' m ,R' k } represents the optimal strategy combination selected by optimization.

6. The automatic teaching and course scheduling system based on artificial intelligence according to claim 1 is characterized in that: The intelligent conflict resolution module comprises: Conflict detection: Conflict detection is performed on the preliminary course scheduling plan, including course time conflict detection, teacher time conflict detection and resource conflict detection; The course time conflict detection is defined as when multiple courses are scheduled in the same time slot and have at least one common student; The teacher time conflict detection is defined as when the same teacher is scheduled to teach multiple courses in the same time period; The resource conflict is defined as when multiple courses have a demand for the same teaching resource in the same time period; Simulate multiple solutions: After a conflict is detected, multiple solutions are simulated to resolve the conflict, including modifying the time slot of the conflicting course, reallocating the teacher's teaching time, and reallocating teaching resources; Adjust the class scheduling plan in real time: Based on the simulated solutions, select the solution with the least conflict and the highest overall utility value, and adjust the preliminary class scheduling plan in real time.

7. The automatic teaching and course scheduling system based on artificial intelligence according to claim 1 is characterized in that: The dynamic demand adjustment module includes: Real-time demand monitoring: Real-time monitoring of demand changes that occur during the teaching process, including new courses, cancelled courses, teacher schedule adjustments, student course selection changes, and emergency resource deployment; Evaluate the impact of adjustments: After detecting changes in demand, evaluate the impact of changes in demand on the existing scheduling plan, including the impact on course schedules, teacher schedules, and resource allocation, expressed as: Impact=w4×Time Impact+w5×Teacher Impact+w6×Resource Impact; Among them, Impact is the comprehensive score of the overall adjustment impact, Time Impact is the impact of demand changes on course schedules, Teacher Impact is the impact of demand changes on teacher schedules, Resource Impact is the impact of demand changes on resource allocation, and w4, w5, and w6 are the weights of time impact, teacher impact, and resource impact, respectively; Dynamically adjust the class schedule: Based on the evaluation results, dynamically generate adjustment plans, giving priority to adjustments that have the least impact on the existing plan and meet new needs.

8. The automatic teaching and course scheduling system based on artificial intelligence according to claim 1 is characterized in that: The resource optimization allocation module includes: Real-time monitoring: Real-time monitoring of all teaching resources to obtain the current usage status, occupancy time, and idle time periods of resources. The monitoring content includes the utilization of classrooms, laboratories, sports facilities, library learning spaces, professional workshops, computing resources, and multi-purpose halls; Resource utilization evaluation: Based on real-time monitoring data, the utilization of various teaching resources is evaluated and the efficiency of current resource utilization is calculated. The evaluation content includes resource idle rate, occupation conflict rate and resource scheduling flexibility; Generation of optimal allocation strategy: Generate optimal resource allocation strategy based on the evaluation results. The optimal allocation strategy includes adjusting the resource allocation of courses, changing the time period for resource use, or reallocating resources.

Images