Smart classroom resource dynamic reservation and scheduling system and method

Abstract

The invention discloses a smart classroom resource dynamic reservation and scheduling system and method, and relates to the technical field of resource scheduling. According to the system, demand analysis or priority pre-evaluation is carried out on a to-be-processed user reservation application, and meanwhile, a scheduling constraint condition of each scheduling period is preset; based on the monitored real-time occupancy state data and the newly added reservation request queue, executing resource matching degree calculation so as to determine the scheduling execution state of each reservation task and / or each classroom resource; whether the scheduling execution state meets a preset scheduling target or not is judged, when the scheduling execution state meets the preset scheduling target, the current scheduling execution state serves as an effective scheduling execution state, and if the scheduling execution state does not meet the preset scheduling target, a rescheduling process is triggered, and resource redistribution of conflicting and / or overload reservation tasks is carried out; and at the end of each scheduling cycle, efficiency quantitative evaluation of the scheduling process is carried out, so that the comprehensive scheduling efficiency of the smart classroom in the dynamic reservation scene is determined, and high adaptability of dynamic reservation and scheduling of smart classroom resources is realized.

Description

Technical Field

[0001] This invention relates to the field of resource scheduling technology, and in particular to a smart classroom resource dynamic reservation and scheduling system and method. Background Technology

[0002] With the deepening of educational informatization and smart campus construction, the teaching models of universities and primary and secondary schools are becoming increasingly diversified. The demand for classroom resources in scenarios such as online and offline blended teaching, interdisciplinary seminars, and club activities is showing personalized, fragmented, and highly flexible characteristics.

[0003] Existing resource scheduling solutions mostly integrate functions within an information technology framework. For example, Chinese invention patent CN118469777B discloses a smart classroom management method and system based on artificial intelligence, which includes: acquiring scheduling information; acquiring target teaching information based on the scheduling information; scheduling teacher resources, classroom resources, and teaching equipment resources; determining the allocation of teaching resources based on the results of scheduling teacher resources, classroom resources, and teaching equipment resources; acquiring classroom environmental information in real time; analyzing student learning behavior data through data mining and machine learning to judge student learning progress in real time and generate personalized progress reports; and generating personalized teaching materials, learning method suggestions, and practice assignments based on personalized progress reports and teaching content through natural language processing and recommendation system technologies.

[0004] This solution enables intelligent empowerment of the entire teaching process, but its core focus is on optimizing the teaching process and providing personalized learning services. It lacks specificity in dynamic reservation response of classroom resources, multi-scenario conflict coordination, and optimal allocation of global resources.

[0005] Against this backdrop, dynamic reservation and intelligent scheduling of classroom resources have become a core component of smart campus construction. Its core objective is to solve resource allocation problems through intelligent means and achieve on-demand allocation, efficient circulation and optimal utilization of classroom resources.

[0006] Existing classroom scheduling systems typically include core functional modules such as user request input, resource information management, reservation approval, conflict detection, and scheduling execution. In terms of execution, the user first submits a reservation request via a terminal, including elements such as the usage time, classroom specifications, and supporting equipment. The resource information management module retrieves basic classroom data and real-time occupancy status. The conflict detection module then compares and analyzes the classroom resource occupancy within the requested time slot. If no conflict exists, approval is automatically granted; otherwise, conflict information is provided to the user, and alternative classrooms or time slots are recommended. Finally, the scheduling execution module generates a scheduling instruction, synchronously updates the classroom usage status, sends a reservation success notification to the user, and archives the scheduling results to the resource information management module for subsequent management and statistical analysis.

[0007] However, while existing classroom scheduling systems can achieve basic reservation and conflict detection functions, they are not well adapted to the concurrent reservations in multiple scenarios, dynamic resource fluctuations, and differentiated needs in smart campuses. No targeted optimization solutions have yet been developed, thus exposing the following technical challenges:

[0008] During peak teaching periods and concentrated periods of large-scale events (such as mid-term and final exam weeks, and school-enterprise cooperation and exchange activities), the concurrency of multiple users submitting reservation requests surges. These reservation demands cover various types, including regular lectures, experimental teaching, and academic conferences, with significant differences in requirements for classroom equipment (such as projectors and experimental instruments), space size, and network environment across different scenarios. Existing technologies often employ fixed reservation processing procedures and single conflict detection logic, lacking the ability to dynamically adapt to concurrent traffic. This easily leads to a backlog of reservation requests and system response delays during peak periods. Furthermore, insufficient consideration is given to the differentiated weighting of different types of demands, failing to prioritize resource supply for core teaching activities and struggling to dynamically adapt to unforeseen circumstances such as temporary class rescheduling. In addition, existing systems mostly use static rules to determine the real-time status of classroom resources based on occupancy / unoccupancy, lacking correlation analysis between fluctuations in usage demand and actual resource utilization. This makes it difficult to optimize reservation matching strategies and dynamic scheduling schemes based on real-time resource status, thus failing to meet the high adaptability requirements of smart classrooms for efficient dynamic reservation and scheduling of resources under multi-scenario, high-concurrency conditions. Summary of the Invention

[0009] To address the technical problems in the prior art, embodiments of the present invention provide a smart classroom resource dynamic reservation and scheduling system and method. The technical solution is as follows:

[0010] On the one hand, a smart classroom resource dynamic reservation and scheduling system is provided. This system includes: a data integration and status monitoring module, used to analyze the needs or pre-assess the priorities of user reservation requests based on received multi-source status data, combined with preset resource type tags and scheduling rule bases, and to preset scheduling constraints for each scheduling cycle; multi-source status data is reported in real time by IoT sensors deployed in the smart classroom, the academic affairs management platform, and user interaction terminals; scheduling constraints include at least the upper limit of total resource capacity, time continuity requirements, and differentiated priority thresholds; and a dynamic resource scheduling evaluation module, used to evaluate the resources based on the monitored data within a preset scheduling evaluation time window. The system uses real-time occupancy status data and a new reservation request queue to calculate resource matching degree, thereby determining the scheduling execution status of each reservation task and / or each classroom resource. The scheduling execution status matching module is used to determine whether the scheduling execution status meets the preset scheduling target. When the preset scheduling target is met, the current scheduling execution status is taken as a valid scheduling execution status. If it does not meet the target, a rescheduling process is triggered to reallocate resources for conflicting and / or overloaded reservation tasks, so that the scheduling execution status remains valid. The scheduling effect evaluation and feedback module is used to perform a quantitative evaluation of the scheduling process at the end of each scheduling cycle, thereby determining the overall scheduling efficiency of the smart classroom in a dynamic reservation scenario.

[0011] On the other hand, a method for dynamic reservation and scheduling of smart classroom resources is provided. This method includes: S1, based on the received multi-source status data and combined with the preset resource type tags and scheduling rule base, performing demand analysis or priority pre-evaluation on the user reservation applications to be processed, and simultaneously setting scheduling constraints for each scheduling cycle; S2, under the preset scheduling evaluation time window, performing resource matching degree calculation based on the monitored real-time occupancy status data and the new reservation request queue to determine the scheduling execution status of each reservation task and / or each classroom resource; S3, determining whether the scheduling execution status meets the preset scheduling target. If the preset scheduling target is met, the current scheduling execution status is taken as a valid scheduling execution status. If not, a rescheduling process is triggered to reallocate resources for conflicting and / or overloaded reservation tasks, so that the scheduling execution status remains valid; S4, at the end of each scheduling cycle, performing a quantitative evaluation of the scheduling process to determine the comprehensive scheduling efficiency of the smart classroom in the dynamic reservation scenario.

[0012] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following:

[0013] 1. This invention first integrates multi-source real-time data from IoT sensors, the academic affairs platform, and user terminals. Based on a preset rule base, it intelligently classifies and pre-assesses the priority of appointment requests, while setting scheduling constraints including capacity, continuity, and priority thresholds. Within a preset scheduling assessment time window, the scheduling execution status of each task is dynamically determined by calculating the resource matching degree between real-time occupancy status data and the new appointment request queue. Subsequently, the scheduling execution status matching module determines whether the status meets preset targets. If not, a rescheduling process is automatically triggered to reallocate resources for conflicting or overloaded tasks, ensuring scheduling effectiveness. After each scheduling cycle, the system quantitatively evaluates indicators such as average response time, allocation success rate, and rescheduling ratio. The overall process effectively solves the problem of dynamic resource adaptation under high concurrency and diverse appointment demands during peak periods by constructing a closed-loop scheduling system consisting of data integration and status monitoring, dynamic evaluation of scheduling resources, scheduling execution status matching, and scheduling effect evaluation and feedback.

[0014] 2. First, the system receives user-submitted reservation requests and performs real-time judgment based on multi-source status data and a preset rule base. If the request meets the first application condition, it is classified as a regular reservation request, and a demand analysis process is executed to check for issues such as time conflicts, resource mismatches, or capacity limits. For conflicting requests, an optimization solution is generated through adaptive adjustment; otherwise, it is handled manually. If the request meets the second application condition, it is classified as a priority reservation request, and a priority pre-assessment process is executed. A priority queue is formed through quantitative scoring, with high-scoring requests entering the fast track for resource reservation, and other requests entering a progressive dynamic matching process. This classification and processing mechanism reduces reliance on manual intervention by automating conflict detection and adaptive resolution for regular requests, improving processing efficiency in high-concurrency scenarios, and avoiding request backlog. At the same time, it optimizes the resource utilization of non-urgent requests through a progressive matching strategy, and incorporates optimization suggestions and pre-scheduled solutions into scheduling constraints in real time, achieving dynamic closed-loop adjustment and enhancing the system's adaptability to complex scenarios such as temporary class rescheduling and sudden demands. Overall, through structured process design and intelligent decision-making mechanisms, this system has achieved fairness, timeliness, and adaptability in resource allocation across various types of high-concurrency booking scenarios, effectively supporting the dynamic scheduling and management of smart classroom resources.

[0015] 3. Under the current scheduling constraints, acquire the classroom reservation time slot occupancy data corresponding to the newly added reservation request queue. Then, monitor the resource matching simulation execution process within the evaluation time window. By calculating the unit request matching time, load increment, and memory usage increment, further derive the matching efficiency value and resource consumption value, achieving a multi-dimensional quantitative evaluation of scheduling performance. Finally, determine the feasibility of the constraints based on preset thresholds: if feasible, mark the task as scheduled and lock the classroom resource; if infeasible, mark it as pending coordination and review. This process simplifies resource status representation through binary vectors, significantly reducing data processing complexity; multi-dimensional performance indicator linkage evaluation can accurately identify scheduling bottlenecks and avoid system lag due to insufficient timeliness or resource overload. At the same time, differentiated marking of task and resource status ensures the orderly execution of effectively scheduled tasks and provides a clear processing direction for tasks awaiting coordination, balancing resource utilization and system stability, and adapting to the high-concurrency, multi-scenario scheduling needs of smart classrooms.

[0016] 4. First, the system receives the judgment results from the dynamic evaluation module for scheduling resources, covering various statuses of scheduled tasks and classroom resources. If all tasks are scheduled and resources are locked within a preset period, the scheduling goal is achieved, and the system is recorded as having a valid execution status. If there are tasks awaiting coordination or resources awaiting review, the goal is not achieved, and the resource reallocation process is initiated. During reallocation, problematic tasks are precisely categorized: excessive tasks requesting the same classroom within the same scheduling period are considered resource conflicts, prompting an adjustment to allocation priority; tasks with more participants than classroom capacity are considered capacity overload, prompting an adjustment to task size. After adjustment, if a fully valid status is achieved, the system is recorded as having a valid execution status; if problems persist, manual intervention is prompted. This process ensures closed-loop control of scheduling effectiveness through periodic status checks, improving execution reliability. Manual intervention prompts balance the efficiency of automated scheduling with the flexibility of special scenarios, effectively ensuring the orderliness and adaptability of smart classroom resource scheduling. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of the structure of the smart classroom resource dynamic reservation and scheduling system provided in an embodiment of the present invention;

[0019] Figure 2 The execution flowchart of the data integration and status monitoring module provided in this embodiment of the invention;

[0020] Figure 3A flowchart of a method for dynamic reservation and scheduling of smart classroom resources provided in an embodiment of the present invention;

[0021] Figure 4 A block diagram for classroom demand heat time-series prediction and capacity monitoring provided in an embodiment of the present invention. Detailed Implementation

[0022] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0023] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0024] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0025] This invention provides a smart classroom resource dynamic reservation and scheduling system, such as... Figure 1 The diagram shown illustrates the structure of a smart classroom resource dynamic reservation and scheduling system. This system may include:

[0026] like Figure 2 The execution flowchart of the data integration and status monitoring module is shown. The data integration and status monitoring module receives the appointment application submitted by the user through the user interaction terminal.

[0027] Scenario 1: Receiving a reservation request submitted by a user through a user interaction terminal. If the multi-source status data reported in real time by the IoT sensors deployed in the smart classroom, the academic affairs management platform, and the user interaction terminal meets the first application condition defined in the preset resource type label and scheduling rule base (e.g., the applicant is a student, the activity type is a club activity, and the target time slot is shown as available in the timetable), then the system determines that the application has clear attributes and normal priority, and does not involve urgent or privileged scheduling. Therefore, it is classified as a regular reservation request, and the corresponding process for demand parsing is executed, specifically:

[0028] The system identifies resource conflict criteria, which include: the application time of a regular appointment application overlaps with a scheduled time slot; the resource type does not match the currently available resource label; and the number of applicants exceeds the smart classroom's capacity limit. If a regular appointment application meets at least one of these criteria, it is marked as a conflicting application and enters the conflict resolution process. If a regular appointment application does not meet any of these criteria, it is marked as a schedulable application and enters the resource matching and automatic scheduling queue. Specifically, based on its application time window, resource requirements, and priority, it enters the system's resource matching engine's pending queue, awaiting automated scheduling decisions with the currently available classroom resource pool.

[0029] The conflict resolution process includes: the scheduling conflict coordinator determines whether a conflict request can be adaptively resolved by adjusting the request time or replacing similar resources. If so, an optimized scheduling suggestion is generated using a multi-objective optimization algorithm (such as heuristic search). This suggestion is then included as an alternative in the current scheduling cycle's solution pool, and the adjustment requirements in the optimized scheduling suggestion (such as time period offset and alternative resource identifier) ​​are recorded as new scheduling constraints. Otherwise, the corresponding conflict request is transferred to a manual review queue for manual intervention, such as a final decision by an administrator based on factors such as urgency and activity importance.

[0030] Scenario 2: If the multi-source status data meets the preset resource type label and the second application condition defined in the scheduling rule base, the system determines that the application involves core teaching activities, emergency meetings, or special events with high priority, requiring priority resource supply. Therefore, the system automatically classifies the appointment application as a priority appointment application and executes the corresponding priority pre-assessment process, specifically:

[0031] The quantitative scoring results of priority reservation applications (derived from the scoring results based on user identity weight, application urgency, activity type influence factor and historical performance record) are recorded as priority scores. The applications are then sorted in descending order of priority scores to form a priority sorting queue. The queue structure ensures that applications with higher scores receive priority scheduling rights during resource competition.

[0032] If there is a reservation application in the priority sorting queue with a priority score higher than the preset priority score, the corresponding reservation application will be recorded as a high-priority scheduling task and enter the resource reservation processing flow. That is, according to the requirements of the high-priority scheduling task, such as dedicated equipment configuration and venue functional attributes, the exclusive matching algorithm will be used to match classroom resources that meet all its requirements and are in an idle state, and the resource will be locked immediately. At the same time, the resource will be recorded as the scheduling constraint condition of the current scheduling cycle to ensure that it is not occupied by other tasks.

[0033] If there are no appointment requests with a priority score higher than the preset priority score in the priority ranking queue, then all corresponding appointment requests will be sorted in descending order according to the preset priority score (based on the smart campus resource scheduling management specifications). This is to ensure that high-priority requests are allocated core resources first, preventing low-priority requests from crowding out valuable resources. Simultaneously, standardized sorting rules improve the traceability of resource scheduling, ensuring that the scheduling results conform to the preset resource allocation strategy and business priority requirements. Subsequently, the dynamic resource allocation process begins.

[0034] Progressive matching is performed through an iterative matching algorithm with multiple rounds and gradually relaxed conditions: The system first matches the original requirements of the application (request time slot, all equipment, specified capacity). When the system finds at least one classroom resource that fully meets the matching conditions of the current round and is either available or bookable, and the allocation scheme does not violate any rigid constraints of the current scheduling cycle (such as the total resource limit or the exclusivity of locked resources), the match is considered successful, and the system will temporarily lock the resource. If the system has traversed all preset rounds of relaxed conditions and still cannot find a classroom resource that simultaneously meets all the following conditions, the match is considered a failure, the application is downgraded to a regular reservation application, and the system re-enters the demand analysis process.

[0035] Scenario 3: If the multi-source status data does not meet the preset resource type label and the first application condition defined in the scheduling rule base, nor does it meet the second application condition, the system determines that the application belongs to the edge case where the rule is not clearly covered, the attributes are ambiguous, or there is a potential anomaly. For example, the application information is incomplete, the resource requirements exceed the normal configuration, or the applicant's permissions are obviously mismatched with the application content. Therefore, in order to avoid the risks of automatic decision-making and ensure scheduling compliance, the appointment application is marked as a pending application and prompts for manual review. For example, the academic affairs administrator can view the application details on the management terminal, contact the applicant to verify the intention, and make a final decision based on management experience and special policies or resubmit after supplementing information.

[0036] Among them, multi-source status data usually includes: (1) physical environment data: classroom actual occupancy status (such as infrared presence sensor, access control status), equipment operation status (such as projector, air conditioner on / off), environmental parameters (such as temperature, humidity, light); (2) academic affairs logic data: timetable scheduling information, course attributes (such as experimental class, theoretical class), teacher / class information, and teaching equipment binding relationship from the academic affairs management platform; (3) user behavior data: applicant identity information, historical reservation records, application additional instructions and urgency level marking from the user interaction terminal.

[0037] The first application criterion typically refers to the criteria for determining regular teaching or ordinary activities. For example: the applicant is a student or a regular faculty member; the activity type is a non-urgent matter such as club activities, self-study, or ordinary meetings; the application period is not within the fixed scheduling time of the academic affairs timetable; and no urgent or priority labels are marked. The second application criterion typically refers to the criteria for determining high-priority or special needs activities. For example: the applicant is a professor, department head, or administrative staff member; the activity type is a national examination, a major university-level conference, an emergency class rescheduling, or receiving foreign guests; and the application is marked with privilege labels such as urgent, important, or teaching support.

[0038] Both the first and second application conditions are dynamically set by the administrator based on school management regulations, historical scheduling experience, and business needs, using logical rule combinations (e.g., user role = teacher, activity type = national-level exam). The preset priority score is set as follows: scoring dimensions: user identity weight (e.g., professor = 10 points, student = 3 points); application urgency (urgent = 10 points, ordinary = 2 points); activity type impact factor (national-level exam = 15 points, club activity = 1 point); historical performance record (good credit adds points, breach of contract deducts points). The priority score is calculated as follows: Priority Score = Σ(dimensional score × weight), with each weight adjusted by the administrator according to school policies.

[0039] The scoring dimensions, application urgency, and corresponding weights mentioned above can be dynamically adjusted based on specific school management policies, resource supply and demand characteristics, and seasonal scheduling needs. For example, during end-of-semester exam week, the system can automatically increase the weight of exam-related activities and temporarily decrease the score for club activities to prioritize exam resources. Such adjustments can be made by administrators manually configuring preset scenario templates, or by the system automatically generating optimization suggestions based on historical scheduling data and then confirming their implementation.

[0040] Dynamic evaluation module for scheduling resources:

[0041] Under the scheduling constraints of the current scheduling cycle, the system obtains the reservation time slot occupancy data of the corresponding smart classroom under the current new reservation request queue through the real-time synchronization interface of smart classroom resource status. The reservation time slot occupancy data is represented by a binary vector, where 1 indicates that the corresponding reservation time slot has been occupied and 0 indicates that the corresponding reservation time slot has not been occupied. The new reservation request queue refers to the set of all user reservation applications newly received by the system within the current scheduling evaluation time window (such as a scheduling cycle of once every 10 minutes) that have not yet started resource matching and scheduling decisions.

[0042] The system monitors the matching simulation execution process of the smart classroom within the current scheduling evaluation time window. This process is driven by the scheduling simulation engine and aims to pre-evaluate the feasibility and performance of different matching strategies without actually consuming resources. The ratio of the total matching time after the simulation to the total number of reservation requests during the simulation is recorded as the unit request matching time. The difference between the load value after the simulation and the load baseline value before the simulation is recorded as the load increment value. The difference between the peak memory usage after the simulation and the memory baseline value before the simulation is recorded as the memory usage increment value. The total matching time represents the total duration between the end timestamp and the start timestamp automatically marked by the timestamp recording interface. The load value and peak memory usage are both monitored by the memory monitoring interface corresponding to the system's computing resources (CPU / processing queue).

[0043] The ratio of the unit request matching time to the preset benchmark matching time is recorded as the matching efficiency value, reflecting the timeliness of the matching process. The resource consumption value, reflecting additional resource overhead, is obtained by averaging the load increment value and memory usage increment value, each compared to its corresponding preset benchmark value. These two increment values ​​measure the additional pressure exerted by the matching simulation on the system's computing and storage resources (memory). The load increment focuses on the concurrent processing pressure or resource contention caused by the matching activity, while the memory increment focuses on the space overhead incurred by data structures and state preservation during algorithm execution. By averaging these values ​​with their respective preset benchmark values ​​(representing the system's acceptable threshold for additional overhead), the resource consumption value is obtained. This integrates two different dimensions of resource overhead into a normalized, dimensionless consumption score.

[0044] If the matching efficiency value is higher than the preset matching efficiency value and the resource consumption value is lower than the preset resource consumption value, the scheduling constraints for the current scheduling period are deemed feasible; otherwise, the scheduling constraints for the current scheduling period are deemed infeasible. The preset matching efficiency value and the preset resource consumption value are determined by the preset personnel based on the smart campus resource scheduling service level agreement and the system performance capacity. For scheduling constraints deemed feasible, the status of the corresponding reservation task is marked as scheduled, and the status of the corresponding classroom resource is synchronously updated to locked. For scheduling constraints deemed infeasible, the status of the corresponding reservation task is marked as pending coordination, and the status of the corresponding classroom resource is synchronously updated to pending review.

[0045] Scheduling execution status matching module:

[0046] Receive the judgment results output by the scheduling resource dynamic evaluation module. The judgment results include the status of scheduled and reserved tasks, the status of scheduled and reserved tasks to be coordinated, the status of classroom resources locked, and the status of classroom resources pending review.

[0047] Scenario 4: If all reservation tasks are in a scheduled state and all classroom resources are in a locked state within a consecutive pre-set number of scheduling cycles (e.g., 3, which can be dynamically configured according to system load rate and business tolerance, such as 5 during peak teaching periods), it indicates that the scheduling execution state has reached the preset scheduling goal and is recorded as a valid scheduling execution state. The preset scheduling goal refers to the core performance state that the system expects to achieve within multiple consecutive scheduling cycles. It is usually defined as: under the premise of ensuring the fairness of resource allocation and the continuity of time, achieving successful scheduling of all pending reservation tasks and deterministic locking of all related classroom resources, and no task is pending or resource is in a pending state. This signifies a stable, conflict-free and fully executed scheduling period.

[0048] Scenario 5: If there are pending scheduling tasks or classroom resources awaiting review within a predetermined number of consecutive scheduling cycles, the current scheduling execution status is determined to have not met the preset scheduling target, and resource reallocation is performed for conflicting and / or overloaded scheduling tasks.

[0049] Scenario 6: If there are more than a preset number (usually more than 1, i.e. there is competition) of reservation tasks requesting to use the same classroom resource within the same scheduling period, the corresponding reservation tasks are determined to be resource conflict tasks, and the resource allocation priority is adjusted. For example, the competing tasks are reordered according to the urgency of the task, the weight of the user's identity, or the historical performance record, and the application with the highest priority is given priority.

[0050] Scenario 7: If the number of users with a certain reservation task exceeds the capacity limit of the smart classroom within the same scheduling period, the corresponding reservation task is determined to be a capacity overload task, and the applicant is prompted to adjust the scale of the reservation task, such as suggesting that the applicant split the task into multiple time periods, divert some people to adjacent classrooms, or enable online synchronous participation mode.

[0051] If, after priority reordering in Scenario 6 and / or scale adjustment in Scenario 7, all scheduled tasks are in a scheduled state within the pre-set number of scheduling cycles, and all classroom resources are in a locked state, then the current scheduling execution state is recorded as a valid scheduling execution state. If there are still scheduled tasks pending coordination or classroom resources pending review, then manual intervention is required. For example, conflict details, attempted adjustment schemes, and suggested decision options (such as forced allocation, resource upgrade, or application rejection) are pushed to the administrator console for final decision.

[0052] Scheduling effect evaluation and feedback module:

[0053] At the end of each scheduling cycle, the average response time, resource allocation success rate, and conflict rescheduling ratio of all processed scheduled tasks are statistically analyzed and calculated. The average response time represents the average time from when the user submits the application to when the system provides the final scheduling result. The resource allocation success rate represents the proportion of scheduled tasks that successfully match and lock resources to the total number of processed tasks. The conflict rescheduling ratio represents the proportion of tasks that trigger the rescheduling process due to conflicts or overload to the total number of tasks.

[0054] When the average response time and the conflict rescheduling ratio both exceed the corresponding preset values, set by the system administrator based on historical service levels and business tolerance, and the resource allocation success rate is lower than the preset allowed allocation success rate, an efficiency alarm is triggered. The administrator is notified via sound, interface pop-up, or message push, and the corresponding scheduling period is marked as inefficient. The preset allowed allocation success rate is usually set based on the school's minimum efficiency requirements for the scheduling system, combined with the statistical distribution of historical success rates, such as the 90th percentile. Otherwise, the corresponding scheduling period is marked as stable, and the scheduling of resource allocation for all scheduled tasks within the current scheduling period is completed.

[0055] This invention provides a method for dynamic reservation and scheduling of smart classroom resources, such as... Figure 3 The flowchart shown is for a method of dynamic reservation and scheduling of smart classroom resources. The processing flow of this method may include the following steps:

[0056] S1. Based on the received multi-source status data and combined with the preset resource type tags and scheduling rule base, perform demand analysis or priority pre-evaluation on the user reservation requests to be processed, and preset scheduling constraints for each scheduling cycle; S2. Under the preset scheduling evaluation time window, based on the monitored real-time occupancy status data and the new reservation request queue, perform resource matching degree calculation to determine the scheduling execution status of each reservation task and / or each classroom resource; S3. Determine whether the scheduling execution status meets the preset scheduling target. If the preset scheduling target is met, the current scheduling execution status is taken as a valid scheduling execution status. If not, trigger the rescheduling process to reallocate resources for conflicting and / or overloaded reservation tasks, so that the scheduling execution status remains valid; S4. At the end of each scheduling cycle, perform a quantitative evaluation of the scheduling process to determine the comprehensive scheduling efficiency of the smart classroom in a dynamic reservation scenario.

[0057] In a specific implementation, for example, during the school's preparation for a week of open classes, faculty members and student clubs from various departments submitted a large number of classroom reservation applications with different time slots, equipment requirements, and priorities. The system, through its data integration and status monitoring module, automatically categorizes regular club activities as regular reservation applications based on multi-source status data and a rule base, and performs conflict detection and adaptive resolution. Simultaneously, applications marked as urgent class rescheduling and teaching demonstration classes are identified as priority reservation applications, initiating priority evaluation and fast-track processing. The dynamic resource scheduling evaluation module, through a simulated matching process, calculates efficiency values ​​and resource consumption under different allocation strategies in real time, dynamically selecting the optimal solution that meets the constraints and locking the resources. The scheduling execution status matching module continuously monitors scheduling consistency over multiple periods. For resource-conflicting tasks (such as multiple open classes competing for the same smart classroom) and capacity-overloaded tasks (such as a lecture having too many registered students), the system reassigns tasks through priority rearrangement and scale adjustment, respectively, until all tasks are completed and reach the scheduled state. Finally, the scheduling effect evaluation and feedback module statistically shows that the average response time of this cycle remains within 5 seconds, the allocation success rate reaches 98%, there is no continuous conflict rescheduling, it is marked as a stable state, and the relevant parameters are fed back to the rule base for self-optimization.

[0058] In summary, this invention achieves precise adaptation and efficient flow of smart classroom resources under multi-scenario, high-concurrency reservation demands by constructing an integrated scheduling system that integrates intelligent classification, dynamic evaluation, state matching, and closed-loop feedback. The system can intelligently distinguish between routine and priority tasks and proactively avoid inefficient allocation through simulation evaluation, significantly improving the processing speed and success rate of requests during peak periods. Its adaptive conflict resolution and progressive matching mechanism effectively resolves resource competition and overload contradictions, ensuring priority supply for core teaching activities. Multi-cycle state consistency judgment and quantitative effect evaluation ensure the stability and continuous optimization capability of the scheduling process. Overall, this system solves the pain points of traditional reservation methods, such as slow response, frequent conflicts, and insufficient priority protection. By replacing manual experience-based scheduling with data-driven decision-making, it improves classroom resource utilization, management refinement, and user satisfaction, providing reliable technical support for the digital governance of smart campuses.

[0059] It should be added that, such as Figure 4The diagram illustrating the time-series prediction and capacity monitoring of classroom demand shows the changes in classroom resource demand and the performance of model predictions over nearly six months after the start of the school year, supporting resource allocation decisions. The diagram uses time as the horizontal axis and classroom demand as the vertical axis. By comparing the solid line representing historical actual demand with the dashed line representing LSTM predicted demand, it visually demonstrates the model's prediction accuracy and changes in resource load: In the complete period from September 2024 to March 2025, during the historical fitting phase (September 2024 to early October 2024), actual and predicted demand highly overlapped. The model captured the normal fluctuations in the 30-55 range and never exceeded the capacity threshold of 60, indicating that resource supply remained within a safe range. Entering the peak warning phase (October 2024 to November 2024, the gray highlighted area in the diagram), demand surged to the 40-80 range and repeatedly exceeded the capacity threshold. The model identified the peak trend in advance, triggering a warning suggesting capacity expansion / allocation. The warning period perfectly corresponds to the actual period of demand stress. During the subsequent decline and rebound phase (December 2024 to March 2025), demand intensity first dropped to the 25-45 range, then rebounded to the 40-60 range in early 2025. The model continuously tracked these fluctuations, providing data support for predicting new peaks and allocating resources in advance. Overall, this graph, through time-series monitoring and prediction verification, not only validates the reliability of the Long Short-Term Memory Network (LSTM) model but also provides a visualized decision-making basis for the dynamic scheduling of smart campus classroom resources.

[0060] The LSTM model's input includes multi-dimensional temporal features: at the hourly level, it integrates features such as classroom reservation request volume, weekday / weekend / holiday, time period attributes (morning, noon, evening / peak hours), and historical popularity values ​​to form an input vector. The output is the classroom demand popularity value for the next scheduling cycle (e.g., 10 minutes), directly mapped to a quantized value between 0 and 100 for capacity threshold verification. The model uses a three-layer stacked LSTM structure: the input layer receives a 6-dimensional feature vector, which is then processed by two LSTM layers, each containing 64 neurons, to capture temporal dependencies. Finally, a fully connected layer outputs a single-dimensional popularity prediction value. Training employs a sliding window time series training method, using the past 72 hours of time series data as the input window to predict the popularity value for the next 10 minutes. Iterative optimization is achieved using the mean squared error loss function. Training data is taken from real reservation records from the past two semesters to ensure the model's generalization ability.

[0061] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0062] This invention is described with reference to flowchart illustrations and / or block diagrams of systems, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0063] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0064] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0065] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0066] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A smart classroom resource dynamic reservation and scheduling system, characterized in that, The system includes: The data integration and status monitoring module is used to analyze the needs or pre-evaluate the priorities of user reservation applications to be processed based on the received multi-source status data and the preset resource type tags and scheduling rule library, while pre-setting the scheduling constraints for each scheduling cycle. The multi-source status data is reported in real time by IoT sensors deployed in the smart classroom, the academic affairs management platform, and user interaction terminals; The scheduling constraints include at least the upper limit of total resource capacity, time continuity requirements, and differentiated priority thresholds; The scheduling resource dynamic evaluation module is used to perform resource matching degree calculation based on the monitored real-time occupancy status data and the new reservation request queue within a preset scheduling evaluation time window, so as to determine the scheduling execution status of each reservation task and / or each classroom resource. The scheduling execution status matching module is used to determine whether the scheduling execution status meets the preset scheduling target. When the preset scheduling target is met, the current scheduling execution status is taken as a valid scheduling execution status. If it does not meet the target, the rescheduling process is triggered to reallocate resources for conflicting and / or overloaded scheduled tasks, so that the scheduling execution status remains valid. The scheduling effect evaluation and feedback module is used to perform a quantitative evaluation of the scheduling process at the end of each scheduling cycle, thereby determining the overall scheduling efficiency of the smart classroom in a dynamic reservation scenario.

2. The smart classroom resource dynamic reservation and scheduling system as described in claim 1, characterized in that, The data integration and status monitoring module includes: Receive reservation requests submitted by users through the user interaction terminal; If the multi-source status data meets the preset resource type label and the first application condition defined in the scheduling rule base, the reservation application is classified as a regular reservation application and the demand is analyzed. If the multi-source status data meets the preset resource type label and the second application condition defined in the scheduling rule base, the reservation application will be classified as a priority reservation application and a priority pre-evaluation will be performed. If the multi-source status data does not meet either the first application condition defined in the preset resource type label and scheduling rule base, nor the second application condition, the reservation application will be marked as a pending application, and a manual review will be requested.

3. The smart classroom resource dynamic reservation and scheduling system as described in claim 2, characterized in that, The requirement analysis includes: Obtain resource conflict judgment conditions, which indicate that the application time corresponding to the regular appointment application overlaps with the scheduled time period, the resource type does not match the currently available resource label, and the number of applicants exceeds the smart classroom capacity limit. If the regular reservation request meets at least one of the above resource conflict judgment conditions, the corresponding regular reservation request will be marked as a conflict request and enter the conflict resolution process. If the regular reservation request does not meet any of the above resource conflict judgment conditions, the corresponding regular reservation request will be marked as a schedulable request and enter the resource matching and automatic scheduling queue. The conflict resolution process includes: determining whether the conflict request can be adaptively resolved by adjusting the request time or replacing similar resources; if so, generating an optimized scheduling suggestion, including the suggestion as an alternative in the current scheduling cycle's solution pool, and recording the adjustment requirements in the optimized scheduling suggestion as scheduling constraints; otherwise, transferring the corresponding conflict request to the manual review queue for manual intervention.

4. The smart classroom resource dynamic reservation and scheduling system as described in claim 2, characterized in that, The priority pre-evaluation includes: The quantitative scoring results of the priority reservation applications are recorded as priority scores, and sorted in descending order of priority scores to form a priority sorting queue. If there is a reservation application in the priority sorting queue with a priority score higher than the preset priority score, the corresponding reservation application will be recorded as a high-priority scheduling task and enter the resource reservation processing flow. If there is no reservation application with a priority score higher than the preset priority score in the priority sorting queue, then all corresponding reservation applications will be sorted in descending order according to the preset priority score and enter the dynamic resource allocation process. The resource reservation process includes: matching available classroom resources according to the needs of the high-priority scheduling tasks, and recording the classroom resources as scheduling constraints for the current scheduling cycle. The dynamic resource allocation process includes: progressively matching the priority reservation requests with the currently available resource pool according to a pre-set priority score order. If a match is found, a message will be displayed indicating that the corresponding priority appointment application will be temporarily locked. If a match fails, the corresponding priority appointment request will be downgraded to a regular appointment request and re-enter the demand analysis process.

5. The smart classroom resource dynamic reservation and scheduling system as described in claim 1, characterized in that, The dynamic evaluation module for scheduling resources includes: Under the scheduling constraints of the current scheduling cycle, obtain the reservation time slot occupancy data of the corresponding smart classroom under the current new reservation request queue. The reservation time slot occupancy data is represented by a binary vector to indicate the space occupancy status, where 1 indicates that the corresponding reservation time slot has been occupied and 0 indicates that the corresponding reservation time slot has not been occupied. Monitor the matching simulation execution process of the smart classroom within the current scheduling and evaluation time window: Based on the total matching time after the matching simulation and the total number of reservation requests during the matching simulation, the unit request matching time is obtained; The load increment value is obtained based on the load value after the matching simulation execution and the load baseline value before the matching simulation execution. Based on the peak memory usage after the matching simulation and the baseline memory usage before the matching simulation, the incremental memory usage value is obtained. The ratio of the unit request matching time to the preset benchmark matching time is processed and recorded as the matching efficiency value, which reflects the timeliness of the matching process. The resource consumption value, which reflects the additional overhead of resources, is obtained by averaging the ratios of the load increment value and the memory usage increment value with their respective preset benchmark values.

6. The smart classroom resource dynamic reservation and scheduling system as described in claim 5, characterized in that, The dynamic evaluation module for scheduling resources also includes: If the matching efficiency value is higher than the preset matching efficiency value and the resource consumption value is lower than the preset resource consumption value, then the scheduling constraint condition of the current scheduling period is determined to be feasible; otherwise, the scheduling constraint condition of the current scheduling period is determined to be infeasible. For scheduling constraints that are deemed feasible, the status of the corresponding scheduled task is marked as scheduled, and the status of the corresponding classroom resource is synchronously updated to locked. For scheduling constraints deemed infeasible, the status of the corresponding scheduled task is marked as pending coordination, and the status of the corresponding classroom resource is simultaneously updated to pending review.

7. The smart classroom resource dynamic reservation and scheduling system as described in claim 1, characterized in that, The scheduling execution status matching module includes: Receive the judgment result output by the scheduling resource dynamic evaluation module, the judgment result includes the status of scheduled reservation tasks, the status of reservation tasks to be coordinated, the status of classroom resources locked, and the status of classroom resources pending review; If all scheduled tasks are in a scheduled state within a preset number of scheduling cycles, and all classroom resources are in a locked state, it indicates that the scheduling execution status has reached the preset scheduling target and is recorded as a valid scheduling execution status. If there are pending scheduling tasks or classroom resources pending review within a preset number of scheduling cycles, the current scheduling execution status is determined to have not reached the preset scheduling target, and resource reallocation is carried out for conflicting and / or overloaded scheduling tasks.

8. The smart classroom resource dynamic reservation and scheduling system as described in claim 7, characterized in that, The resource reallocation for conflicting and / or overloaded scheduled tasks specifically includes: If more than the preset number of reservation tasks request the use of the same classroom resource within the same scheduling period, the corresponding reservation tasks are determined to be resource conflict tasks, and an adjustment of resource allocation priority is prompted. If the number of users with a certain reservation task exceeds the capacity limit of the smart classroom within the same scheduling period, the corresponding reservation task is determined to be a capacity overload task, and an adjustment to the size of the reservation task is prompted. If, after adjusting the resource allocation priority and / or the size of the reservation tasks as described above, all reservation tasks are in a scheduled state within a preset number of scheduling cycles, and all classroom resources are in a locked state, then the current scheduling execution state is recorded as a valid scheduling execution state. If there are still pending appointment tasks or classroom resources pending review, a prompt will appear indicating that manual intervention is required.

9. The smart classroom resource dynamic reservation and scheduling system as described in claim 1, characterized in that, The scheduling effect evaluation and feedback module includes: At the end of each scheduling cycle, the average response time, resource allocation success rate, and conflict rescheduling ratio of all processed scheduled tasks are statistically analyzed and calculated. When the average response time and the conflict rescheduling ratio both exceed the corresponding preset values, and the resource allocation success rate is lower than the preset allowed allocation success rate, an efficiency alarm is triggered, and the corresponding scheduling period is marked as inefficient. Otherwise, mark the corresponding scheduling period as a stable state and complete the scheduling of all scheduled task resource allocations within the current scheduling period.

10. A method for dynamic reservation and scheduling of smart classroom resources, applied to the smart classroom resource dynamic reservation and scheduling system described in any one of claims 1-9, characterized in that, Includes the following steps: S1, based on the received multi-source status data, combined with the preset resource type tags and scheduling rule base, performs demand analysis or priority pre-evaluation on the user reservation application to be processed, and at the same time presets the scheduling constraints for each scheduling cycle. S2, within the preset scheduling evaluation time window, based on the monitored real-time occupancy status data and the newly added reservation request queue, performs resource matching degree calculation to determine the scheduling execution status of each reservation task and / or each classroom resource; S3, determine whether the scheduling execution state meets the preset scheduling target. If the preset scheduling target is met, the current scheduling execution state is taken as a valid scheduling execution state. If it is not met, trigger the rescheduling process to reallocate resources for conflicting and / or overloaded scheduled tasks so that the scheduling execution state remains valid. S4. At the end of each scheduling cycle, the efficiency of the scheduling process is quantitatively evaluated to determine the overall scheduling efficiency of the smart classroom in the dynamic reservation scenario.

Images