Intelligent curriculum schedule arrangement method and system

Abstract

The invention relates to the technical field of artificial intelligence, in particular to an intelligent curriculum schedule arrangement method and system, and the method comprises the following steps: defining teacher nodes, student nodes, curriculum nodes and classroom nodes based on the information of teachers, students, curriculums and classrooms, building the relation between the nodes, analyzing the time conflict, burden and classroom capacity, endowing each edge with a corresponding weight, and carrying out the arrangement of the curriculum schedule. And obtaining graph structure data. According to the method, the information node relation network is constructed, the course arrangement problem is converted into graph structure data processing, teacher arrangement, student demands, course capacity, time conflicts and other constraint conditions are quantified, node states are updated layer by layer, the course arrangement influence is accurately evaluated, the optimization efficiency is improved, constraint weight distribution is dynamically adjusted, key contradictions are preferentially solved, and the course arrangement efficiency is improved. According to the method, balance and rationality are considered, a curriculum schedule is adjusted in combination with real-time data, student course selection and teacher time change are rapidly adapted, resource waste and insufficient coordination of static arrangement are avoided, and an efficient and flexible curriculum arrangement scheme is realized.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an intelligent course schedule arrangement method and system. Background Art

[0002] The field of artificial intelligence technology is a research field that simulates, extends and expands the theories, methods, technologies and application systems of human intelligence. Its core goal is to enable machines to have the capabilities of perception, reasoning, learning and decision-making. This technical field covers multiple sub-fields, including machine learning, deep learning, natural language processing, computer vision, expert systems, etc. Artificial intelligence has a wide range of applications in multiple industries, especially in data analysis, automated decision-making, intelligent recommendation, speech recognition, image processing, robot control, etc., and has made significant progress. In the field of intelligent course timetable arrangement, AI technology especially involves intelligent algorithms, optimization technology and pattern recognition methods, which optimize course timetable arrangements through simulation and calculation, improve efficiency, reduce human intervention, and meet complex needs.

[0003] Among them, the main purpose of the intelligent course timetable arrangement method is to automatically generate the optimal course timetable through artificial intelligence technology, taking into full consideration the constraints and needs of students, teachers, classrooms and other aspects. This method uses algorithm models and data-driven methods to perform computational optimization under different constraints to achieve automation, personalization and efficiency of course arrangement. Its uses include automatically scheduling course timetables for educational institutions, solving problems such as time conflicts, waste of resources and inefficiency in traditional manual scheduling, and improving coordination and resource utilization efficiency between schools, teachers and students.

[0004] There are many deficiencies in the existing technology in intelligent course timetable arrangement. Most traditional methods fail to quantify complex node relationships through graph structures or weights, resulting in low accuracy in detecting course conflicts. It is difficult to fully consider the multiple constraints between teachers, students and classrooms. Static scheduling methods are difficult to adapt to dynamically changing data. When students' course selection or teachers' schedules change, the adjustment process is cumbersome and easily leads to new conflicts, affecting the efficiency and flexibility of the overall course arrangement. The existing technology has limited optimization capabilities in balancing hard constraints and soft constraints, and cannot effectively solve problems such as uneven teacher burdens or limited student course choices. Due to the lack of a dynamic adjustment mechanism driven by real-time data, resource allocation often results in excessive waste or insufficiency, which is not conducive to the efficient use of school resources. It is also difficult to meet personalized needs in complex scenarios, making the efficiency and coordination of course timetable arrangement far below the actual demand level. Summary of the invention

[0005] In order to solve the many shortcomings of the existing technology in intelligent course schedule arrangement, most traditional methods fail to quantify complex node relationships through graph structure or weight, resulting in low accuracy in detecting course conflicts, and it is difficult to fully consider the multiple constraints between teachers, students and classrooms. The static scheduling method is difficult to adapt to dynamically changing data. When students' course selection or teacher schedule changes, the adjustment process is cumbersome and easily leads to new conflicts, affecting the efficiency and flexibility of the overall course arrangement. The existing technology has limited optimization capabilities in balancing hard constraints and soft constraints, and cannot effectively solve problems such as uneven teacher burdens or limited student course selection. Due to the lack of a dynamic adjustment mechanism driven by real-time data, resource allocation often results in excessive waste or insufficiency, which is not conducive to the efficient use of school resources, and it is difficult to meet personalized needs in complex scenarios, making the efficiency and coordination of course schedule arrangement far lower than the actual demand level. The embodiment of the present invention provides a method and system for intelligent course schedule arrangement. The technical solution is as follows:

[0006] On the one hand, a smart course schedule arrangement method is provided, the method comprising:

[0007] S1: Based on the information of teachers, students, courses and classrooms, define teacher nodes, student nodes, course nodes and classroom nodes, establish the relationship between nodes, analyze time conflicts, burdens and classroom capacity, assign corresponding weights to each edge and obtain graph structure data;

[0008] S2: Based on the graph structure data, information is transmitted on the relationship between nodes, each node is initialized, the influence of the edge weights of adjacent nodes is analyzed, node information is updated according to the edge weights, and state information between nodes is transmitted layer by layer to obtain node state update results;

[0009] S3: Based on the node status update result, analyze the constraint conditions, evaluate the impact of hard constraints and soft constraints, calculate the violation degree of each constraint, and obtain the constraint condition optimization result;

[0010] S4: Based on the constraint optimization result, the resource allocation of the course schedule is optimized by dynamically adjusting the weights between the hard constraints and the soft constraints, and the constraints with large weights are adjusted first to generate an optimized course allocation plan;

[0011] S5: Based on the optimized course allocation plan, combined with real-time change data, the course schedule is adjusted in real time. According to the node status, the weight of the edge is updated, the relationship between each node is evaluated, the time schedule is adjusted, information transmission is executed and the node status is updated, and a dynamically adjusted intelligent course scheduling plan is generated.

[0012] As a further solution of the present invention, the graph structure data includes teacher nodes, student nodes, course nodes, classroom nodes and their mutual relationships, the node status update result includes the status after the node information is updated, the constraint optimization result includes the degree of conflict between teacher teaching times, the degree of classroom capacity limitation, the degree of balance between teacher burdens, and the degree of balance between student course selections, the optimized course allocation plan includes a resource allocation optimization plan and a priority adjustment result, and the dynamically adjusted intelligent course scheduling plan includes real-time course adjustment results, updated node status, and edge weight update status.

[0013] As a further solution of the present invention, based on the information of teachers, students, courses and classrooms, teacher nodes, student nodes, course nodes and classroom nodes are defined, the relationship between nodes is established, time conflicts, burdens and classroom capacity are analyzed, and corresponding weights are assigned to each edge. The specific steps of obtaining graph structure data are as follows:

[0014] S101: Based on the information of teachers, students, courses and classrooms, extract the teacher course allocation records, student course selection data, course time schedule, classroom number and capacity, clean up irrelevant data and fill in missing items, integrate classified data, and obtain the node basic data set;

[0015] S102: Based on the node basic data set, analyze the teacher course number list, extract the student course selection record, call the course-related classroom number and available time period information, build the teacher course, student course, course classroom related data table, correct the duplicate and conflicting items, summarize the corrected data, and obtain the node relationship network;

[0016] S103: Based on the node relationship network, each edge is assigned a weight index, the quantitative index of teacher course time distribution is called, the student course time matching record is analyzed, the classroom capacity utilization rate and the course conflict ratio are calculated, the edge is assigned a corresponding weight, the incorrectly assigned edge is corrected, and the graph structure data is obtained.

[0017] As a further solution of the present invention, based on the graph structure data, information is transmitted on the relationship between nodes, each node is initialized, the influence of the edge weights of adjacent nodes is analyzed, node information is updated according to the edge weights, and the state information between nodes is transmitted layer by layer. The steps of obtaining the node state update result are specifically as follows:

[0018] S201: extracting edge weights of relationships between nodes based on the graph structure data, analyzing the numerical impact of edge weights on associated node states, integrating edge weights into node initial states, accumulating node state values, and obtaining initial node state update results;

[0019] S202: based on the initial update result of the node state, extract the node state value and the weight of the adjacent edges, weight the adjacent node state values ​​and transmit them to the target node, adjust the state distribution range by normalization, integrate the processed state values, and obtain the node state change result;

[0020] S203: Based on the node state change result, the node state value is parsed layer by layer, the numerical parameters are extracted and gradually transmitted to the target node, the parameters are cumulatively transmitted to the target node state, the influence of the edge weight on the cumulative value is analyzed and updated, and the node state update result is obtained.

[0021] As a further solution of the present invention, based on the node status update result, the constraint conditions are analyzed, the influence of hard constraints and soft constraints is evaluated, the violation degree of each constraint is calculated, and the steps of obtaining the constraint condition optimization result are specifically as follows:

[0022] S301: Based on the node status update result, extract the hard constraints of teacher teaching time and classroom capacity, parse the node time period and capacity parameters, compare the conflict distribution of node time and teaching time, calculate the capacity exceeding impact weight, integrate the conflict distribution data, and generate hard constraint analysis results;

[0023] S302: Based on the hard constraint analysis results, extract the soft constraint conditions of teacher load balance and student course selection balance, filter the teaching time and course selection frequency parameters in the nodes, analyze the conflicting nodes that do not meet the conditions and sort them out, and obtain the soft constraint analysis results;

[0024] S303: Based on the soft constraint analysis results, extract the hard constraint and soft constraint conflict data, filter the conflict node time period, capacity, teaching time and course selection frequency parameters, calculate the conflict weight ratio and adjust the node status item by item to obtain the constraint optimization result.

[0025] As a further solution of the present invention, the conflict weight ratio is calculated according to the formula:

[0026]

[0027] Among them, W represents the conflict weight ratio, C1 represents the weight coefficient of time period conflict, T1 represents the frequency of time period conflict, C2 represents the weight coefficient of capacity conflict, T2 represents the degree of capacity conflict, C3 represents the weight coefficient of teaching time conflict, F3 represents the frequency of teaching time conflict, L1 represents the mean value of course selection frequency, L2 represents the standard deviation of course selection frequency, D1 represents the depth of node conflict, N1 represents the number of adjustment nodes, and N2 represents the total number of conflicting nodes.

[0028] As a further solution of the present invention, based on the constraint optimization result, the resource allocation of the course schedule is optimized by dynamically adjusting the weights between the hard constraints and the soft constraints, and the constraints with large weights are adjusted first. The steps of generating the optimized course allocation plan are specifically as follows:

[0029] S401: Based on the constraint optimization result, extract the hard constraint and soft constraint weight data, analyze the time conflict node and the classroom capacity allocation node, count the conflict status and sort the weight conditions, and obtain the constraint weight priority data in combination with the soft constraint status data sorting conditions;

[0030] S402: Based on the constraint weight priority data, extract the priority hard constraint conditions, parse the time conflict nodes and adjust the time parameter allocation, eliminate time overlap, adjust the capacity allocation status, check the teacher teaching and student selection allocation in the soft constraint conditions, integrate the adjusted node status, and obtain the course resource adjustment result;

[0031] S403: Based on the course resource adjustment result, analyze the node time and space allocation status, check the matching between the adjusted time period and the classroom capacity, calculate the course allocation status index value, integrate the adjusted node status, and obtain the optimized course allocation plan.

[0032] As a further solution of the present invention, the course allocation status index value is calculated according to the formula:

[0033]

[0034] Among them, S represents the optimized course allocation status indicator value, B represents the classroom capacity, and E represents the length of the time period. Represents the total number of teachers teaching the course, A i It represents the matching degree of the teacher’s teaching in the i-th course, Q represents the weighted value of the student’s choice preference, P represents the teaching load of the course, G represents the teacher’s teaching burden, and M represents the number of students.

[0035] As a further solution of the present invention, based on the optimized course allocation plan, combined with real-time change data, the course schedule is adjusted in real time, the weight of the edge is updated according to the node status, the relationship between each node is evaluated, the time arrangement is adjusted, information transmission is performed and the node status is updated, and the steps of generating a dynamically adjusted intelligent course scheduling plan are specifically as follows:

[0036] S501: Based on the optimized course allocation plan, extract the student course selection and teacher available time data, list the course time constraints, student needs and teacher time matching conditions one by one, analyze the initial relationship between courses and time, check conflicts and duplications, and obtain the initial course time allocation table;

[0037] S502: Based on the course time initial allocation table, extract the newly added course selection, teacher time period update and student course withdrawal data, parse the affected course nodes, associate and analyze the change data and map the course time node relationship, update the node weight, and obtain dynamic course association structure data;

[0038] S503: Based on the dynamic course association structure data, adjust the course node time schedule, resolve the conflicting edges and reallocate the time periods, optimize the conflicting node arrangement, maintain the original allocation of non-conflicting nodes, update the association weights between nodes, check the correctness of the adjusted arrangement, and generate a dynamically adjusted intelligent course scheduling plan.

[0039] On the other hand, an electric vehicle state monitoring system is provided, the electric vehicle state monitoring system is used to execute the above electric vehicle state monitoring method, the system comprises:

[0040] The teacher information processing module extracts the teacher's available time period based on the information of teachers, students, courses, and classrooms, analyzes the matching between course types and time periods, screens the course-related data within the time period, allocates teaching time nodes, and screens the matching data based on course types and time nodes to obtain teacher teaching-related information;

[0041] The student information processing module screens the course selection demand data based on the student course selection and registration status data, cross-checks the registered courses with the unmet course requirements, analyzes the unmatched items and the course selection range, integrates the matched requirements and status data, and obtains the student course selection status;

[0042] The course association construction module extracts the teaching time period, student demand and classroom capacity based on the teacher teaching association information and student course selection status, analyzes time conflict and overcapacity data, maps the relationship between courses, teachers, students and classrooms, assigns priority weights, screens and adjusts conflicting items, and obtains course association relationship graph data;

[0043] The status information update module analyzes the teaching time period, student demand and classroom capacity data based on the course association relationship graph data, screens the edge weights of adjacent nodes, parses and updates the status parameters, transfers the updated status to adjacent nodes, iterates the weight and status transfer, and generates the node status update result;

[0044] The constraint evaluation module screens the teaching time conflict and classroom capacity overload data based on the node status update results, extracts the teacher burden and student course selection demand balance data, analyzes the hard constraint and soft constraint differences, screens the constraint deviation data, integrates the comparison results, and generates the constraint analysis results;

[0045] The course dynamic adjustment module is based on the constraint analysis results, combined with the changed student course selection and teacher available time data, to screen the node status in the changed data, extract the edge weights and adjust the weights and time schedules, update the course association and time allocation data, screen the adjusted conflicting nodes and status relationships, and generate a dynamically adjusted intelligent course scheduling plan.

[0046] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0047] By constructing a node relationship network based on teacher, student, course and classroom information, the complex course scheduling problem is transformed into graph structure data processing. By analyzing the relationship between nodes and assigning weights to the edges, the constraints of various aspects such as teacher teaching arrangements, student course selection needs, course capacity and time conflicts are fully quantified. The node status update method layer by layer in the information transmission process accurately evaluates the impact of adjacent nodes on the overall course scheduling, significantly improving the optimization efficiency of course scheduling. The weight distribution of hard constraints and soft constraints is dynamically adjusted to make resource allocation more flexible. While giving priority to solving key contradictions, constraints are taken into account to enhance the balance and rationality of course scheduling. Combined with real-time changing data, the course schedule is dynamically adjusted to quickly adapt to changes in students' course selection preferences and teachers' available time, effectively avoiding resource waste and lack of coordination caused by static scheduling. This method maximizes resource utilization while improving scheduling efficiency and reducing conflicts, and can dynamically meet personalized needs, providing educational institutions with efficient and flexible course scheduling solutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a schematic diagram of the workflow of the present invention;

[0049] Figure 2 This is a detailed flow chart of S1 of the present invention;

[0050] Figure 3 This is a detailed flow chart of S2 of the present invention;

[0051] Figure 4 This is a detailed flow chart of S3 of the present invention;

[0052] Figure 5 This is a detailed flow chart of S4 of the present invention;

[0053] Figure 6 This is a detailed flow chart of S5 of the present invention;

[0054] Figure 7 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0055] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0056] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0057] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0058] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0059] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0060] See also Figure 1 The embodiment of the present invention provides an intelligent course schedule arrangement method, and the processing flow of the method may include the following steps:

[0061] S1: Based on the information of teachers, students, courses and classrooms, define teacher nodes, student nodes, course nodes and classroom nodes, establish the relationship between teachers and courses, students and courses, courses and classrooms, analyze time conflicts, burdens and classroom capacity, assign corresponding weights to each edge and obtain graph structure data;

[0062] S2: Based on the graph structure data, the relationship between nodes is transmitted, each node is initialized, the influence of the edge weights of adjacent nodes is analyzed, the node information is updated according to the edge weights, the state information between nodes is transmitted layer by layer, and the node state update result is obtained;

[0063] S3: Based on the node status update results, analyze the constraints, evaluate the hard constraints including teacher teaching time conflicts and classroom capacity limitations, and the soft constraints including teacher load balance and student course selection balance, calculate the violation degree of each constraint, and obtain the constraint optimization results;

[0064] S4: Based on the optimization results of the constraints, the resource allocation of the course schedule is optimized by dynamically adjusting the weights between the hard constraints and the soft constraints. The constraints with large weights are adjusted first to generate an optimized course allocation plan.

[0065] S5: Based on the optimized course allocation plan, combined with real-time changing data, including student course selection and teacher available time, the course schedule is adjusted in real time. The node status in the graph structure is analyzed according to dynamic changes, the edge weights are updated, the relationship between each node is evaluated, the time schedule is adjusted, information transmission is performed and the node status is updated to generate a dynamically adjusted intelligent course schedule.

[0066] The graph structure data includes teacher nodes, student nodes, course nodes, classroom nodes and their relationships. The node status update results include the status after the node information is updated. The constraint optimization results include the degree of conflict between teachers' teaching times, the degree of classroom capacity limitations, the degree of balance between teachers' burdens, and the degree of balance between students' course selections. The optimized course allocation plan includes the resource allocation optimization plan and priority adjustment results. The dynamically adjusted intelligent course scheduling plan includes the real-time course adjustment results, the updated node status, and the edge weight update status.

[0067] Specifically, if Figure 2 As shown in the figure, based on the information of teachers, students, courses and classrooms, teacher nodes, student nodes, course nodes and classroom nodes are defined, the relationship between nodes is established, time conflicts, burdens and classroom capacity are analyzed, and corresponding weights are assigned to each edge. The specific steps to obtain graph structure data are as follows:

[0068] S101: Based on the information of teachers, students, courses and classrooms, extract the teacher course allocation records, student course selection data, course time schedule, classroom number and capacity, clean up irrelevant data and fill in missing items, integrate classified data, and obtain the node basic data set;

[0069] The teacher course allocation records are classified according to semester, course name, and teacher number. Duplicate records are screened and abnormal entries that do not conform to the course schedule are eliminated, such as duplicate allocations or course information that does not conform to the semester logic. For student course selection data, the correlation between student number, course number and semester information is screened to remove abnormal or duplicate records. At the same time, missing items caused by student omissions or data errors can be filled. Intelligent inference or completion can be made through the historical records of students' course selection. In terms of course time arrangement, different course time periods are classified into non-conflicting ones, and conflicting time period records in the same classroom are identified and corrected. At the same time, course records that exceed the time range are eliminated. In the process of processing classroom numbers and capacity, consistency checks are performed in combination with the basic data of building numbers and actual physical capacity. For erroneous or missing data, the historical course usage records of the building where the classroom is located are used to complete it. When integrating data, all data are cross-compared according to the four dimensions of teachers, students, courses, and classrooms. The seamless connection between data is ensured through unified coding, and finally a node basic data set is generated, laying the foundation for subsequent association operations.

[0070] S102: Based on the node basic data set, analyze the teacher course number list, extract the student course selection records, call the course-related classroom number and available time information, build the teacher course, student course, course classroom related data table, correct the duplicate and conflicting items, summarize the corrected data, and obtain the node relationship network;

[0071] Extract the teacher course number list from the node basic data set, compare each number with the student course selection record corresponding to the course one by one, form a matching mapping table between teacher and student courses, and check whether each course has a clear classroom number and corresponding available time period by calling the course-associated classroom number and its corresponding available time period information. If some courses lack clear classroom numbers or time arrangements, intelligent supplements are made based on the classroom's historical utilization records and course priority distribution. In order to correct duplicate and conflicting items, for problems such as repeated teaching by teachers, repeated course selection by students, and overlapping course time periods, conflicting items are adjusted by matching classroom capacity and time period arrangement constraints, and solutions that minimize conflicts are retained first. All corrected data are summarized according to the three dimensions of teachers, students, and classrooms to ensure that there are no missing items or conflicts in the associated data table, and finally a node relationship network is formed with network topology characteristics and association logic.

[0072] S103: Based on the node relationship network, assign each edge according to the weight index, call the quantitative index of teacher course time distribution, analyze the student course time matching record, calculate the classroom capacity utilization rate and course conflict ratio, assign the edge corresponding weight, correct the wrongly assigned edge, and obtain the graph structure data;

[0073] First, according to the association between teachers and courses, students and courses, and courses and classrooms, an initial weight is assigned to each edge in the node relationship network. The initial weight is allocated according to the closeness of the association and the distribution of time constraints. For the distribution of teacher course hours, by calculating the load ratio of each teacher's teaching time, the excessively high or low distribution is recorded and reflected in the edge weight to avoid over-concentrated arrangements or idle resources. In the student course time matching record, by analyzing the concentration of course selection in different time periods in the student course schedule, the time period causing high-frequency conflicts is identified, and matching parameters are added to the weight. The classroom capacity utilization rate is calculated by the actual capacity occupancy ratio between nodes to ensure that the edges with too low capacity are assigned lower weights. At the same time, punitive corrections are performed on the edges with a higher proportion of course conflicts. When correcting the wrongly assigned edges, the edges that are repeatedly assigned or caused by logical errors are corrected one by one. After multiple rounds of screening, the graph structure data is finally obtained to provide accurate and standardized basic data for intelligent scheduling.

[0074] Specifically, if Figure 3 As shown in the figure, based on the graph structure data, the relationship between nodes is transmitted, each node is initialized, the influence of the edge weights of adjacent nodes is analyzed, the node information is updated according to the edge weights, and the state information between nodes is transmitted layer by layer. The specific steps to obtain the node state update result are:

[0075] S201: extracting edge weights of relationships between nodes based on graph structure data, analyzing the numerical impact of edge weights on associated node states, integrating edge weights into node initial states, accumulating node state values, and obtaining initial node state update results;

[0076] The weight value of each edge is extracted from the graph structure data in turn, mapped to the associated start node and target node, and the bidirectional influence of the weight is recorded. For the weight of each edge, combined with the actual influencing factors in the course arrangement, such as the teaching time of the teacher's course period, the concentration of students' course selection, and the actual utilization rate of the classroom, the influence intensity of each edge on the associated node is calculated one by one, and a higher state influence value is assigned to the edge with a larger weight (such as the edge between the high-frequency course selection and the key teacher node), while a lower influence value is assigned to the edge with a smaller weight. The state influence values ​​of all edges are integrated into the initial state of the node, and the initial state value of the node is accumulated. For example, in a simple example, a teacher node is associated with three course nodes, and the edge weights correspond to the course teaching time of 3 hours, 2 hours, and 1 hour, respectively. After the accumulation operation, the initial state value of the teacher node is 3+2+1=6. Through this accumulation mechanism, the initial update result of the node state is obtained, providing an accurate initial value for the subsequent state propagation operation.

[0077] S202: based on the initial update result of the node state, extract the node state value and the weight of the adjacent edges, weight the adjacent node state values ​​and transmit them to the target node, adjust the state distribution range by normalization, integrate the processed state values, and obtain the node state change result;

[0078] First, the initial state value of each node and the weight of its adjacent edges are extracted. By analyzing the relationship between the weight value and the state value of the adjacent node, the role of each edge in the state value transfer is determined. For the weighted processing of the state value, different influences are exerted on the state values ​​of the adjacent nodes according to the size of the edge weight, and the adjacent node state values ​​corresponding to the high-weight edge are given a larger influence ratio. When the state value is transferred to the target node, the state values ​​from multiple adjacent nodes are superimposed, and the weight influence of the transfer path is recorded at the same time to ensure that the role of each edge is reasonably reflected. In the normalization adjustment of the state distribution range, the state value is limited according to the logic of the course schedule, such as limiting the upper and lower limits of the node state value to ensure that the state value does not exceed the reasonable range. The integrated state value includes the adjusted target node state and the influence of its associated edges, and finally generates the node state change result to provide data support for further state updates.

[0079] S203: Based on the node state change result, the node state value is parsed layer by layer, the numerical parameters are extracted and gradually transmitted to the target node, the parameters are cumulatively transmitted to the target node state, the influence of the edge weight on the cumulative value is analyzed and updated, and the node state update result is obtained;

[0080] First, the state value of each layer of nodes is analyzed. By disassembling the numerical parameters in the state change results, the state transfer parameters associated with the nodes are extracted layer by layer. In the process of gradually transferring the numerical parameters to the target node, the path weight of each transfer is recorded, and the role ratio of the transfer parameter is adjusted according to the weight value. For example, high-weight edges have a greater cumulative contribution to the target node state value. In the process of accumulating transfer parameters, it is ensured that the update of the state value of each target node is accurately calculated, and the state transfer results from multiple paths are superimposed to form a complete state accumulation result. In the impact analysis of edge weights, the edge weights are updated according to the contribution of the current transfer path to the target node state. For example, the weight value of the edge with insufficient effect is reduced, and the weight value of the edge with greater contribution to the state is increased. Through multiple rounds of layer-by-layer analysis and update, the node state update result is obtained. This result has higher accuracy and rationality, and provides important basic data support for the optimization decision of intelligent course timetable arrangement.

[0081] Specifically, if Figure 4 As shown in the figure, based on the node status update results, the constraints are analyzed, the impact of hard constraints and soft constraints is evaluated, the degree of violation of each constraint is calculated, and the steps to obtain the constraint optimization results are as follows:

[0082] S301: Based on the node status update result, extract the hard constraints of teacher teaching time and classroom capacity, parse the node time period and capacity parameters, compare the conflict distribution of node time and teaching time, calculate the capacity exceeding impact weight, integrate the conflict distribution data, and generate the hard constraint analysis results;

[0083] The data related to the teacher's teaching time in the node status update results are extracted one by one, and the distribution of the teacher's teaching time period is analyzed to see if there is a conflict between the time period arrangement of each node. If the time period of a course overlaps with the teacher's teaching time or exceeds the teacher's available time range, it is marked as a conflict node and the relevant parameters are recorded. The classroom capacity parameters are analyzed, and the actual number of students who choose the course when the course is arranged in a specific classroom is compared with the classroom capacity. If the number of students who choose the course exceeds the classroom capacity, the proportion of the excess capacity is counted and the degree of impact on the course arrangement is calculated. By classifying all nodes with conflict distribution, the two problems of time conflict and capacity excess are distinguished, and the conflict distribution data is integrated to form a hard constraint analysis result. The result contains detailed records of the conflict situation, which provides a clear direction and data support for subsequent adjustments.

[0084] S302: Based on the hard constraint analysis results, extract the soft constraint conditions of teacher load balance and student course selection balance, filter the teaching time and course selection frequency parameters in the nodes, analyze the conflicting nodes that do not meet the conditions and sort them out, and obtain the soft constraint analysis results;

[0085] First, according to the unresolved node conflicts in the hard constraint analysis results, the teaching time parameters related to the teacher burden balance are extracted, the total teaching time of each teacher in the current scheduling status is counted, the total teaching time is compared with the established reasonable range, the teacher nodes with too heavy or too light teaching burden are screened and the relevant parameters are recorded. At the same time, the node data of the student course selection balance is analyzed, the course selection frequency distribution of each course is counted, and the courses with too many or too few students are marked as conflict nodes. For the conflict nodes, through sorting and classification, the specific situations in which the burden balance and selection balance are not met are clarified to form the soft constraint analysis results. This result provides a soft reference for the optimization of the intelligent course schedule, ensuring that the rationality and balance of the course scheduling are further improved on the basis of meeting the hard constraints.

[0086] S303: Based on the soft constraint analysis results, extract the hard constraint and soft constraint conflict data, filter the conflict node time period, capacity, teaching time and course selection frequency parameters, calculate the conflict weight ratio and adjust the node status item by item to obtain the constraint optimization result;

[0087] Calculate the conflict weight ratio according to the formula:

[0088]

[0089] Where W represents the conflict weight ratio, C1 represents the weight coefficient of time period conflict, T1 represents the frequency of time period conflict, C2 represents the weight coefficient of capacity conflict, T2 represents the degree of capacity conflict, C3 represents the weight coefficient of teaching time conflict, F3 represents the frequency of teaching time conflict, L1 represents the average frequency of course selection, L2 represents the standard deviation of course selection frequency, D1 represents the depth of node conflict, N1 represents the number of adjustment nodes, and N2 represents the total number of conflicting nodes;

[0090] This formula is used to calculate the conflict weight ratio in the course schedule, and the result is used to guide the optimization adjustment of the conflict nodes;

[0091] C1: weight coefficient of time period conflict, set to 0.4, reflecting the importance of time conflict in the overall conflict;

[0092] T1: The frequency of time period conflicts. If it is set to 3, it means that three time conflicts occurred during the monitoring period.

[0093] C2: weight coefficient of capacity conflict, set to 0.3, reflecting the importance of classroom capacity conflict in the overall conflict;

[0094] T2: the degree of capacity conflict, which is set to 10, indicating that the number of people exceeding the classroom capacity limit is 10;

[0095] C3: The weight coefficient of the conflict of teaching time, which is set to 0.2, reflecting the importance of the conflict of teaching time in the overall conflict;

[0096] F3: The frequency of class time conflicts, set to 2, indicating that there were 2 class time conflicts during the monitoring period;

[0097] L1: the average of the course selection frequency, set to 50, indicating that each course is selected 50 times on average;

[0098] L2: standard deviation of course selection frequency, set to 5, indicating that the standard deviation of course selection frequency is 5;

[0099] D1: The depth of the node conflict, set to 4, indicating that the node level involved in the conflict is 4;

[0100] N1: The number of nodes to be adjusted. Set to 6, indicating that the number of nodes to be adjusted is 6;

[0101] N2: The total number of conflicting nodes, set to 12, indicating that the total number of conflicting nodes is 12;

[0102] Substitute the parameters into the formula for calculation:

[0103] Calculate the molecular part: C1·T1+C2·T2-C3·F3=0.4×3+0.3×10-0.2×2=1.2+3-0.4=3.8;

[0104] Take the absolute value: |3.8|=3.8;

[0105] Calculate the denominator: (L1+L2)·D1=(50+5)×4=55×4=220;

[0106] Take the square root:

[0107] Calculate the adjustment factor:

[0108] Comprehensive calculation:

[0109] The calculation result W ≈ 0.0143 shows that the conflict weight ratio of the current course arrangement is low, which means that the overall conflict level is not high, the conflict level in the course arrangement is low, and the urgency of optimization and adjustment is not high, but potential problems still need to be paid attention to.

[0110] Specifically, if Figure 5 As shown in the figure, based on the constraint optimization results, the resource allocation of the course schedule is optimized by dynamically adjusting the weights between hard constraints and soft constraints. Constraints with large weights are adjusted first. The specific steps for generating the optimized course allocation plan are as follows:

[0111] S401: Based on the constraint optimization results, extract the hard constraint and soft constraint weight data, analyze the time conflict nodes and classroom capacity allocation nodes, count the conflict status and sort the weight conditions, combine the soft constraint status data sorting conditions, and obtain the constraint weight priority data;

[0112] First, the relevant weight data of hard constraints and soft constraints are extracted from the optimization results, the nodes related to time conflicts are listed separately, and the conflict type and severity of each time conflict node are analyzed, such as the overlap between the time period of a course and the available time of the course or teacher. For the classroom capacity allocation node, the difference between the actual number of students enrolled and the allocation of classroom capacity is extracted, the nodes are marked according to the proportion of excess capacity, and the conflict status of the nodes is statistically classified. When arranging the weight conditions, the degree of influence of time conflicts and capacity allocation is hierarchically sorted to ensure that high-conflict weight nodes are given priority in subsequent adjustments. When combining the soft constraint status data, the nodes with uneven teaching burdens of teachers and unbalanced course choices of students are sorted according to their distribution in the optimization results. The corresponding priority adjustment conditions are considered comprehensively with the priority of the hard constraint nodes to form constraint weight priority data, providing a clear direction and basis for further adjustments.

[0113] S402: Based on the constraint weight priority data, extract the priority hard constraint conditions, parse the time conflict nodes and adjust the time parameter allocation, eliminate time overlap, adjust the capacity allocation status, check the teacher teaching and student selection allocation in the soft constraint conditions, integrate the adjusted node status, and obtain the course resource adjustment results;

[0114] Prioritize high-weight nodes under hard constraints, reallocate time periods of time-conflicting nodes to avoid overlapping with other courses. When adjusting time, try to retain the time period requirements of teachers and students according to the associated weights of the nodes, such as shifting time arrangements to non-high-frequency usage periods to ensure the rational use of time period resources. When adjusting capacity allocation status, prioritize nodes with excess capacity, and mitigate conflicts by reallocating classrooms, limiting the number of course selections, or increasing teaching space. For the distribution of teacher teaching and student selection in soft constraints, appropriately reduce the amount of teaching or adjust the teaching time for nodes with excessive teacher teaching burdens, and adjust the start time of courses with unbalanced student selections to improve the uniformity of selection distribution. Through multiple rounds of integrated adjustment of node status, ensure that hard constraints are met first, while taking soft constraints into account to obtain course resource adjustment results.

[0115] S403: Based on the course resource adjustment result, analyze the node time and space allocation status, check the matching of the adjusted time period and classroom capacity, calculate the course allocation status index value, integrate the adjusted node status, and obtain the optimized course allocation plan;

[0116] Calculate the course assignment status indicator value according to the formula:

[0117]

[0118] Among them, S represents the optimized course allocation status indicator value, B represents the classroom capacity, and E represents the length of the time period. Represents the total number of teachers teaching the course, A i represents the matching degree of the teacher's teaching in the i-th course, Q represents the weighted value of the student's choice preference, P represents the teaching load of the course, G represents the teacher's teaching load, and M represents the number of students;

[0119] Detailed explanation of the formula and the process of formula calculation and derivation:

[0120] This formula is used to calculate the optimized course allocation status index S. By comprehensively considering multiple factors such as classroom capacity, time period length, teacher teaching effectiveness, student preferences, course load, teacher teaching burden and student number, an optimized course resource allocation status is obtained. The calculated S value will directly affect the rationality of resource allocation. The optimized result can be used to adjust the teaching plan and resource allocation.

[0121] Classroom capacity B: This parameter refers to the maximum number of people that a classroom can accommodate. It is determined based on the size of the actual venue, facility configuration, and teaching needs. It is obtained by measuring and counting the number of people that can be accommodated in each classroom. In the specific case, the capacity of classroom 1 is 60 people, the capacity of classroom 2 is 80 people, and the capacity of classroom 3 is 50 people.

[0122] Time segment length E: refers to the duration of each teaching time segment, in hours. According to the teaching arrangement, the time segment length is determined between 1 and 3 hours. In the actual teaching process, according to the course arrangement, the time segment is set to 1.5 hours;

[0123] The total effectiveness of teachers' teaching This parameter is the sum of the teacher teaching matching degrees of the courses. The teacher teaching matching degree of each course is A. i It reflects the matching degree between the teacher's teaching quality and the course requirements. The matching degree ranges from 0 to 1. The closer to 1, the higher the matching degree. The weighted calculation is performed based on the teacher's historical teaching evaluation, course requirements and teaching expertise. For this case, the teacher's teaching matching value A1 is 0.8, A2 is 0.9, and A3 is 0.85. Therefore, the total teaching effectiveness is:

[0124] The weighted value Q of student selection preference: This parameter reflects the student's preference for courses. It is weighted and calculated based on the student's historical course selection data, course evaluation, and course content. The weighted value of each course is affected by the number of students enrolled and the student's preference. In this case, the preference value of course 1 is 1.2, the preference value of course 2 is 1.1, and the preference value of course 3 is 1.0. Therefore, the weighted value Q of the student's selection preference is: Q = 1.2 + 1.1 + 1.0) = 3.3;

[0125] Course teaching load P: represents the teaching burden of each course, which is obtained by comprehensive evaluation of course duration and complexity of course content. According to teaching needs, the course load factor is calculated as follows: load = teaching hours × course complexity index. The load of course 1 is set to 1.5, the load of course 2 is set to 1.8, and the load of course 3 is set to 1.4. Therefore, the load P is: P = (1.5 + 1.8 + 1.4) = 4.7;

[0126] Teacher teaching burden G: refers to the total teaching time or number of teaching times per week, reflecting the teacher's work intensity. The teacher's teaching burden is calculated based on the teaching schedule and working hours. For example, Teacher 1's teaching time per week is 12 hours, Teacher 2's teaching time per week is 10 hours, and Teacher 3's teaching time per week is 15 hours. Therefore, the teacher's teaching burden G is: G = (12 + 10 + 15) = 37 hours;

[0127] Number of students M: represents the total number of students taking each course. In this case, the number of students in Course 1 is 200, the number of students in Course 2 is 150, and the number of students in Course 3 is 180. Therefore, the number of students M is: M = (200 + 150 + 180) = 530;

[0128] The parameters are as follows: B = 60 (the capacity of the selected classroom is set to 60 people), T = 1.5 (the length of the time period is 1.5 hours), (the sum of the effectiveness of teachers’ teaching), Q = 3.3 (the weighted value of students’ choice preference), P = 4.7 (course teaching load), G = 37 (teacher’s teaching load), M = 530 (number of students);

[0129] Substitute into the calculation:

[0130]

[0131] The calculation result S≈2.45 shows that the optimized course allocation status index value is 2.45, which reflects the degree of optimization of resource allocation. The higher the value, the better the optimization effect of resource matching and scheduling, and the more efficiently it can meet multiple factors such as classroom capacity, time arrangement, teacher teaching and student needs.

[0132] Specifically, if Figure 6 As shown in the figure, based on the optimized course allocation plan, combined with real-time change data, the course schedule is adjusted in real time. According to the node status, the weight of the edge is updated, the relationship between each node is evaluated, the time schedule is adjusted, information transmission is performed and the node status is updated. The specific steps for generating a dynamically adjusted intelligent course schedule are as follows:

[0133] S501: Based on the optimized course allocation plan, extract the student course selection and teacher available time data, list the course time constraints, student needs and teacher time matching conditions one by one, analyze the initial relationship between courses and time, check conflicts and duplications, and obtain the initial course time allocation table;

[0134] First, integrate the student course selection records with the teacher's available time data, and list the time constraints of each course in detail, including the course's teaching cycle, duration, and the available time range of the required classroom. For student needs, analyze the distribution of their total course selection and course time to ensure that there is no time overlap or excessive concentration in each student's schedule. According to the teacher's time matching conditions, compare each teacher's teaching time schedule with the course schedule one by one to avoid teachers being unable to complete their teaching tasks due to time conflicts. When analyzing the initial relationship between courses and time, construct a mapping table between courses and time periods, clarify the correspondence between courses and node times, and screen for conflicts and duplications, such as multiple courses being scheduled in the same time period or the same teacher needing to teach at the same time. By counting and classifying all conflicts, an initial course time allocation table containing all course time constraints and associations is formed, providing a clear reference for dynamic adjustments.

[0135] S502: Based on the initial course time allocation table, extract the data of newly added course selection, teacher time period update and student course withdrawal, parse the affected course nodes, associate and analyze the changed data and map the course time node relationship, update the node weight, and obtain the dynamic course association structure data;

[0136] From the newly added course selection data, extract the courses and time period information selected by students one by one, map the newly added course demand to the original time schedule, analyze the changes in classroom capacity and time period pressure caused by the newly added course selection, update the teacher time period data, and analyze the impact of teacher time adjustment on the courses he teaches, such as course conflicts or misalignment with student needs caused by time period changes. For student course withdrawal data, check one by one whether the change in the number of students enrolled in the affected courses changes the classroom capacity utilization rate, and analyze the impact of course withdrawal on the teacher's teaching time load. When associating and analyzing the changed data, associate and map all affected nodes with adjacent nodes to form a dynamic adjustment model of the course time node relationship. By updating the node weights, redistribute the time period pressure caused by the changes in the new or exit data, ensure that the dynamic course association structure data can reflect the latest course selection and teacher time adjustment, and provide accurate input data for subsequent course time optimization.

[0137] S503: Based on the dynamic course association structure data, adjust the course node time schedule, resolve the conflicting edges and reallocate the time periods, optimize the conflicting node arrangement, maintain the original allocation of non-conflicting nodes, update the association weights between nodes, check the correctness of the adjusted arrangement, and generate a dynamically adjusted intelligent course scheduling plan;

[0138] First, the course nodes in the dynamic course association structure data are checked one by one, and the conflicting nodes and edges caused by changes in time periods or the number of course enrollments are located. The conflicting edges are reallocated, and the time periods are adjusted to unoccupied available time periods, while ensuring that they match the teacher's teaching time and the classroom usage time. When optimizing the arrangement of conflicting nodes, the scheme with the least overlap of time periods is given priority to minimize the impact on course nodes, and the original allocation of non-conflicting nodes is maintained to avoid affecting the stability of the overall arrangement due to the adjustment of conflicting nodes. When updating the association weights between nodes, the weight of each edge is recalculated according to the adjusted time period, and the latest course schedule is closely combined with students' course selection needs, teacher time constraints and classroom utilization. When checking the correctness of the adjusted arrangement, the time arrangement and hard constraints of each node are checked one by one to ensure that all course arrangements meet the established requirements, and a dynamically adjusted intelligent course arrangement plan is generated to provide optimized and reasonable results for the implementation of intelligent scheduling.

[0139] like Figure 7 As shown, an intelligent course schedule arrangement system includes:

[0140] The teacher information processing module extracts the teacher's available time period based on the information of teachers, students, courses, and classrooms, analyzes the matching between course types and time periods, screens the course-related data within the time period, allocates teaching time nodes, and screens the matching data based on course types and time nodes to obtain teacher teaching-related information;

[0141] The student information processing module screens the course selection demand data based on the student course selection and registration status data, cross-checks the registered courses with the unmet course requirements, analyzes the unmatched items and the course selection range, integrates the matched requirements and status data, and obtains the student course selection status;

[0142] The course association construction module extracts teaching time periods, student needs and classroom capacity based on teacher teaching association information and student course selection status, analyzes time conflicts and overcapacity data, maps the relationship between courses, teachers, students and classrooms, assigns priority weights, screens and adjusts conflicting items, and obtains course association relationship graph data;

[0143] The status information update module is based on the course association graph data, analyzes the teaching time period, student demand and classroom capacity data, screens the edge weights of adjacent nodes, parses and updates the status parameters, transfers the updated status to adjacent nodes, iterates the weight and status transfer, and generates the node status update results;

[0144] The constraint evaluation module screens the teaching time conflict and classroom capacity overload data based on the node status update results, extracts the balance data between teacher burden and student course selection demand, analyzes the difference between hard constraints and soft constraints, screens the constraint deviation data, integrates the comparison results, and generates the constraint analysis results;

[0145] The dynamic course adjustment module is based on the results of constraint analysis, combined with the changing student course selection and teacher available time data, to screen the node status in the changing data, extract the edge weights and adjust the weights and time schedules, update the course association and time allocation data, screen the adjusted conflicting nodes and status relationships, and generate a dynamically adjusted intelligent course scheduling plan.

[0146] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An intelligent course schedule arrangement method, characterized in that: The following steps are involved: Based on the information of teachers, students, courses and classrooms, define teacher nodes, student nodes, course nodes and classroom nodes, establish the relationship between nodes, analyze time conflicts, burdens and classroom capacity, assign corresponding weights to each edge and obtain graph structure data; Based on the graph structure data, information is transmitted on the relationship between nodes, each node is initialized, the influence of the edge weights of adjacent nodes is analyzed, node information is updated according to the edge weights, and state information between nodes is transmitted layer by layer to obtain node state update results; Based on the node status update result, the constraint conditions are analyzed, the influence of hard constraints and soft constraints is evaluated, the violation degree of each constraint is calculated, and the constraint condition optimization result is obtained; Based on the optimization results of the constraint conditions, the resource allocation of the course schedule is optimized by dynamically adjusting the weights between the hard constraints and the soft constraints, and the constraint conditions with large weights are adjusted first to generate an optimized course allocation plan; Based on the optimized course allocation plan, combined with real-time changing data, the course schedule is adjusted in real time. According to the node status, the weight of the edge is updated, the relationship between each node is evaluated, the time schedule is adjusted, information transmission is executed and the node status is updated, and a dynamically adjusted intelligent course scheduling plan is generated.

2. The intelligent course schedule arrangement method according to claim 1, characterized in that: The graph structure data includes teacher nodes, student nodes, course nodes, classroom nodes and their mutual relationships; the node status update result includes the status after the node information is updated; the constraint optimization result includes the degree of conflict between teacher teaching time, the degree of classroom capacity limitation, the degree of balance between teacher burdens, and the degree of balance between student course selections; the optimized course allocation plan includes a resource allocation optimization plan and a priority adjustment result; the dynamically adjusted intelligent course scheduling plan includes real-time course adjustment results, updated node status, and edge weight update status.

3. The intelligent course schedule arrangement method according to claim 1, characterized in that: Based on the information of teachers, students, courses, and classrooms, define teacher nodes, student nodes, course nodes, and classroom nodes, establish the relationship between nodes, analyze time conflicts, burdens, and classroom capacity, and assign corresponding weights to each edge. The specific steps to obtain graph structure data are as follows: Based on the information of teachers, students, courses and classrooms, we extract the teacher course allocation records, student course selection data, course time schedule, classroom number and capacity, clean up irrelevant data and fill in missing items, integrate classified data, and obtain the node basic data set; Based on the node basic data set, analyze the teacher course number list, extract the student course selection records, call the course-related classroom number and available time period information, build the teacher course, student course, course classroom related data table, correct the duplicate and conflicting items, summarize the corrected data, and obtain the node relationship network; Based on the node relationship network, each edge is assigned a weight index, the quantitative index of teacher course hour distribution is called, the student course time matching records are analyzed, the classroom capacity utilization rate and the course conflict ratio are calculated, the edges are assigned corresponding weights, the incorrectly assigned edges are corrected, and the graph structure data is obtained.

4. The intelligent course schedule arrangement method according to claim 1, characterized in that: Based on the graph structure data, information is transmitted between nodes, each node is initialized, the influence of the edge weights of adjacent nodes is analyzed, node information is updated according to the edge weights, and the state information between nodes is transmitted layer by layer. The specific steps of obtaining the node state update result are: Based on the graph structure data, extract the edge weights of the relationships between nodes, analyze the numerical impact of the edge weights on the states of the associated nodes, integrate the edge weights into the initial states of the nodes, accumulate the node state values, and obtain the initial update results of the node states; Based on the initial update result of the node state, the node state value and the weight of the adjacent edges are extracted, the adjacent node state values ​​are weighted and transmitted to the target node, the state distribution range is adjusted in combination with normalization, the processed state values ​​are integrated, and the node state change result is obtained; Based on the node state change result, the node state value is parsed layer by layer, the numerical parameters are extracted and gradually transferred to the target node, the parameters are cumulatively transferred to the target node state, the influence of the edge weight on the cumulative value is analyzed and updated, and the node state update result is obtained.

5. The intelligent course schedule arrangement method according to claim 1, characterized in that: Based on the node status update result, the constraint conditions are analyzed, the influence of hard constraints and soft constraints is evaluated, the violation degree of each constraint is calculated, and the steps of obtaining the constraint condition optimization result are specifically as follows: Based on the node status update result, extract the hard constraints of teacher teaching time and classroom capacity, parse the node time period and capacity parameters, compare the conflict distribution of node time and teaching time, calculate the capacity exceeding impact weight, integrate the conflict distribution data, and generate hard constraint analysis results; Based on the hard constraint analysis results, extract the soft constraint conditions of teacher load balance and student course selection balance, filter the teaching time and course selection frequency parameters in the nodes, analyze the conflicting nodes that do not meet the conditions and sort them out, and obtain the soft constraint analysis results; Based on the soft constraint analysis results, the hard constraint and soft constraint conflict data are extracted, the conflict node time period, capacity, teaching duration and course selection frequency parameters are screened, the conflict weight ratio is calculated and the node status is adjusted item by item to obtain the constraint optimization result.

6. The intelligent course schedule arrangement method according to claim 5, characterized in that: The conflict weight ratio is calculated according to the formula: Among them, W represents the conflict weight ratio, C1 represents the weight coefficient of time period conflict, T1 represents the frequency of time period conflict, C2 represents the weight coefficient of capacity conflict, T2 represents the degree of capacity conflict, C3 represents the weight coefficient of teaching time conflict, F3 represents the frequency of teaching time conflict, L1 represents the mean value of course selection frequency, L2 represents the standard deviation of course selection frequency, D1 represents the depth of node conflict, N1 represents the number of adjustment nodes, and N2 represents the total number of conflicting nodes.

7. The intelligent course schedule arrangement method according to claim 1, characterized in that: Based on the constraint optimization results, the resource allocation of the course schedule is optimized by dynamically adjusting the weights between the hard constraints and the soft constraints. The constraints with large weights are adjusted first. The steps for generating the optimized course allocation plan are as follows: Based on the constraint optimization results, extract the hard constraint and soft constraint weight data, analyze the time conflict nodes and classroom capacity allocation nodes, count the conflict status and sort the weight conditions, and obtain the constraint weight priority data in combination with the soft constraint status data sorting conditions; Based on the constraint weight priority data, priority hard constraints are extracted, time conflict nodes are resolved and time parameter allocation is adjusted, time overlap is eliminated, capacity allocation status is adjusted, teacher teaching and student selection allocation in soft constraints are checked, the adjusted node status is integrated, and course resource adjustment results are obtained; Based on the course resource adjustment results, the node time and space allocation status is analyzed, the matching of the adjusted time period and classroom capacity is checked, the course allocation status index value is calculated, the adjusted node status is integrated, and the optimized course allocation plan is obtained.

8. The intelligent course schedule arrangement method according to claim 7, characterized in that: Calculate the course assignment status indicator value according to the formula: Among them, S represents the optimized course allocation status indicator value, B represents the classroom capacity, and E represents the length of the time period. Represents the total number of teachers teaching the course, A i It represents the matching degree of the teacher’s teaching in the i-th course, Q represents the weighted value of the student’s choice preference, P represents the teaching load of the course, G represents the teacher’s teaching burden, and M represents the number of students.

9. The intelligent course schedule arrangement method according to claim 1, characterized in that: Based on the optimized course allocation plan, combined with real-time change data, the course schedule is adjusted in real time, the weight of the edge is updated according to the node status, the relationship between each node is evaluated, the time arrangement is adjusted, information transmission is performed and the node status is updated, and the steps of generating a dynamically adjusted intelligent course arrangement plan are as follows: Based on the optimized course allocation plan, extract the student course selection and teacher available time data, list the course time constraints, student needs and teacher time matching conditions one by one, analyze the initial relationship between courses and time, check conflicts and duplications, and obtain the initial course time allocation table; Based on the initial course time allocation table, extract the newly added course selection, teacher time period update and student course withdrawal data, parse the affected course nodes, associate and analyze the change data and map the course time node relationship, update the node weight, and obtain dynamic course association structure data; Based on the dynamic course association structure data, the course node time schedule is adjusted, the conflicting edges are resolved and the time periods are reallocated, the conflicting node arrangement is optimized, the original allocation of non-conflicting nodes is maintained, the association weights between nodes are updated, the correctness of the adjusted arrangement is checked, and a dynamically adjusted intelligent course scheduling plan is generated.

10. An intelligent curriculum timetable arrangement system, characterized in that: According to the intelligent course schedule arrangement method according to any one of claims 1 to 9, the system comprises: The teacher information processing module extracts the teacher's available time period based on the information of teachers, students, courses, and classrooms, analyzes the matching between course types and time periods, screens the course-related data within the time period, allocates teaching time nodes, and screens the matching data based on course types and time nodes to obtain teacher teaching-related information; The student information processing module screens the course selection demand data based on the student course selection and registration status data, cross-checks the registered courses with the unmet course requirements, analyzes the unmatched items and the course selection range, integrates the matched requirements and status data, and obtains the student course selection status; The course association construction module extracts the teaching time period, student demand and classroom capacity based on the teacher teaching association information and student course selection status, analyzes time conflict and overcapacity data, maps the relationship between courses, teachers, students and classrooms, assigns priority weights, screens and adjusts conflicting items, and obtains course association relationship graph data; The status information update module analyzes the teaching time period, student demand and classroom capacity data based on the course association relationship graph data, screens the edge weights of adjacent nodes, parses and updates the status parameters, transfers the updated status to adjacent nodes, iterates the weight and status transfer, and generates the node status update result; The constraint evaluation module screens the teaching time conflict and classroom capacity overload data based on the node status update results, extracts the teacher burden and student course selection demand balance data, analyzes the hard constraint and soft constraint differences, screens the constraint deviation data, integrates the comparison results, and generates the constraint analysis results; The course dynamic adjustment module is based on the constraint analysis results, combined with the changed student course selection and teacher available time data, to screen the node status in the changed data, extract the edge weights and adjust the weights and time schedules, update the course association and time allocation data, screen the adjusted conflicting nodes and status relationships, and generate a dynamically adjusted intelligent course scheduling plan.

Images