Teaching resource scheduling system and method driven by multi-parameter optimization algorithm

Abstract

The invention discloses a teaching resource scheduling system and method driven by a multi-parameter optimization algorithm. The method comprises the steps of collecting teaching subject types, time consumption of each subject, the total class number, the student number of each class, the classroom capacity and the teaching subject of each teacher in a semester; setting a target condition of the teaching resource scheduling scheme, wherein the target condition comprises a maximum resource utilization rate; setting constraint conditions of the teaching resource scheduling scheme, wherein the constraint conditions comprise a classroom capacity constraint, a teacher time constraint and a classroom uniqueness constraint; according to the target condition and the constraint condition, utilizing an optimization heuristic algorithm to generate an optimal teaching resource scheduling scheme; the resource utilization rate is maximized, the number of times of violating teacher time constraints is reduced, the teacher interval time is reasonably arranged, it is ensured that the teachers have enough lesson preparation and rest time, and the teaching efficiency, quality and teacher satisfaction are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of teaching resource scheduling, and in particular to a teaching resource scheduling system and method driven by a multi-parameter optimization algorithm. Background Art

[0002] In the modern educational environment, the efficient scheduling and reasonable allocation of teaching resources (including teachers, classrooms, etc.) are key tasks in the management of schools and educational institutions. With the continuous increase in the number of courses and teaching needs, how to arrange courses under limited resource conditions and avoid teacher teaching conflicts, waste of resources and insufficient teaching venues has become an important challenge in teaching management.

[0003] Traditional teaching resource scheduling mainly relies on manual arrangement or simple scheduling software. These methods can meet the needs when the scale is small and the constraints are few. However, with the expansion of school scale and the complexity of teaching requirements, such methods are stretched; manual scheduling is not only time-consuming and labor-intensive, but also lacks flexibility and cannot achieve optimal scheduling under multiple constraints, thus affecting teaching efficiency and resource utilization.

[0004] Therefore, it is an urgent problem for those skilled in the art to propose a teaching resource scheduling system and method driven by a multi-parameter optimization algorithm to solve the difficulties existing in the prior art. Summary of the invention

[0005] The purpose of the present invention is to provide a teaching resource scheduling system and method driven by a multi-parameter optimization algorithm to solve the deficiencies in the background technology.

[0006] In order to achieve the above object, the present invention provides the following technical solution: a teaching resource scheduling method driven by a multi-parameter optimization algorithm, comprising:

[0007] Collect the types of subjects taught during the semester, the time spent on each subject, the total number of classes, the number of students in each class, the capacity of each classroom, and the subjects taught by each teacher;

[0008] Set the target conditions for the teaching resource scheduling plan: The target conditions include maximizing resource utilization;

[0009] Set the constraints of the teaching resource scheduling plan, including classroom capacity constraints, teacher time constraints and classroom uniqueness constraints;

[0010] According to the target conditions and constraints, the optimization heuristic algorithm is used to generate the optimal teaching resource scheduling plan.

[0011] Furthermore, the time required for each subject is the average number of classes required to complete all teaching of the subject; the teacher time constraint is that each teacher can only teach one class in the same day and time period; the classroom uniqueness constraint is that a classroom can only arrange one subject in the same time period.

[0012] Furthermore, the method for generating the optimal teaching resource scheduling scheme includes:

[0013] Step 10, randomly generate n groups of scheduling plans, each group of scheduling plans includes J days of subject arrangement data, each day of subject arrangement data includes K class arrangement data, the product of J and K is less than or equal to the total number of classes, and the course arrangement data includes subject type, time, classroom, teacher and class;

[0014] Step 11, calculating the fitness value of each group of scheduling schemes;

[0015] Step 12: Sort the fitness values ​​in descending order, select the scheduling scheme corresponding to the first y fitness values, y<n, and mark it as the parent scheduling scheme;

[0016] Step 13: Perform cross-operation on any day's subject arrangement data in any two groups of parent scheduling plans to generate a child scheduling plan;

[0017] Step 14: Perform random position mutation on any two days of any class schedule data in the child scheduling plan to generate a new scheduling plan, and update n groups of scheduling plans;

[0018] Step 15: Repeat steps 11 to 14, stop iteration when the preset number of iterations is reached, and select the scheduling plan with the highest fitness as the preliminary scheduling plan;

[0019] Step 16: randomly combine the J-day subject arrangement data in the preliminary scheduling plan into U groups of unit-day subject arrangement data, where U is an integer greater than 1 and less than the ratio of J to the unit day;

[0020] Step 17, the subject arrangement data of group U unit days is replicated E times, and alternative scheduling schemes of group U are generated, and the fitness values ​​of alternative scheduling schemes of group U are calculated in sequence; E is less than or equal to the ratio of J to the number of unit days;

[0021] Step 18: Select the alternative scheduling scheme with the largest fitness value from the U group of alternative scheduling schemes as the optimal teaching resource scheduling scheme.

[0022] Furthermore, the method for calculating the fitness value of the scheduling scheme includes:

[0023]

[0024]

[0025] In the formula, SZ n is the fitness value of the nth group of scheduling schemes; SY j SK is the scheduling fitness value of the K-class course scheduling data on the jth day in the nth group scheduling plan; j is the sum of the number of violations of the teacher's time constraint on the jth day in the nth group scheduling plan; JC j is the number of classrooms not scheduled on the jth day in the nth group scheduling plan; RB j is the classroom capacity ratio on the jth day in the nth group scheduling plan;

[0026] KS n KC is the class time fitness value of the nth group scheduling plan; i KS is the time taken by the i-th subject in the n-th group scheduling plan; i is the actual scheduled time for the i-th subject in the n-th group scheduling plan; I is the total number of subject types; β1, β2, α1, α2, α3, and α4 are all preset coefficients, which are values ​​greater than 0.

[0027] Furthermore, the classroom capacity ratio is the absolute value of the difference between the sum of the number of students attending each class and the corresponding classroom capacity ratio and 1.

[0028] Furthermore, the number of unscheduled classrooms on the jth day is the sum of the number of unscheduled classrooms when each class is scheduled on the jth day.

[0029] Furthermore, the actual scheduled time for the i-th subject is the sum of the total number of classes scheduled for the i-th subject in the scheduling plan.

[0030] Furthermore, obtaining the optimal teaching resource scheduling plan also includes sorting the fitness values ​​of the U group of alternative scheduling plans in descending order, selecting the first Q group of alternative scheduling plans, and selecting the alternative scheduling plan with the largest teacher interval time coefficient from the Q group of alternative scheduling plans as the optimal teaching resource scheduling plan; replacing step 18.

[0031] Furthermore, the teacher interval coefficient is the reciprocal of the sum of the number of times the teacher gives consecutive lectures within a unit number of days.

[0032] A teaching resource scheduling system driven by a multi-parameter optimization algorithm is used to implement the teaching resource scheduling method driven by the multi-parameter optimization algorithm. The system includes:

[0033] The data collection module is used to collect the types of subjects taught during the semester, the time spent on each subject, the total number of classes, the number of students in each class, the capacity of each classroom, and the subjects taught by each teacher;

[0034] The target setting module is used to set the target conditions of the teaching resource scheduling plan: the target conditions include maximizing resource utilization;

[0035] The constraint setting module is used to set the constraint conditions of the teaching resource scheduling plan, including classroom capacity constraint, teacher time constraint and classroom uniqueness constraint;

[0036] The scheduling module is used to generate the optimal teaching resource scheduling plan based on the target conditions and constraints using the optimization heuristic algorithm.

[0037] The technical effects of the teaching resource scheduling system and method driven by a multi-parameter optimization algorithm provided by the present invention are as follows:

[0038] The present invention realizes the optimal resource allocation in a complex teaching environment; in order to achieve efficient scheduling, the system sets strict constraints, including classroom capacity constraints, teacher time constraints, and classroom uniqueness constraints; the system first randomly generates multiple groups of scheduling plans, each group of plans covers the subject arrangement data for the entire semester.

[0039] The fitness of each scheduling scheme is obtained by calculating the following factors: the number of unscheduled classrooms per day, the sum of the number of violations of teacher time constraints, and the classroom capacity ratio; the fitness calculation combines these factors to evaluate the resource utilization and constraint violations of each scheduling scheme; after fitness sorting, the first several groups of schemes are selected as "parents" and new schemes are generated through crossover operations. The crossover operation is achieved by exchanging the subject schedule data of different days in the parent scheme to promote genetic recombination and diversity.

[0040] To avoid local optimal solutions, the system randomly mutates the positions of child plans in each round of iteration, such as swapping the class schedule data for any two days. This mutation step ensures the flexibility and diversity of the scheduling plan and promotes global optimization. After multiple iterations, the plan with the highest fitness is selected as the preliminary scheduling plan.

[0041] Subsequently, the preliminary plan is split into several groups of units (such as a weekly course schedule), and multiple alternative scheduling plans are generated; then the optimal alternative plan is selected through fitness calculation to maximize resource utilization, reduce the number of violations of teacher time constraints, and reasonably arrange teacher intervals, etc., to ensure that teachers have enough time to prepare lessons and rest, and to improve teaching efficiency, quality and teacher satisfaction.

[0042] The scheduling plan generated by this optimization process can significantly reduce conflicts in teaching resources, improve classroom utilization, and achieve efficient allocation of teaching resources; this plan not only improves teaching effectiveness and the rationality of course arrangements, but also improves the satisfaction of teachers and students, ensuring the smoothness and quality of the teaching process. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0044] Figure 1 A schematic diagram of a teaching resource scheduling system driven by a multi-parameter optimization algorithm of the present invention;

[0045] Figure 2 The scheduling scheme of the present invention comprises a schematic diagram;

[0046] Figure 3 This is a flow chart of the teaching resource scheduling method driven by the multi-parameter optimization algorithm of the present invention. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be an intermediate element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be an intermediate element at the same time.

[0049] Example 1

[0050] like Figure 1 As shown, the teaching resource scheduling system and method driven by the multi-parameter optimization algorithm of this embodiment include a data acquisition module, a target setting module, a constraint setting module and a scheduling module, which are connected by wire and / or wirelessly.

[0051] The data collection module is used to collect information on the types of subjects taught during the semester, the time required for each subject (i.e. the average number of classes required to complete all teaching of the subject), the total number of classes (i.e. the sum of the time required for each subject), the number of students in each class, the capacity of each classroom, and the subjects taught by each teacher.

[0052] The target setting module is used to set the target conditions of the teaching resource scheduling plan: the target conditions include maximizing resource utilization.

[0053] The constraint setting module is used to set the constraints of the teaching resource scheduling plan. The constraints include classroom capacity constraints (i.e. the number of students in a class cannot exceed the capacity of the arranged classroom), teacher time constraints (i.e. each teacher can only teach one class on the same day and at the same time period), and classroom uniqueness constraints (i.e. a classroom can only arrange one subject at the same time period).

[0054] The scheduling module is used to generate the optimal teaching resource scheduling plan based on the target conditions and constraints using the optimization heuristic algorithm.

[0055] The method of generating the optimal teaching resource scheduling plan includes:

[0056] See also Figure 2 As shown, step 10, randomly generate n groups of scheduling plans, each group of scheduling plans includes J days of subject arrangement data, each day of subject arrangement data includes K class arrangement data, the product of J and K is less than or equal to the total number of classes; the course arrangement data includes subject type, time, classroom, teacher and class.

[0057] Step 11, calculating the fitness value of each group of scheduling schemes;

[0058]

[0059] In the formula, SZ n is the fitness value of the nth group of scheduling schemes; SY j SK is the scheduling fitness value of the K-class course scheduling data on the jth day in the nth group scheduling plan; j is the sum of the number of violations of the teacher's time constraint on the jth day in the nth group scheduling plan; JC j is the number of classrooms not scheduled on the jth day in the nth group scheduling plan, that is, the sum of the number of classrooms not scheduled when each class is scheduled on the jth day. For example, if there are K classes in a day, the number of classrooms not scheduled when the first class is scheduled is 0, and so on. The sum of the number of classrooms not scheduled when each class is scheduled is the number of classrooms not scheduled; RB j is the classroom capacity ratio on the jth day in the nth group scheduling plan (i.e., the absolute value of the difference between the sum of the number of students attending each class and the corresponding classroom capacity ratio and 1, and the number of students attending the class is determined according to the class); the above indicators reflect the resource utilization rate.

[0060] KS n KC is the class time fitness value of the nth group scheduling plan; i KS is the time required for the i-th subject in the n-th group scheduling plan (i.e., the average number of classes required to complete all teaching of the subject); iis the actual time scheduled for the i-th subject in the n-th group scheduling plan (i.e., the total number of classes scheduled for the i-th subject in the scheduling plan); I is the total number of subject types. β1, β2, α1, α2, α3, and α4 are all preset coefficients, which are values ​​greater than 0.

[0061] Step 12: Sort the fitness values ​​in descending order, select the scheduling scheme corresponding to the first y fitness values, y<n, and mark it as the parent scheduling scheme.

[0062] Step 13: Perform cross-operation on any day's subject arrangement data in any two groups of parent scheduling plans to generate a child scheduling plan.

[0063] It is further explained that cross-operation is performed on the subject arrangement data of any day, for example, the subject arrangement data of the 5th day of two sets of parent scheduling schemes are swapped to ensure the diversity of the schemes and avoid falling into local optimality.

[0064] Step 14: Perform random position mutation on any two days of any class schedule data in the offspring scheduling plan, generate a new scheduling plan, and update n groups of scheduling plans.

[0065] To further illustrate, the random position variation, for example, swaps the fifth class schedule data corresponding to the fifth day and the tenth day of the offspring scheduling plan.

[0066] Step 15: Repeat steps 11 to 14, stop iteration when the preset number of iterations is reached, and select the scheduling plan with the highest fitness as the preliminary scheduling plan.

[0067] Step 16. Randomly combine the J days of subject arrangement data in the preliminary scheduling plan into U groups of unit day subject arrangement data. Odd-numbered days can be 5 days as a unit or 10 days as a unit. You can choose according to the actual situation. Usually 5 days are a unit day, that is, one week of subject arrangement data. U is an integer greater than 1 and less than the ratio of J to the unit day.

[0068] Step 17, copy the subject arrangement data of group U unit days E times, generate alternative scheduling plans for group U, and calculate the fitness values ​​of the alternative scheduling plans for group U in turn (the fitness value calculation method is consistent with the scheduling plan); E is less than or equal to the ratio of J to the number of unit days; avoid the product of group U unit days and E exceeding J days, that is, complete the teaching of all subjects within J days.

[0069] Step 18: Select the alternative scheduling scheme with the largest fitness value from the U group of alternative scheduling schemes as the optimal teaching resource scheduling scheme.

[0070] Example 2

[0071] This embodiment provides another method for obtaining the optimal teaching resource scheduling plan, which takes into account that teachers feel tired and their energy decreases after teaching many classes in a row, which affects the teaching quality and reduces student satisfaction. Obtaining the optimal teaching resource scheduling plan also includes sorting the fitness values ​​of the U group of alternative scheduling plans in descending order, selecting the first Q groups of alternative scheduling plans, and selecting the alternative scheduling plan with the largest teacher interval time coefficient from the Q group of alternative scheduling plans as the optimal teaching resource scheduling plan, replacing step 18.

[0072] The teacher interval coefficient is the reciprocal of the sum of the number of times the teacher gives consecutive classes on each day within a unit number of days.

[0073] In this embodiment, when selecting the optimal teaching resource scheduling plan, the target conditions and constraint conditions are taken into consideration, and an alternative scheduling plan with a teacher interval time coefficient is selected to avoid arranging teachers to teach continuously to the greatest extent possible, so that teachers have sufficient preparation time and rest time, improve the teaching quality, and achieve teaching resource scheduling with maximum teacher satisfaction and optimal teaching quality.

[0074] Example 2

[0075] See also Figure 3 As shown, this embodiment provides a teaching resource scheduling method driven by a multi-parameter optimization algorithm, including:

[0076] Collect the types of subjects taught during the semester, the time spent on each subject, the total number of classes, the number of students in each class, the capacity of each classroom, and the subjects taught by each teacher;

[0077] Set the target conditions for the teaching resource scheduling plan: The target conditions include maximizing resource utilization;

[0078] Set the constraints of the teaching resource scheduling plan, including classroom capacity constraints, teacher time constraints and classroom uniqueness constraints;

[0079] According to the target conditions and constraints, the optimization heuristic algorithm is used to generate the optimal teaching resource scheduling plan.

[0080] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A teaching resource scheduling method driven by a multi-parameter optimization algorithm, characterized in that: include: Collect the types of subjects taught during the semester, the time spent on each subject, the total number of classes, the number of students in each class, the capacity of each classroom, and the subjects taught by each teacher; Set the target conditions for the teaching resource scheduling plan: The target conditions include maximizing resource utilization; Set the constraints of the teaching resource scheduling plan, including classroom capacity constraints, teacher time constraints and classroom uniqueness constraints; According to the target conditions and constraints, the optimization heuristic algorithm is used to generate the optimal teaching resource scheduling plan.

2. The teaching resource scheduling method driven by a multi-parameter optimization algorithm according to claim 1, characterized in that: The time required for each subject is the average number of classes required to complete all teaching of the subject; the teacher time constraint is that each teacher can only teach one class in the same day and time period; the classroom uniqueness constraint is that a classroom can only arrange one subject in the same time period.

3. The teaching resource scheduling method driven by a multi-parameter optimization algorithm according to claim 2 is characterized in that: The method of generating the optimal teaching resource scheduling plan includes: Step 10, randomly generate n groups of scheduling plans, each group of scheduling plans includes J days of subject arrangement data, each day of subject arrangement data includes K class arrangement data, the product of J and K is less than or equal to the total number of classes, and the course arrangement data includes subject type, time, classroom, teacher and class; Step 11, calculating the fitness value of each group of scheduling schemes; Step 12: Sort the fitness values ​​in descending order, select the scheduling scheme corresponding to the first y fitness values, y<n, and mark it as the parent scheduling scheme; Step 13: Perform cross-operation on any day's subject arrangement data in any two groups of parent scheduling plans to generate a child scheduling plan; Step 14: Perform random position mutation on any two days of any class schedule data in the child scheduling plan to generate a new scheduling plan, and update n groups of scheduling plans; Step 15: Repeat steps 11 to 14, stop iteration when the preset number of iterations is reached, and select the scheduling plan with the highest fitness as the preliminary scheduling plan; Step 16: randomly combine the J-day subject arrangement data in the preliminary scheduling plan into U groups of unit-day subject arrangement data, where U is an integer greater than 1 and less than the ratio of J to the unit day; Step 17, the subject arrangement data of group U unit days is replicated E times, and alternative scheduling schemes of group U are generated, and the fitness values ​​of alternative scheduling schemes of group U are calculated in sequence; E is less than or equal to the ratio of J to the number of unit days; Step 18: Select the alternative scheduling scheme with the largest fitness value from the U group of alternative scheduling schemes as the optimal teaching resource scheduling scheme.

4. The teaching resource scheduling method driven by a multi-parameter optimization algorithm according to claim 3 is characterized in that: The fitness value calculation method of the scheduling scheme includes: In the formula, SZ n is the fitness value of the nth group of scheduling schemes; SY j SK is the scheduling fitness value of the K-class course scheduling data on the jth day in the nth group scheduling plan; j is the sum of the number of violations of the teacher's time constraint on the jth day in the nth group scheduling plan; JC j is the number of classrooms not scheduled on the jth day in the nth group scheduling plan; RB j is the classroom capacity ratio on the jth day in the nth group scheduling plan; KS n KC is the class time fitness value of the nth group scheduling plan; i KS is the time taken by the i-th subject in the n-th group scheduling plan; i is the actual scheduled time for the i-th subject in the n-th group scheduling plan; I is the total number of subject types; β1, β2, α1, α2, α3, and α4 are all preset coefficients, which are values ​​greater than 0.

5. The teaching resource scheduling method driven by a multi-parameter optimization algorithm according to claim 4 is characterized in that: The classroom capacity ratio is the absolute value of the difference between the sum of the number of students attending each class and the corresponding classroom capacity ratio and 1.

6. The teaching resource scheduling method driven by a multi-parameter optimization algorithm according to claim 4 is characterized in that: The number of unscheduled classrooms on the jth day is the sum of the number of classrooms that were not scheduled when each class was scheduled on the jth day.

7. The teaching resource scheduling method driven by a multi-parameter optimization algorithm according to claim 4, characterized in that: The actual scheduled time for the i-th subject is the sum of the total number of classes scheduled for the i-th subject in the scheduling plan.

8. The teaching resource scheduling method driven by a multi-parameter optimization algorithm according to claim 4, characterized in that: Obtaining the optimal teaching resource scheduling plan also includes sorting the fitness values ​​of the U group of alternative scheduling plans in descending order, selecting the first Q group of alternative scheduling plans, and selecting the alternative scheduling plan with the largest teacher interval time coefficient from the Q group of alternative scheduling plans as the optimal teaching resource scheduling plan; replacing step 18.

9. The teaching resource scheduling method driven by a multi-parameter optimization algorithm according to claim 8, characterized in that: The teacher interval coefficient is the reciprocal of the sum of the number of times the teacher gives consecutive classes on each day within a unit number of days.

10. A teaching resource scheduling system driven by a multi-parameter optimization algorithm, used to implement the teaching resource scheduling method driven by a multi-parameter optimization algorithm according to any one of claims 1 to 9, characterized in that: The system comprises: The data collection module is used to collect the types of subjects taught during the semester, the time spent on each subject, the total number of classes, the number of students in each class, the capacity of each classroom, and the subjects taught by each teacher; The target setting module is used to set the target conditions of the teaching resource scheduling plan: the target conditions include maximizing resource utilization; The constraint setting module is used to set the constraint conditions of the teaching resource scheduling plan, including classroom capacity constraint, teacher time constraint and classroom uniqueness constraint; The scheduling module is used to generate the optimal teaching resource scheduling plan based on the target conditions and constraints using the optimization heuristic algorithm.

Images