Art education intelligent course arrangement method and system based on demand analysis

Abstract

The invention discloses an art education intelligent course arrangement method and system based on demand analysis, and relates to the technical field of data processing, and the method comprises the steps: connecting an art training management platform, and receiving M classes, course type labels, student labels and teacher labels, M being an integer greater than 1; performing multi-course conflict analysis based on the class student labels to generate a first rigid demand constraint; based on the class teacher label and the course type label, distributed demand analysis of the same type of course teachers is carried out, and a second rigid demand constraint is generated; in combination with the first and second rigid demand constraints and class hour load balance soft constraints of students and teachers, course arrangement is optimized in a preset course arrangement period, and an optimal course arrangement scheme is generated, so that the technical effects of improving course arrangement efficiency and optimizing course arrangement flexibility and individuation level are achieved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an intelligent course scheduling method and system for art education based on demand analysis. Background Art

[0002] Course arrangements not only need to take into account the needs of students and the teaching arrangements of teachers, but also need to balance the use of various resources to improve educational efficiency.

[0003] Existing scheduling methods are mostly used in general education fields, such as basic education and higher education, and mainly focus on the class schedule of students and teachers, course conflict detection, etc. Scheduling methods mostly rely on manual scheduling, constraint programming or rule-driven methods, and have technical problems such as low scheduling efficiency, insufficient personalization and lack of flexibility. Summary of the invention

[0004] The present invention provides an intelligent course scheduling method and system for art education based on demand analysis to solve the technical problems of low course scheduling efficiency, insufficient personalization level and lack of flexibility in the prior art, and achieve the technical effect of improving course scheduling efficiency and optimizing course scheduling flexibility and personalization level.

[0005] In a first aspect, the present invention provides an intelligent course scheduling method for art education based on demand analysis, wherein the method comprises:

[0006] Connect to the art training management platform, receive M classes, M course type labels, M class student labels and M class teacher labels, where M is an integer greater than 1.

[0007] A multi-course conflict analysis of students is performed based on the M class student labels to generate a first hard demand constraint condition for students with course conflicts.

[0008] Based on the M class teacher labels and the M course type labels, distributed demand constraints for teachers of the same type of courses are performed to generate a second hard demand constraint condition.

[0009] Taking the first hard demand constraint condition and the second hard demand constraint condition as hard constraints, and the class load balance of any student and any teacher as soft constraints, the class scheduling is optimized for the M classes within the preset scheduling cycle to generate the optimal scheduling plan.

[0010] In a second aspect, the present invention further provides an art education intelligent class scheduling system based on demand analysis, wherein the system comprises:

[0011] The label acquisition module is used to connect to the art training management platform, receive M classes, M course type labels, M class student labels and M class teacher labels, where M is an integer greater than 1.

[0012] The conflict analysis module is used to perform multi-course conflict analysis on students based on the M class student labels, and generate a first hard demand constraint condition for students with course conflicts.

[0013] The distribution constraint module is used to perform distributed demand constraints on teachers of the same type of courses based on the M class teacher labels and the M course type labels, and generate a second hard demand constraint condition.

[0014] The scheduling optimization module is used to optimize the class scheduling for the M classes within a preset class scheduling cycle, using the first hard demand constraint condition and the second hard demand constraint condition as hard constraints, and the class load balance of any student and any teacher as a soft constraint, to generate an optimal class scheduling plan.

[0015] The present invention discloses an art education intelligent class scheduling method and system based on demand analysis, comprising: connecting to an art training management platform, receiving M classes, M course type labels, M class student labels and M class teacher labels, wherein M is an integer greater than 1; performing student multi-course conflict analysis based on the M class student labels, and generating a first hard demand constraint condition on students with course conflicts; performing distributed demand constraints on teachers of the same type of courses based on the M class teacher labels and the M course type labels, and generating a second hard demand constraint condition; taking the first hard demand constraint condition and the second hard demand constraint condition as hard constraints, taking the class load balance of any student and any teacher as soft constraints, performing class scheduling optimization for M classes within a preset class scheduling cycle, and generating an optimal class scheduling plan. The art education intelligent class scheduling method and system based on demand analysis disclosed by the present invention solves the technical problems of low class scheduling efficiency, insufficient personalization level and lack of flexibility, and achieves the technical effects of improving class scheduling efficiency and optimizing class scheduling flexibility and personalization level. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of the process of the intelligent scheduling method for art education based on demand analysis of the present invention;

[0017] Figure 2 It is a structural diagram of the intelligent scheduling system for art education based on demand analysis of the present invention.

[0018] Description of reference numerals: label acquisition module 11, conflict analysis module 12, distribution constraint module 13, arrangement optimization module 14. DETAILED DESCRIPTION

[0019] The technical solution provided in the embodiments of the present invention is to solve the technical problems of low class scheduling efficiency, insufficient personalization level and lack of flexibility in the prior art. The overall idea adopted is as follows:

[0020] First, connect to the art training management platform, receive M classes, M course type labels, M class student labels, and M class teacher labels, where M is an integer greater than 1. Then, perform multi-course conflict analysis on students based on the M class student labels, thereby generating the first hard demand constraint for students with course conflicts. Then, based on the M class teacher labels and the M course type labels, perform distributed demand constraints on teachers of the same type of courses to generate a second hard demand constraint. Next, take the first hard demand constraint and the second hard demand constraint as hard constraints, and take the class load balance of any student and any teacher as a soft constraint, optimize the class scheduling for the M classes within the preset scheduling cycle, and generate the optimal scheduling plan. Finally, output the optimal scheduling plan.

[0021] The above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods of the specification to better understand the above technical solution. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments used only to explain the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. In addition, it should be noted that, for the convenience of description, only the parts related to the present invention are shown in the drawings, rather than all of them.

[0022] Embodiment 1

[0023] Figure 1 The figure is a flow chart of the method for intelligent scheduling of art education courses based on demand analysis of the present invention, wherein the method comprises:

[0024] S100: Connect to the art training management platform, receive M classes, M course type labels, M class student labels and M class teacher labels, where M is an integer greater than 1.

[0025] Specifically, first, the API interface is used to connect with the art training management platform, and identity authentication and permission management are performed through the platform to ensure the security and legality of the data; then, combined with the preset data exchange format, such as JSON or XML, the specific field names, types and their associations of classes, course type labels, student labels and teacher labels are defined, and M classes, M course type labels, M class student labels and M class teacher labels are extracted.

[0026] Optionally, class information represents multiple art training classes set up on the platform, including class ID, class name, class grade, etc.; course type label is used to identify the type of course, involving course ID, course type (such as music, dance, drama, etc.); student label reflects the type or characteristics of the student, including student ID, student name, student ID number, corresponding class, etc.; similarly, teacher label includes teacher ID, teacher name, teaching subjects, corresponding class, etc.

[0027] By connecting to the art training management platform, relevant data on classes, courses, students and teachers can be automatically obtained to meet the needs of training institutions of different sizes and provide a basis for subsequent teaching course arrangement analysis and decision-making.

[0028] S200: Performing a multi-course conflict analysis on students based on the M class student labels, and generating a first hard demand constraint condition for students with course conflicts.

[0029] Specifically, the first hard demand constraint condition is used to constrain and avoid course time conflicts caused by students registering for multiple courses at the same time, that is, through the first hard demand constraint condition, it is detected whether the course time periods registered by each student overlap.

[0030] In some embodiments, a multi-course conflict analysis of students is performed based on the M class student tags to generate a first hard requirement constraint condition for students with course conflicts, including:

[0031] Based on the M class student labels, duplicate students in the M classes are identified to generate the course conflicting students; the duplicate class sets corresponding to the course conflicting students are extracted; and the first hard demand constraint condition is that the class schedules of the duplicate class sets do not overlap at all.

[0032] Specifically, first, traverse M class student labels, and perform de-duplication matching through class student labels, that is, for each student, find all the corresponding classes and courses to determine whether the same student appears in multiple classes; then, record all students in multiple classes and output them as course conflict students, which represent the set of students who may have course conflicts; then, for the identified course conflict students, traverse their corresponding class sets to construct the students' repeated class sets; then, for each repeated class set, obtain its class schedule to check whether all the course schedules of the repeated class set overlap as the first hard demand constraint. If there is a conflict, it is deemed that the first hard demand constraint is not met, and the course schedule needs to be adjusted to ensure that there is no course conflict.

[0033] Specifically, the class schedule includes the start time and end time of each course. By comparing the start time and end time, it is determined whether each course overlaps and judges the conflict. For example, if the course time of class C01 corresponding to student S001 is from 9:00AM to 10:30AM, and the course time of class C02 corresponding to student S001 is from 10:00AM to 11:30AM, then the two courses of student S001 conflict.

[0034] Through the above steps, the first hard demand constraint is determined, and then multi-course conflict analysis can be performed on students in M ​​classes to identify students with course conflicts and their corresponding duplicate class sets, providing a basis for subsequent course scheduling optimization.

[0035] S300: Based on the M class teacher tags and the M course type tags, distributed demand constraints are performed on teachers of the same type of courses to generate a second hard demand constraint condition.

[0036] In some embodiments, distributed demand constraints for teachers of the same type of course are performed based on the M class teacher tags and the M course type tags to generate a second hard demand constraint condition, including:

[0037] Based on the M class teacher labels and the M course type labels, identify the same type of class combinations corresponding to teachers belonging to the same course type; and take the fact that the class schedules of all classes in the same type of class combinations do not completely overlap as the second hard demand constraint condition.

[0038] Specifically, first, based on the class teacher labels and course type labels obtained from the art training management platform, determine the teaching teachers and course types of each class, identify all classes and teachers under the same course type and group them accordingly, and ensure that each class is associated with the corresponding course type.

[0039] Specifically, for classes of the same course type, the class schedules of the corresponding classes are collected and recorded, wherein the class schedule of each class includes multiple time periods; then, for multiple classes of the same course type, the second hard requirement constraint is configured that the class schedules should not completely overlap. In other words, if the class schedules of some classes partially overlap, ensure that the class schedule of at least one class does not completely overlap with that of other classes, to ensure that a substitute teacher can still be arranged when a teacher takes leave.

[0040] Through the above steps, according to the class teacher label and course type label, the teacher and class combination of the same course type is identified, and the class scheduling overlap detection is performed on these classes. The second hard requirement constraint condition that the class scheduling time does not completely overlap is set to ensure that even if some teachers take leave, the class schedule can still be arranged reasonably to avoid class time conflicts of the same course type.

[0041] S400: Taking the first hard demand constraint condition and the second hard demand constraint condition as hard constraints, and taking the class load balance of any student and any teacher as soft constraints, optimizing the class scheduling for the M classes within a preset class scheduling cycle, and generating an optimal class scheduling plan.

[0042] Specifically, the first hard demand constraint condition and the second hard demand constraint condition are hard constraints, that is, the first hard demand constraint condition and the second hard demand constraint condition are necessary conditions, while the class load balance of any student and any teacher is a non-necessary condition, that is, the optimal constraint dimension is sought as much as possible under the premise of satisfying the hard constraints.

[0043] Specifically, the load balancing of the class hours of any student and any teacher is used to ensure the uniformity of the class hours of students and teachers as much as possible, thereby avoiding the situation of consecutive class hours.

[0044] In some embodiments, taking the first hard demand constraint condition and the second hard demand constraint condition as hard constraints, taking the class load balance of any student and any teacher as soft constraints, performing class scheduling optimization for the M classes within a preset class scheduling cycle, and generating an optimal class scheduling plan, including:

[0045] Determine M scheduling cycle requirements for the M classes; based on the M scheduling cycle requirements, optimize the class time arrangement of the M classes within the preset scheduling cycle through an intelligent scheduling module to generate the optimal scheduling plan, wherein the intelligent scheduling module performs collaborative optimization based on the hard constraints and the soft constraints.

[0046] Specifically, according to characteristic indicators such as the type of course and the type of student group, the specific scheduling cycle requirements of each class are analyzed and determined, including the frequency of teaching in each class within a specific cycle, teaching time period (such as the total length of classes per week, class distribution, average daily class hours per week), etc., and the quantified results are used to generate the scheduling cycle requirements for each class; then, the scheduling is optimized based on the scheduling cycle requirements. The first hard demand constraint (student conflict) in the optimization process is used to ensure that there is no time conflict between students across classes during the scheduling process, that is, to ensure that the same student does not participate in courses in multiple classes in the same time period; and the second hard demand constraint (teacher conflict) ensures that different classes of the same course type will not be scheduled in exactly the same time period, so as to prevent conflicts in teacher resources and ensure that there are alternative options when teachers are on leave or unavailable.

[0047] Specifically, under the premise of meeting hard constraints, soft constraints should be used to balance the class load of teachers and students in each class as much as possible to avoid excessive concentration of teachers or students.

[0048] Optionally, the intelligent class scheduling module uses intelligent optimization algorithms such as genetic algorithms, particle swarm optimization (PSO), simulated annealing (SA), etc. to perform multiple iterative optimizations, thereby simultaneously optimizing multiple constraint objectives to find the optimal solution; among them, exemplarily, the penalty factor of the intelligent class scheduling module is configured according to the hard constraints, and the evaluation factor of the intelligent class scheduling module is defined according to the soft constraints.

[0049] In some implementations, based on the M scheduling cycle requirements, the intelligent scheduling module optimizes the class time arrangement of the M classes within the preset scheduling cycle to generate the optimal scheduling plan, including:

[0050] Determine a preset set of available classrooms and the corresponding number of students that can be accommodated; take the preset set of available classrooms and the number of students that can be accommodated as space constraints, and within a preset class scheduling period, use the intelligent class scheduling module to take the first hard demand constraint condition and the second hard demand constraint condition as hard constraints, and randomly generate a number of candidate class scheduling plans that simultaneously meet the first hard demand constraint condition and the second hard demand constraint condition; calculate the class load balancing fitness of any student and any teacher for a number of candidate class scheduling plans, and generate a soft constraint fitness; based on the soft constraint fitness, maximize the soft constraint fitness of the several candidate class scheduling plans to generate the optimal class scheduling plan.

[0051] Specifically, first, the detailed information of the available classrooms is collected, including the name, number, number of students that can be accommodated, equipment support, etc. of each classroom, and classroom matching and screening are performed accordingly to create an available classroom set. Each classroom in the available classroom set is associated with its corresponding maximum number of students that can be accommodated, ensuring that each class can be matched with a classroom of appropriate size when scheduling classes; then, the preset available classroom set and the number of students that can be accommodated are used as space constraints to randomly generate a set of scheduling plans, and the scheduling plans are screened based on the first hard demand constraint and the second hard demand constraint as hard constraints, and the screening results are the above-mentioned several candidate scheduling plans.

[0052] Specifically, several candidate class scheduling plans are analyzed and calculated respectively, and the class load balance fitness corresponding to any student and any teacher in the candidate class scheduling plan is obtained as the soft constraint fitness, wherein the load balance fitness refers to an evaluation index used to measure the load balance of class hours, such as the average daily class hours, the variance of daily class hours in a week, the entropy of class hour data, etc. A plan with better load balance will have a higher fitness, while a plan with unbalanced load will have a lower fitness; then, the intelligent class scheduling module performs an optimization process based on the calculated soft constraint fitness, and the optimization goal is to maximize the soft constraint fitness, that is, to find a class scheduling plan with the best load balance and the most reasonable class hour allocation. In other words, the load balance fitness is the cost function value of the optimization process of the intelligent class scheduling module.

[0053] Through the above method steps, it is possible to ensure that all hard constraints are met while achieving optimal load balancing during class hours, thereby improving the rationality of the teaching arrangement and helping to improve the efficiency of classroom resource utilization.

[0054] In some implementations, based on the soft constraint fitness, performing soft constraint fitness maximization optimization on the plurality of candidate class scheduling plans to generate the optimal class scheduling plan includes:

[0055] For the several candidate class scheduling plans, identify the class time distribution of all students in any plan and perform a balance analysis to generate a student class time load balance index; for the several candidate class scheduling plans, identify the class time distribution of all teachers in any plan and perform a balance analysis to generate a teacher class time load balance index; weight the student class time load balance index and the teacher class time load balance index to generate a number of soft constraint fitnesses corresponding to the several candidate class scheduling plans; based on the several soft constraint fitnesses, determine whether there is a candidate class scheduling plan with a soft constraint fitness greater than or equal to a preset fitness, and if so, generate the optimal class scheduling plan; if not, based on the spatial constraints, the hard constraints and the soft constraints, update the several candidate class scheduling plans and repeat the analysis, and so on, iterate the optimization multiple times until an optimal class scheduling plan with a soft constraint fitness greater than or equal to the preset fitness is generated.

[0056] Specifically, the soft-constrained fitness maximization optimization is performed. First, for each candidate class scheduling plan, the class time distribution of all students is analyzed, that is, the class time period of each student in different courses, and the total class time of each course; then, the class time distribution balance of all students is calculated, and the student class time load balance index is generated. Among them, the student class time load balance index is used to characterize the deviation of the student class time distribution (such as standard deviation). The smaller the deviation, the more balanced the class time distribution.

[0057] Specifically, the same method and principle as that of obtaining the student class load balancing index is adopted to analyze the class distribution of all teachers for each candidate class scheduling plan, record their teaching periods and the number of class hours for each class, and calculate the balance of class distribution of all teachers.

[0058] Furthermore, different scheduling plans may attach different importance to the balance between students and teachers. Therefore, different weight coefficients are assigned to the student class load balancing index and the teacher class load balancing index. The student class load balancing index and the teacher class load balancing index are weighted to obtain the soft constraint fitness of each candidate scheduling plan. The higher the soft constraint fitness, the more ideal the scheduling plan is in terms of class load balance.

[0059] Specifically, according to the calculated soft constraint fitness, determine whether there is a candidate class scheduling plan whose fitness is greater than or equal to the preset fitness threshold; if there is a plan that meets the conditions, then the plan is selected as the optimal class scheduling plan; if the optimal class scheduling plan that meets the conditions is not found, the intelligent class scheduling module will update the current candidate class scheduling plan, and the updated candidate class scheduling plan will again calculate and analyze the soft constraint fitness, and through multiple rounds of iterations, until the soft constraint fitness is greater than or equal to the preset fitness threshold, the optimal class scheduling plan is generated.

[0060] Through the above analysis and optimization steps, the final scheduling plan can ensure the balanced class load of students and teachers on the basis of meeting all rigid requirements, avoiding excessive concentration or imbalance. At the same time, the automated iterative optimization process greatly improves the efficiency of scheduling and reduces the error rate of scheduling.

[0061] In some implementations, the method further includes:

[0062] If the number of iterative optimizations reaches the preset number of iterations and the optimal class scheduling plan has not been output, based on the space constraint, the hard constraint and the soft constraint, the classes corresponding to the same type of courses in the M classes are merged and fitted for class scheduling optimization, and a class merging recommendation plan with a soft constraint fitness greater than or equal to the preset fitness and a corresponding class scheduling plan are generated;

[0063] The optimal class scheduling plan is generated based on the class merging recommendation plan and the corresponding class scheduling plan.

[0064] Specifically, multiple rounds of optimization are performed through the intelligent scheduling module, and candidate scheduling plans are gradually adjusted based on the load balancing of students and teachers' class hours to ensure compliance with hard constraints (such as student course conflicts, teacher scheduling conflicts, etc.) and soft constraints (such as load balancing). After each round of optimization, the calculated soft constraint fitness is used to determine whether the optimal scheduling plan that meets the preset fitness threshold is found. If the soft constraint fitness is still not greater than or equal to the preset fitness threshold after the set number of iterations, the scheduling is further optimized based on the restrictions of space constraints, hard constraints and soft constraints, and classes of the same type of courses are merged and fitted, that is, classes of the same type of courses are merged as needed to form a new merged class set, so as to improve the flexibility of scheduling and the efficiency of resource utilization.

[0065] For example, first, identify all classes under the same course type and determine their scheduling needs; then, merge similar classes based on actual classroom capacity, number of students, and course schedule; for example, if the number of students in some classes is similar, they can be merged into one large class to reduce conflicts in scheduling. The merged class will have higher scheduling flexibility and can be scheduled in fewer time periods, thereby optimizing the use of time and classroom resources.

[0066] Specifically, after merging the classes, the same intelligent scheduling module as mentioned above is used to perform new scheduling optimization for the merged classes, wherein the optimization goal is still to maximize the load balance of students and teachers and meet hard and soft constraints.

[0067] Specifically, through the merged classes and optimized class scheduling results, a class merger recommendation plan and a corresponding class scheduling plan are generated to provide reasonable class merger and time arrangement suggestions for more efficient class scheduling.

[0068] In summary, the method for intelligent scheduling of art education courses based on demand analysis provided by the present invention has the following technical effects:

[0069] By connecting to the art training management platform, M classes, M course type labels, M class student labels and M class teacher labels are received, where M is an integer greater than 1; based on the M class student labels, multi-course conflict analysis of students is performed to generate a first hard demand constraint for students with course conflicts; based on the M class teacher labels and the M course type labels, distributed demand constraints are performed on teachers of the same type of courses to generate a second hard demand constraint; with the first hard demand constraint and the second hard demand constraint as hard constraints, and the class load balance of any student and any teacher as a soft constraint, class scheduling optimization is performed for M classes within a preset scheduling cycle to generate an optimal scheduling plan, thereby achieving the technical effect of improving scheduling efficiency and optimizing scheduling flexibility and personalization level.

[0070] Embodiment 2

[0071] Figure 2 This is a schematic diagram of the structure of the art education intelligent scheduling system based on demand analysis of the present invention. Figure 1 The flowchart of the method for intelligent scheduling of art education courses based on demand analysis of the present invention can be shown as follows: Figure 2 The structure shown is implemented.

[0072] Based on the same concept as the method for intelligent scheduling of art education courses based on demand analysis in the above embodiment, the present invention also provides an intelligent scheduling system for art education courses based on demand analysis, which includes:

[0073] The label acquisition module 11 is used to connect to the art training management platform, receive M classes, M course type labels, M class student labels and M class teacher labels, where M is an integer greater than 1.

[0074] The conflict analysis module 12 is used to perform multi-course conflict analysis on students based on the M class student labels, and generate a first hard demand constraint condition on students with course conflicts.

[0075] The distribution constraint module 13 is used to perform distributed demand constraints on teachers of the same type of courses based on the M class teacher tags and the M course type tags, and generate a second hard demand constraint condition.

[0076] The scheduling optimization module 14 is used to optimize the class scheduling for the M classes within a preset class scheduling cycle, using the first hard demand constraint condition and the second hard demand constraint condition as hard constraints, and the class load balance of any student and any teacher as a soft constraint, to generate an optimal class scheduling plan.

[0077] In some embodiments, the conflict analysis module 12 includes:

[0078] A duplicate student identification unit is used to identify duplicate students in the M classes based on the student labels of the M classes, and generate the course conflicting students.

[0079] The repeated class set extraction unit is used to extract the repeated class sets corresponding to the students with course conflicts.

[0080] The hard demand constraint condition generating unit is used to set the first hard demand constraint condition that the class schedules of the repeated class sets do not overlap at all.

[0081] In some embodiments, the distribution constraint module 13 includes:

[0082] The same type class combination identification unit is used to identify the same type class combination corresponding to teachers belonging to the same course type based on the M class teacher labels and the M course type labels.

[0083] The rigid class scheduling constraint condition generating unit is used to take the non-complete overlap of the class scheduling times of all classes in the same type of class combination as the second rigid demand constraint condition.

[0084] In some embodiments, the layout optimization module 14 includes:

[0085] The class scheduling cycle requirement determination unit is used to determine the M class scheduling cycle requirements of the M classes.

[0086] The intelligent class scheduling unit is used to optimize the class time arrangement of the M classes within the preset class scheduling cycle based on the requirements of the M class scheduling cycles through the intelligent class scheduling module to generate the optimal class scheduling plan, wherein the intelligent class scheduling module performs collaborative optimization based on the hard constraints and the soft constraints.

[0087] In some implementations, the intelligent course scheduling unit in the scheduling optimization module 14 includes:

[0088] The available classroom set determining unit is used to determine a preset available classroom set and the corresponding number of students that can be accommodated.

[0089] A candidate class scheduling plan generating unit is used to use the preset available classroom set and the number of students that can be accommodated as space constraints, and through the intelligent class scheduling module within a preset class scheduling cycle, use the first hard demand constraint condition and the second hard demand constraint condition as hard constraints to randomly generate a number of candidate class scheduling plans that simultaneously meet the first hard demand constraint condition and the second hard demand constraint condition.

[0090] The soft constraint fitness calculation unit is used to calculate the class load balancing fitness of any student and any teacher for a number of candidate class scheduling plans, and generate soft constraint fitness.

[0091] The soft constraint fitness maximization optimization unit is used to perform soft constraint fitness maximization optimization on the several candidate class scheduling plans based on the soft constraint fitness to generate the optimal class scheduling plan.

[0092] In some implementations, the execution steps of the soft constraint fitness maximization optimization unit in the arrangement optimization module 14 include:

[0093] For the several candidate class scheduling plans, identify the class time distribution of all students in any plan and perform a balance analysis to generate a student class time load balance index.

[0094] For the several candidate class scheduling plans, identify the class time distribution of all teachers in any plan and perform a balance analysis to generate a teacher class time load balance indicator.

[0095] The student class load balancing index and the teacher class load balancing index are weighted to generate a plurality of soft constraint fitnesses corresponding to the plurality of candidate class scheduling plans.

[0096] Based on the several soft constraint fitnesses, determine whether there is a candidate class scheduling plan whose soft constraint fitness is greater than or equal to the preset fitness; if so, generate the optimal class scheduling plan.

[0097] If not, based on the space constraints, the hard constraints and the soft constraints, the several candidate class scheduling plans are updated and then analyzed repeatedly, and so on, iteratively optimized multiple times until an optimal class scheduling plan is generated with a soft constraint fitness greater than or equal to a preset fitness.

[0098] In some implementations, the execution steps of the soft constraint fitness maximization optimization unit in the arrangement optimization module 14 further include:

[0099] If the number of iterative optimization reaches the preset number of iterations and the optimal class scheduling plan has not been output, the class scheduling optimization is performed after merging and fitting the classes corresponding to the same type of courses in the M classes based on the spatial constraints, the hard constraints and the soft constraints, and a class merging recommendation plan and a corresponding class scheduling plan are generated whose soft constraint fitness is greater than or equal to the preset fitness.

[0100] The optimal class scheduling plan is generated based on the class merging recommendation plan and the corresponding class scheduling plan.

[0101] It should be understood that the embodiments mentioned in this specification focus on their differences from other embodiments. The specific embodiments in the aforementioned embodiment one are also applicable to the art education intelligent scheduling system based on demand analysis described in embodiment two. For the sake of brevity of the specification, they will not be further elaborated here.

[0102] It should be understood that the embodiments disclosed in the present invention and the above description can enable those skilled in the art to use the present invention to implement the present invention. At the same time, the present invention is not limited to the above-mentioned embodiments. It should be understood that those skilled in the art can still modify the technical solutions recorded in the above-mentioned embodiments, or replace some of the technical features therein by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. An intelligent scheduling method for art education based on demand analysis, characterized in that: include: Connect to the art training management platform, receive M classes, M course type labels, M class student labels and M class teacher labels, where M is an integer greater than 1; Performing a multi-course conflict analysis on students based on the M class student labels, and generating a first hard demand constraint condition on students with course conflicts; Based on the M class teacher tags and the M course type tags, distributed demand constraints for teachers of the same type of course are performed to generate a second hard demand constraint condition; Taking the first hard demand constraint condition and the second hard demand constraint condition as hard constraints, and the class load balance of any student and any teacher as soft constraints, the class scheduling is optimized for the M classes within the preset scheduling cycle to generate the optimal scheduling plan.

2. The method for intelligent scheduling of art education courses based on demand analysis as claimed in claim 1, characterized in that: Based on the M class student labels, a multi-course conflict analysis of students is performed to generate a first hard demand constraint condition for students with course conflicts, including: Based on the student labels of the M classes, duplicate students in the M classes are identified to generate the course conflicting students; Extract the duplicate class set corresponding to the students with course conflicts; The first hard requirement constraint condition is that the class schedules of the repeated class sets do not overlap at all.

3. The method for intelligent scheduling of art education courses based on demand analysis as claimed in claim 1, characterized in that: Based on the M class teacher tags and the M course type tags, distributed demand constraints for teachers of the same type of course are performed to generate a second hard demand constraint condition, including: Based on the M class teacher labels and the M course type labels, identifying the same type of class combinations corresponding to teachers belonging to the same course type; The second hard demand constraint condition is that the class schedules of all classes in the same type of class combination do not completely overlap.

4. The method for intelligent scheduling of art education courses based on demand analysis as claimed in claim 1, characterized in that: Taking the first hard demand constraint condition and the second hard demand constraint condition as hard constraints, taking the class load balance of any student and any teacher as soft constraints, optimizing the class scheduling for the M classes within a preset class scheduling cycle, and generating an optimal class scheduling plan, including: Determine the M scheduling cycle requirements for the M classes; Based on the requirements of the M scheduling cycles, the class time arrangement of the M classes is optimized within the preset scheduling cycle through the intelligent scheduling module to generate the optimal scheduling plan, wherein the intelligent scheduling module performs collaborative optimization based on the hard constraints and the soft constraints.

5. The method for intelligent scheduling of art education courses based on demand analysis as claimed in claim 4, characterized in that: Based on the M scheduling cycle requirements, the intelligent scheduling module optimizes the class time arrangement of the M classes within the preset scheduling cycle to generate the optimal scheduling plan, including: Determine the preset available classroom set and the corresponding number of students that can be accommodated; Taking the preset available classroom set and the number of students that can be accommodated as space constraints, within a preset class scheduling period, using the intelligent class scheduling module, taking the first hard demand constraint condition and the second hard demand constraint condition as hard constraints, randomly generate a number of candidate class scheduling plans that simultaneously meet the first hard demand constraint condition and the second hard demand constraint condition; Calculate the class load balance fitness of any student and any teacher for several candidate class scheduling plans and generate soft constraint fitness; Based on the soft constraint fitness, the soft constraint fitness of the several candidate class scheduling plans is maximized to generate the optimal class scheduling plan.

6. The method for intelligent scheduling of art education courses based on demand analysis as claimed in claim 5, characterized in that: Based on the soft constraint fitness, the plurality of candidate class scheduling plans are optimized by maximizing the soft constraint fitness to generate the optimal class scheduling plan, including: For the plurality of candidate class scheduling plans, identifying the class time distribution of all students in any plan and performing a balance analysis to generate a student class time load balance index; For the plurality of candidate class scheduling plans, identify the class time distribution of all teachers in any plan and perform a balance analysis to generate a teacher class time load balance index; Weighting the student class load balancing index and the teacher class load balancing index to generate a plurality of soft constraint fitnesses corresponding to the plurality of candidate class scheduling schemes; Based on the several soft constraint fitnesses, determining whether there is a candidate class scheduling plan whose soft constraint fitness is greater than or equal to a preset fitness, and if so, generating the optimal class scheduling plan; If not, based on the space constraints, the hard constraints and the soft constraints, the several candidate class scheduling plans are updated and then analyzed repeatedly, and so on, iteratively optimized multiple times until an optimal class scheduling plan is generated with a soft constraint fitness greater than or equal to a preset fitness.

7. The method for intelligent scheduling of art education courses based on demand analysis as claimed in claim 6, characterized in that: Also includes: If the number of iterative optimizations reaches the preset number of iterations and the optimal class scheduling plan has not been output, based on the space constraint, the hard constraint and the soft constraint, the classes corresponding to the same type of courses in the M classes are merged and fitted for class scheduling optimization, and a class merging recommendation plan with a soft constraint fitness greater than or equal to the preset fitness and a corresponding class scheduling plan are generated; The optimal class scheduling plan is generated based on the class merging recommendation plan and the corresponding class scheduling plan.

8. The intelligent scheduling system for art education based on demand analysis is characterized by: The system is used to execute the method for intelligent scheduling of art education courses based on demand analysis according to any one of claims 1 to 7, and the system comprises: The label acquisition module is used to connect to the art training management platform and receive M classes, M course type labels, M class student labels and M class teacher labels, where M is an integer greater than 1; A conflict analysis module, used for performing multi-course conflict analysis on students based on the M class student labels, and generating a first hard demand constraint condition on students with course conflicts; A distribution constraint module, used for performing distributed demand constraints on teachers of the same type of courses based on the M class teacher labels and the M course type labels, and generating a second hard demand constraint condition; The scheduling optimization module is used to optimize the class scheduling for the M classes within a preset class scheduling cycle, using the first hard demand constraint condition and the second hard demand constraint condition as hard constraints, and the class load balance of any student and any teacher as a soft constraint, to generate an optimal class scheduling plan.

Images