Smart campus management system and method based on Internet of Things

Abstract

The invention discloses a smart campus management system and method based on the Internet of Things, and relates to the technical field of smart campus management. The whole system is based on the Internet of Things technology, various kinds of information such as the use condition of a classroom and the working state of equipment can be obtained and updated in real time, and accurate data support is provided for course scheduling. The method comprises the following steps: preprocessing data required by course scheduling; generating a primary course scheduling base; calculating the fitness of the primary course scheduling base; performing selection, crossover and mutation processing by using a genetic algorithm to generate a secondary course scheduling base; detecting conflicts again; and judging whether the generated ultimate course scheduling base reaches a termination condition or not. According to the method, the intelligent and automatic course scheduling is realized, the efficiency, flexibility and accuracy of course scheduling are improved, and the method has important significance for improving the teaching quality and management level of a smart campus.

Description

Technical Field

[0001] The present invention belongs to the technical field of smart campus management, and specifically relates to a smart campus management system and method based on the Internet of Things. Background Art

[0002] Course scheduling technology aims to track and evaluate students' learning status in real time through intelligent means, and then make intelligent adjustments to courses to improve learning effectiveness and efficiency. In general, course scheduling technology can be based on artificial intelligence algorithms to assign corresponding courses according to the scheduler's work subjects, and collect their test scores and study time after completing the course. By analyzing this data, the system can automatically adjust the frequency of course push or issue targeted guidance alerts to meet the learning needs of different students.

[0003] Although course scheduling technology has many advantages, it also has some limitations in practical applications:

[0004] Difficulty in resource planning: Course scheduling technology usually requires allocating resources based on specific task requirements. However, it is difficult to accurately estimate the resource requirements of each task. If the planning deviation is large, it may reduce the performance of the system itself.

[0005] Difficulty in memory usage and allocation: In practical applications, memory usage and allocation is also a difficult problem. If too little memory is allocated, the task may fail; if too much memory is allocated, resources will be wasted. Therefore, how to reasonably allocate memory resources while ensuring the smooth completion of tasks is an important issue that course scheduling technology needs to solve. Summary of the invention

[0006] In order to overcome the shortcomings and deficiencies of the above-mentioned prior art, the first purpose of the present invention is to provide a smart campus management system based on the Internet of Things; the first purpose of the present invention is to provide a smart campus management method based on the Internet of Things.

[0007] The first object of the present invention adopts the following technical solution:

[0008] The smart campus management system based on the Internet of Things includes a course scheduling management module, a course change management module, an evaluation feedback module, a resource management module, and a progress management module;

[0009] Course scheduling management module: used to schedule courses and automatically generate course schedules through intelligent scheduling algorithms;

[0010] Course change management module: used to handle course changes, including time, classroom, and teacher changes, and to notify relevant personnel in a timely manner;

[0011] Evaluation and feedback module: used to collect fitness indicators, including total conflicts, resource utilization, and student satisfaction, to evaluate the effectiveness and efficiency of the system;

[0012] Resource management module: used to monitor resource usage in real time through IoT technology and manage various teaching resources on campus, including classrooms and teachers;

[0013] Progress management module: used to track the progress of the course, including teaching progress and student learning progress, and provide progress reports and visualization tools to help teachers and administrators understand the progress of the course.

[0014] The second object of the present invention adopts the following technical solution:

[0015] The smart campus management method based on the Internet of Things has the following process:

[0016] Step 1: Preprocess the data required for course scheduling;

[0017] Step 2: Generate a primary course scheduling base;

[0018] Step 3: Calculate the fitness of the primary course scheduling base;

[0019] Step 4: Use genetic algorithm to perform selection, crossover and mutation processing to generate secondary course scheduling base;

[0020] Step 5: Conflict re-detection;

[0021] Step 6: Determine whether the generated ultimate course scheduling base has reached the termination condition.

[0022] Preferably, step one is as follows:

[0023] S101, pre-processing teacher information;

[0024] Each teacher is given a unique ID: J1, J2, ..., Ji, where i is the teacher number; the teaching time period is a set of binary bits, 1 means that the teacher can teach, and 0 means that the teacher cannot teach, and the time period is used as the selection condition;

[0025] S102, pre-processing course information;

[0026] Each course is given a unique ID: k1, k2, ..., ki, where i is the course number; each course needs to specify the instructor, teaching time and classroom; teaching time t means teaching in the tth time period; teaching classroom: Di, i is the classroom number;

[0027] S103. Associate courses with teachers. Each four-tuple list [(course k1, teacher J1, teaching time 1, classroom D1), (course k2, teacher J2, teaching time 2, classroom D2), ..., (course ki, teacher Ji, teaching time t, classroom Di)] is a course scheduling base, which represents a course scheduling base, where t represents different time periods in a day.

[0028] Preferably, step 2 is as follows:

[0029] S201, randomly generate a primary course scheduling base;

[0030] Determine the number S of primary course scheduling bases; for each course, randomly extract an element from each of the teacher optional set, the teaching time optional set, and the teaching classroom optional set to obtain a teacher Ji, a teaching time t, and a teaching classroom Di; wherein the teacher optional set, the teaching time optional set, and the teaching classroom optional set are the teaching teacher set, the teaching time set, and the teaching classroom set respectively;

[0031] S202, conflict detection;

[0032] Create a time-classroom-teacher matrix to track the allocation of each time period, classroom, and teacher, and detect conflicts between randomly generated course scheduling elements based on course scheduling constraints;

[0033] When a time conflict is detected, a time conflict signal is generated and a time conflict elimination adjustment instruction is issued;

[0034] When a classroom conflict is detected, a classroom conflict signal is generated and a classroom conflict elimination adjustment instruction is issued;

[0035] When a teacher conflict is detected, a teacher conflict signal is generated and a teacher conflict elimination adjustment instruction is issued;

[0036] The constraints are as follows:

[0037] a. A class can only take one course in a time period;

[0038] b. A teacher can only teach one course in a period of time;

[0039] c. A course can only be arranged in one classroom during one time period;

[0040] d. The number of students in class cannot exceed the capacity of the classroom;

[0041] e. Different types of classrooms must match the corresponding courses;

[0042] S203, executing the conflict elimination adjustment instruction;

[0043] When receiving a time conflict elimination adjustment instruction, reallocate the time to reallocate the time period of one or more courses to a time period without conflict;

[0044] When receiving classroom conflict elimination adjustment instructions, change classrooms;

[0045] When receiving the teacher conflict elimination adjustment instruction, replace the teacher;

[0046] When the conflict cannot be resolved directly, adjust the priority of the course scheduling base and reschedule; continue to traverse the courses in the next course scheduling base until all conflicts are checked and resolved;

[0047] S204. Repeat steps S201 to S203 until a set number of primary course scheduling bases are generated.

[0048] As a preference, step three is specifically as follows:

[0049] S301, collect fitness indicators, including total number of conflicts, resource utilization, and student satisfaction;

[0050] The total number of conflicts includes the total number of conflicts in time, classrooms, and teacher resources;

[0051] Resource utilization rate includes the utilization rate of classroom and teacher resources;

[0052] Student satisfaction includes students’ preferences for course time, classroom, and instructor;

[0053] Traverse each course in the primary scheduling base, calculate the total number of conflicts c, and generate the conflict penalty coefficient R1 through the calculation formula. The formula is as follows:

[0054] R1=α1*c;

[0055] Among them, α1 is the conflict penalty weight coefficient, which is used to adjust the intensity of conflict penalty, and c is the total number of conflicts;

[0056] Calculate resource utilization, resources include classrooms and teachers, and generate utilization bonus coefficient R2 through calculation formula. The formula is as follows:

[0057] R2=α2*r;

[0058] Among them, α2 is the utilization reward weight coefficient, which is used to adjust the intensity of utilization rewards, and r is the average resource utilization;

[0059] Calculate student satisfaction, including students' preferences for course time and classroom, and generate the satisfaction reward coefficient R3 through the calculation formula. The formula is as follows:

[0060]

[0061] Among them, α3 is the satisfaction reward weight coefficient, which is used to adjust the intensity of the satisfaction reward, z is the total satisfaction, which is calculated based on the students' preferences for course time and classroom, and zz is the satisfaction when all courses are arranged at the students' preferred time and classroom;

[0062] Substitute the conflict penalty coefficient R1, utilization rate reward coefficient R2, and satisfaction reward coefficient R3 into the fitness calculation formula to obtain the fitness P. The calculation formula is as follows:

[0063]

[0064] As a preference, step four is specifically as follows:

[0065] S401, randomly selecting n primary course scheduling operators, where n is an integer greater than 0;

[0066] Compare the fitness values ​​of the n primary course scheduling operators and select the primary course scheduling operator with the highest fitness as the parent;

[0067] Repeat the above steps until the parent primary course scheduling operator that reaches the set number threshold is selected;

[0068] S402, randomly selecting two parent primary course scheduling operators, exchanging some of their genes, and generating a new child primary course scheduling operator;

[0069] Parent 1 [(k1,J1,1,D1),(k2,J2,2,D2),(k3,J3,3,D3)] and parent 2 [(k4,J4,4,D4),(k5,J5,5,D5),(k6,J6,6,D6)], when the crossover point is at the second position, then the crossover offspring 1 [(k1,J1,1,D1),(k5,J5,5,D5),(k3,J3,3,D3)] and offspring 2 [(k4,J4,4,D4),(k2,J2,2,D2),(k6,J6,6,D6)];

[0070] S403. Randomly change the genes of the primary course scheduling operator to introduce new genetic mutations and generate new offspring primary course scheduling operators, including randomly changing the instructor, teaching time or teaching classroom of the course. For the primary course scheduling operator [(k7,J7,7,D7),(k8,J8,8,D8),(k9,J9,9,D9)], select the gene at the second position for mutation and change its teacher ID from J8 to J10. The mutated individuals are [(k7,J7,7,D7),(k8,J10,8,D8),(k9,J9,9,D9)].

[0071] As a preference, step five is specifically as follows:

[0072] The secondary course scheduling bases generated after selection, crossover and mutation are traversed one by one for conflict detection to ensure that no new conflicts are introduced;

[0073] S501, check time conflicts;

[0074] For each course, check whether its assigned time slot overlaps with other courses’ time slots and whether it conflicts with the time availability of the assigned classroom and teacher in that time slot. If a time conflict is found, record the time.

[0075] S502, check classroom conflicts;

[0076] For each course, check whether the assigned classroom is occupied by other courses in the same time period, and whether the classroom requirements of other courses do not conflict with the classroom requirements of this course, including classroom capacity and equipment. If a classroom conflict is found, record the classroom number;

[0077] S503, Check teacher conflicts:

[0078] For each course, check whether the assigned teacher is occupied by other courses in the same time period. If a teacher conflict is found, record the teacher number;

[0079] S504. If a conflict is detected, the conflict is processed according to its type and severity: the time, classroom, and teacher of the conflicting course are reallocated. If the conflict cannot be resolved, the course scheduling base is marked as invalid and deleted. The above processing generates the ultimate course scheduling base.

[0080] As a preference, step six is ​​specifically as follows:

[0081] Calculate the fitness value of the ultimate course scheduling base. The process is the same as the process of calculating the fitness of the primary course scheduling base in step 3. According to the fitness value of the ultimate course scheduling base, determine whether the optimal conditions are met: when the fitness value reaches the preset solution, it is determined that the current ultimate course scheduling base meets the optimal conditions.

[0082] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0083] 1. The present invention pre-processes the data before course scheduling, which can remove redundant and erroneous data and ensure the accuracy of subsequent course scheduling base generation; the pre-processed data can more directly reflect the students' learning needs and the actual situation of course resources, thereby improving the efficiency and pertinence of course scheduling.

[0084] 2. The present invention uses genetic algorithms to select, crossover and mutate primary course scheduling genes, which can simulate the survival of the fittest mechanism in the biological evolution process and automatically find the optimal course scheduling plan; the global search capability and robustness of the genetic algorithm make the course scheduling results more stable and reliable, and can adapt to the scheduling needs in different scenarios.

[0085] 3. After generating the secondary course scheduling base, the present invention performs conflict re-detection, which can timely discover and correct conflicts and errors that may occur in the scheduling process, and ensure the correctness and feasibility of the scheduling results; it determines whether the generated ultimate course scheduling base meets the termination conditions, and can ensure that the scheduling process is terminated after reaching the preset goal, avoiding unnecessary calculations and waste of resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0086] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0087] Figure 1 The module diagram of the smart campus management system based on the Internet of Things of the present invention is shown;

[0088] Figure 2 The flowchart of the smart campus management method based on the Internet of Things of the present invention is shown. DETAILED DESCRIPTION

[0089] 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.

[0090] Example 1

[0091] See also Figure 1 As shown, the IoT-based smart campus management system of this embodiment includes a course scheduling management module, a course change management module, an evaluation feedback module, a resource management module, and a progress management module.

[0092] The smart campus management system based on the Internet of Things includes course scheduling management module, course change management module, evaluation feedback module, resource management module, and progress management module;

[0093] Course scheduling management module: used to schedule courses and automatically generate course schedules through intelligent scheduling algorithms;

[0094] Course change management module: used to handle course changes, including time, classroom, and teacher changes, and to notify relevant personnel in a timely manner;

[0095] Evaluation and feedback module: used to collect fitness indicators, including total conflicts, resource utilization, and student satisfaction, to evaluate the effectiveness and efficiency of the system;

[0096] Resource management module: used to monitor resource usage in real time through IoT technology and manage various teaching resources on campus, including classrooms and teachers;

[0097] Progress management module: used to track the progress of the course, including teaching progress and student learning progress, and provide progress reports and visualization tools to help teachers and administrators understand the progress of the course.

[0098] The beneficial effects of this embodiment include: providing a more intelligent, efficient and flexible solution for campus course scheduling through real-time data collection, intelligent analysis and optimized scheduling.

[0099] Example 2

[0100] See also Figure 2 As shown, the smart campus management method based on the Internet of Things in this embodiment has the following process:

[0101] Step 1: Preprocess the data required for course scheduling.

[0102] S101. Preprocess teacher information.

[0103] Each teacher is given a unique ID: J1, J2, ..., Ji, where i is the teacher number; the teaching time period is a set of binary bits; for example, the teaching time period: [1, 0, 1, 0], where [1, 0, 1, 0] means that the 1st and 3rd time periods can be taught, but the 2nd and 4th time periods cannot be taught), and the time period is used as the selection condition.

[0104] S102: Pre-process course information.

[0105] Each course is given a unique ID: k1, k2, ..., ki, where i is the course number; each course needs to specify the instructor, teaching time and classroom, for example: course ID: k1, teaching time: 2 (indicating that the course is taught in the second time period); teaching classroom: Di, i is the classroom number.

[0106] S103. Associate courses with teachers, where each four-tuple list [(course k1, teacher J1, teaching time 1, classroom D1), (course k2, teacher J2, teaching time 2, classroom D2), ..., (course ki, teacher Ji, teaching time t, classroom Di)] is a course scheduling base, representing a course scheduling base, where t represents different time periods in a day (such as time period 1 represents 8:00-9:30 am, time period 2 represents 9:45-11:15 am, etc.).

[0107] Step 2: Generate the primary course scheduling base.

[0108] S201. Randomly generate a primary course scheduling base.

[0109] Determine the number S of primary course scheduling bases;

[0110] For each course, a teacher Ji, a teaching time t and a teaching classroom Di are obtained by randomly extracting an element from the optional teacher set, the optional teaching time set and the optional teaching classroom set respectively; among which, the optional teacher set, the optional teaching time set and the optional teaching classroom set are the set of teachers who can teach, the set of time that can teach, and the set of classrooms that can teach, respectively.

[0111] S202: Conflict detection.

[0112] Create a time-classroom-teacher matrix to track the allocation of each time period, classroom, and teacher, and detect conflicts between randomly generated course scheduling elements based on course scheduling constraints;

[0113] When a time conflict is detected, a time conflict signal is generated and a time conflict elimination adjustment instruction is issued;

[0114] When a classroom conflict is detected, a classroom conflict signal is generated and a classroom conflict elimination adjustment instruction is issued;

[0115] When a teacher conflict is detected, a teacher conflict signal is generated and a teacher conflict elimination adjustment instruction is issued.

[0116] Schedule conflict: Two or more courses are assigned to the same teacher or the same classroom at the same time.

[0117] Classroom conflict: Two or more classes are assigned to the same classroom at the same time, but with different instructors or course requirements.

[0118] Teacher conflict: A teacher is assigned to multiple courses at the same time.

[0119] The constraints are as follows:

[0120] 1. A class can only take one course in a time period;

[0121] 2. A teacher can only teach one course in a period of time;

[0122] 3. A course can only be arranged in one classroom during one time period;

[0123] 4. The number of students in class cannot exceed the capacity of the classroom;

[0124] 5. Different types of classrooms must match the corresponding courses.

[0125] S203: Execute the conflict elimination adjustment instruction.

[0126] When a time conflict elimination adjustment instruction is received, the time is reallocated to reallocate the time period of one or more courses to a time period without conflict.

[0127] When receiving classroom conflict elimination adjustment instructions, change classrooms.

[0128] When receiving teacher conflict elimination adjustment instructions, replace the teacher.

[0129] When conflicts cannot be resolved directly, adjust the priority of the course scheduling base and reschedule. This may require re-evaluating the requirements and constraints of all courses.

[0130] Based on the outcome of the conflict resolution, the data structure used to track allocations is updated.

[0131] Continue iterating through the courses in the next course schedule base until all conflicts have been checked and resolved.

[0132] S204. Repeat steps S201 to S203 until a set number of primary course scheduling bases are generated.

[0133] Step 3: Calculate the fitness of the primary course scheduling base.

[0134] S301. Collect fitness indicators, including total number of conflicts, resource utilization, and student satisfaction.

[0135] Total Conflicts: Measures the total number of conflicts in time, classroom, or teacher resources in the scheduling plan.

[0136] Resource utilization: measures the efficiency of using classroom, teacher and other resources.

[0137] Student satisfaction: assessed based on student preferences regarding course time, classroom, etc.

[0138] Traverse each course in the primary scheduling base, calculate the total number of conflicts c, and generate the conflict penalty coefficient R1 through the calculation formula. The formula is as follows:

[0139] R1=α1*c;

[0140] Among them, α1 is the conflict penalty weight coefficient, which is used to adjust the intensity of the conflict penalty, and c is the total number of conflicts.

[0141] Calculate resource utilization, resources include classrooms and teachers, and generate utilization bonus coefficient R2 through calculation formula. The formula is as follows:

[0142] R2=α2*r;

[0143] Among them, α2 is the utilization reward weight coefficient, which is used to adjust the intensity of utilization reward, and r is the average resource utilization.

[0144] Calculate student satisfaction, including students' preferences for course time and classroom, and generate the satisfaction reward coefficient R3 through the calculation formula. The formula is as follows:

[0145]

[0146] Among them, α3 is the satisfaction reward weight coefficient, which is used to adjust the intensity of the satisfaction reward, z is the total satisfaction, which is calculated based on students' preferences for course time and classroom, and zz is the satisfaction when all courses are scheduled at the students' preferred time and classroom.

[0147] Substitute the conflict penalty coefficient R1, utilization rate reward coefficient R2, and satisfaction reward coefficient R3 into the fitness calculation formula to obtain the fitness P. The calculation formula is as follows:

[0148]

[0149] Step 4: Use genetic algorithm to perform selection, crossover and mutation to generate secondary course scheduling base.

[0150] S401, randomly selecting n primary course scheduling operators, where n is an integer greater than 0;

[0151] Compare the fitness values ​​of the n primary course scheduling operators and select the primary course scheduling operator with the highest fitness as the parent;

[0152] The above steps are repeated until the parent primary course scheduling operator that reaches the set quantity threshold is selected.

[0153] S402. Randomly select two parent primary course scheduling operators, exchange some of their genes, and generate a new child primary course scheduling operator.

[0154] For example: Parent 1 [(k1,J1,1,D1),(k2,J2,2,D2),(k3,J3,3,D3)] and Parent 2 [(k4,J4,4,D4),(k5,J5,5,D5),(k6,J6,6,D6)], when the intersection is at the second position, then the crossover will result in Offspring 1 [(k1,J1,1,D1),(k5,J5,5,D5),(k3,J3,3,D3)] and Offspring 2 [(k4,J4,4,D4),(k2,J2,2,D2),(k6,J6,6,D6)].

[0155] S403, randomly changing the genes of some primary course scheduling operators, introducing new genetic mutations, and generating new offspring primary course scheduling operators, including randomly changing the instructor, teaching time, or teaching classroom of a certain course. For example: for the primary course scheduling operator [(k7, J7, 7, D7), (k8, J8, 8, D8), (k9, J9, 9, D9)], select the gene at the second position for mutation, and change its teacher ID from J8 to J10, then the mutated individuals are [(k7, J7, 7, D7), (k8, J10, 8, D8), (k9, J9, 9, D9)].

[0156] Step 5: Re-detect the conflict.

[0157] The secondary course scheduling bases generated after selection, crossover and mutation are traversed one by one for conflict detection to ensure that no new conflicts are introduced.

[0158] S501, check time conflict:

[0159] For each course, check whether its assigned time slot overlaps with other courses' time slots and conflicts with the time availability of the assigned classroom and instructor during that time slot.

[0160] If you find a time conflict, record the conflict information.

[0161] S502, check classroom conflicts:

[0162] For each course, check whether its assigned classroom is occupied by other courses in the same time period, and whether the classroom requirements of other courses do not conflict with the classroom requirements of this course (such as classroom capacity, equipment, etc.).

[0163] If classroom conflicts are discovered, record the conflict information.

[0164] S503, Check teacher conflicts:

[0165] For each course, check whether the assigned teacher is occupied by other courses in the same time period. If a teacher conflict is found, record the conflict information.

[0166] S504, if a conflict is detected, handle it according to the type and severity of the conflict: reallocate the time, classroom, and teacher of the conflicting course; if the conflict cannot be resolved, mark the course scheduling base as invalid and delete it;

[0167] The above processing generates the ultimate course scheduling base.

[0168] Step 6: Determine whether the generated ultimate course scheduling base has reached the termination condition.

[0169] The process of calculating the fitness value of the ultimate course scheduling base is the same as the process of calculating the fitness value of the primary course scheduling base in step 3, and will not be repeated here.

[0170] According to the fitness value of the ultimate course scheduling base, it is judged whether the optimal condition is met: when the fitness value reaches the preset solution, it is judged that the current ultimate course scheduling base meets the optimal condition.

[0171] The beneficial effects of this embodiment include: through steps such as data preprocessing, genetic algorithm optimization, conflict re-detection and termination condition judgment, the intelligent and automated course scheduling is realized, the efficiency and accuracy of scheduling are improved, the quality and feasibility of scheduling results are ensured, and it is of great significance to improve the teaching quality and management level of smart campuses.

[0172] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

[0173] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. The smart campus management system based on the Internet of Things is characterized by: It includes course scheduling management module, course change management module, evaluation feedback module, resource management module and progress management module; Course scheduling management module: used to schedule courses and automatically generate course schedules through intelligent scheduling algorithms; Course change management module: used to handle course changes, including time, classroom, and teacher changes, and to notify relevant personnel in a timely manner; Evaluation and feedback module: used to collect fitness indicators, including total conflicts, resource utilization, and student satisfaction, to evaluate the effectiveness and efficiency of the system; Resource management module: used to monitor resource usage in real time through IoT technology and manage various teaching resources on campus; Progress management module: used to track the progress of the course, including teaching progress and student learning progress, and provide progress reports and visualization tools to help teachers and administrators understand the progress of the course.

2. A smart campus management method based on the Internet of Things, characterized in that: The process is as follows: Step 1: Preprocess the data required for course scheduling; Step 2: Generate a primary course scheduling base; Step 3: Calculate the fitness of the primary course scheduling base; Step 4: Use genetic algorithm to perform selection, crossover and mutation processing to generate secondary course scheduling base; Step 5: Conflict re-detection; Step 6: Determine whether the generated ultimate course scheduling base has reached the termination condition.

3. The method for managing a smart campus based on the Internet of Things according to claim 2, characterized in that: The step 1 is specifically as follows: S101, pre-processing teacher information; Each teacher is given a unique ID: J1, J2, ..., Ji, where i is the teacher number; the teaching time period is a set of binary bits, 1 means that the teacher can teach, and 0 means that the teacher cannot teach, and the time period is used as the selection condition; S102, pre-processing course information; Each course is given a unique ID: k1, k2, ..., ki, where i is the course number; each course needs to specify the instructor, teaching time and classroom; teaching time t means teaching in the tth time period; teaching classroom: Di, i is the classroom number; S103. Associate courses with teachers. Each four-tuple list [(course k1, teacher J1, teaching time 1, classroom D1), (course k2, teacher J2, teaching time 2, classroom D2), ..., (course ki, teacher Ji, teaching time t, classroom Di)] is a course scheduling base, which represents a course scheduling base, where t represents different time periods in a day.

4. The method for managing a smart campus based on the Internet of Things according to claim 2, characterized in that: The step 2 is specifically as follows: S201, randomly generate a primary course scheduling base; Determine the number S of primary course scheduling bases; for each course, randomly extract an element from each of the teacher optional set, the teaching time optional set, and the teaching classroom optional set to obtain a teacher Ji, a teaching time t, and a teaching classroom Di; wherein the teacher optional set, the teaching time optional set, and the teaching classroom optional set are the teaching teacher set, the teaching time set, and the teaching classroom set respectively; S202, conflict detection; Create a time-classroom-teacher matrix to track the allocation of each time period, classroom, and teacher, and detect conflicts between randomly generated course scheduling elements based on course scheduling constraints; When a time conflict is detected, a time conflict signal is generated and a time conflict elimination adjustment instruction is issued; When a classroom conflict is detected, a classroom conflict signal is generated and a classroom conflict elimination adjustment instruction is issued; When a teacher conflict is detected, a teacher conflict signal is generated and a teacher conflict elimination adjustment instruction is issued; The constraints are as follows: a. A class can only take one course in a time period; b. A teacher can only teach one course in a period of time; c. A course can only be arranged in one classroom during one time period; d. The number of students in class cannot exceed the capacity of the classroom; e. Different types of classrooms must match the corresponding courses; S203, executing the conflict elimination adjustment instruction; When receiving a time conflict elimination adjustment instruction, reallocate the time to reallocate the time period of one or more courses to a time period without conflict; When receiving classroom conflict elimination adjustment instructions, change classrooms; When receiving the teacher conflict elimination adjustment instruction, replace the teacher; When the conflict cannot be resolved directly, adjust the priority of the course scheduling base and reschedule; continue to traverse the courses in the next course scheduling base until all conflicts are checked and resolved; S204. Repeat steps S201 to S203 until a set number of primary course scheduling bases are generated.

5. The method for managing a smart campus based on the Internet of Things according to claim 2, characterized in that: The step three is as follows: S301, collect fitness indicators, including total number of conflicts, resource utilization, and student satisfaction; The total number of conflicts includes the total number of conflicts in time, classrooms, and teacher resources; Resource utilization rate includes the utilization rate of classroom and teacher resources; Student satisfaction includes students’ preferences for course time, classroom, and instructor; Traverse each course in the primary scheduling base, calculate the total number of conflicts c, and generate the conflict penalty coefficient R1 through the calculation formula. The formula is as follows: R1=α1*c; Among them, α1 is the conflict penalty weight coefficient, which is used to adjust the intensity of conflict penalty, and c is the total number of conflicts; Calculate resource utilization, resources include classrooms and teachers, and generate utilization bonus coefficient R2 through calculation formula. The formula is as follows: R2＝α2*r； Among them, α2 is the utilization reward weight coefficient, which is used to adjust the intensity of utilization rewards, and r is the average resource utilization; Calculate student satisfaction, including students' preferences for course time and classroom, and generate the satisfaction reward coefficient R3 through the calculation formula. The formula is as follows: Among them, α3 is the satisfaction reward weight coefficient, which is used to adjust the intensity of the satisfaction reward, z is the total satisfaction, which is calculated based on the students' preferences for course time and classroom, and zz is the satisfaction when all courses are arranged at the students' preferred time and classroom; Substitute the conflict penalty coefficient R1, utilization rate reward coefficient R2, and satisfaction reward coefficient R3 into the fitness calculation formula to obtain the fitness P. The calculation formula is as follows:

6. The method for managing a smart campus based on the Internet of Things according to claim 2, characterized in that: The step 4 is as follows: S401, randomly selecting n primary course scheduling operators, where n is an integer greater than 0; Compare the fitness values ​​of the n primary course scheduling operators and select the primary course scheduling operator with the highest fitness as the parent; Repeat the above steps until the parent primary course scheduling operator that reaches the set number threshold is selected; S402, randomly selecting two parent primary course scheduling operators, exchanging some of their genes, and generating a new child primary course scheduling operator; Parent 1 [(k1,J1,1,D1),(k2,J2,2,D2),(k3,J3,3,D3)] and parent 2 [(k4,J4,4,D4),(k5,J5,5,D5),(k6,J6,6,D6)], when the crossover point is at the second position, then the crossover offspring 1 [(k1,J1,1,D1),(k5,J5,5,D5),(k3,J3,3,D3)] and offspring 2 [(k4,J4,4,D4),(k2,J2,2,D2),(k6,J6,6,D6)]; S403. Randomly change the genes of the primary course scheduling operator to introduce new genetic mutations and generate new offspring primary course scheduling operators, including randomly changing the instructor, teaching time or teaching classroom of the course. For the primary course scheduling operator [(k7,J7,7,D7),(k8,J8,8,D8),(k9,J9,9,D9)], select the gene at the second position for mutation and change its teacher ID from J8 to J10. The mutated individuals are [(k7,J7,7,D7),(k8,J10,8,D8),(k9,J9,9,D9)].

7. The method for managing a smart campus based on the Internet of Things according to claim 2, characterized in that: The step five is as follows: The secondary course scheduling bases generated after selection, crossover and mutation are traversed one by one for conflict detection to ensure that no new conflicts are introduced; S501, check time conflicts; For each course, check whether its assigned time slot overlaps with other courses’ time slots and whether it conflicts with the time availability of the assigned classroom and teacher in that time slot. If a time conflict is found, record the time. S502, check classroom conflicts; For each course, check whether the assigned classroom is occupied by other courses in the same time period, and whether the classroom requirements of other courses do not conflict with the classroom requirements of this course, including classroom capacity and equipment. If a classroom conflict is found, record the classroom number; S503, Check teacher conflicts: For each course, check whether the assigned teacher is occupied by other courses in the same time period. If a teacher conflict is found, record the teacher number; S504. If a conflict is detected, the conflict is processed according to its type and severity: the time, classroom, and teacher of the conflicting course are reallocated. If the conflict cannot be resolved, the course scheduling base is marked as invalid and deleted. The above processing generates the ultimate course scheduling base.

8. The method for managing a smart campus based on the Internet of Things according to claim 2, characterized in that: The step six is ​​as follows: Calculate the fitness value of the ultimate course scheduling base. The process is the same as the process of calculating the fitness of the primary course scheduling base in step 3. According to the fitness value of the ultimate course scheduling base, determine whether the optimal conditions are met: when the fitness value reaches the preset solution, it is determined that the current ultimate course scheduling base meets the optimal conditions.

Images