Intelligent automatic class scheduling method, system and storage medium

Abstract

The present invention discloses an intelligent automatic class scheduling method, system and storage medium, and relates to the field of information-based education technology. Aiming at the problems of insufficient personalized class scheduling, limited algorithm efficiency and high difficulty in dynamic adjustment, the present invention generates a personalized demand set by real-time monitoring of the special demand status of teachers and students, accurately matches courses and classroom resources, calculates the priority coefficient Pxs of personalized class scheduling requests based on the total available teacher time Zsc, the course continuity index Zkc and the student schedule conflict value Zkb, generates an optimized class scheduling plan, and evaluates it by calculating the optimized value Yhz; at the same time, adopts resource matching and real-time monitoring methods to monitor classroom resources and teacher load data, and generates a first resource matching value Rhz1; and by calculating the second resource matching value Rhz2, quickly judges the matching degree of the plan, realizes dynamic adjustment and optimization, ensures that the plan changes adaptively, and improves the efficiency and flexibility of class scheduling.

Description

Technical Field

[0001] The present invention relates to the field of information-based education technology, and in particular to an intelligent automatic class scheduling method, system and storage medium. Background Art

[0002] The intelligent automatic class scheduling method originated from the development needs of educational informatization, and can be traced back to the rise of educational management software in the late 20th century. With the continuous advancement of computer technology, especially the maturity of artificial intelligence and algorithm optimization technology, the complexity and efficiency problems of traditional manual class scheduling have been effectively alleviated. The automatic class scheduling system uses intelligent algorithms to optimize class scheduling by combining multiple factors such as school resources, teachers and students' schedules. In recent years, with the introduction of big data technology, intelligent class scheduling has further developed in the direction of personalization and dynamism, which not only improves the efficiency of class scheduling, but also can be flexibly adjusted according to teaching needs.

[0003] With the development of educational institutions, the automatic scheduling methods used in educational institutions often have the following technical shortcomings:

[0004] 1. Insufficient personalized scheduling: The current system is mostly based on a unified scheduling model, with weak support for personalized solutions, making it difficult to optimize and adjust according to the special needs of teachers or students.

[0005] 2. Limited algorithm efficiency: When faced with complex constraints and large-scale data, the computational efficiency of existing algorithms is low, which can easily lead to long computational waits or suboptimal solutions, affecting the quality of scheduling results.

[0006] 3. Difficulty in dynamic adjustment: Once the class schedule is generated, existing technologies make it difficult to make dynamic adjustments based on real-time situations (such as course cancellations, changes in the number of students), and lack real-time feedback and adaptive capabilities. Summary of the invention

[0007] In view of the deficiencies in the prior art, the present invention provides an intelligent automatic class scheduling method, system and storage medium, which solve the technical problems in the background technology of insufficient personalized class scheduling, limited algorithm efficiency and high difficulty in dynamic adjustment.

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent automatic class scheduling method, comprising the following steps:

[0009] S1. Obtain the basic information related to the class scheduling of the education and training institution in advance, including teacher information, student information, course scheduling requirements, classroom resources and timetable, and mark each teacher, student and course with a serial number;

[0010] S2. Real-time monitoring of special needs information of teachers and students and dynamic changes of special needs information, generating personalized needs sets, determining personalized class scheduling requests that need to be processed first based on the personalized needs sets, preliminarily matching courses and classroom resources for these personalized class scheduling requests, and generating primary class scheduling plans;

[0011] S3. According to the personalized class scheduling request obtained in step S2, the constraint condition related data related to the personalized class scheduling request is monitored, including the total available time of the teacher Zsc, the course continuity index Zkc and the student schedule conflict value Zkb, a constraint condition data set is constructed, and a relative priority coefficient Pxs of the personalized class scheduling request with sequence number i is generated based on the constraint condition data set; then, according to the relative priority coefficient Pxs, the personalized class scheduling request with sequence number i is matched with class scheduling resources to generate an advanced class scheduling plan; then, the optimization value Yhz of each advanced class scheduling plan is calculated and evaluated to determine whether it meets the optimization class scheduling goal;

[0012] S4, real-time monitoring of resource usage in the course scheduling process, including data related to the real-time occupancy status of classroom resources and data related to the teacher's teaching load, generating a teaching load data set, and comparing the resource allocation in the advanced course scheduling plan with the actual resource usage, generating a first resource matching value Rhz1 and evaluating it, and determining whether the advanced course scheduling plan with sequence number i needs to be adjusted;

[0013] S5. If the advanced class scheduling plan with serial number i needs to be adjusted, the adjusted advanced class scheduling plan will be re-marked, a secondary class scheduling plan will be generated and the value Yhz will be re-optimized, and the second resource matching value Rhz2 will be calculated at the same time; the optimized value Yhz of the secondary class scheduling plan will be compared with the second resource matching value Rhz2, and finally the optimized class scheduling plan will be determined.

[0014] Preferably, S1 includes S11, specifically:

[0015] S11. First, collect all kinds of basic information related to class scheduling within the education and training institution; the relevant basic information includes: the teacher's name, title, professional direction, available time period and class preference, the student's name, student number, class, course selection and course conflict, the course name, course type, course duration, course number limit and teaching objectives of the course schedule, the classroom number, capacity, equipment configuration and usage time, as well as the semester start and end dates, class hours and school fixed activity time; the above relevant basic information is obtained through the preset database interface;

[0016] Next, the acquired teachers, students, courses and classroom resources are numbered and labeled respectively; specifically, teachers are classified and numbered according to their positions, available time and teaching needs, students are numbered according to their course selection and class assignments, courses are numbered according to the type, teaching objectives and duration of required and elective courses, and classroom resources are numbered according to their physical location, capacity and equipment.

[0017] Preferably, S2 includes S21 and S22, specifically:

[0018] S21. Real-time collection and update of special needs information of teachers and students. Special needs information of teachers includes teaching time preference, unavailable status in specific time periods, professional requirements, course load and temporary course adjustment needs; special needs information of students includes course preference, learning progress, course conflicts, priority requirements of individual courses and temporary course adjustments. The collected special needs information is processed in real time through the dynamic update module of the system to ensure the timeliness and accuracy of the information;

[0019] S22. Generate a set of personalized class scheduling requests that need to be processed in priority based on the personalized demand set, and classify and screen them; then, based on the personalized class scheduling requests, call the pre-collected course schedule and classroom resource data, and make a preliminary match on the personalized class scheduling requests, including cross-comparing the teacher's available time period with the student's course needs, and matching resources based on the classroom's availability and capacity requirements; during the matching process, comprehensively consider various constraints, including the teacher's teaching time preference, the student's course conflict situation and the classroom's resource limitations, and finally generate several primary class scheduling plans.

[0020] Preferably, S3 includes S31 and S32, specifically:

[0021] S31, where the specific calculation formula of the relative priority coefficient Pxs of the personalized course scheduling request with sequence number i is as follows:

[0022] ;

[0023] Combining personalized needs and the generated priority coefficient Pxs, a primary scheduling plan is generated by extracting qualified resources from the teacher, student and classroom resource libraries, and performing preliminary matching according to the priority of personalized needs, and scheduling resources are matched for the personalized scheduling request with sequence number i; each primary scheduling plan meets the constraints, including the teacher's available time, course continuity and student schedule conflicts.

[0024] Preferably,

[0025] S32, collect the resource utilization rate Xzy, teacher workload Xjs and student distribution density Xxs of each primary class scheduling plan in real time through relevant class scheduling monitoring equipment and fit them to obtain the optimized value Yhz. The specific calculation formula is as follows:

[0026] ;

[0027] By comparing and evaluating the preset optimization threshold Q with the optimization value Yhz, it is determined whether the optimization scheduling goal is met. The specific evaluation contents are as follows:

[0028] If the optimization value Yhz ≥ optimization threshold Q, it means that the scheduling plan meets the optimization scheduling goal, and the resource utilization, teacher workload and student distribution density are all as expected;

[0029] If the optimization value Yhz<optimization threshold Q, it means that the class scheduling plan does not meet the optimization scheduling goal, and the class scheduling plan needs to be further adjusted.

[0030] Preferably, S4 includes S41 and S42, specifically:

[0031] S41. Real-time monitoring and data collection of classroom resources and teacher teaching loads involved in the scheduling process, including data related to the real-time occupancy status of classroom resources and data related to teachers' teaching loads; real-time collection and generation of teaching load data sets through preset data interfaces; wherein the teaching load data sets cover the actual workload of all teachers in the current cycle, including scheduled time periods, remaining available time periods, and the allocation of specific teaching tasks in each time period; then, the preset resource allocation related data in the current advanced scheduling plan are compared with the teaching load data sets collected through real-time monitoring, including matching the actual workload of teachers with the expected workload of teachers in the scheduling plan, and comparing the expected usage of the classroom with the actual occupancy status.

[0032] Preferably,

[0033] S42, after comparing the resource allocation in the current advanced class scheduling plan with the actual resource usage, the classroom occupancy ratio Yjs, the teacher workload difference value Yzf and the resource utilization rate difference value Yyl are obtained and then calculated to obtain the first resource matching value Rhz1. The specific calculation formula is as follows:

[0034] ;

[0035] Through the preset matching threshold W and the first resource matching value Rhz1, it is determined whether the advanced course scheduling plan with sequence number i needs to be adjusted. The specific evaluation content is as follows:

[0036] When the first resource matching value Rhz1 ≥ matching threshold W: it indicates that the resource allocation in the current advanced course scheduling plan matches the actual resource usage normally, and no further adjustment is required;

[0037] When the first resource matching value Rhz1 is less than the matching threshold W, it indicates that the resource allocation in the current advanced class scheduling plan is abnormally matched with the actual resource usage. At this time, the advanced class scheduling plan with serial number i is adjusted, including reallocating classroom resources and adjusting teacher teaching time periods.

[0038] Preferably, S5 includes S51, specifically:

[0039] S51, by real-time collection of resource usage related data of the adjusted secondary scheduling plan with sequence number i, including teacher available time period utilization rate Jsy, classroom switching frequency Jsc, teacher cross-day work intensity parameter Jsk and classroom equipment utilization rate Jsb; extracting resource usage related data of the adjusted secondary scheduling plan, and obtaining the second resource matching value Rhz2 by the following formula:

[0040] ;

[0041] The optimization value Yhz of the secondary scheduling plan is compared and evaluated with the second resource matching value Rhz2, and the optimized scheduling plan is finally determined. The specific contents are as follows:

[0042] When the adjusted secondary scheduling plan optimization value Yhz ≥ the second resource matching value Rhz2, it means that the actual usage of the adjusted secondary scheduling plan meets expectations. At this time, the system determines this plan as the final optimized scheduling plan;

[0043] When the adjusted secondary class scheduling optimization value Yhz is less than the second resource matching value Rhz2, it means that the actual usage of the adjusted secondary class scheduling plan does not meet expectations, and the current secondary class scheduling plan is adjusted again.

[0044] An intelligent automatic course scheduling system includes a data collection and annotation module, a personalized demand processing module, a constraint condition and optimization calculation module, a resource usage monitoring module, and a program adjustment and optimization module;

[0045] The data collection and labeling module obtains the basic information related to the course scheduling of the teaching and training institution in advance, including teacher information, student information, course scheduling requirements, classroom resources and timetable, and labels each teacher, student and course with a serial number;

[0046] The personalized demand processing module monitors the special demand information of teachers and students and the dynamic changes of the special demand information in real time, generates a personalized demand set, determines the personalized class scheduling requests that need to be processed first based on the personalized demand set, preliminarily matches courses and classroom resources for these personalized class scheduling requests, and generates a primary class scheduling plan;

[0047] The constraint condition and optimization calculation module monitors the constraint condition related data related to the personalized class scheduling request, including the total available teacher time Zsc, the course continuity index Zkc and the student schedule conflict value Zkb, according to the personalized class scheduling request obtained in step S2, constructs a constraint condition data set, and generates a relative priority coefficient Pxs of the personalized class scheduling request with sequence number i based on the constraint condition data set; then, according to the relative priority coefficient Pxs, the personalized class scheduling request with sequence number i is matched with class scheduling resources to generate an advanced class scheduling plan; then, the optimization value Yhz of each advanced class scheduling plan is calculated and evaluated to determine whether it meets the optimization class scheduling goal;

[0048] The resource usage monitoring module monitors the resource usage in the course scheduling process in real time, including data related to the real-time occupancy status of classroom resources and data related to the teacher's teaching load, generates a teaching load data set, and compares the resource allocation in the advanced course scheduling plan with the actual resource usage, generates a first resource matching value Rhz1 and evaluates it, and determines whether the advanced course scheduling plan with sequence number i needs to be adjusted;

[0049] The plan adjustment and optimization module, if the advanced class scheduling plan with serial number i needs to be adjusted, will re-mark the adjusted advanced class scheduling plan, generate a secondary class scheduling plan and re-optimize the value Yhz, and calculate the second resource matching value Rhz2 at the same time; compare the optimized value Yhz of the secondary class scheduling plan with the second resource matching value Rhz2, and finally determine the optimized class scheduling plan.

[0050] An intelligent automatic class scheduling storage medium stores a computer program, including the following steps. The computer program stores computer instructions, and when the instructions are executed by a processor, an intelligent automatic class scheduling method is implemented.

[0051] The present invention provides an intelligent automatic class scheduling method, system and storage medium. It has the following beneficial effects:

[0052] (1) This intelligent automatic class scheduling method, system and storage medium, in order to solve the problem of insufficient personalized class scheduling, generates a personalized demand set by real-time monitoring of the special demand status and dynamic changes of teachers and students, and determines the personalized class scheduling requests that need to be processed first based on the personalized demand set, and preliminarily matches these requests with courses and classroom resources to ensure that they can be accurately matched according to the teacher's teaching time preference, course load, and students' course conflicts and priority needs, thereby realizing optimized support for personalized class scheduling. The relative priority coefficient Pxs of the personalized class scheduling request is calculated by the teacher's total available time Zsc, the course continuity index Zkc and the student's schedule conflict value Zkb. While meeting personalized needs, a primary class scheduling plan that meets various constraints is generated; and the plan is evaluated by calculating the optimization value Yhz to ensure that personalized needs are accurately met.

[0053] (2) In order to solve the problem of limited algorithm efficiency, the intelligent automatic class scheduling method, system and storage medium of the present invention adopt resource matching and real-time monitoring to monitor the resource usage in the class scheduling process, including the real-time occupancy status of classroom resources and the teaching load of teachers. By generating a teaching load data set and comparing the resource allocation of the advanced class scheduling plan with the actual resource usage, a first resource matching value Rhz1 is generated. By comparing the optimized value Yhz with the preset matching threshold W, the matching degree of the class scheduling plan is quickly judged. At the same time, by real-time collection of the teacher's available time period utilization rate Jsy, the classroom switching frequency Jsc, the teacher's cross-day work intensity parameter Jsk and the classroom equipment utilization rate Jsb, the second resource matching value Rhz2 of the adjusted secondary class scheduling plan is further calculated to ensure that the secondary class scheduling plan can still maintain efficient calculation speed and reasonable plan output under large-scale data processing and complex constraints.

[0054] (3) This intelligent automatic class scheduling method, system and storage medium are designed to solve the problem of high difficulty in dynamic adjustment, especially after generating a primary class scheduling plan, it can be dynamically adjusted according to real-time conditions, such as teachers' temporary class adjustment needs, changes in the number of students or course cancellations; by recalculating the optimization value Yhz of the class scheduling plan and adjusting the second resource matching value Rhz2 based on real-time data, the class scheduling plan is gradually dynamically optimized to ensure that all class scheduling plans can be adaptively adjusted according to real-time changes, thereby achieving the best match between resource allocation and course arrangement, improving the system's real-time feedback capability and adaptability, and solving the problem of lack of flexibility in existing technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 A schematic diagram of the steps of an intelligent automatic class scheduling method of the present invention;

[0056] Figure 2This is a schematic diagram of the framework structure of an intelligent automatic class scheduling system of the present invention. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0058] Example 1

[0059] See also Figure 1 The present invention provides an intelligent automatic class scheduling method, comprising the following steps:

[0060] S1. Obtain the basic information related to the class scheduling of the education and training institution in advance, including teacher information, student information, course scheduling requirements, classroom resources and timetable, and mark each teacher, student and course with a serial number;

[0061] S2. Real-time monitoring of special needs information of teachers and students and dynamic changes of special needs information, generating personalized needs sets, determining personalized class scheduling requests that need to be processed first based on the personalized needs sets, preliminarily matching courses and classroom resources for these personalized class scheduling requests, and generating primary class scheduling plans;

[0062] S3. According to the personalized class scheduling request obtained in step S2, the constraint condition related data related to the personalized class scheduling request is monitored, including the total available time of the teacher Zsc, the course continuity index Zkc and the student schedule conflict value Zkb, a constraint condition data set is constructed, and a relative priority coefficient Pxs of the personalized class scheduling request with sequence number i is generated based on the constraint condition data set; then, according to the relative priority coefficient Pxs, the personalized class scheduling request with sequence number i is matched with class scheduling resources to generate an advanced class scheduling plan; then, the optimization value Yhz of each advanced class scheduling plan is calculated and evaluated to determine whether it meets the optimization class scheduling goal;

[0063] S4, real-time monitoring of resource usage in the course scheduling process, including data related to the real-time occupancy status of classroom resources and data related to the teacher's teaching load, generating a teaching load data set, and comparing the resource allocation in the advanced course scheduling plan with the actual resource usage, generating a first resource matching value Rhz1 and evaluating it, and determining whether the advanced course scheduling plan with sequence number i needs to be adjusted;

[0064] S5. If the advanced class scheduling plan with serial number i needs to be adjusted, the adjusted advanced class scheduling plan will be re-marked, a secondary class scheduling plan will be generated and the value Yhz will be re-optimized, and the second resource matching value Rhz2 will be calculated at the same time; the optimized value Yhz of the secondary class scheduling plan will be compared with the second resource matching value Rhz2, and finally the optimized class scheduling plan will be determined.

[0065] In this embodiment, S1 obtains the basic information data related to class scheduling of the teaching and training institution in advance, and marks the teacher information, student information, course scheduling requirements, classroom resources and timetable with serial numbers, thereby ensuring the integrity of the data and the accuracy of subsequent matching; S2 generates a personalized demand set and matches the priority class scheduling request by real-time monitoring of the special needs information of teachers and students and the dynamic changes of special needs information, which can accurately handle the teacher's available time preference, course load and student course conflicts, and generate a primary class scheduling plan; S3 constructs a constraint condition data set for merging calculation by monitoring the total available time of teachers Zsc, the course continuity index Zkc and the student schedule conflict value Zkb The priority coefficient Pxs enables the advanced scheduling plan to meet personalized needs and constraints, ensures the accuracy of the optimization value Yhz, and improves the rationality of the plan; S4 generates a teaching load data set by real-time monitoring of the real-time occupancy status of classroom resources and the teaching load of teachers, and then merges and compares it with the advanced scheduling plan to generate the first resource matching value Rhz1, which can timely discover the difference between resource allocation and actual use, and quickly determine whether the advanced scheduling plan needs to be adjusted; S5 uses the optimization value Yhz and the second resource matching value Rhz2 of the secondary scheduling plan to ensure that the adjusted secondary scheduling plan can better adapt to actual needs, and finally determines the optimized scheduling plan to make the plan more flexible and more matching.

[0066] Example 2

[0067] S1 includes S11, specifically:

[0068] S11. First, collect all kinds of basic information related to class scheduling within the education and training institution; the relevant basic information includes: the teacher's name, title, professional direction, available time period and class preference, the student's name, student number, class, course selection and course conflict, the course name, course type, course duration, course number limit and teaching objectives of the course schedule, the classroom number, capacity, equipment configuration and usage time, as well as the semester start and end dates, class hours and school fixed activity time; the above relevant basic information is obtained through the preset database interface;

[0069] Next, the acquired teachers, students, courses and classroom resources are numbered and labeled respectively; specifically, teachers are classified and numbered according to their positions, available time and teaching needs, students are numbered according to their course selection and class assignments, courses are numbered according to the type, teaching objectives and duration of required and elective courses, and classroom resources are numbered according to their physical location, capacity and equipment.

[0070] In this embodiment, by collecting various basic information related to class scheduling within the teaching and training institution, including detailed data on teachers, students, courses and classroom resources, the completeness and accuracy of the information is ensured; by numbering and labeling multiple factors such as teacher's position, available time period, class preference, student course selection and class assignment, it is helpful to achieve accurate resource matching in subsequent class scheduling; in addition, detailed labeling of course type, teaching objectives and classroom resources ensures the rationality of the class scheduling plan under various constraints; this step plays a foundation-laying role in the entire class scheduling method, ensuring that resources in subsequent steps can be efficiently matched and meet personalized needs, providing complete and high-quality data support for the class scheduling system, and helping to generate more optimized class scheduling plans and improve overall class scheduling efficiency and accuracy.

[0071] Example 3

[0072] S2 includes S21 and S22, specifically:

[0073] S21. Real-time collection and update of special needs information of teachers and students. Special needs information of teachers includes teaching time preference, unavailable status in specific time periods, professional requirements, course load and temporary course adjustment needs; special needs information of students includes course preference, learning progress, course conflicts, priority requirements of individual courses and temporary course adjustments. The collected special needs information is processed in real time through the dynamic update module of the system to ensure the timeliness and accuracy of the information;

[0074] S22. Generate a set of personalized class scheduling requests that need to be processed in priority based on the personalized demand set, and classify and screen them; then, based on the personalized class scheduling requests, call the pre-collected course schedule and classroom resource data, and make a preliminary match on the personalized class scheduling requests, including cross-comparing the teacher's available time period with the student's course needs, and matching resources based on the classroom's availability and capacity requirements; during the matching process, comprehensively consider various constraints, including the teacher's teaching time preference, the student's course conflict situation and the classroom's resource limitations, and finally generate several primary class scheduling plans.

[0075] In this embodiment, S21 and S22 ensure the timeliness and accuracy of personalized demand data by real-time collection and updating of the special demand status of teachers and students, dynamically process teachers' teaching time preferences, course loads, and students' course conflicts, priority needs and other information, so that the system can effectively respond to these special needs; generate and screen priority scheduling requests based on the personalized demand set, which helps to accurately locate the resources that need to be matched first, and ensure that the scheduling plan is more flexible and targeted under complex constraints; comprehensively match the teachers' available time periods, students' course needs and classroom resource data, and consider factors such as teaching time preferences, classroom capacity and student conflicts, so as to achieve more reasonable resource allocation and ultimately generate candidate scheduling plans; this process plays a key role in the entire scheduling method, ensuring efficient and accurate scheduling under a variety of constraints, thereby enhancing the system's personalized scheduling capabilities.

[0076] Example 4

[0077] S3 includes S31 and S32, specifically:

[0078] S31, where the specific calculation formula of the relative priority coefficient Pxs of the personalized course scheduling request with sequence number i is as follows:

[0079] ;

[0080] Combining personalized needs and the generated priority coefficient Pxs, a primary scheduling plan is generated by extracting qualified resources from the teacher, student and classroom resource libraries, and performing preliminary matching according to the priority of personalized needs, and scheduling resources are matched for the personalized scheduling request with sequence number i; each primary scheduling plan meets the constraints, including the teacher's available time, course continuity and student schedule conflicts.

[0081] S32, collect the resource utilization rate Xzy, teacher workload Xjs and student distribution density Xxs of each primary class scheduling plan in real time through relevant class scheduling monitoring equipment and fit them to obtain the optimized value Yhz. The specific calculation formula is as follows:

[0082] ;

[0083] By comparing and evaluating the preset optimization threshold Q with the optimization value Yhz, it is determined whether the optimization scheduling goal is met. The specific evaluation contents are as follows:

[0084] If the optimization value Yhz ≥ optimization threshold Q, it means that the scheduling plan meets the optimization scheduling goal, and the resource utilization, teacher workload and student distribution density are all as expected;

[0085] If the optimization value Yhz<optimization threshold Q, it means that the class scheduling plan does not meet the optimization scheduling goal, and the class scheduling plan needs to be further adjusted.

[0086] In this embodiment, S31 generates a relative priority coefficient Pxs of a personalized class scheduling request, and according to the coefficient, qualified resources are extracted from the teacher, student and classroom resource libraries to ensure that the primary class scheduling plan meets the constraints such as the teacher's available time Zsc, the course continuity Zkc and the student schedule conflict Zkb, so that the class scheduling plan can reasonably match resources and meet personalized needs; S32 collects resource utilization Xzy, teacher workload Xjs and student distribution density Xxs in real time through the class scheduling monitoring equipment. The collection of these lower-level parameters can ensure comprehensive monitoring of the actual use of resources, and calculate the optimized value Yhz through fitting. The optimized value is compared and evaluated with the preset optimization threshold Q to determine whether the primary class scheduling plan meets the optimization goal; if the optimized value Yhz<optimization threshold Q, it means that the plan is insufficient in some aspects and needs to be further adjusted to ensure that the final class scheduling effect is more optimized.

[0087] Example 5

[0088] S4 includes S41 and S42, specifically:

[0089] S41. Real-time monitoring and data collection of classroom resources and teacher teaching loads involved in the scheduling process, including data related to the real-time occupancy status of classroom resources and data related to teachers' teaching loads; real-time collection and generation of teaching load data sets through preset data interfaces; wherein the teaching load data sets cover the actual workload of all teachers in the current cycle, including scheduled time periods, remaining available time periods, and the allocation of specific teaching tasks in each time period; then, the preset resource allocation related data in the current advanced scheduling plan are compared with the teaching load data sets collected through real-time monitoring, including matching the actual workload of teachers with the expected workload of teachers in the scheduling plan, and comparing the expected usage of the classroom with the actual occupancy status.

[0090] S42, after comparing the resource allocation in the current advanced class scheduling plan with the actual resource usage, the classroom occupancy ratio Yjs, the teacher workload difference value Yzf and the resource utilization rate difference value Yyl are obtained and then calculated to obtain the first resource matching value Rhz1. The specific calculation formula is as follows:

[0091] ;

[0092] Through the preset matching threshold W and the first resource matching value Rhz1, it is determined whether the advanced course scheduling plan with sequence number i needs to be adjusted. The specific evaluation content is as follows:

[0093] When the first resource matching value Rhz1 ≥ matching threshold W: it indicates that the resource allocation in the current advanced course scheduling plan matches the actual resource usage normally, and no further adjustment is required;

[0094] When the first resource matching value Rhz1 is less than the matching threshold W, it indicates that the resource allocation in the current advanced class scheduling plan is abnormally matched with the actual resource usage. At this time, the advanced class scheduling plan with serial number i is adjusted, including reallocating classroom resources and adjusting teacher teaching time periods.

[0095] In this embodiment, S41 is used to monitor and collect the classroom resource occupancy status and teacher teaching load data involved in the course scheduling process in real time, and generate a teaching load data set to ensure that the system can fully understand the teacher's actual workload and the use of classroom resources. These data include the teacher's scheduled class time periods, remaining available time periods, and specific teaching task allocation. By comparing these data with the preset resource allocation data, the deviation between the teacher's actual workload and the expected workload can be effectively identified, and the expected use of the classroom can be matched with the actual occupancy status;

[0096] S42 further obtains the classroom occupancy ratio Yjs through a specific collection method, obtains it based on the ratio of the actual occupancy time of the classroom to the expected occupancy time, calculates the teacher workload difference value Yzf according to the difference between the actual teaching time and the expected teaching time, and obtains the resource utilization difference value Yyl through the difference between the actual resource utilization rate and the expected resource utilization rate, generates the first resource matching value Rhz1 through calculation, and compares and evaluates it with the preset matching threshold W. When the first resource matching value Rhz1 is less than the matching threshold W, it means that the resource allocation is unreasonable, and the classroom resources need to be reallocated and the teacher's teaching time period needs to be adjusted. This process effectively improves the resource utilization efficiency and the rationality of the class scheduling plan, ensuring the efficiency and accuracy of the class scheduling plan after dynamic adjustment.

[0097] Example 6

[0098] S5 includes S51, specifically:

[0099] S51, by real-time collection of resource usage related data of the adjusted secondary scheduling plan with sequence number i, including teacher available time period utilization rate Jsy, classroom switching frequency Jsc, teacher cross-day work intensity parameter Jsk and classroom equipment utilization rate Jsb; extracting resource usage related data of the adjusted secondary scheduling plan, and obtaining the second resource matching value Rhz2 by the following formula:

[0100] ;

[0101] The optimization value Yhz of the secondary scheduling plan is compared and evaluated with the second resource matching value Rhz2, and the optimized scheduling plan is finally determined. The specific contents are as follows:

[0102] When the adjusted secondary scheduling plan optimization value Yhz ≥ the second resource matching value Rhz2, it means that the actual usage of the adjusted secondary scheduling plan meets expectations. At this time, the system determines this plan as the final optimized scheduling plan;

[0103] When the adjusted secondary class scheduling optimization value Yhz is less than the second resource matching value Rhz2, it means that the actual usage of the adjusted secondary class scheduling plan does not meet expectations, and the current secondary class scheduling plan is adjusted again.

[0104] In this embodiment, S51 is used to collect in real time the resource usage data in the adjusted secondary scheduling plan, including the teacher's available time period utilization rate Jsy, the classroom switching frequency Jsc, the teacher's cross-day work intensity parameter Jsk and the classroom equipment utilization rate Jsb. The collection of these parameters ensures comprehensive monitoring of the adjusted resource usage. The rationality of the teacher's time period utilization rate is understood through the teacher's available time period utilization rate Jsy, the classroom switching frequency Jsc reflects the frequent switching of classrooms, the teacher's cross-day work intensity parameter Jsk measures the appropriateness of the teacher's cross-day work intensity, and the classroom equipment utilization rate Jsb is used to evaluate the classroom equipment. Effective utilization of equipment; S52 calculates the second resource matching value Rhz2 and compares and evaluates it with the optimization value Yhz to determine whether the adjusted second-order class scheduling plan meets the optimization goal. If the optimization value Yhz≥the second resource matching value Rhz2, it indicates that the resource matching degree and utilization efficiency of the plan meet the standards, and the system determines it as the final optimization plan. If the optimization value Yhz<the second resource matching value Rhz2, it indicates that the plan still has the problem of unreasonable resource allocation and needs to be adjusted again; this process ensures the efficiency and matching degree of the class scheduling plan after dynamic adjustment, and improves the optimization ability and resource utilization effect of the class scheduling plan.

[0105] Example 7

[0106] Please refer to Figure 1 and Figure 2 ,Specifically: An intelligent automatic course scheduling system includes a data collection and annotation module, a ,personalized demand processing module, a constraint condition and optimization ,computation module, a resource usage monitoring module and a ,scheme adjustment and optimization module;

[0107] The data collection and labeling module obtains the basic information related to the course scheduling of the teaching and training institution in advance, including teacher information, student information, course scheduling requirements, classroom resources and timetable, and labels each teacher, student and course with a serial number;

[0108] The personalized demand processing module monitors the special demand information of teachers and students and the dynamic changes of the special demand information in real time, generates a personalized demand set, determines the personalized class scheduling requests that need to be processed first based on the personalized demand set, preliminarily matches courses and classroom resources for these personalized class scheduling requests, and generates a primary class scheduling plan;

[0109] The constraint condition and optimization calculation module monitors the constraint condition related data related to the personalized class scheduling request, including the total available teacher time Zsc, the course continuity index Zkc and the student schedule conflict value Zkb, according to the personalized class scheduling request obtained in step S2, constructs a constraint condition data set, and generates a relative priority coefficient Pxs of the personalized class scheduling request with sequence number i based on the constraint condition data set; then, according to the relative priority coefficient Pxs, the personalized class scheduling request with sequence number i is matched with class scheduling resources to generate an advanced class scheduling plan; then, the optimization value Yhz of each advanced class scheduling plan is calculated and evaluated to determine whether it meets the optimization class scheduling goal;

[0110] The resource usage monitoring module monitors the resource usage in the course scheduling process in real time, including data related to the real-time occupancy status of classroom resources and data related to the teacher's teaching load, generates a teaching load data set, and compares the resource allocation in the advanced course scheduling plan with the actual resource usage, generates a first resource matching value Rhz1 and evaluates it, and determines whether the advanced course scheduling plan with sequence number i needs to be adjusted;

[0111] The plan adjustment and optimization module, if the advanced class scheduling plan with serial number i needs to be adjusted, will re-mark the adjusted advanced class scheduling plan, generate a secondary class scheduling plan and re-optimize the value Yhz, and calculate the second resource matching value Rhz2 at the same time; compare the optimized value Yhz of the secondary class scheduling plan with the second resource matching value Rhz2, and finally determine the optimized class scheduling plan.

[0112] An intelligent automatic class scheduling storage medium stores a computer program, including the following steps. The computer program stores computer instructions, and when the instructions are executed by a processor, an intelligent automatic class scheduling method is implemented.

[0113] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent automatic course scheduling method, characterized by: The following steps are involved: S1. Obtain the basic information related to the class scheduling of the education and training institution in advance, including teacher information, student information, course scheduling requirements, classroom resources and timetable, and mark each teacher, student and course with a serial number; S2. Real-time monitoring of special needs information of teachers and students and dynamic changes of special needs information, generating personalized needs sets, determining personalized class scheduling requests that need to be processed first based on the personalized needs sets, preliminarily matching courses and classroom resources for these personalized class scheduling requests, and generating primary class scheduling plans; S3. According to the personalized class scheduling request obtained in step S2, the constraint-related data related to the personalized class scheduling request is monitored, including the total available teacher time Zsc, the course continuity index Zkc, and the student schedule conflict value Zkb, and a constraint data set is constructed. Based on the constraint data set, a relative priority coefficient Pxs of the personalized class scheduling request with sequence number i is generated, which is specifically generated by the following formula: Then, according to the relative priority coefficient Pxs, the personalized class scheduling request with sequence number i is matched with class scheduling resources to generate an advanced class scheduling plan; then the optimization value Yhz of each advanced class scheduling plan is calculated and evaluated to determine whether it meets the optimization class scheduling goal. The resource utilization rate Xzy, teacher workload Xjs and student distribution density Xxs of each primary class scheduling plan are collected in real time through relevant class scheduling monitoring equipment and fitted to obtain the optimization value Yhz. The specific calculation formula is as follows: S4. Real-time monitoring of resource usage during the course scheduling process, including data related to the real-time occupancy status of classroom resources and data related to the teacher's teaching load, generates a teaching load data set, and compares the resource allocation in the advanced course scheduling plan with the actual resource usage, generates a first resource matching value Rhz1 and evaluates it, and determines whether the advanced course scheduling plan with sequence number i needs to be adjusted; wherein, after comparing the resource allocation in the current advanced course scheduling plan with the actual resource usage, obtains the classroom occupancy ratio Yjs, the teacher workload difference value Yzf and the resource utilization difference value Yyl, and then calculates to obtain the first resource matching value Rhz1. The specific calculation formula is as follows: S5. If the advanced class scheduling plan with sequence number i needs to be adjusted, the adjusted advanced class scheduling plan is re-marked, a secondary class scheduling plan is generated and the value Yhz is re-optimized, and the second resource matching value Rhz2 is calculated at the same time. The specific calculation process is: By collecting the resource usage related data of the adjusted secondary scheduling plan with serial number i in real time, including the teacher's available time utilization rate Jsy, the classroom switching frequency Jsc, the teacher's cross-day work intensity parameter Jsk and the classroom equipment utilization rate Jsb; extracting the resource usage related data of the adjusted secondary scheduling plan, the second resource matching value Rhz2 is calculated by the following formula: Finally, the optimization value Yhz of the secondary scheduling plan is compared with the second resource matching value Rhz2, and the optimized scheduling plan is finally determined.

2. The intelligent automatic course scheduling method according to claim 1, characterized in that: S1 includes S11, specifically: S11. First, collect all kinds of basic information related to class scheduling within the education and training institution; the relevant basic information includes: the teacher's name, title, professional direction, available time period and class preference, the student's name, student number, class, course selection and course conflict, the course name, course type, course duration, course number limit and teaching objectives of the course schedule, the classroom number, capacity, equipment configuration and usage time, as well as the semester start and end dates, class hours and school fixed activity time; the above relevant basic information is obtained through the preset database interface; Next, the acquired teachers, students, courses and classroom resources are numbered and labeled respectively; specifically, teachers are classified and numbered according to their positions, available time and teaching needs, students are numbered according to their course selection and class assignments, courses are numbered according to the type, teaching objectives and duration of required and elective courses, and classroom resources are numbered according to their physical location, capacity and equipment.

3. The intelligent automatic course scheduling method according to claim 2, characterized in that: S2 includes S21 and S22, specifically: S21. Real-time collection and update of special needs information of teachers and students. Special needs information of teachers includes teaching time preference, unavailable status in specific time periods, professional requirements, course load and temporary course adjustment needs; special needs information of students includes course preference, learning progress, course conflicts, priority requirements of individual courses and temporary course adjustments. The collected special needs information is processed in real time through the dynamic update module of the system to ensure the timeliness and accuracy of the information; S22. Generate a set of personalized class scheduling requests that need to be processed in priority based on the personalized demand set, and classify and screen them; then, based on the personalized class scheduling requests, call the pre-collected course schedule and classroom resource data, and make a preliminary match on the personalized class scheduling requests, including cross-comparing the teacher's available time period with the student's course needs, and matching resources based on the classroom's availability and capacity requirements; during the matching process, comprehensively consider various constraints, including the teacher's teaching time preference, the student's course conflict situation and the classroom's resource limitations, and finally generate several primary class scheduling plans.

4. The intelligent automatic course scheduling method according to claim 3, characterized in that: S3 includes S31 and S32, specifically: S31. Combining personalized needs and the generated priority coefficient Pxs, a primary scheduling plan is generated by extracting qualified resources from the teacher, student and classroom resource libraries, and performing preliminary matching according to the priority of personalized needs, and scheduling resources are matched for the personalized scheduling request with sequence number i; each primary scheduling plan meets the constraints, including the teacher's available time, course continuity and student schedule conflicts.

5. The intelligent automatic course scheduling method according to claim 4, characterized in that: S32, compare and evaluate the preset optimization threshold Q with the optimization value Yhz to determine whether it meets the optimization scheduling goal. The specific evaluation content is as follows: If the optimization value Yhz ≥ optimization threshold Q, it means that the course scheduling plan meets the optimization course scheduling goal, and the resource utilization rate, teacher workload and student distribution density are all as expected; If the optimization value Yhz<optimization threshold Q, it means that the class scheduling plan does not meet the optimization scheduling goal, and the class scheduling plan needs to be further adjusted.

6. The intelligent automatic course scheduling method according to claim 5, characterized in that: S4 includes S41 and S42, specifically: S41, real-time monitoring and data collection of classroom resources and teacher teaching load involved in the course scheduling process, including data related to the real-time occupancy status of classroom resources and data related to the teacher's teaching load; Collect and generate teaching load data sets in real time through a preset data interface; The teaching load data set covers the actual workload of all teachers in the current cycle, including the scheduled class periods, the remaining available time periods, and the specific teaching task distribution in each time period; then the resource allocation related data preset in the current advanced scheduling plan is compared with the teaching load data set collected by real-time monitoring, including matching the actual workload of teachers with the expected workload of teachers in the scheduling plan, and comparing the expected usage of classrooms with the actual occupancy status.

7. The intelligent automatic course scheduling method according to claim 6, characterized in that: S42, evaluating the preset matching threshold W and the first resource matching value Rhz1 to determine whether the advanced course scheduling plan with sequence number i needs to be adjusted. The specific evaluation content is as follows: When the first resource matching value Rhz1 ≥ matching threshold W: it indicates that the resource allocation in the current advanced course scheduling plan matches the actual resource usage normally, and no further adjustment is required; When the first resource matching value Rhz1 is less than the matching threshold W, it indicates that the resource allocation in the current advanced class scheduling plan is abnormally matched with the actual resource usage. At this time, the advanced class scheduling plan with serial number i is adjusted, including reallocating classroom resources and adjusting teacher teaching time periods.

8. The intelligent automatic course scheduling method according to claim 7, characterized in that: S5 includes S51, specifically: S51, compare and evaluate the optimization value Yhz of the secondary scheduling plan with the second resource matching value Rhz2, and finally determine the optimized scheduling plan, the specific contents of which are as follows: When the adjusted secondary scheduling plan optimization value Yhz ≥ the second resource matching value Rhz2, it means that the actual usage of the adjusted secondary scheduling plan meets expectations. At this time, the system determines this plan as the final optimized scheduling plan; When the adjusted secondary class scheduling optimization value Yhz is less than the second resource matching value Rhz2, it means that the actual usage of the adjusted secondary class scheduling plan does not meet expectations, and the current secondary class scheduling plan is adjusted again.

9. An intelligent automatic class scheduling system, applied to an intelligent automatic class scheduling method according to any one of claims 1 to 8, characterized in that: It includes data collection and annotation module, personalized demand processing module, constraint condition and optimization calculation module, resource usage monitoring module and solution adjustment and optimization module; The data collection and labeling module obtains the basic information related to the course scheduling of the teaching and training institution in advance, including teacher information, student information, course scheduling requirements, classroom resources and timetable, and labels each teacher, student and course with a serial number; The personalized demand processing module monitors the special demand information of teachers and students and the dynamic changes of the special demand information in real time, generates a personalized demand set, determines the personalized class scheduling requests that need to be processed first based on the personalized demand set, preliminarily matches courses and classroom resources for these personalized class scheduling requests, and generates a primary class scheduling plan; The constraint condition and optimization calculation module monitors the constraint condition related data related to the personalized class scheduling request, including the total available teacher time Zsc, the course continuity index Zkc and the student schedule conflict value Zkb, according to the personalized class scheduling request obtained in step S2, constructs a constraint condition data set, and generates a relative priority coefficient Pxs of the personalized class scheduling request with sequence number i based on the constraint condition data set; then, according to the relative priority coefficient Pxs, the personalized class scheduling request with sequence number i is matched with class scheduling resources to generate an advanced class scheduling plan; then, the optimization value Yhz of each advanced class scheduling plan is calculated and evaluated to determine whether it meets the optimization class scheduling goal; The resource usage monitoring module monitors the resource usage in the course scheduling process in real time, including data related to the real-time occupancy status of classroom resources and data related to the teacher's teaching load, generates a teaching load data set, and compares the resource allocation in the advanced course scheduling plan with the actual resource usage, generates a first resource matching value Rhz1 and evaluates it, and determines whether the advanced course scheduling plan with sequence number i needs to be adjusted; The plan adjustment and optimization module, if the advanced class scheduling plan with serial number i needs to be adjusted, will re-mark the adjusted advanced class scheduling plan, generate a secondary class scheduling plan and re-optimize the value Yhz, and calculate the second resource matching value Rhz2 at the same time; compare the optimized value Yhz of the secondary class scheduling plan with the second resource matching value Rhz2, and finally determine the optimized class scheduling plan.

10. An intelligent automatic class scheduling storage medium, on which a computer program is stored, characterized in that: The method comprises the following steps: the computer program stores computer instructions, and when the instructions are executed by a processor, an intelligent automatic class scheduling method as described in any one of claims 1 to 8 is implemented.

Images