Intelligent campus integrated management system and method

Abstract

The invention relates to the technical field of education management, in particular to a smart campus integrated management system and method, and the system comprises a course arrangement module, a teacher matching module, a resource scheduling module, a behavior monitoring module and an interaction guiding module. Through intelligent processing, course arrangement and teacher matching optimization, the teaching resource utilization efficiency is improved, errors and deviations in manual processing are avoided, the matching degree of courses and students is improved by means of intelligent screening and conflict elimination, course conflicts are reduced, matching is carried out according to the qualification and preference of teachers, teacher resource configuration is optimized, and the teaching efficiency is improved. The accurate scheduling of classroom and equipment resources avoids resource waste and insufficiency, the smooth campus management is ensured, the behavior monitoring technology and the safety perception means track the behaviors in the teaching process in real time, the interactive guidance provides immediate feedback and guidance in the case of abnormality, the potential safety hazard is reduced, and the teaching efficiency is improved. And the intelligent safety guarantee level of the campus is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of education management, and particularly to an intelligent campus integrated management system and method. Background Art

[0002] The technical field of education management includes technologies for effectively managing aspects such as the education process, educational resources, school facilities, and education quality. The core content of this field mainly involves student information management, faculty and staff management, classroom teaching arrangement, curriculum resource scheduling, examination management, student status management, teaching quality monitoring, etc. Education management technology aims to optimize the daily operation management of schools through information technology, improve management efficiency, reduce labor costs, enhance the traceability and transparency of data. With the continuous development of information technology, education management has gradually developed towards intelligence and automation, and an intelligent education management system has gradually taken shape, promoting the effective allocation and application of educational resources.

[0003] Among them, the intelligent campus integrated management system refers to a system designed specifically for schools and realizing integrated management through information technology. This system involves multiple aspects such as student information management, faculty and staff management, teaching resource scheduling, and campus security management. For the problems of the daily operation management of schools, it integrates information such as students, teachers, courses, and equipment in a centralized manner, uses means such as data management, identity authentication, reservation, and attendance management to improve campus management efficiency, and monitors and manages various campus affairs in real time through a network platform.

[0004] The existing technologies face many bottlenecks in resource scheduling and management in actual operation. For example, although the existing technologies can provide information such as course management and teacher allocation, they lack effective automated scheduling and rely on manual input and judgment, resulting in a large amount of inefficient time and resource waste. There are risks of manual review and manual processing in the scheduling of classrooms and equipment, which easily leads to uneven resource allocation. Especially in peak periods or in the case of course conflicts, the system lacks the ability of dynamic adjustment and optimization and is difficult to meet the real-time changing needs. Although there have been some progress in teaching quality monitoring, the existing monitoring means mainly focus on traditional classroom feedback and have not penetrated into the comprehensive evaluation of student behavior, interaction, and teacher teaching methods, and cannot comprehensively grasp the multi-dimensional performance of education quality, thereby limiting the depth of education quality improvement. Security monitoring mainly relies on manual judgment of abnormal behaviors by humans, and in the face of a complex campus environment, misjudgment or missed judgment is likely to occur, directly affecting the optimal allocation of educational resources and the accuracy of campus management. Summary of the Invention

[0005] The purpose of the present invention is to solve the deficiencies existing in the prior art, and to propose an intelligent campus integrated management system and method.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: A smart campus comprehensive management system comprises: The course scheduling module obtains student performance data and course selection information in the smart campus, screens low-performing courses based on course difficulty and time preference, adjusts conflicting course combinations, optimizes rules based on the course schedule, and makes learning adjustments to obtain a detailed list of course scheduling; The teacher matching module retrieves the teacher's teaching qualifications, course competency conditions and teaching method preferences according to the course requirements in the course scheduling and allocation details table, compares whether the teacher matches the competency conditions of the required course, screens the candidate teacher list according to the matching degree, and generates a course teaching assignment list; The resource scheduling module extracts the available time periods and equipment information of the classroom according to the course time periods and teacher arrangement in the course teaching assignment list, determines whether the resources meet the course equipment and capacity standards, screens the available space and marks the conflict exclusion items, and forms a space and equipment use plan; The behavior monitoring module calls the allocated teaching venue location in the space and equipment usage plan, identifies the behavior detection data of the smart campus security perception, extracts the crowd trajectory and density changes in the video, determines whether there are gathering anomalies and behavioral interference during the teaching period, and obtains the abnormal behavior distribution map.

[0007] As a further solution of the present invention, the course scheduling and allocation details table includes course priority levels, time conflict identifiers, course adjustment results, and matching feasibility scores; the course teaching assignment list includes teacher matching scores, recommended teaching teachers, course correspondences, and teaching modes; the space and equipment use plan includes classroom number information, available time period range, equipment type distribution, and resource conflict marks; the abnormal behavior distribution map includes a personnel gathering density map, abnormal behavior categories, risk level areas, and time period marking information.

[0008] As a further solution of the present invention, the course arrangement module includes: The grade screening submodule obtains the student grade data and course selection information in the smart campus, extracts the course grade and difficulty deviation coefficient, screens the course numbers whose deviation coefficient is greater than the benchmark value, determines whether the number of repeated course selections in the original course selection record exceeds the threshold, and obtains the number of repeated course selections; The time matching submodule calls the course number and time period in the course repeat elective quantity, detects the intersection interval between the course and the current time schedule, and determines whether it is below the class time conflict threshold, extracts the qualified course group, and calculates the interval difference with the time preference parameter to obtain the class time preference adaptability; The rule allocation submodule extracts conflicting course combinations based on the class time preference adaptability, determines whether the matching degree between the idle time period and the class schedule meets the benchmark value for class scheduling, screens feasible combinations, and compares them with the numbers of the courses to be scheduled to obtain a detailed list of class scheduling.

[0009] As a further solution of the present invention, the teacher matching module includes: The teacher qualification analysis submodule extracts the subject category, teaching years and teaching method records of teachers in the teacher information database based on the subject direction, teaching years requirement and teaching method type of the courses in the course scheduling and allocation details table, determines whether the set standards are met item by item, and generates a subject teaching method matching evaluation result; The competency matching calculation submodule calls the teaching method matching evaluation results of the subject, extracts the teaching years, teaching preference values and competency index values of teachers who meet the requirements, identifies the weighted structural relationship for each index, and uses the formula based on the number of applied courses: ; Calculate the course competency matching value of each teacher, sort the matching values, and form a matching sorting table; in, Indicates The course competency matching value of teachers, Indicates The number of years of teaching experience of each teacher, Indicates The teaching preference values of teachers, Indicates Teacher in Performance value on each competency indicator, Indicates The number of courses reported by teachers, Indicates the total number of competency indicators; The candidate screening and dispatching submodule calls the matching sorting table, selects a list of teacher candidates according to the matching value, checks the conflicts between teaching time and class, removes conflicting items, and obtains a course teaching dispatch list.

[0010] As a further solution of the present invention, the resource scheduling module includes: The course time period matching submodule extracts the course start and end time and the teacher's class time interval according to the course teaching assignment list, the course time period and the teacher arrangement, matches the classroom idle time period, eliminates holidays and administrative occupied time periods, and obtains a matching time period set; The space equipment screening submodule extracts the classroom capacity and equipment configuration based on the matching time period set, identifies the number of students in the course and compares it with the classroom capacity, analyzes the coverage ratio between the equipment required for the course and the classroom equipment, and superimposes the inverse value of the missing equipment using the formula: ; Calculate the classroom screening coefficient, sort the sizes to extract the priority items, and obtain the available space screening set; Among them, represents the classroom screening coefficient, represents the total number of students in the course, represents the classroom capacity, represents the number of required equipment for the course, represents the number of matching equipment items in the classroom, represents the total number of course equipment items, represents the reciprocal value of the missing equipment item; The conflict exclusion annotation sub-module calls the available space screening set, compares the classroom location and facility sharing situation, annotates the classrooms with time conflicts and equipment overlaps, and eliminates the conflict items to form a space and equipment usage plan.

[0011] As a further solution of the present invention, the behavior monitoring module includes: The venue positioning sub-module calls the space and equipment usage plan, extracts the venue number, time arrangement and space coordinates, compares the current time with the planned time, screens the recognizable teaching venues, and obtains the teaching venue time matching degree value; The trajectory density analysis sub-module identifies the crowd image area in the video according to the teaching venue time matching degree value, extracts the number of people and spatial positions, analyzes the changes in the frequency of people in the unit area and the space coverage rate, and obtains the crowd trajectory density distribution quantity; The abnormal behavior judgment sub-module compares the crowd trajectory density distribution quantity with the normal fluctuation reference value, judges whether the density increase amplitude exceeds the limit, extracts the trajectory stability degree and the personnel overlap offset value, analyzes the change degree, and uses the formula: ; Calculate the abnormal behavior offset value, compare it with the aggregation threshold, identify the over-limit area and interference level, and obtain the abnormal behavior distribution map; Among them, represents the abnormal behavior offset value, represents the lower limit value of the trajectory stability degree, represents the upper limit value of the trajectory stability degree, represents the density increase rate, represents the personnel overlap offset value, represents the area of the crowd movement speed change amount, represents the area of the change amount of the number of people accounted for, represents the density distribution increase difference, represents the total number of areas.

[0012] As a further solution of the present invention, the system further includes an interactive guidance module: The interactive guidance module captures on-site feedback information by extracting voice recognition, analyzing voice commands and keywords, judging the effectiveness of commands and the completeness of feedback, and counting the types and distribution of response modes to form the execution status of smart campus risk guidance according to the risk area number identified in the abnormal behavior distribution map; The smart campus risk guidance execution status includes voice command type, response behavior label, execution area number, and feedback integrity classification.

[0013] As a further solution of the present invention, the interactive guidance module includes: The speech analysis submodule analyzes the time, space instructions and behavior keywords in the speech according to the risk area number identified in the abnormal behavior distribution map, determines the effectiveness of the instruction according to the matching relationship between the behavior keywords and the number, and evaluates the effectiveness of the feedback in combination with the integrity of the time and space instructions to obtain the instruction response recognition rate; The response judgment submodule calls the command response recognition rate, counts the distribution density of each type of feedback under the risk area number according to the number of types of semantic keywords in the feedback data, compares the relationship between keyword distribution and feedback frequency, and obtains the response type distribution density value; The execution statistics submodule calls the response type distribution density value, identifies the offset quantity and frequency difference of keywords between numbers, analyzes the variation range of the offset value, and forms the execution status of smart campus risk relief.

[0014] The smart campus comprehensive management method is implemented based on the above-mentioned smart campus comprehensive management system, and includes the following steps: S1: Obtain student performance data and course selection information in the smart campus, screen low-scoring courses, extract course information with difficulty levels and time matching below the threshold, eliminate arrangements that conflict with the current schedule, reorganize courses, and obtain a detailed list of course scheduling; S2: Based on the course scheduling and allocation details table, extract course demand items, combine the teaching years, teaching frequency and teaching method data in the teacher resume database, identify the similarity between teacher qualifications and course competency, select the data of teachers with high matching rankings, and establish a teacher course matching list; S3: Based on the teacher course matching list, extract the class schedule and teacher tasks, search for available classrooms and determine the capacity demand match, check the equipment configuration and course requirements, filter out the non-matching items and summarize the matching results, and obtain the venue resource allocation summary table; S4: Based on the venue resource allocation summary table, analyze the monitoring data of the configured teaching space, identify the peak of crowd activity density and high-frequency intersection areas, evaluate the dense distribution of time nodes of abnormal actions, and generate a behavior interference layer of the teaching area; S5: Based on the teaching area behavior interference layer, analyze the spatial risk number data and voice feedback, identify risk instructions and keywords, evaluate the command parsing ability, classify the correspondence between effective responses and area numbers, and form the execution status of risk guidance in the smart campus.

[0015] Compared with the prior art, the advantages and positive effects of the present invention are as follows: In the present invention, through an intelligent processing method, links such as course arrangement and teacher matching are optimized, not only significantly improving the utilization efficiency of teaching resources, but also avoiding common errors and deviations in the manual processing process. The intelligent screening and conflict elimination means for course arrangement ensure an improved matching degree between students and courses, while reducing unnecessary course conflicts. Intelligent matching based on teachers' teaching qualifications and preferences optimizes the allocation of teacher resources, ensuring a high degree of fit between teaching effects and teacher qualifications. The precise allocation of resources for classrooms and equipment avoids problems of resource waste and insufficiency, thus ensuring the smooth operation of campus management. By combining behavior monitoring technology with security perception means, it is possible to track the behaviors of students and teachers in real time during the teaching process, promptly discover potential abnormal behaviors or gatherings, and respond quickly to ensure the safety of the campus and a good teaching environment. The innovative means of interactive guidance can provide instant feedback and guidance solutions when abnormalities are monitored in real time, effectively reducing potential safety hazards and enhancing the intelligent security guarantee level of the campus. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is the system flow chart of the present invention; Figure 2 is the flow chart of the course arrangement module in the present invention; Figure 3 is the flow chart of the teacher matching module in the present invention; Figure 4 is the flow chart of the resource scheduling module in the present invention; Figure 5 is the flow chart of the behavior monitoring module in the present invention; Figure 6 is the flow chart of the interactive guidance module in the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0018] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention. In addition, in the description of the present invention, the meaning of "a plurality of" is two or more, unless otherwise specifically defined.

[0019] Please refer to Figure 1 , the present invention provides a technical solution: an integrated intelligent campus management system includes: The course scheduling module obtains the student achievement data and course selection information in the intelligent campus, screens low-performance courses according to course difficulty and time preference, judges the suitability with the current class schedule, adjusts the conflict course combination, optimizes the rules according to the class schedule, and makes learning adjustments to obtain the detailed schedule allocation list; The teacher matching module, according to the course requirements in the schedule allocation list, retrieves the teaching qualifications, course competency conditions and teaching method preferences of teachers, compares whether the competency conditions of teachers match the required courses, screens the candidate teacher list according to the matching degree, and generates the course teaching assignment list; The resource scheduling module, according to the course time period and teacher arrangement content in the course teaching assignment list, extracts the available time period of the classroom and the equipment supporting information, judges whether the resources meet the course equipment and capacity standards, screens the available space and marks the conflict exclusion items to form the space and equipment usage plan; The behavior monitoring module calls the allocated teaching place location in the space and equipment usage plan, identifies the behavior detection data of the intelligent campus security perception, extracts the crowd trajectory and density change in the video, and judges whether there are aggregation anomalies and behavior interference phenomena during teaching to obtain the abnormal behavior distribution map; The interactive guidance module, based on the risk area numbers marked in the abnormal behavior distribution map, captures the on-site feedback information by extracting speech recognition, analyzes the voice commands and keywords, judges the effectiveness of the commands and the integrity of the feedback, counts the types and pointing distributions of the response modes, and forms the execution status of the risk guidance in the intelligent campus.

[0020] The course scheduling allocation details table includes course priority levels, time conflict indicators, course adjustment results, and matching feasibility scores. The course teaching assignment list includes teacher matching scores, recommended teaching teachers, course correspondences, and teaching modes. The space and equipment usage plan includes classroom number information, available time period ranges, equipment type distributions, and resource conflict markers. The abnormal behavior distribution map includes personnel aggregation density maps, abnormal behavior categories, risk level areas, and time period annotation information. The intelligent campus risk mitigation execution status includes voice command types, response behavior tags, execution area numbers, and feedback integrity classifications.

[0021] Please refer to Figure 2 , the course scheduling module includes: The grade screening sub-module obtains the student grade data and course selection information in the intelligent campus, extracts the course grade and difficulty deviation coefficient, filters the course numbers with deviation coefficients greater than the benchmark value, determines whether the number of repeated course selections in the original course selection records exceeds the threshold, and obtains the course repeated selection quantity; Extract the grade records and course registration information of students in the current semester from the intelligent campus. The data is automatically updated and stored by the student information management. For example, a student's grade in the mathematics course is 75 points and has registered for the physics course in the next semester. This data acquisition process needs to ensure the accuracy and timeliness of the data so that subsequent screening operations can be performed based on the latest data. Screen based on the deviation coefficient between the course grade value and the course difficulty value. Compare the grade of each course with the standard difficulty coefficient of the course, and calculate the deviation value. For example, the difficulty coefficient of the mathematics course is 80 and the grade is 75, and the deviation coefficient is calculated as 75 - 80 = -5. If the deviation coefficient is greater than the course difficulty benchmark coefficient, for example, the benchmark coefficient is set to -10, this means that courses with grades more than 10 points lower than the standard difficulty need to be focused on. Extract such course numbers and determine whether the number of repetitions in the historical course selection records exceeds the repeated course selection threshold. The threshold is set so that a student cannot take the same course more than three times. If it exceeds, this indicates that the student's study plan needs to be adjusted to avoid over-concentration on courses with mismatched difficulties. Finally, form a set of corresponding course numbers and time periods, and obtain the course repeated selection quantity. The quantity helps the academic affairs department understand the universality of course retakes and the learning tendencies of students, so as to optimize and adjust the course plan. For example, if it is found that a large number of students repeat the selection of the physics course, it is necessary to consider analyzing whether the teaching method or difficulty setting of this course is appropriate.

[0022] The time matching sub-module calls the course numbers and time periods in the course repeated selection quantity, detects the intersection interval between the course and the current class schedule time period, determines whether it is lower than the class hour conflict threshold, extracts the eligible course groups, and measures the interval difference with the time preference parameter to obtain the class hour preference adaptability; By comparing the time schedule in the student's current course schedule with the time of the courses marked as repeated electives, ensure that there is no time conflict. For example, if the student has a math class scheduled on Monday morning, and the repeated elective physics class is also scheduled on Monday morning, this time period will be marked as a conflicting period. Determine whether the interval value is lower than the class conflict threshold. This threshold is set to 30 minutes, that is, the minimum time overlap allowed is no more than 30 minutes. If the conflict time is greater than this threshold, it needs to be adjusted. Extract the course group that meets the conditions and calculate the interval difference with the time preference parameter. For example, if the student prefers to have no class on Wednesday afternoon, but the current course conflict requires rescheduling, calculate the difference with the preferred time period to optimize the student's overall course experience and obtain the class preference adaptability. This adaptability helps academic administrators understand how to adjust courses to meet the time preferences of most students, thereby reducing course conflicts and improving course participation.

[0023] The rule allocation submodule extracts conflicting course combinations based on the class time preference adaptability, determines whether the matching degree between the free time period and the class schedule meets the benchmark value for class scheduling, selects feasible combinations, and compares them with the numbers of the courses to be scheduled to obtain a detailed list of class scheduling; According to the class time preference adaptation and course number, extract the conflicting course combinations in the current schedule. For example, if a student's chemistry class conflicts with his physics class, the course arrangement needs to be adjusted. Determine whether the matching value with the free time period in the schedule is greater than the scheduling adaptation benchmark value. The benchmark value is set by the academic affairs department based on the course participation and student satisfaction survey. For example, it is set to 70%, which means that the adjusted course time must ensure that at least 70% of students can participate without time conflict. Screen feasible combinations and compare them with the course numbers to be scheduled. For example, adjust the chemistry class from Wednesday morning to Friday afternoon, while the physics class remains in the original time period. Establish an allocation result set and obtain the scheduling allocation details table. This detailed table records in detail the time of each adjusted course, the participating students and their preference satisfaction, providing a detailed guide for the implementation of adjustments for the academic affairs management to ensure that the course arrangement meets both teaching needs and students' time preferences.

[0024] See also Figure 3 , the teacher matching module includes: The teacher qualification analysis submodule extracts the subject categories, teaching years and teaching methods of teachers in the teacher information database based on the course direction, teaching years and teaching methods in the course scheduling and allocation details table, and determines whether they meet the set standards item by item to generate the subject teaching method matching evaluation results; Retrieval and matching of teacher information in the database to ensure that the qualifications of teachers correspond to the course requirements. For example, assume that a certain university is about to offer an advanced calculus course, which requires a teacher with more than 5 years of teaching experience and a background in applied mathematics. At this time, the teacher database is retrieved to screen out a list of teachers who meet the conditions. During the screening process, the professional background, teaching years, and teaching style of each teacher are compared in detail, and the degree of compliance with the course requirements is calculated to generate an evaluation result for the matching of teaching methods for the subject. This operation process is achieved through data comparison and logical judgment to ensure that each candidate teacher is precisely matched according to the specific course requirements.

[0025] The competent matching calculation sub-module calls the evaluation result of the matching of teaching methods for the subject, extracts the teaching years, teaching preference values, and competent index values of the teachers who meet the requirements, identifies the weighted structural relationship for each index, and combines the number of courses declared. Using the formula: ; Calculate the course competent matching value for each teacher, sort the matching values, and form a matching ranking list; Among them, represents the course competent matching value of the th teacher, represents the teaching years of the th teacher, represents the teaching preference value of the th teacher, represents the performance value of the th teacher on the th competent condition index, represents the number of courses declared by the th teacher, represents the total number of competent condition indexes; Extract the teaching years, teaching preference values, and each course competent condition index values of each teacher who meets the conditions. Record the above three types of data as , and respectively, and further extract the number of courses declared by each teacher to construct a comprehensive calculation logic structure. Among them, the teaching years directly calculates the complete teaching cycle through the employment start and end time fields in the teacher database, in years. For example, if teacher number T023 joined in 2011 and the current year is 2025, the calculated teaching years is 14 years; The teaching preference value is obtained by quantifying the historical teaching type records of teachers. For example, the quantified standard values 7, 8, and 9 are set for lecture type, interactive type, and project type respectively. If the teacher's preference is interactive type, its value is set to 8; Competency indicators for each course By quantifying the performance scores of teachers in specific competency dimensions, with a value range of 0 - 10, evaluation dimensions such as "mastery of course knowledge", "classroom control ability", "course feedback satisfaction", etc. For example, if a teacher's scores on three indicators are 8, 9, and 7 respectively, then ; Number of courses declared Is the number of courses that the teacher has applied for or been assigned during the current class scheduling period, directly extracted from the system. If teacher T023 has declared a total of 3 courses this semester, then ; Taking teacher T023 as an example, substituting the values: , , , ; Substituting into the formula gives: ; The operation result shows that the course competency matching value of teacher T023 is 68. The higher the value, the stronger the comprehensive adaptability in terms of teaching experience, course competency level, and teaching preference. Subsequently, the values of all teachers are sorted to form a matching ranking value table, and this ranking will be used as the basis for subsequent candidate teacher screening; Among them, is the course competency matching value of the th teacher, with no unit; is the teaching years, with the unit of year; is the teaching method preference value, which is a dimensionless score; is the quantitative score of the teacher under the th competency condition, with no unit; is the number of courses declared by the teacher, with no unit; all dimensions in the formula have been unified, and a unified scoring structure is formed through linear weighting and square root adjustment to ensure the comparability of values among different teachers, and finally a matching ranking value table is generated by sorting.

[0026] The candidate screening and assignment sub-module calls the matching ranking table, selects the teacher candidate list based on the matching value, checks for conflicts in teaching time and classes, eliminates the conflict items, and obtains the course teaching assignment list; The process of screening the most suitable candidates according to preset criteria. For example, when a new physics course needs to be arranged in a semester, the teacher with the highest competency is selected based on the matching value of the teacher. During the selection process, the teacher's schedule is considered, and those teachers with time conflicts are excluded. It is also necessary to consider whether the teacher's class management ability matches the students' acceptance methods. Through such a screening mechanism, it can be ensured that each course is taught by the most suitable teacher, thereby improving the teaching effect and obtaining the course teaching assignment list. The result is determined by comprehensively analyzing the teacher's schedule, teaching ability, and course requirements, ensuring the optimal allocation of educational resources.

[0027] Please refer to Figure 4 , the resource scheduling module includes: The course time period matching sub-module extracts the start and end times of the course and the teacher's class time interval according to the course teaching assignment list and the course time period and teacher arrangement, matches the free time period of the classroom, eliminates the holiday and administrative occupation periods, and obtains the set of matching time periods; In the actual application scenario of the smart campus, to optimize the course arrangement to avoid waste of teaching resources, first import the course scheduling information of all courses and teachers from the educational administration database. For example, the physics course is taught by Professor Li from 9:00 to 11:00 on Wednesday morning. This data is used as input to query the free time of each classroom. For example, Classroom 101 in the Physics Building is free on Wednesday morning. This information is automatically extracted from the educational administration database. Further analysis and matching are carried out to compare the overlapping of the course time and the teacher's time, and the intersection of the two times is obtained through set operations. The non-teaching time occupied by public holidays and administrative activities is automatically excluded. For example, if it is found that an administrative meeting is arranged during Professor Li's physics class time, that time period will be automatically excluded. Through such detailed operations, a set of matching time periods is obtained, including all eligible course and classroom combinations. The data will be directly fed back to the educational administration department for actual teaching resource allocation. The educational administration department makes the final arrangements for teachers and classrooms based on the information to ensure the optimal use of resources.

[0028] The space equipment screening sub-module extracts the classroom capacity and equipment configuration based on the set of matching time periods, identifies the number of students in the course and compares it with the classroom capacity, analyzes the coverage ratio between the equipment required for the course and the classroom equipment, and combines the reciprocal value of the missing equipment for superposition. The formula is used: ; Calculate the classroom screening coefficient, sort the sizes to extract the priority items, and obtain the available space screening set; Among them, represents the classroom screening coefficient, represents the total number of students in the course, represents the classroom capacity, represents the number of equipment required for the course, Represents the number of matching device items in the classroom, Represents the total number of course equipment items, Represents the reciprocal value of the missing device item; In the application in the smart campus scenario, it can be carried out in combination with specific teaching arrangements. For example, when the school arranges a large lecture for a course of "Fundamentals of Artificial Intelligence", it is necessary to screen out the venues whose capacity and equipment configuration meet the requirements at the same time from the available classrooms. First, based on the course arrangement information, the expected number of students in class is obtained. The total number of students enrolled in this course is set to 180, and this value is the parameter A. The basic information of the library lecture hall is read from the classroom database of the teaching building. The maximum capacity of this classroom is 200, corresponding to the parameter B. The necessary teaching equipment marked in the course teaching requirement form is 3 items including a high-definition projector, a smart audio, and an interactive whiteboard, corresponding to the parameter D. Then, the existing equipment configuration of the library lecture hall is extracted from the classroom equipment list. After comparison, it is found that it has a high-definition projector and a smart audio, but lacks an interactive whiteboard. The number of matching items is 2, corresponding to the parameter E. The total number of equipment requirements is 3, corresponding to the parameter F. The number of missing devices is 1 item, and the reciprocal of the missing device is 1, corresponding to the parameter G; Since there are dimensional differences in the capacity number of people and the number of devices in the participating items, unit conversion is performed uniformly. First, the number of people and the capacity items are normalized to a ratio to participate in the square root operation, and the device items are converted into a standard matching rate and then participate in the subsequent operation; Substituting specific values: A = 180 (people), B = 200 (people), D = 3 (items), E = 2 (items), F = 3 (items), G = 1 (item); The first step is to sum and take the square root: ; The second step is to find the fractional term: ; The third step is to take the absolute value: ; Finally, the classroom screening coefficient Q of this classroom is 18.82. Similarly, this coefficient calculation will be carried out for all candidate classrooms, and they will be sorted in ascending order according to the Q value. The smaller the value, the closer the classroom matches the course; G represents the reciprocal value of the missing device item (0 if there is no missing item, 1 if there is 1 missing item). This formula quantitatively evaluates the classroom matching in three dimensions by integrating the capacity matching degree, the equipment matching ratio, and the missing item penalty term. The finally output classroom screening coefficient Q is the result of this step and is used as the basis for subsequent space optimization and sorting; By introducing the inverse term of equipment shortage into the weighted structure, the impact of resource shortage on space optimization can be highlighted, and a screening function is jointly constructed through the normalized capacity and equipment matching values to form the basis for classroom availability ranking. The result shows that the library lecture hall has a certain priority in the matching of this course, and the Q value of 18.82 is the comparable numerical result for classroom optimization in this step.

[0029] The conflict exclusion annotation sub-module calls the available space screening set, compares the classroom locations with the facility sharing situations, annotates the classrooms with time conflicts and equipment overlaps, eliminates the conflict items, and forms the space and equipment usage plan; In the classroom management of the smart campus, the application scenario is to handle the time and resource conflicts in classroom usage. For example, when allocating classrooms, check the geographical locations and facility sharing situations of all candidate classrooms. Suppose classrooms 101 and 102 in the physics building are applied for by two different departments during the same time period, and both need to use the only mobile projector in the building. First, retrieve the relevant information of the classrooms from the available space screening set, and then identify the overlapping and conflict points by comparing the course and equipment requirements. For example, if two courses need the projector at the same time, mark the conflict and remind the educational administration manager. All classroom options with unresolved conflicts will be excluded, and a space and equipment usage plan will be formed. This plan will ensure that all courses are carried out without resource conflicts and optimize the usage efficiency of classroom resources.

[0030] Please refer to Figure 5 , the behavior monitoring module includes: The venue positioning sub-module calls the space and equipment usage plan, extracts the venue number, time arrangement, and space coordinates, compares the current time with the planned time, screens the identifiable teaching venues, and obtains the teaching venue time matching degree value; Extract the venue number, time arrangement, and space coordinates. This process depends on the teaching venue management. The venue number is obtained by scanning the device identification code, the time arrangement is matched by comparing the course schedule in the schedule management with the actual time, and the space coordinates are obtained through GIS (Geographic Information System) positioning to ensure the accuracy of the obtained venue information. In the smart campus management, for example, in a usage case of a certain university, each classroom is equipped with a unique QR code and positioning chip. Managers can view the usage status and location information of each classroom in real time for daily management and rapid response to emergencies. Finally, compare the current time with the planned time, screen the identifiable teaching venues, and obtain the teaching venue time matching degree value. The value is calculated by comparing the real-time time data in GIS with the preset time in the teaching schedule management, and calculating the time deviation value. If the time deviation is within the allowable range (such as ±5 minutes), it is considered that the time matches. In actual use, for example, during the use of a certain teaching building in Peking University, it can quickly identify whether the classrooms to be used are reserved according to the schedule, effectively avoiding the conflict and waste of classroom resources.

[0031] The trajectory density analysis sub-module identifies the crowd image area in the video according to the teaching venue time matching degree value, extracts the number of people and the spatial positions, analyzes the change of the personnel frequency and the spatial coverage rate in the unit area, and obtains the crowd trajectory density distribution quantity; According to the time matching degree value of the teaching venue, identify the crowd image area in the video, capture real-time video through the camera installed in the classroom, and then use image processing software for crowd detection. The specific process includes using a deep learning model to analyze the images captured by the camera to identify the outlines and quantities of people in the images. For example, in a large lecture hall in a teaching building of Huazhong University of Science and Technology, through this technology, the attendance of students can be monitored in real time, the number of people and their spatial positions can be extracted, the frequency of people in the unit area and the change of spatial coverage rate can be calculated. The frequency calculation is based on the number of people appearing in consecutive camera image frames, and the spatial coverage rate is determined according to the ratio of the space occupied by the crowd to the total space of the classroom, obtaining the crowd trajectory density distribution quantity. In a certain simulation exercise, the management personnel can, based on data analysis, determine whether the distribution of students in the classroom is uniform and whether there are overcrowded areas, so as to timely adjust the classroom use strategy or issue a safety warning.

[0032] The abnormal behavior judgment sub-module judges whether the density increase exceeds the limit according to the crowd trajectory density distribution quantity, compared with the normal fluctuation reference value, extracts the trajectory stability degree and the personnel overlap offset value, analyzes the degree of change, and uses the formula: ; Calculate the abnormal behavior offset value, compare it with the aggregation threshold, identify the over-limit area and the interference level, and obtain the abnormal behavior distribution map; Among them, represents the abnormal behavior offset value, represents the lower limit value of the trajectory stability degree, represents the upper limit value of the trajectory stability degree, represents the density increase rate, represents the personnel overlap offset value, represents the area the change amount of the crowd movement speed in the area, represents the area the proportion of the changed number of people in the area, represents the density distribution increase difference, represents the total number of areas; Compare with the normal fluctuation reference value to judge whether the density increase exceeds the limit. This reference value is set as the average crowd density change interval in the past 5 same time periods, and the set interval is between 0.15 and 0.35. When the currently measured crowd density increase rate is greater than 0.35, it is in an over-limit state. The process of extracting the trajectory stability degree and the personnel overlap offset value is as follows: First, compare the changes in the coordinates of the center of gravity of the crowd in the images taken every 5 seconds. The stability of the trajectory is represented by calculating the change value of the moving distance of the center of gravity per unit time period. The lower limit value a and the upper limit value b of the trajectory stability are the minimum and maximum crowd center of gravity offset distances in consecutive frames, respectively. After unit conversion, they are unified into meters and set as a = 0.5 and b = 2.3 respectively; The density increase rate W is obtained by subtracting 1 from the ratio of the current density in the unit area to the density in the previous period. In this calculation, the current density in the unit area is 3.2 people / ㎡, and the previous period is 2.4 people / ㎡, so W = (3.2 / 2.4) - 1 ≈ 0.33; The personnel overlap offset value d is calculated from the average deviation of the pixel center of gravity of the number of people in the spatial overlap area in the image. After normalization, it is converted into a physical scale, d = 1.8 meters; Change amount of crowd movement speed It is obtained by finding the difference in the movement speed of personnel between frames. Select k = 3 sampling areas as the calculation basis, and the speed changes in the three areas are 0.6, 0.9, and 0.3 m / s respectively; Corresponding proportion of the number of people with change They are 0.4, 0.35, and 0.25 respectively; The density distribution increase difference g is calculated by the difference between the current trajectory density distribution and the reference trajectory density value. The current value is 0.28, and the reference value is 0.21, so g = 0.28 - 0.21 = 0.07; Substitute the above values into the formula for actual operation: ; The result shows that the behavior offset of the crowd in the current area is 2.165. This value represents the comprehensive anomaly index, which is used to determine whether there is an abnormal behavior aggregation. If the safety threshold is set to 1.8, the current value has exceeded the aggregation anomaly determination range. Subsequently, this area will be marked as a behavior interference area, and the marked area will be mapped to the plane distribution map to generate an abnormal behavior distribution map; Through the joint measurement of the trajectory stability, density change rate, and moving speed offset, the dynamic behavior characteristics can be introduced in addition to the spatial density overrun judgment, so as to enhance the discrimination dimension of behavior recognition and construct an index system with behavior dynamic adaptability. This result can be used as a basic participation item for modules such as behavior interference level calculation and regional risk classification processing for calling and extension.

[0033] Please refer to Figure 6 , the interactive guidance module includes: The voice parsing sub-module determines the effectiveness of the instruction based on the risk area numbers marked in the abnormal behavior distribution map by analyzing the time, space instructions, and behavior keywords in the voice, and combines the integrity evaluation of the time and space instructions to obtain the instruction response recognition rate according to the matching relationship between the behavior keywords and the numbers; It plays an important role in the risk management of smart campuses. For example, when the school holds a large-scale event, by capturing the on-site feedback information, it can quickly identify potential safety hazards and abnormal behaviors. Based on the actual voice information obtained, it first detects the time and space instructions in the voice content, such as "immediately" and "in the playground", and at the same time identifies behavior keywords such as "gathering" and "loud noise". It judges the directivity and effectiveness of the voice instruction through data. For example, if the instruction "gather immediately in the playground" matches the risk area number, it is considered a valid emergency gathering instruction. Next, it combines the integrity of the time and space instructions, such as confirming whether the voice instruction clearly mentions the specific execution time and location, to evaluate the integrity of the feedback. An effective instruction needs to have complete time and space information. By comparing the integrity and directivity of each instruction through algorithms, it calculates the integrity ratio of the instruction. For example, if 100 voice instructions are analyzed and 80 of them contain complete time and space instructions, the instruction integrity is considered 80%. Finally, it calculates the instruction response recognition rate based on the valid and complete instructions. This result directly affects the subsequent response measures and risk warning adjustments. In this way, the smart campus can give early warnings and make preparations before an event occurs, greatly improving the efficiency and accuracy of emergency responses. Finally, it obtains the instruction response recognition rate, showing the proportion of valid and complete instructions.

[0034] The response judgment sub-module calls the instruction response recognition rate, counts the distribution density of each type of feedback under the risk area number according to the number of types of semantic keywords in the feedback data, and compares the relationship between the keyword distribution and the feedback frequency to obtain the response type distribution density value; Analyze the time matching amount, space matching amount, and behavior matching amount of each instruction in the recognition rate, especially for different feedback types in the teaching building and dormitory areas, and count the number of types of semantic keywords in each type of feedback. For example, in the teaching building area, keywords such as "print" and "borrow" appear frequently, while in the dormitory area, keywords such as "laundry" and "order food" are more common. By comparing the distribution density and frequency of the keywords, it effectively identifies the basic needs of students in different areas of the campus and is executed by analyzing the occurrence patterns and frequencies of the semantic keywords, thus providing data support for the optimization of campus services. Finally, it obtains the response type distribution density value. The calculation of this value is based on the standard deviation and average methods in statistics, reflecting the similarities and differences in the needs of each area. The density value is shown as 0.75, indicating that the demand distribution is relatively uniform but there is still room for improvement.

[0035] The execution statistics submodule calls the response type distribution density value, identifies the offset quantity and frequency difference of keywords between numbers, analyzes the variation range of the offset value, and forms the execution status of smart campus risk guidance; Analyze the specific feedback frequency of the data under each area number of the campus. For example, count the feedback frequency of the keyword "borrowing" in the library and the feedback frequency in the teaching building, calculate the number of regional offsets and frequency differences of the keywords. Assuming that the frequency of the keyword "borrowing" in the teaching building is 10 times per hour, and in the library it is 40 times per hour, the number of offsets is 30 times. By analyzing the fluctuation range of the offset, generate the trend degree of the smart campus risk relief execution status. The trend degree is calculated by the linear regression model, which reflects the changing trend of each keyword, thereby providing real-time risk assessment and resource optimization suggestions for campus management. The value of the trend degree is 0.65, indicating that the current campus resource allocation efficiency is relatively high, but attention should be paid to the dynamic balance of services between the teaching building and the library.

[0036] The smart campus comprehensive management method is implemented based on the above-mentioned smart campus comprehensive management system, and includes the following steps: S1: Obtain student performance data and course selection information in the smart campus, screen low-scoring courses, extract course information with difficulty levels and time matching below the threshold, eliminate arrangements that conflict with the current schedule, reorganize courses, and obtain a detailed list of course scheduling; S2: Based on the course scheduling and allocation details table, extract course demand items, combine the teaching years, teaching frequency and teaching method data in the teacher resume database, identify the similarity between teacher qualifications and course competency, select the data of teachers with high matching ranking, and establish a teacher course matching list; S3: Based on the teacher course matching list, extract the class schedule and teacher tasks, search for available classrooms and determine the capacity demand match, check the equipment configuration and course requirements, filter out the non-matching items and summarize the matching results, and obtain the venue resource allocation summary table; S4: Based on the venue resource allocation summary table, analyze the monitoring data of the configured teaching space, identify the peak of crowd activity density and high-frequency cross-regions, evaluate the dense distribution of time nodes of abnormal actions, and generate a behavior interference layer for the teaching area; S5: Based on the behavior interference layer of the teaching area, analyze the spatial risk number data and voice feedback, identify risk instructions and keywords, evaluate command parsing, classify the effective response and area number correspondence, and form the execution status of smart campus risk guidance.

[0037] The above are only the preferred embodiments of the present invention, and do not limit the present invention in other forms. Any person skilled in the relevant art may use the technical content disclosed above to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. An integrated management system for a smart campus, characterized in that, The system comprises: The course scheduling module obtains student performance data and course selection information in the smart campus, screens low-performing courses based on course difficulty and time preference, adjusts conflicting course combinations, optimizes rules based on the course schedule, and makes learning adjustments to obtain a detailed list of course scheduling; The teacher matching module retrieves the teacher's teaching qualifications, course competency conditions and teaching method preferences according to the course requirements in the course scheduling and allocation details table, compares whether the teacher matches the competency conditions of the required course, screens the candidate teacher list according to the matching degree, and generates a course teaching assignment list; The resource scheduling module extracts the available time periods and equipment information of the classroom according to the course time periods and teacher arrangement in the course teaching assignment list, determines whether the resources meet the course equipment and capacity standards, screens the available space and marks the conflict exclusion items, and forms a space and equipment use plan; The behavior monitoring module calls the allocated teaching venue location in the space and equipment usage plan, identifies the behavior detection data of the smart campus security perception, extracts the crowd trajectory and density changes in the video, determines whether there are gathering anomalies and behavioral interference during the teaching period, and obtains the abnormal behavior distribution map.

2. The integrated intelligent campus management system according to claim 1, characterized in that The course scheduling and allocation details table includes course priority level, time conflict identification, course adjustment results, and matching feasibility score; the course teaching assignment list includes teacher matching score, recommended teaching teachers, course correspondence, and teaching mode; the space and equipment use plan includes classroom number information, available time period range, equipment type distribution, and resource conflict mark; the abnormal behavior distribution map includes personnel gathering density map, behavior abnormality category, risk level area, and time period marking information.

3. The integrated intelligent campus management system according to claim 1, characterized in that The course arrangement module includes: The grade screening submodule obtains the student grade data and course selection information in the smart campus, extracts the course grade and difficulty deviation coefficient, screens the course numbers whose deviation coefficient is greater than the benchmark value, determines whether the number of repeated course selections in the original course selection record exceeds the threshold, and obtains the number of repeated course selections; The time matching submodule calls the course number and time period in the course repeat elective quantity, detects the intersection interval between the course and the current time schedule, and determines whether it is below the class time conflict threshold, extracts the qualified course group, and calculates the interval difference with the time preference parameter to obtain the class time preference adaptability; The rule allocation submodule extracts conflicting course combinations based on the class time preference adaptability, determines whether the matching degree between the idle time period and the class schedule meets the benchmark value for class scheduling, screens feasible combinations, and compares them with the numbers of the courses to be scheduled to obtain a detailed list of class scheduling.

4. The intelligent campus integrated management system according to claim 3, wherein The teacher matching module includes: The teacher qualification analysis submodule extracts the subject category, teaching years and teaching method records of teachers in the teacher information database based on the subject direction, teaching years requirement and teaching method type of the courses in the course scheduling and allocation details table, determines whether the set standards are met item by item, and generates a subject teaching method matching evaluation result; The competent matching calculation sub-module calls the matching evaluation results of the subject teaching method, extracts the teaching years, teaching preference values and competent index values of teachers meeting the requirements, identifies the weighted structural relationships for each index, and combines the number of declared courses. Using the formula: ； Calculate the course competent matching value of each teacher, sort the matching values, and form a matching ranking list; Among them, represents the course competency matching value of the th teacher, represents the teaching years of the th teacher, represents the teaching preference value of the th teacher, represents the performance value of the th teacher on the th competency condition indicator, represents the number of courses declared by the th teacher, represents the total number of competency condition indicators; The candidate screening and assignment sub-module calls the matching ranking list, selects the teacher candidate list according to the matching value, checks the conflicts of teaching time and classes, eliminates the conflicting items, and obtains the course teaching assignment list.

5. The integrated intelligent campus management system according to claim 4, characterized in that, The resource scheduling module includes: The course time period matching sub-module extracts the start and end times of the course and the teacher's class time interval according to the course teaching assignment list, the course time period and the teacher arrangement, matches the free time period of the classroom, eliminates the holiday and administrative occupation periods, and obtains the set of matching time periods; The space and equipment screening sub-module extracts the classroom capacity and equipment configuration based on the set of matching time periods, identifies the number of students in the course and compares it with the classroom capacity, analyzes the coverage ratio between the equipment required for the course and the classroom equipment, and combines the reciprocal value of the missing equipment for superposition. Using the formula: ； Calculate the classroom screening coefficient, sort the sizes and extract the priority items to obtain the available space screening set; Among them, represents the classroom screening coefficient, represents the total number of students in the course, represents the classroom capacity, represents the number of equipment required for the course, represents the number of matching equipment items in the classroom, represents the total number of course equipment items, represents the reciprocal value of the missing equipment items; The conflict exclusion and marking sub-module calls the available space screening set, compares the classroom location and the facility sharing situation, marks the classrooms with time conflicts and equipment overlaps, and eliminates the conflicting items to form the space and equipment usage plan.

6. The integrated intelligent campus management system according to claim 5, characterized in that, The behavior monitoring module includes: The venue positioning sub-module calls the space and equipment usage plan, extracts the venue number, time arrangement and space coordinates, compares the current time with the planned time, screens the identifiable teaching venues, and obtains the teaching venue time matching degree value; The trajectory density analysis sub-module identifies the crowd image area in the video according to the teaching venue time matching degree value, extracts the number of people and the space position, analyzes the change of the personnel frequency and space coverage rate in the unit area, and obtains the crowd trajectory density distribution quantity; The abnormal behavior judgment sub-module compares the crowd trajectory density distribution quantity with the normal fluctuation reference value according to the crowd trajectory density distribution quantity, judges whether the density increase exceeds the limit, extracts the trajectory stability degree and the personnel overlap offset value, analyzes the change degree, and uses the formula: ； Calculate the abnormal behavior offset value, compare it with the aggregation threshold, identify the over-limit area and the interference level, and obtain the abnormal behavior distribution map; Among them, represents the abnormal behavior offset value, represents the lower limit value of the trajectory stability degree, represents the upper limit value of the trajectory stability degree, represents the density increase rate, represents the personnel overlap offset value, represents the area of the change in the crowd movement speed, represents the area of the proportion of the changed number of people, represents the density distribution increase difference, represents the total number of areas.

7. The integrated intelligent campus management system according to claim 1, characterized in that The system also includes an interactive guidance module: The interactive guidance module extracts the voice recognition to capture the on-site feedback information according to the risk area number marked in the abnormal behavior distribution map, analyzes the voice commands and keywords, judges the effectiveness of the commands and the integrity of the feedback, counts the types of response modes and the pointing distribution, and forms the execution status of the smart campus risk guidance; The execution status of the smart campus risk guidance includes voice command type, response behavior label, execution area number, and feedback integrity classification.

8. The integrated intelligent campus management system according to claim 7, wherein, The interactive guidance module includes: The speech analysis submodule analyzes the time, space instructions and behavior keywords in the speech according to the risk area number identified in the abnormal behavior distribution map, determines the effectiveness of the instruction according to the matching relationship between the behavior keywords and the number, and evaluates the effectiveness of the feedback in combination with the integrity of the time and space instructions to obtain the instruction response recognition rate; The response judgment submodule calls the command response recognition rate, counts the distribution density of each type of feedback under the risk area number according to the number of types of semantic keywords in the feedback data, compares the relationship between keyword distribution and feedback frequency, and obtains the response type distribution density value; The execution statistics submodule calls the response type distribution density value, identifies the offset quantity and frequency difference of keywords between numbers, analyzes the variation range of the offset value, and forms the execution status of smart campus risk relief.

9. A comprehensive management method for a smart campus, characterized in that, The method is used to implement the smart campus integrated management system according to any one of claims 1 to 8, and comprises the following steps: S1: Obtain student performance data and course selection information in the smart campus, screen low-scoring courses, extract course information with difficulty levels and time matching below the threshold, eliminate arrangements that conflict with the current schedule, reorganize courses, and obtain a detailed list of course scheduling; S2: Based on the course scheduling and allocation details table, extract course demand items, combine the teaching years, teaching frequency and teaching method data in the teacher resume database, identify the similarity between teacher qualifications and course competency, select the data of teachers with high matching rankings, and establish a teacher course matching list; S3: Based on the teacher course matching list, extract the class schedule and teacher tasks, search for available classrooms and determine the capacity demand match, check the equipment configuration and course requirements, filter out the non-matching items and summarize the matching results, and obtain the venue resource allocation summary table; S4: Based on the venue resource allocation summary table, analyze the monitoring data of the configured teaching space, identify the peak of crowd activity density and high-frequency intersection areas, evaluate the dense distribution of time nodes of abnormal actions, and generate a behavior interference layer of the teaching area; S5: Based on the teaching area behavior interference layer, analyze the space risk number data and voice feedback, identify risk instructions and keywords, evaluate command parsability, classify the effective response and area number correspondence, and form the smart campus risk guidance execution status.

Images