A big data-based smart campus management platform

Abstract

The present application relates to the field of big data analysis, and particularly relates to a smart campus management platform based on big data. The present application determines the number of three-dimensional model segmented into spatial region model based on the collected environmental characteristic parameters through the multi-source data acquisition module; determines the utilization rate similarity of each spatial region based on the comparison result of the personnel label area proportion and the space utilization rate threshold in the three-dimensional model through the data analysis module; divides the environmental impact level based on the utilization rate similarity through the grade division module; determines whether to adjust the refrigeration capacity and the air exchange frequency of the environment based on the interval of the personnel density under the condition of being in the first preset environmental impact level through the monitoring strategy module. The present application significantly reduces the probability of accidents in the campus large-scale activities by accurately analyzing the related data of the environment and the personnel, effectively improves the environmental comfort, and significantly improves the efficiency of the campus activity management.

Description

Technical Field

[0001] This invention relates to the field of big data analytics, and more particularly to a smart campus management platform based on big data. Background Technology

[0002] With the continuous development of information technology, the concept of smart campuses has gradually become popular, and various smart campus management platforms have emerged, realizing the digitalization and intelligentization of campus management. However, when large-scale events are held on campus, especially when large numbers of people gather in large indoor venues, traditional smart campus management platforms still have significant shortcomings. In such scenarios, the flow of people is complex and dense, and the distribution of people in different areas changes dynamically as the event progresses. Existing platforms often struggle to collect and process this dynamic data comprehensively and in real time, and also find it difficult to adjust management strategies promptly based on the actual situation.

[0003] Patent application publication number CN116452379B discloses a smart campus management system based on big data. This invention provides a smart campus management system based on big data, including a basic information module, a video surveillance module, and a central processing module. The basic information module is used to acquire basic information about the smart campus. The video surveillance module is used to establish communication connections with video surveillance equipment in various areas of the smart campus, acquire video surveillance data collected by the video surveillance equipment, and transmit the acquired video surveillance data to the central processing module. The central processing module includes a database module and an intelligent analysis module. The database module is used to classify, store, and manage the basic information of the smart campus and the acquired video surveillance data, constructing a smart campus monitoring database. The intelligent analysis module is used to perform intelligent big data analysis based on the obtained video surveillance data, obtain personnel behavior analysis results, and output corresponding management information based on the obtained personnel behavior analysis results. This invention helps to improve the intelligence level of smart campus management.

[0004] Therefore, the following problems exist in the existing technology:

[0005] Existing technologies do not consider the problem of low accuracy in guiding the evacuation of personnel in different spatial areas due to differences in ambient temperature when large-scale campus events are held in indoor venues. Summary of the Invention

[0006] To address this issue, the present invention provides a smart campus management platform based on big data, which overcomes the problem in existing technologies where, in environments with large gatherings such as large indoor venues for campus events, the distribution of people in different spatial areas varies due to differences in ambient temperature, resulting in low accuracy of the 3D model in guiding the evacuation of people and thus low campus management efficiency.

[0007] To achieve the above objectives, the present invention provides a smart campus management platform based on big data, comprising:

[0008] The multi-source data acquisition module generates a 3D model corresponding to the target area based on the point cloud data of the target area, and determines the number of spatial region models to be divided into the 3D model based on the environmental feature parameters of the acquired target area.

[0009] The data analysis module determines the space utilization threshold for the target area based on the number of acquired spatial region models, and determines the utilization similarity of each spatial region based on the comparison between the actual acquired personnel tag area ratio and the space utilization threshold in the three-dimensional model.

[0010] The grading module classifies environmental impact levels based on the similarity of utilization rates of models in each spatial region.

[0011] The monitoring strategy module determines whether to adjust the cooling capacity and air exchange rate of the corresponding spatial area based on the range of personnel density when the environmental impact level of each spatial area is at the first preset environmental impact level. After the adjustment of the cooling capacity and air exchange rate is completed, the spatial area for guiding evacuation is determined based on the range of personnel density.

[0012] The environmental characteristic parameters include temperature and carbon dioxide concentration.

[0013] Furthermore, the multi-source data acquisition module determines the number of spatial region models to be divided into the three-dimensional model based on environmental feature characterization values, which is either a first predetermined number or a second predetermined number; wherein, the feature characterization values ​​are calculated by a first influencing factor determined based on the actual temperature in the target region and a second influencing factor determined based on the actual carbon dioxide concentration in the target region.

[0014] Furthermore, the data analysis module determines the proportion of personnel tag area based on the actual personnel tag area and the effective safe area extracted from the spatial region model; wherein, the actual personnel tag area is determined by obtaining the personnel tag coordinates.

[0015] Furthermore, the data analysis module determines the space utilization threshold for the target area as a first space utilization threshold or a second space utilization threshold based on the number of acquired spatial region models.

[0016] Furthermore, the monitoring strategy module compares the acquired personnel density with a preset first personnel density threshold to determine whether it is within a first abnormal range; or compares it with a preset second personnel density threshold to determine whether it is within a second abnormal range.

[0017] Furthermore, when the personnel density is in the first abnormal range, the monitoring strategy module adjusts the cooling capacity and air exchange rate of the corresponding spatial area, and then triggers the multi-source data acquisition module to update the environmental characteristic parameters of the corresponding spatial area and the number of spatial area models segmented into the three-dimensional model.

[0018] The data analysis module is used to respond to and update the spatial utilization threshold and utilization similarity for the spatial region;

[0019] The classification module reclassifies the environmental impact level based on the similarity of the corresponding spatial regions after the update.

[0020] Furthermore, the monitoring strategy module determines the number of people to be evacuated and several available space areas for evacuation based on the personnel density of the re-divided spatial area.

[0021] The environmental impact level of the redefined spatial area belongs to the first preset environmental impact level.

[0022] Furthermore, the monitoring strategy module determines the first evacuation target area based on the location of the determined spatial area requiring evacuation in the three-dimensional model and the surrounding spatial areas that are not at the first preset environmental impact level.

[0023] Furthermore, the monitoring strategy module determines a second evacuation target area based on the actual number of people in the first evacuation target area; wherein, the second evacuation target area is determined according to the actual number of people in the first evacuation target area and the number of people to be evacuated.

[0024] Furthermore, the monitoring strategy module determines whether there is an anomaly in the evacuation based on the difference between the number of people to be evacuated and the number of the second evacuation target people.

[0025] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention provides a smart campus management platform based on big data. By monitoring environmental parameters to determine the number of model segments, it analyzes the ideal value of space utilization and compares it with the actual personnel area ratio to obtain a similarity in space utilization. Environmental impact levels are then classified based on this similarity. When the environment is under a first preset environmental impact level, it further determines whether the personnel density range is in a first abnormal range, thereby determining the cooling capacity and air exchange rate of the adjusted area. After adjustment, environmental parameters are re-acquired. If the environment is still under a first preset environmental impact level, it further determines whether the personnel density range is in a second abnormal range, thereby determining the space area for guided evacuation. The evacuation target area is determined by extracting spatial distance relationships and the number of evacuees from the 3D model, and evacuation is considered complete when the number of evacuees is zero. This invention, through multi-module collaborative work, accurately analyzes and processes relevant characteristic data of the environment, personnel, and models, significantly reducing the probability of accidents during large-scale events, effectively improving the environmental comfort of event venues, and significantly improving the efficiency of campus event management.

[0026] In particular, the multi-source data acquisition module uses LiDAR scanning to acquire high-precision point cloud data and generate corresponding 3D models, providing accurate spatial benchmarks for subsequent spatial segmentation and evacuation decisions. Simultaneously, temperature sensors and carbon dioxide detectors monitor environmental characteristics of the target area in real time, and UWB indoor positioning tracks personnel tag coordinates, constructing a real-time multi-source data acquisition system encompassing 3D models, environmental conditions, and personnel locations. The accurate acquisition and fusion of this fundamental data is a prerequisite for all subsequent analysis and decision-making. The LiDAR scanning and UWB indoor positioning components offer flexible deployment and reusability, significantly reducing long-term management costs.

[0027] In particular, the data analysis module calculates environmental characteristic values ​​based on real-time environmental parameters, including temperature and carbon dioxide concentration, and dynamically determines the number of spatial region models segmented by the 3D model, including a first or second predetermined number, enabling the model segmentation to respond sensitively to environmental changes. The number of spatial region models segmented by the 3D model determines the space utilization threshold for the target area, including a first or second space utilization threshold. Using personnel tag coordinates obtained through UWB positioning, a standardized safety envelope circle algorithm is applied to calculate the actual personnel tag area, and the effective safety area is extracted from the 3D model to accurately calculate the personnel tag area ratio. By comparing the personnel tag area ratio with the corresponding space utilization threshold, the utilization similarity of each spatial region is determined. The data analysis module quantifies the deviation of environmental conditions and accurately assesses the spatial carrying capacity, providing an objective and accurate data foundation for risk classification.

[0028] Furthermore, the environmental impact level is classified based on the similarity of the spatial region models through a grading module. This grading mechanism can accurately distinguish the actual risk level of different regions, providing a core basis for subsequent implementation of differentiated management strategies that match the risk level.

[0029] In particular, through the monitoring strategy module, when the environmental impact level of each spatial area is at the first preset environmental impact level, if the population density is in the first abnormal range, i.e., in a relatively crowded state, the cooling capacity and air exchange rate of the corresponding area will be adjusted first to improve environmental comfort. After adjustment, the multi-source data acquisition module is triggered to re-collect the environmental parameters of the spatial area and update the number of spatial area models; the data analysis module updates the space utilization threshold and utilization similarity of the spatial area accordingly; the level classification module reclassifies the level based on the updated similarity, forming a closed-loop feedback for environmental regulation. This gradual, closed-loop regulation strategy prioritizes improving the environment with minimal intervention cost, effectively improving management efficiency and reducing interference with normal order.

[0030] Furthermore, through the monitoring strategy module, if the environment remains at the first preset environmental impact level after environmental control measures, and the population density is in the second abnormal zone (i.e., in a dangerous and crowded state), the precise number of people requiring evacuation is calculated based on the coordinates of the personnel tags, and the spatial area for guiding evacuation is determined. First, using the spatial relationships in the 3D model, the closest area with a safe environmental impact level is selected as the first evacuation target area. Second, the effective safe area margin of the first target area is calculated, and combined with the preset per capita evacuation area threshold, the number of people it can accommodate is determined. If the capacity of the first target evacuation area is less than the number of people requiring evacuation (i.e., it cannot accommodate them all at once), the maximum capacity is allocated to the first target area, and the remaining number of people requiring evacuation is updated. Next, the used first target evacuation area is excluded from the 3D model, and the next safe area is selected as the second evacuation target area based on distance from nearest to farthest. Finally, the capacity of the second target evacuation area is calculated; if it is greater than or equal to the remaining number of people requiring evacuation, all remaining people are allocated to the second target area. If the number of people to be evacuated is less than the remaining number, the second target area is considered the new first target area, and the partial allocation and personnel update process is recursively executed. Finally, when it is confirmed that the number of people to be evacuated is zero, the evacuation of the area is considered complete. This significantly improves the efficiency and accuracy of evacuation route planning and resource allocation in emergency situations, maximizes the use of safe evacuation space, effectively reduces local congestion, and significantly reduces the probability of safety accidents. Attached Figure Description

[0031] Figure 1 This is a structural block diagram of a smart campus management platform based on big data, as described in an embodiment of the present invention.

[0032] Figure 2 This invention provides a logical decision diagram for determining the space utilization threshold of the target area.

[0033] Figure 3 This invention provides a logic determination diagram for adjusting the cooling capacity and air exchange rate of a space area when the personnel density of that space area is located in the first abnormal area.

[0034] Figure 4 This invention provides a logical decision diagram for determining the spatial area where the personnel density is located in the second abnormal area and guiding evacuation. Detailed Implementation

[0035] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0036] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0037] Please see Figure 1 , Figure 2 , Figure 3 as well as Figure 4 The diagram shown is a structural block diagram of a smart campus management platform based on big data according to an embodiment of the present invention; a logical decision diagram for determining the space utilization threshold of the target area according to an embodiment of the present invention; a logical decision diagram for adjusting the cooling capacity and air exchange rate of the corresponding space area when the personnel density of the space area is in the first abnormal area according to an embodiment of the present invention; and a logical decision diagram for determining the space area for guiding evacuation when the personnel density of the space area is in the second abnormal area according to an embodiment of the present invention.

[0038] This invention provides a smart campus management platform based on big data, comprising:

[0039] The multi-source data acquisition module generates a 3D model corresponding to the target area based on the point cloud data of the target area, and determines the number of spatial region models to be divided into the 3D model based on the environmental feature parameters of the acquired target area.

[0040] The data analysis module determines the space utilization threshold for the target area based on the number of acquired spatial region models, and determines the utilization similarity of each spatial region based on the comparison between the actual acquired personnel tag area ratio and the space utilization threshold in the three-dimensional model.

[0041] The grading module classifies environmental impact levels based on the similarity of utilization rates of models in each spatial region.

[0042] The monitoring strategy module determines whether to adjust the cooling capacity and air exchange rate of the corresponding spatial area based on the range of personnel density when the environmental impact level of each spatial area is at the first preset environmental impact level. After the adjustment of the cooling capacity and air exchange rate is completed, the spatial area for guiding evacuation is determined based on the range of personnel density.

[0043] The environmental characteristic parameters include temperature and carbon dioxide concentration.

[0044] In this embodiment, the number of model segments is determined by monitoring environmental parameters. The RANSAC algorithm is used to extract effective active ground point cloud data excluding obstacles, and an active plane projection is constructed. This projection is then divided into several regions according to the determined number of model segments. Based on these regions, several spatial region models are correspondingly segmented. The ideal value of space utilization is analyzed based on the determined number of spatial region model segments, and compared with the actual proportion of personnel area to obtain a similarity in space utilization. Environmental impact levels are classified based on the similarity in space utilization. When the environment is under a first preset environmental impact level, it is further determined whether the personnel density interval is in a first abnormal interval. This determines the adjustment of the cooling capacity and air exchange rate of the spatial region environment. After adjustment, environmental parameters are re-acquired. If the environment is still under a first preset environmental impact level, it is further determined whether the personnel density interval is in a second abnormal interval. This determines the spatial region for evacuation guidance. The evacuation target area is determined by the spatial distance relationships extracted from the 3D model and the number of evacuees. Evacuation is considered complete when the number of evacuees is zero. This invention, through the collaborative work of multiple modules, accurately analyzes and processes relevant characteristic data of the environment, personnel, and models, significantly reducing the probability of accidents during large-scale events, while effectively improving the environmental comfort of event venues and significantly improving the efficiency of campus event management.

[0045] In this embodiment, the lidar scanning component mainly includes: several lidar scanning stations, each set in a single spatial area of ​​15 meters by 15 meters, for collecting point cloud data of the target area; and a lidar data processing algorithm generating a three-dimensional model based on the cloud data of each station.

[0046] In this embodiment, the LiDAR scanning component clearly presents the spatial structure of each area, providing accurate basic data for subsequent analysis of whether the distribution in different areas is reasonable and whether the space is fully utilized, resulting in a more intuitive and detailed understanding of the site conditions. Furthermore, both the LiDAR scanning stations and data processing software can be repeatedly deployed and used in subsequent large-scale events. The hardware only needs slight adjustments to the location based on the site layout of the new event, and the software system does not need to be redeveloped; it can directly import the scanning data of the new site to generate the corresponding 3D model, avoiding redundant construction costs. This allows the campus to continuously utilize existing equipment resources in long-term event management, improving management efficiency while reducing investment costs.

[0047] In this embodiment, the personnel tag coordinates are obtained through a UWB indoor positioning component, which mainly includes: several UWB positioning tags, which are worn by relevant participants to emit UWB signals; and several UWB positioning base stations, which are used to collect tag coordinates in each area, determine them as personnel tag coordinates, and count the number of tags.

[0048] In this embodiment, by utilizing UWB indoor positioning components to monitor personnel distribution in real time, potentially hazardous or crowded areas can be identified promptly, providing precise data for guiding personnel evacuation or adjusting environmental control equipment. Tags can be reused across different events; they only need to be distributed to participants before the event and collected afterward. Once the base station is installed, it does not require frequent disassembly. For subsequent large-scale events, simply turning on the device and updating the participants' tag information allows for direct reuse. This design enables the entire positioning system to function continuously across multiple large-scale events, reducing hardware procurement costs, improving equipment utilization efficiency, and allowing for efficient resource utilization in long-term campus personnel management.

[0049] In this embodiment, the process of classifying environmental impact levels based on the utilization similarity of each spatial region model using the level classification module includes: if the utilization similarity of the spatial region model is less than or equal to a predetermined spatial utilization similarity threshold, then the environmental impact level of the spatial region model is determined to be a first preset environmental impact level; if the utilization similarity of the spatial region model is greater than the predetermined spatial utilization similarity threshold, then the environmental impact level of the spatial region model is determined to be a non-first preset environmental impact level. The spatial utilization similarity threshold is pre-determined, and the spatial utilization similarity under comfortable environmental conditions within three months of a historical period is extracted, its average value is calculated, and the spatial utilization similarity threshold is set to 0.9 times the average value.

[0050] Specifically, the multi-source data acquisition module determines the number of spatial region models to be divided into the three-dimensional model based on environmental feature characterization values, which is either a first predetermined number or a second predetermined number; wherein, the feature characterization values ​​are calculated by a first influencing factor determined based on the actual temperature in the target region and a second influencing factor determined based on the actual carbon dioxide concentration in the target region.

[0051] In this embodiment, the temperature and carbon dioxide concentration in the target area are acquired in real time. The ratio of the actual temperature to a preset temperature threshold is determined as a first influencing factor; the ratio of the actual carbon dioxide concentration to a preset concentration threshold is determined as a second influencing factor; the sum of the first and second influencing factors is determined as a feature characterization value. If the actual feature characterization value is greater than or equal to the preset feature characterization value, the environmental risk is high, and fine segmentation is determined, then the number of spatial regions to be cut is determined as a first predetermined number; if the actual feature characterization value is less than the preset feature characterization value, the environmental risk is low, and basic segmentation is determined, then the number of spatial regions to be cut is determined as a second predetermined number. The temperature and carbon dioxide thresholds are pre-determined, and the average values ​​of the temperature and carbon dioxide concentration under comfortable environmental conditions within three months of the historical period are calculated as the corresponding thresholds. The preset feature characterization value is 2.15; the first and second predetermined numbers are pre-determined, and the average values ​​of the number of spatial region models segmented from the 3D model within three months of the historical period are calculated, with the first predetermined number set to 0.9 times the average and the second predetermined number set to 0.7 times the average.

[0052] Specifically, the data analysis module determines the proportion of personnel tag area based on the actual personnel tag area and the effective safe area extracted from the spatial region model; wherein, the actual personnel tag area is determined by obtaining the personnel tag coordinates.

[0053] In this embodiment, the coordinates of all personnel within a spatial area are acquired in real time using UWB indoor positioning. A circular area is generated centered on each person's coordinates. The areas of all non-overlapping circles are summed to obtain the actual personnel tag area. The effective safe area after removing obstacles is extracted from the 3D model of the spatial area to obtain the personnel tag area ratio.

[0054] Specifically, the data analysis module determines the space utilization threshold for the target area as either a first threshold or a second threshold based on the number of spatial region models acquired.

[0055] In this embodiment, the number of spatial region models received from the multi-source data acquisition module is determined by several factors. When the number is a first predetermined number (representing the number of finely segmented areas), a first threshold for space utilization is selected. When the number is a second predetermined number (representing the number of basic segments), a second threshold for space utilization is selected. The space utilization thresholds are pre-determined, calculated by extracting the space utilization rate over three months in a comfortable environment and calculating its average. The first threshold is set to 1.1 times the average, and the second threshold is set to 1.3 times the average. The first threshold being lower than the second threshold enhances risk sensitivity while preventing over-warning. By setting dynamic thresholds, the accuracy of risk assessment is improved, while the false alarm rate is reduced, significantly enhancing the accuracy and response efficiency of safety warnings. By accurately distinguishing risk levels, insufficient response in high-risk situations or overreaction in low-risk situations is reduced, effectively minimizing the occurrence of mass discomfort events during large-scale events and reducing disorder caused by unnecessary evacuations.

[0056] Specifically, the monitoring strategy module compares the acquired personnel density with a preset first personnel density threshold to determine whether it is within a first abnormal range; or compares it with a preset second personnel density threshold to determine whether it is within a second abnormal range.

[0057] In this embodiment, by acquiring the number of personnel tags in a spatial area and the corresponding area of ​​the spatial area, the personnel density is calculated. When the personnel density is greater than or equal to a preset first personnel density threshold, the personnel density of the spatial area is determined to be in a first abnormal interval. When the personnel density is in the first abnormal interval, if the personnel density is greater than or equal to a preset second personnel density threshold, the personnel density of the spatial area is determined to be in a second abnormal interval. The personnel density thresholds are pre-determined, and the average personnel density over a three-month period under comfortable environmental conditions is calculated. The first threshold is set to 1.05 times the average, and the second threshold is set to 1.3 times the average. The first threshold being less than the second threshold is used to distinguish between situations affecting the comfort of the human spatial environment and situations affecting personnel safety.

[0058] Specifically, when the personnel density is in the first abnormal range, the monitoring strategy module adjusts the cooling capacity and air exchange rate of the corresponding spatial area, and then triggers the multi-source data acquisition module to update the environmental characteristic parameters of the corresponding spatial area and the number of spatial area models segmented into the three-dimensional model.

[0059] The data analysis module is used to respond to and update the spatial utilization threshold and utilization similarity for the spatial region;

[0060] The classification module reclassifies the environmental impact level based on the similarity of the corresponding spatial regions after the update.

[0061] In this embodiment, when the personnel density is within the first abnormal range, the cooling capacity and air exchange rate of the corresponding spatial area are adjusted. The cooling adjustment amount is set to the difference between the current temperature and the temperature threshold, and the air exchange rate is set to 1.5 times the air exchange rate corresponding to the carbon dioxide concentration threshold. The average time of significant changes in temperature and carbon dioxide concentration after adjusting the cooling capacity and air exchange rate of the corresponding spatial area in the historical period is used as the cooling waiting time. Then, environmental characteristic parameters are re-collected, the number of spatial area models segmented into the three-dimensional model is updated, the space utilization threshold and utilization similarity are re-determined, and the environmental impact level is reclassified based on the updated similarity of the spatial areas.

[0062] Specifically, the monitoring strategy module determines the number of people to be evacuated and several available space areas for evacuation based on the personnel density of the re-divided spatial area.

[0063] The environmental impact level of the redefined spatial area belongs to the first preset environmental impact level.

[0064] In this embodiment, if the environment is still at the first preset environmental impact level after environmental control, it is determined whether the personnel density is in the second abnormal range, that is, whether the personnel density affects personnel safety. If it is in the second abnormal range, the number of people to be evacuated is obtained by multiplying the difference between the personnel density of the space area and the first threshold of personnel density by the area of ​​the area, and the spatial area for guiding evacuation is further determined.

[0065] Specifically, the monitoring strategy module determines the first evacuation target area based on the location of the spatial area requiring evacuation in the three-dimensional model and the surrounding spatial areas that are not at the first preset environmental impact level.

[0066] In this embodiment, in the three-dimensional model, the region with the shortest Euclidean distance to the current region is found by the shortest path algorithm, and the environmental impact level of the region is not the first preset environmental impact level. Then, the spatial region is determined as the first evacuation target region to ensure the shortest evacuation path, reduce the time for personnel to move, and reduce the risk of congestion.

[0067] Specifically, the monitoring strategy module determines the second evacuation target area based on the actual number of people in the first evacuation target area; wherein, the second evacuation target area is determined according to the actual number of people in the first evacuation target area and the number of people to be evacuated.

[0068] In this embodiment, the actual number of people in the first evacuation target area is obtained, and the difference between the actual number of people and the threshold number of people that the space area can accommodate is calculated to determine the number of people that the first evacuation target area can accommodate. If the number of people that the first evacuation target area can accommodate is greater than or equal to the number of people to be evacuated, the evacuation is considered complete; if it is less than the number of people to be evacuated, a second evacuation target area needs to be determined.

[0069] Specifically, the monitoring strategy module determines whether there is an abnormality in the evacuation based on the difference between the number of people to be evacuated and the number of the second evacuation target people.

[0070] In this embodiment, the difference between the number of people to be evacuated and the number of people that the first evacuation target area can accommodate is calculated and determined as the second evacuation target number. The nearest surrounding spatial area other than the first evacuation target area is extracted from the 3D model, and the environmental impact level of this spatial area is not a first preset environmental impact level. The surrounding spatial area meeting the above conditions is then determined as the second evacuation target area. The actual number of people in the second evacuation target area is obtained, and the difference between the actual number of people and the threshold number that the spatial area can accommodate is calculated and determined as the number of people that the second evacuation target area can accommodate. If the difference between the number of people that the second evacuation target area can accommodate and the second evacuation target number is greater than or equal to zero, the evacuation is considered complete. If it is not zero, a new evacuation target area needs to be repeatedly allocated to evacuate people, excluding the area already assigned to evacuation, until the difference is zero, at which point the evacuation is considered complete.

[0071] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

[0072] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A big data-based smart campus management platform, characterized in that, include: The multi-source data acquisition module generates a 3D model corresponding to the target area based on the point cloud data of the target area, and determines the number of spatial region models to be divided into the 3D model based on the environmental feature parameters of the acquired target area. The data analysis module determines the space utilization threshold for the target area based on the number of acquired spatial region models, and determines the utilization similarity of each spatial region based on the comparison between the actual acquired personnel tag area ratio and the space utilization threshold in the three-dimensional model. The grading module classifies environmental impact levels based on the similarity of utilization rates of models in each spatial region. The monitoring strategy module determines whether to adjust the cooling capacity and air exchange rate of the corresponding spatial area based on the range of personnel density when the environmental impact level of each spatial area is at the first preset environmental impact level. After the adjustment of the cooling capacity and air exchange rate is completed, the multi-source data acquisition module is triggered to re-acquire environmental feature parameters and update the number of spatial area models segmented into the three-dimensional model. The data analysis module updates the spatial utilization threshold and utilization similarity of spatial regions based on the number of updated spatial region models. The classification module reclassifies the environmental impact level based on the updated utilization similarity, forming a closed-loop feedback for environmental regulation. If the environment is still at the first preset environmental impact level, the spatial area for guiding evacuation will be determined based on the range of personnel density. The environmental characteristic parameters include temperature and carbon dioxide concentration.

2. The smart campus management platform based on big data according to claim 1, characterized in that, The multi-source data acquisition module determines, based on environmental feature characterization values, the number of spatial region models to be divided into the 3D model, which is either a first predetermined number or a second predetermined number; wherein... The characteristic value is calculated using a first influencing factor determined based on the actual temperature in the target area and a second influencing factor determined based on the actual carbon dioxide concentration in the target area.

3. The smart campus management platform based on big data according to claim 1, characterized in that, The data analysis module determines the proportion of personnel tag area based on the actual personnel tag area and the effective safe area extracted from the spatial region model; wherein, the actual personnel tag area is determined by obtaining the personnel tag coordinates. 4.The big data-based smart campus management platform according to claim 1, characterized in that, The data analysis module determines the space utilization threshold for the target area as either a first threshold or a second threshold based on the number of acquired spatial region models. 5.The big data-based smart campus management platform according to claim 1, characterized in that, The monitoring strategy module compares the acquired personnel density with a preset first personnel density threshold to determine whether it is within a first abnormal range; or compares it with a preset second personnel density threshold to determine whether it is within a second abnormal range.

6. The smart campus management platform based on big data according to claim 5, characterized in that, When the personnel density is in the first abnormal range, the monitoring strategy module adjusts the cooling capacity and air exchange rate of the corresponding spatial area, and then triggers the multi-source data acquisition module to update the environmental characteristic parameters of the corresponding spatial area and the number of spatial area models segmented into the three-dimensional model. The data analysis module is used to respond to and update the spatial utilization threshold and utilization similarity for the spatial region; The classification module reclassifies the environmental impact level based on the similarity of the corresponding spatial regions after the update.

7. The smart campus management platform based on big data according to claim 6, characterized in that, The monitoring strategy module determines the number of people to be evacuated and several available space areas to guide the evacuation based on the personnel density of the re-divided spatial area. The environmental impact level of the redefined spatial area belongs to the first preset environmental impact level. 8.The big data-based smart campus management platform according to claim 7, characterized in that, The monitoring strategy module determines the first evacuation target area based on the location of the spatial area requiring evacuation in the three-dimensional model and the surrounding spatial areas that are not at the first preset environmental impact level. 9.The big data-based smart campus management platform according to claim 8, characterized in that, The monitoring strategy module determines the second evacuation target area based on the actual number of people in the first evacuation target area; wherein, the second evacuation target area is determined according to the actual number of people in the first evacuation target area and the number of people to be evacuated.

10. The smart campus management platform based on big data according to claim 9, characterized in that, The monitoring strategy module determines whether there is an abnormality in the evacuation based on the difference between the number of evacuees that the second evacuation target area can accommodate and the number of people in the second evacuation target area. The number of people in the second evacuation target area is determined based on the difference between the number of people to be evacuated and the number of people that the first evacuation target area can accommodate. The number of evacuees that the first evacuation target area can accommodate is determined based on the difference between the actual number of people in the first evacuation target area and the threshold number of people that the space area can accommodate. The number of evacuees that the second evacuation target area can accommodate is determined based on the difference between the actual number of people in the second evacuation target area and the threshold number of people that the space area can accommodate.

Images