A fire emergency management method for a big data education platform of an educational institution

Abstract

The present application relates to the technical field of fire emergency treatment, and particularly discloses a fire emergency management method for a big data education platform of an educational institution, which comprises: patrol management determination, fire emergency simulation evaluation, and fire emergency management feedback. The structure data of the region to which the educational institution belongs and the patrol management data of the big data fire education cloud platform are quantitatively compared, so that more accurate patrol indication values of the region to which the educational institution belongs can be determined. The fire emergency simulation of the pre-management educational institution region is carried out, and the fire emergency simulation evaluation index of the pre-management educational institution region is evaluated. Finally, the fire emergency simulation process of the pre-management educational institution region is input into the big data fire education cloud platform and visually displayed, so as to improve the emergency response capability to real fire events and improve the overall fire safety management level of the big data fire education cloud platform in the educational institution.

Description

Technical Field

[0001] This invention relates to the field of fire emergency response technology, specifically a fire emergency management method for a big data education platform used in educational institutions. Background Technology

[0002] Currently, with the continuous expansion of the number and scale of various schools, training institutions, and other educational venues, which typically have high population density and complex building structures, higher requirements are placed on fire safety. However, existing fire emergency management systems have the following problems:

[0003] Traditional fire alarm systems can only extinguish fires by following pre-set emergency procedures when a fire occurs. Furthermore, current fire emergency management plans lack effective emergency drill mechanisms when predicting fires. As a result, the ability to prevent, mitigate, and respond to fires is not effectively improved, ultimately failing to enhance the overall fire safety management level of educational venues.

[0004] For example, invention patent CN112215564A discloses a smart fire emergency management system and its method. The smart fire emergency management method includes the following steps: Step S1: The smart fire emergency management system guides the user to configure one or more modules of the basic management module, education and training module, equipment management module, and on-site management module; Step S2: The smart fire emergency management system guides the user to input one or more modules of the dual prevention module, emergency response module, event management module, operation management module, and target management module. The disclosed smart fire emergency management system and its method help improve the level of integration and the coverage of control.

[0005] For example, invention patent CN112348729A discloses an integrated smart fire safety big data platform system, including a smart operation large screen module, an IoT device management module, a fire intelligent early warning and monitoring module, a fire safety hazard inspection module, a smart big data application analysis module, a fire safety publicity and education module, a fire safety business management module, and a unit management module; all of the above modules are controlled by a data analysis and control module. This system can: 1) construct a real-time and effective fire safety supervision network through the collection and analysis of various effective fire information; and 2) construct a precise urban rapid response system through the real-time joint operations of various fire forces, thereby improving fire fighting and rescue capabilities and fire prevention supervision and management levels, and further enhancing the city's fire prevention, disaster reduction, and relief capabilities.

[0006] Based on the above technical solutions, it was found that the existing emergency procedures are still followed in the technical solutions for fire emergency management. This extensive approach to fire emergency management is not conducive to refined emergency control. At the same time, due to the large fluctuations in the availability of fire-fighting equipment, there is a possibility of inaccurate prediction results, which leads to the inability to carry out efficient fire emergency response during the event and fails to improve the level of fire safety management. Summary of the Invention

[0007] To address the shortcomings of existing technologies, this invention provides a fire emergency management method for a big data education platform used in educational institutions, which can effectively solve the problems mentioned in the background technology.

[0008] To achieve the above objectives, the present invention provides the following technical solution: a fire emergency management method for a big data education platform for educational institutions, comprising: patrol management judgment: collecting structural data of the area to which the educational institution belongs and patrol management data of the big data fire education cloud platform, thereby determining the patrol indicator value of the area to which the educational institution belongs, and comparing it with a preset patrol indicator threshold; fire emergency simulation evaluation: marking the area to which the educational institution belongs with the patrol indicator value greater than the patrol indicator threshold as a pre-managed educational institution area, thereby conducting a fire emergency simulation on the pre-managed educational institution area, obtaining the fire emergency simulation data of the pre-managed educational institution area, and evaluating the fire emergency simulation evaluation index of the pre-managed educational institution area; fire emergency management feedback: comparing the fire emergency simulation evaluation index of the pre-managed educational institution area with a preset fire emergency simulation evaluation reference index, and finally providing management feedback on the fire emergency simulation process of the pre-managed educational institution area.

[0009] As a further method, the inspection indicator values ​​of the area where the educational institution is located are compared with preset inspection indicator thresholds. The specific comparison process is as follows:

[0010] If the inspection indicator value of the area where the educational institution is located is greater than the preset inspection indicator threshold, a fire emergency simulation will be conducted for the area where the educational institution is located. If the inspection indicator value of the area where the educational institution is located is less than or equal to the preset inspection indicator threshold, the inspection indicator values ​​of various areas will be extracted, and the order of the inspection indicator values ​​will be used as the order of fire inspection and investigation. The order of fire inspection and investigation will be transmitted to the big data fire education cloud platform for management and prompting.

[0011] As a further method, the management feedback of the fire emergency simulation process in the pre-managed educational institution area is as follows:

[0012] The fire emergency simulation evaluation index of the pre-managed educational institution area is compared with the preset fire emergency simulation evaluation reference index. If the fire emergency simulation evaluation index of the pre-managed educational institution area is greater than the preset fire emergency simulation evaluation reference index, then a fire emergency simulation is conducted on the pre-managed educational institution area, the fire emergency simulation process of the pre-managed educational institution area is extracted, and the fire emergency simulation process of the pre-managed educational institution area is input into the big data fire education cloud platform for visualization. If the fire emergency simulation evaluation index of the pre-managed educational institution area is equal to or less than the fire emergency simulation evaluation reference index, then management feedback is provided on the fire emergency simulation process of the pre-managed educational institution area.

[0013] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects:

[0014] (1) This invention provides a fire emergency management method for a big data education platform for educational institutions. It quantitatively compares the structural data of the area to which the educational institution belongs with the inspection management data of the big data fire education cloud platform. By integrating the quantitative analysis of data from fire equipment, sensors and cameras, it can determine more accurate inspection index values ​​for the area to which the educational institution belongs. It conducts fire emergency simulation on the pre-managed educational institution area and evaluates the fire emergency simulation evaluation index of the pre-managed educational institution area, which greatly reduces the possibility of inaccurate pre-disaster prediction results. It compares the results with the preset fire emergency simulation evaluation reference index and inputs the fire emergency simulation process of the pre-managed educational institution area into the big data fire education cloud platform for visualization. This improves the emergency response capability to real fire events, that is, it enables efficient fire emergency response during fire accidents, and ultimately improves the overall fire safety management level of educational institutions.

[0015] (2) This invention collects structural data of the area where the educational institution is located and inspection and management data of the big data fire education cloud platform. By conducting comprehensive inspection and monitoring of the educational institution, that is, conducting targeted and detailed inspections of fire sensors, fire cameras and fire equipment, the inspection index value of the area where the educational institution is located can be obtained, timely discover and take corresponding measures to solve the fire hazard areas in the educational institution that are not inspected, and improve the accuracy of subsequent fire warnings.

[0016] (3) This invention conducts fire emergency simulation on the pre-managed educational institution area and obtains fire emergency simulation data of the pre-managed educational institution area. By comparing the fire emergency simulation evaluation index of the pre-managed educational institution area with the preset fire emergency simulation evaluation reference index, the fire emergency simulation process of the pre-managed educational institution area is finally input into the big data fire education cloud platform and visualized. This makes the big data fire education cloud platform an efficient and intelligent fire management system. Once an abnormal situation or fire signal is detected, the big data fire education cloud platform can immediately activate the emergency simulation plan and respond to the accident safely and accurately, thereby improving the management of fire emergency. Attached Figure Description

[0017] The present invention will be further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present invention. For those skilled in the art, other drawings can be obtained based on the following drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of the method flow of the present invention. Detailed Implementation

[0019] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0020] The following section provides a detailed explanation of the application scenarios of this invention and the steps of the method:

[0021] This invention applies to educational institutions in large, densely populated areas. Due to their complex structure and high personnel density, accurate, efficient, and safe response plans before an accident occurs can ensure the substantial safety of the area and enable efficient firefighting efforts during an accident. Therefore, this invention focuses on exploring the effectiveness of pre-accident fire emergency management and makes a series of judgment analyses, as follows:

[0022] The statistical analysis tools (such as SQL, R, and Python) built into the Big Data Fire Safety Education Cloud Platform are used to statistically analyze and extract structural data (i.e., the functional coverage area and building volume of this invention) from the regional database (the data repository within the Big Data Fire Safety Education Cloud Platform, which will be explained in detail later). This data is then transmitted to the Big Data Fire Safety Education Cloud Platform in real time via an edge computing gateway. Simultaneously, the Big Data Fire Safety Education Cloud Platform has an integrated intelligent inspection device inspection page to collect data related to inspection management (i.e., the monitoring coverage area of ​​fire cameras, the number of qualified fire sensors, the operational output inspection data of fire cameras, and the corresponding fire equipment data). Historical fault data); The big data fire safety education cloud platform utilizes its built-in data analysis module to determine the inspection indicator value of the area where the educational institution is located based on real-time received structural data, inspection management data, and historical fault data. If the inspection indicator value of the area where the educational institution is located exceeds the preset inspection indicator threshold, the big data fire safety education cloud platform marks the area as a pre-managed educational institution area. The big data fire safety education cloud platform will automatically trigger the corresponding fire emergency simulation system through cloud notification services, and simultaneously send the structural data, inspection management data, and other relevant data requiring fire simulation (e.g., fire sensor locations, fire camera locations, online status, etc.) corresponding to the pre-managed educational institution area to the fire safety education cloud platform. The emergency simulation system allows for comprehensive emergency simulation of pre-managed educational institution areas by simulating fire scenarios and planning evacuation routes. (This simulation is based on structural data, inspection and management data, and other relevant data required for fire simulation within the pre-managed educational institution area. For example, if the main building volume of a certain type of structure in the pre-managed educational institution area is 100 cubic meters, then the simulated building volume in the emergency simulation process should also be 100 cubic meters.) During the emergency simulation, the big data fire education cloud platform utilizes the real-time monitoring interface of the fire emergency simulation system to obtain real-time data on the pre-managed educational institution area. The fire emergency simulation data is processed through a built-in data analysis module to ultimately assess the fire emergency simulation evaluation index of the pre-managed educational institution area. The big data fire education cloud platform compares the assessed fire emergency simulation evaluation index with a preset fire emergency simulation evaluation reference index. If the fire emergency simulation evaluation index of the pre-managed educational institution area is greater than the fire emergency simulation evaluation reference index, the big data fire education cloud platform notifies the fire emergency simulation system, which then automatically uploads the simulation process to the big data fire education cloud platform through the data input interface. The big data fire education cloud platform then visualizes the simulation process using visualization tools (such as large screen displays and mobile device displays).

[0023] The above process can be interpreted in another way:

[0024] The Big Data Fire Safety Education Cloud Platform is a comprehensive platform for fire management in the area where educational institutions are located. It has multiple capabilities, including data acquisition, data processing, signal transmission, and signal reception. Therefore, it can perform operations such as collecting structural data and determining patrol indicators as described in this invention. The role of the edge computing gateway is to perform preliminary data processing and analysis near the data generation point, reducing the bandwidth consumption of transmitting large amounts of raw data to the cloud and improving the real-time performance and response speed of data processing. It can integrate multiple communication protocols, support the access of different types of sensor data, and then upload the processed key information to the Big Data Fire Safety Education Cloud Platform for subsequent data analysis.

[0025] The big data fire safety education cloud platform has a built-in data analysis module that integrates advanced technologies such as big data processing, machine learning, and artificial intelligence. This enables the platform to provide comprehensive, accurate, and real-time data analysis services, thereby improving the effectiveness of fire safety education and management.

[0026] The big data fire safety education cloud platform marks this area as a pre-managed educational institution area. This marking is usually displayed in the platform's visual interface in the form of a specific color, icon, or label for easy and quick identification.

[0027] The big data fire safety education cloud platform will automatically trigger the corresponding fire emergency simulation system through cloud notification services. The conditions for triggering the fire emergency simulation can be defined in the platform's backend settings, such as when the inspection indicators of a certain area exceed a preset threshold. Once the triggering conditions are met, the platform's cloud notification service will automatically start. This is typically achieved through API calls, email services, SMS services, or integrated instant messaging tools. For example, the platform can use API calls to notify relevant safety management personnel about the upcoming fire emergency simulation. Simultaneously, to ensure the fire emergency simulation system can perform accurately, the platform needs to synchronously send the structural data, inspection management data, and other relevant data required for fire simulation to the pre-managed educational institution area. This can be done through the following methods:

[0028] The platform exchanges data with the fire emergency simulation system through an API interface. The API interface allows the platform to extract the required data (such as spatial layout, equipment location, historical inspection records, etc.) from the database and send the data to the fire emergency simulation system in JSON, XML or other formats. After receiving the data, the fire emergency simulation system will verify the data to ensure its integrity and accuracy. Then, the system will build or update the simulation scenario based on the received data to conduct simulated fire drills or training.

[0029] The fire emergency simulation system is a highly realistic and comprehensive training tool that can construct realistic scenarios such as buildings, city blocks, or factory interiors (this invention is mainly for educational institutions). It can also simulate different types of fires, including initial fires and rapidly spreading fires, and supports drills for various emergency response strategies, such as evacuating people, using fire-fighting equipment, and carrying out fire-fighting operations. This fire emergency simulation system provides a realistic and accurate emergency foundation for actual rescue work.

[0030] If the fire emergency simulation evaluation index of the pre-managed educational institution area is greater than the fire emergency simulation evaluation reference index, the big data fire education cloud platform will notify the fire emergency simulation system to take the next step. The notification method can be that the big data fire education cloud platform connects with the fire emergency simulation system through the API interface. This method does not require manual intervention, and the systems directly interact with each other and execute commands.

[0031] After receiving a notification, the fire emergency simulation system automatically uploads the simulation process to the big data fire safety education cloud platform through the data input interface. The fire emergency simulation system sends the data generated during the simulation (such as personnel evacuation routes, time, equipment usage, emergency response efficiency, etc.) to the cloud platform through API interface or data transmission protocol (such as FTP, SFTP). In this way, the big data fire safety education cloud platform can obtain the simulation process of the fire emergency simulation system in real time for subsequent analysis, optimization and education purposes.

[0032] Reference Figure 1 As shown, the present invention provides a fire emergency management method for a big data education platform for educational institutions, including: patrol management judgment: collecting structural data of the area to which the educational institution belongs and patrol management data of the big data fire education cloud platform, thereby determining the patrol indicator value of the area to which the educational institution belongs, and comparing it with a preset patrol indicator threshold.

[0033] It should be explained that the reason for determining the inspection index values ​​for the area where the educational institution is located and comparing them with the preset inspection index thresholds is that subsequent fire emergency simulations require certain simulation resources. If the data input before the simulation deviates too much from the actual situation, the subsequent emergency simulation will be largely ineffective, wasting resources and rendering the work ineffective. Therefore, in order to ensure that the subsequent fire simulations have simulation data that is closer to and more accurate than the actual situation, efficient data determination is required before the simulation to ensure that the subsequent fire emergency simulation will not have unsatisfactory simulation results due to inaccurate data input.

[0034] Specifically, the inspection indicator values ​​for the area where the educational institution is located are compared with preset inspection indicator thresholds. The specific comparison process is as follows:

[0035] If the inspection indicator value of the area where the educational institution is located is greater than the preset inspection indicator threshold in the fire emergency simulation database, it indicates that the institution's inspection and management work has met or exceeded the preset fire inspection standards. In other words, the institution's performance in fire safety inspections, maintenance of fire-fighting facilities, and ensuring unobstructed fire exits is good and meets or exceeds the prescribed inspection requirements. The inspection indicator threshold is a pre-set inspection qualification standard or indicator in the fire emergency simulation database, used to measure the institution's management level in fire safety inspections and to determine whether an institution's fire safety inspections have reached the required level. A fire emergency simulation is then conducted on the area where the educational institution is located. If the inspection indicator value of the area is less than or equal to the preset inspection indicator threshold, it indicates that the area has performed well in fire safety inspections, maintenance of fire-fighting facilities, and ensuring unobstructed fire exits. If there are deficiencies or non-compliance with regulations, then the inspection indicator values ​​for various areas are extracted. Specifically, areas with inspection indicator values ​​less than or equal to preset inspection indicator thresholds are extracted (this indicates that the inspection indicator values ​​for multiple categories of areas are lower than the standard values; the inspection indicator values ​​for each category of area can be equal to or less than the categories of areas within the educational institution's jurisdiction, because it is possible that some areas have inspection indicator values ​​greater than the preset threshold, while others have values ​​less than or equal to the preset threshold). The resulting order of the inspection indicator values ​​is arranged from largest to smallest, serving as the order for fire safety inspections. This order is then transmitted to the big data fire safety education cloud platform for management and notification. The specific management process is as follows:

[0036] First, the big data fire safety education cloud platform, through on-site inspections or other methods, identifies various areas where the inspection indicator values ​​are less than or equal to preset inspection indicator thresholds, as well as specific problems and deficiencies in inspection management. For the identified problems, detailed improvement measures and timelines are developed, which may include equipment repair or replacement, and the installation of fire-fighting equipment in areas not covered by fire emergency systems. The improvement plan is then implemented (inspecting and checking each area according to the fire safety inspection sequence to prevent loopholes in the inspection of certain areas), while a monitoring mechanism is established to ensure the effective implementation of all measures. This may involve regular reviews and continuous monitoring of equipment status. Based on the implementation results, the inspection indicator values ​​of the aforementioned areas are reassessed, and a comprehensive judgment is made on whether the inspection management of the area where the educational institution is located is qualified, ensuring high-quality fire safety management.

[0037] Furthermore, the specific process for collecting structural data on the region to which the educational institution is located is as follows:

[0038] The areas where educational institutions are located are divided according to functional area types, categorized into various types. The Big Data Fire Safety Education Cloud Platform uses GIS (Geographic Information System) to collect geographic information data such as the geographical location, building floor plans, and functional zoning maps of educational institutions. It also collects attribute data, such as purpose, area, capacity, and distribution of fire safety facilities. The geographic information data and attribute data are integrated to form a unified regional database (stored within the Big Data Fire Safety Education Cloud Platform). Using machine learning algorithms (such as cluster analysis) built into the Big Data Fire Safety Education Cloud Platform, educational institutions are automatically classified according to their attribute characteristics, such as teaching areas, experimental areas, office areas, dormitory areas, and canteen areas, thus obtaining the specific categories defined by functional area types. Each functional area is assigned a unique identifier (ID). The classification information and structural data (such as area, number of fire safety facilities, and capacity) of each functional area are stored in the regional database. The Big Data Fire Safety Education Cloud Platform then uses its built-in statistical analysis tools (such as SQL, R, and Python) to statistically extract the structural data of each type of area from the regional database.

[0039] The structural data for each type of area includes the functional coverage area and the building volume. The functional coverage area represents the land area occupied by each type of area. For example, if a type of area has one floor, the land area is the functional coverage area of ​​one floor. If a type of area has five floors, the land area is the functional coverage area of ​​five floors. The building volume represents the total volume of the building. For example, if a type of area is a teaching area with three floors, the building volume is the total spatial volume of the three-story teaching area, including the internal classroom area, corridor area, and stairwell area.

[0040] The structural data of various regions are used as the structural data of the regions to which the educational institutions belong.

[0041] Specifically, the inspection management data of the big data fire safety education cloud platform refers to the inspection data most recently conducted before the fire emergency simulation. It represents the time spent conducting fire safety inspections of educational institutions, typically including the entire process from the start of the inspection to the completion of all scheduled inspection items. Specifically, it includes the fire camera monitoring coverage area of ​​various regions, the number of qualified fire sensors in various regions, and the operational output inspection data corresponding to each fire camera in each region. The inspection management data of the big data fire safety education cloud platform is obtained from the integrated intelligent inspection device inspection page of the platform itself; the detailed acquisition process is not explained in this example. The fire camera monitoring coverage area represents the area that the fire camera can monitor during inspection; this area is less than or equal to the area covered by the aforementioned functions.

[0042] The operational output inspection data for each fire camera in each area includes the online duration, memory usage, and minimum screen resolution for each fire camera in each area.

[0043] Furthermore, the specific process for determining the inspection indicator values ​​for the area to which the educational institution belongs is as follows:

[0044] The monitoring coverage area of ​​the fire cameras in each type of area is compared with the functional coverage area of ​​each type of area to obtain the monitoring coverage area ratio of each type of area. Specifically, the monitoring coverage area of ​​the fire cameras is divided by the functional coverage area.

[0045] The building volume of each type of area is matched with the number of qualified fire sensors corresponding to each pre-set building volume interval in the fire emergency simulation database to obtain the number of qualified fire sensors for each type of area. The matching process is as follows:

[0046] Each building volume range corresponds to a fire sensor reference qualified number. By querying the building volume range to which the building volume of a certain type of area belongs, the fire sensor reference qualified number corresponding to that building volume range is the fire sensor reference qualified number for that type of area.

[0047] The above-mentioned building volume range is used to match the corresponding reference number of qualified fire sensors. Specifically, since the space covered by fire sensors is fixed, but fire sensors can be distributed in different locations within a region, there will be overlapping coverage areas. Therefore, when the building volume is similar, there will likely be the same number of fire sensors. In the fire emergency simulation database, a range matching rule has been pre-set. Based on different building volumes, the range of building volume is determined, and thus the reference number of qualified fire sensors is obtained. The specific range matching rule will not be explained in detail in this example, but only for a specific example. For example, if the building volume is 80 cubic meters and 90 cubic meters, the reference number of qualified fire sensors will be 2 in both cases. However, the placement of the fire sensors may be different, and the covered space area will also be different, but ultimately the fire sensors will completely cover the space.

[0048] Based on the monitoring coverage area ratio of various regions, the number of qualified fire sensors in various regions, and the reference number of qualified fire sensors in various regions, the first inspection characteristic index of each region is determined by comprehensive processing, and the specific expression is as follows:

[0049]

[0050] In the formula, MCR k The monitoring coverage area ratio of the k-th category area is specifically the ratio of the area monitored and covered by fire cameras to the fixed building area of ​​the area. The larger the ratio, the closer the area covered by the fire cameras is to the building area.

[0051] The reference ratio for monitoring coverage area of ​​the k-th type of area preset for the fire emergency simulation database refers to the area covered by the fire camera being equal to the fixed floor area of ​​the building in the area, that is, the floor area of ​​the area completely covered by the fire camera.

[0052] CQA k The number of qualified fire sensors in the k-th category area refers to the number of inspections corresponding to the volume of the building covered by the fire sensors.

[0053] The reference number of qualified fire sensors for the k-th category area refers to the number of fire sensors that completely cover the volume of the building's main structure.

[0054] e is a natural constant, k is the number of each type of region, k = 1, 2, 3, ..., p, where p is the total number of types of regions.

[0055] As the first inspection characteristic index for the k-th type of area, in this example, during the inspection of educational institutions, it is crucial to determine whether the fire-fighting equipment (i.e., fire sensors, fire cameras, etc.) can completely cover the area to which the educational institution belongs. This is because if there is a significant discrepancy between the inspection results and the actual building area (e.g., fire cameras do not cover the entire building footprint, or fire sensors fail to cover the entire building volume), it will not only affect real-time accident monitoring but also increase the risk of accident spread. Furthermore, it will negatively impact the subsequent fire emergency simulation in this example. Simultaneously, both fire cameras and fire sensors belong to fire-fighting equipment and are closely related. If fire cameras fail to monitor and cover the entire area, even if fire sensors detect an accident, the central platform cannot view it in real time through the cameras, affecting subsequent rescue efforts. Similarly, if fire sensors fail to monitor and cover the entire building volume, even if fire cameras detect an accident, the central platform cannot send fire extinguishing commands to nearby fire sensors, also affecting subsequent rescue efforts. In conclusion, during fire inspections, it is necessary to focus on inspecting the emergency management capabilities of fire-fighting equipment to improve the subsequent efficient accident resolution capabilities.

[0056] Historical fault data for each type of fire-fighting equipment in various regions is obtained, specifically including the number of faults and the duration of each fault. The historical fault data for each type of fire-fighting equipment in various regions is obtained from the integrated intelligent inspection equipment inspection page of the big data fire education cloud platform. The detailed acquisition process is not explained in this example. The fire-fighting equipment includes, but is not limited to, the fire cameras and fire sensors mentioned above.

[0057] Based on the online duration, memory usage, and minimum output resolution of each fire camera in various areas, as well as the number of malfunctions and duration of each malfunction for each fire equipment in various areas, the second inspection characteristic index for each area is determined through comprehensive processing. The specific expression is as follows:

[0058]

[0059] Among them, CPI kc The patrol characterization index for the c-th fire camera in the k-th region is a characterization value obtained by comprehensively processing the online duration, memory usage, and minimum screen output resolution of the fire camera.

[0060] B1 is the patrol characterization weight factor corresponding to the fire camera preset in the fire emergency simulation database. When using it, the patrol characterization weight factor corresponding to the fire camera can be directly obtained from the fire emergency simulation database. The correspondence can be a pre-set mapping relationship. For example, the memory usage of the fire camera and the patrol characterization weight factor corresponding to the fire camera preset in the fire emergency simulation database form a mapping set. The real-time memory usage of the fire camera is mapped to obtain the patrol characterization weight factor corresponding to the fire camera. The mapping relationship can be one-to-one or many-to-one. In this example, its value range is [0, 1].

[0061] FPI ka The inspection characterization index for the a-th fire-fighting equipment in the k-th region is a characterization value obtained by comprehensively processing the number of faults occurring and the duration of each fault.

[0062] B2 is the pre-set inspection characterization weight factor for fire equipment in the fire emergency simulation database. When using it, the inspection characterization weight factor for fire equipment can be directly obtained from the fire emergency simulation database. The correspondence can be a pre-set mapping relationship. For example, the number of faults corresponding to fire equipment and the pre-set inspection characterization weight factor for fire equipment in the fire emergency simulation database form a mapping set. The real-time fault occurrence number mapping set of fire equipment can be used to obtain the inspection characterization weight factor for fire equipment. The mapping relationship can be one-to-one or many-to-one. In this example, its value range is [0, 1].

[0063]

[0064] In the formula, OLT kc The online duration of the c-th fire camera in the k-th region represents the online time from the start of the fire camera's online status to the current time, excluding offline, fault, and other times.

[0065] The online reference duration for the c-th fire camera preset in the fire emergency simulation database represents the reference online time length set for the fire camera.

[0066] MEM kc Let represent the memory usage of the c-th fire camera in the k-th region. This indicates that during the real-time video processing of the fire camera, the memory usage includes video buffering and temporary memory required for encoding / decoding.

[0067] The preset memory reference usage for the c-th fire camera in the fire emergency simulation database represents a reference memory usage value defined when the fire camera is processing video in real time.

[0068] LMR kc Let be the minimum resolution of the output image of the c-th fire camera in the k-th area, representing the minimum resolution of the output image of the fire camera during the inspection process.

[0069] LMR Δ The preset resolution for the output of the fire camera in the fire emergency simulation database represents the minimum preset resolution of the output image from the fire camera. If the resolution is lower than this value, the output image from the fire camera will be blurry or stuttering.

[0070] FC ka Let be the number of failures corresponding to the a-th fire-fighting equipment in the k-th area, representing the total number of failures that occurred from the start of operation of the fire-fighting equipment to the time of this inspection.

[0071] The number of permissible failures for the a-th fire-fighting equipment pre-set in the fire emergency simulation database represents the maximum permissible number of failures for the specified fire-fighting equipment.

[0072] FD kaq Let q represent the duration of the qth failure corresponding to the ath fire-fighting equipment in the kth category area. This indicates the duration of each failure of the fire-fighting equipment, such as the time during which the image is not monitored in real time when a fire camera malfunctions.

[0073] For the second inspection characteristic index of the k-th category area, in this example, the fire camera is not only related to the area structure mentioned above, but its own factors will also affect the inspection results. That is, if the online duration of the fire camera deviates from the specified reference value, the shorter the online duration of the fire camera, the less conducive it is to the alarm behavior when an accident occurs. Similarly, if the online duration of the fire camera is longer, the longer the usage time, the more likely it is to have negative phenomena such as a blurry output image due to environmental factors during use, which may lead to alarm errors. In addition, during the output process, due to the blurry image, the memory usage will fluctuate greatly, that is, the memory usage exceeds the defined reference value. At the same time, if the memory usage is much lower than the defined reference value, the output image will differ greatly from the actual image, and there is a possibility of image loss. That is, the resolution of the output image is lower than the specified minimum value, which is not conducive to the subsequent actions of the main platform to locate the location of the accident through the transmitted image, and increases the possibility of the accident spreading.

[0074] During fire safety inspections of educational institutions, it is necessary not only to strictly inspect the operation of fire cameras, but also to check other fire equipment, which can significantly impact fire emergency response. If fire equipment experiences a high number of malfunctions, exceeding the prescribed number of malfunctions, and is not replaced in a timely manner, it will be unable to provide effective emergency response in the event of an accident. Furthermore, the more malfunctions a fire equipment experiences, the more problems will arise, leading to longer repair times. The repair time is essentially the duration of the malfunction, meaning that the duration of the malfunction will increase with the number of malfunctions, ultimately hindering the efficient resolution of accidents.

[0075] In summary, both the operation and malfunction of fire-fighting equipment will affect the inspection results of educational institutions. Furthermore, the operation and malfunction of fire-fighting equipment are closely related. If the operating efficiency of fire-fighting equipment is low (i.e., online time deviates from the reference value, memory usage deviates from the reference value, or screen output resolution is lower than the defined value), it indicates a problem in the operation of the fire-fighting equipment, increasing the risk of equipment malfunction and inoperability. If the number of malfunctions exceeds the permitted number or the malfunction time is prolonged, repair or even replacement is required after the inspection, increasing inspection time. Therefore, the negative value of the inspection indicator for the area where the educational institution is located in this expression increases, ultimately affecting the subsequent simulated emergency response.

[0076] k is the number of each type of area, k = 1, 2, 3, ..., p, p is the total number of types of areas, c is the number of each fire camera, c = 1, 2, 3, ..., f, f is the total number of fire cameras, a is the number of each fire equipment, a = 1, 2, 3, ..., i, i is the total number of fire equipment, q is the number of each fault, q = 1, 2, 3, ..., u, u is the total number of faults.

[0077] By combining the first and second inspection characterization indicators of various regions, the inspection index values ​​of the regions where educational institutions are located are obtained through data processing. These inspection index values ​​are used to characterize the management level of the regions where educational institutions are located and to provide data basis for fire emergency simulation of pre-managed educational institution regions.

[0078] Specifically, the inspection indicator value for the area where the educational institution is located is expressed as follows:

[0079]

[0080] In the formula, The first inspection characteristic index for the k-th type of region. This is the second inspection characterization index for the k-th type of region.

[0081] A1 is the weight factor corresponding to the first patrol characterization index preset in the fire emergency simulation database. When using it, the weight factor corresponding to the first patrol characterization index can be directly obtained from the fire emergency simulation database. The correspondence can be a pre-set mapping relationship. For example, the monitoring coverage area ratio and the weight factor corresponding to the first patrol characterization index preset in the fire emergency simulation database form a mapping set. The real-time monitoring coverage area ratio mapping set is used to obtain the weight factor corresponding to the first patrol characterization index. The mapping relationship can be one-to-one or many-to-one. In this example, its value range is [0, 1].

[0082] A2 is the weight factor corresponding to the second patrol characterization index preset in the fire emergency simulation database. When using it, the weight factor corresponding to the second patrol characterization index can be directly obtained from the fire emergency simulation database. The correspondence can be a pre-set mapping relationship. For example, the online duration of fire cameras and the weight factor corresponding to the second patrol characterization index preset in the fire emergency simulation database form a mapping set. The weight factor corresponding to the second patrol characterization index is obtained by mapping the real-time online duration of fire cameras. The mapping relationship can be one-to-one or many-to-one. In this example, its value range is [0, 1].

[0083] k is the number of each type of region, k = 1, 2, 3, ..., p, where p is the total number of types of regions.

[0084] ξ represents the inspection indicator value for the area where the educational institution is located. In this example, inspecting the educational institution involves multiple factors, including not only checking the operation and malfunction of various fire-fighting equipment, but also the structure of the educational institution area itself, which affects the inspection results. To ensure the quality of the inspection results, it is necessary to ensure that the fire-fighting equipment can cover the entire structure of the educational institution area. Since accidents can occur in various locations within the educational institution area and cannot be quantitatively assessed, the inspection must ensure that the fire-fighting equipment can monitor all locations in the area. At the same time, it is also necessary to ensure that the fire-fighting equipment can transmit images and perform accident alarms in real time. This requires analyzing the operation and malfunction of the fire-fighting equipment and carrying out timely repairs or replacements to provide data support for the effective use of resources in subsequent fire emergency simulations.

[0085] In one specific embodiment, the present invention collects structural data of the area where the educational institution is located and inspection and management data of the big data fire safety education cloud platform. By conducting comprehensive inspection and monitoring of the educational institution, that is, by conducting targeted and detailed inspections of fire sensors, fire cameras and fire equipment, the inspection index values ​​of the area where the educational institution is located can be obtained, and corresponding measures can be taken in a timely manner to solve the fire hazard areas in the educational institution that fail to meet the inspection standards, thereby improving the accuracy of subsequent fire warnings.

[0086] Fire emergency simulation assessment: The areas where educational institutions belong to the region with inspection indicator values ​​greater than the inspection indicator threshold are marked as pre-managed educational institution areas. Fire emergency simulations are then conducted on these pre-managed educational institution areas to obtain fire emergency simulation data and to evaluate the fire emergency simulation assessment index of these areas.

[0087] It should be noted that the aforementioned fire emergency simulation of the pre-managed educational institution area is because the fire emergency simulation system can conduct comprehensive emergency simulation of the pre-managed educational institution area through methods such as simulating fire scenarios and planning personnel evacuation routes. The specific simulation process is as follows:

[0088] The simulation automatically starts based on specific conditions (such as sensors detecting smoke or abnormal temperature). Once the fire trigger point is determined, the fire emergency simulation system begins to simulate the fire scenario, including the following elements:

[0089] The fire emergency simulation system simulates different types of fires (such as electrical fires, chemical fires, and oil fires) and their sources (such as electrical equipment and chemical laboratories). Based on factors such as fire type, building materials, and ventilation conditions, the system simulates the fire spread process, including the speed and direction of flame and smoke diffusion, and simulates temperature changes after a fire occurs and their impact on the environment and building structure. Simultaneously with the fire scenario simulation, the system begins simulating and planning personnel evacuation routes.

[0090] Based on the building layout, fire location, fire spread direction, and current environmental conditions, the system automatically generates the optimal evacuation route. Since the specific route generation process is automatically generated by the fire emergency simulation system, and this automatic generation process is not the focus of this example, it will not be explained in detail here. Considering the density and flow speed of people within the building (based on the characteristics of different groups, such as students, teachers, and people with disabilities), the system simulates the movement of people during evacuation. The system simulates obstacles that may be encountered during evacuation (such as collapsed building materials, closed doors) and crowd congestion, dynamically adjusting the evacuation route. During the evacuation process, the system also simulates emergency response measures.

[0091] The system simulates the use and effectiveness of fire hydrants, fire extinguishers, and other firefighting equipment; it also simulates the arrival time, movement routes, and firefighting operations of firefighters; and it simulates the arrival of emergency medical teams and the treatment of injured personnel. As the emergency response progresses, the system simulates the control and extinguishing of the fire.

[0092] The system simulates the use of extinguishing agents (such as water, foam, and dry powder) and the gradual control of the fire. After the main fire is extinguished, the system assesses the risk of reignition and potential fire sources that require further treatment. It also simulates the cooling of the building and the emission of smoke to ensure safety. Finally, it handles potential fire sources to complete the entire fire emergency simulation process. During this process, the fire emergency simulation system continuously monitors temperature changes after fire extinguishing. If the temperature remains higher than the preset temperature threshold in the fire emergency simulation database for a period of time after fire extinguishing (the temperature threshold here refers to the preset temperature value used to determine whether there is a risk of reignition after fire extinguishing), it may indicate a potential risk of reignition. Therefore, the fire emergency simulation system can determine that the fire has not been completely extinguished.

[0093] Before conducting a simulation, the fire emergency simulation system requires the input of various data related to the educational institution area, including but not limited to:

[0094] The educational institution's building floor plan, floor plan, room structure diagram, building materials, fire resistance rating, and fire compartmentation information; the distribution of personnel within the educational institution, including the number and location of faculty, staff, students, and visitors, information on special groups (such as young children, the elderly, and people with disabilities), and personnel flow characteristics (such as peak hours and personnel density distribution); a distribution map of fire protection facilities, including fire extinguishers, fire hydrants, fire alarms, emergency lighting, etc., and the location and accessibility data of safety exits; environmental data (such as indoor and outdoor temperature, humidity, and wind speed), historical fire records and emergency response data of the educational institution; real-time monitoring data, such as camera video streams, fire alarm system status, sensor data (smoke, temperature, etc.), and real-time pedestrian flow monitoring data, used to dynamically adjust evacuation routes and strategies.

[0095] Specifically, the fire emergency simulation data for the pre-managed educational institution area includes the total fire simulation duration, evacuation duration, response time of each fire-fighting equipment, and total amount of extinguishing agent used. All of the above fire emergency simulation data are extracted by the big data fire education cloud platform using the real-time monitoring interface of the fire emergency simulation system. The evacuation duration refers to the length of time that all personnel in the area are away from the accident site and in a safe location, and the total fire simulation duration refers to the length of time from the start of the accident to the complete resolution of the accident.

[0096] Furthermore, the assessment of the fire emergency simulation evaluation index for the pre-managed educational institution area is as follows:

[0097] The evacuation time of the pre-managed educational institution area is compared with the total fire simulation time to obtain the evacuation time ratio of the pre-managed educational institution area, specifically the evacuation time divided by the total fire simulation time.

[0098] The response times of each fire-fighting device in the pre-managed educational institution area are accumulated and averaged sequentially. Specifically, the response times of each fire-fighting device in the pre-managed educational institution area are first accumulated to obtain the total response time of the fire-fighting devices in the pre-managed educational institution area. Then, the average response time is calculated by dividing the total number of fire-fighting devices by the average response time of the fire-fighting devices in the pre-managed educational institution area.

[0099] Therefore, based on the evacuation time ratio of the pre-managed educational institution area, the average response time of the fire-fighting equipment in the pre-managed educational institution area, and the total amount of fire extinguishing agent used in the pre-managed educational institution area, a fire emergency simulation evaluation index for the pre-managed educational institution area is comprehensively evaluated. The fire emergency simulation evaluation index for the pre-managed educational institution area is used to characterize the degree of evaluation of the fire emergency simulation in the pre-managed educational institution area.

[0100] Specifically, the fire emergency simulation evaluation index for the pre-managed educational institution area is expressed as follows:

[0101]

[0102] In the formula, EPR is the proportion of evacuation time in the pre-managed educational institution area, representing the ratio of the evacuation time in this fire emergency simulation to the total fire duration.

[0103] ARR is the average response time of fire equipment in the pre-managed educational institution area. It represents the average response time of fire equipment in this fire emergency simulation. The response time of each fire equipment represents the length of time from the time of the accident to the time when the fire equipment alarms.

[0104] TFA stands for Total Fire Extinguishing Agents Used in Pre-Managed Educational Institution Areas. It represents the total amount of various fire extinguishing agents used to extinguish fires, including but not limited to foam extinguishing agents, dry powder extinguishing agents, carbon dioxide extinguishing agents, and metal extinguishing agents.

[0105] TFA Δ The preset reference total amount of extinguishing agent used in the fire emergency simulation database represents the reference amount of extinguishing agent to be used in this fire emergency simulation.

[0106] E1 is the influence factor corresponding to the unit value of the evacuation time ratio preset in the fire emergency simulation database. When using it, the influence factor corresponding to the unit value of the evacuation time ratio can be directly obtained from the fire emergency simulation database. The correspondence can be a pre-set mapping relationship. For example, the evacuation time ratio and the influence factor corresponding to the unit value of the evacuation time ratio preset in the fire emergency simulation database form a mapping set. The influence factor corresponding to the unit value of the evacuation time ratio is obtained from the real-time evacuation time ratio mapping set. The mapping relationship can be one-to-one or many-to-one. In this example, its value range is [0, 1].

[0107] E2 is the influence factor corresponding to the unit value of the average response time of fire equipment preset in the fire emergency simulation database. When using it, the influence factor corresponding to the unit value of the average response time of fire equipment can be directly obtained from the fire emergency simulation database. The correspondence can be a pre-set mapping relationship. For example, the average response time of fire equipment and the influence factor corresponding to the unit value of the average response time of fire equipment preset in the fire emergency simulation database form a mapping set. The influence factor corresponding to the unit value of the average response time of fire equipment can be obtained from the real-time average response time mapping set. The mapping relationship can be one-to-one or many-to-one. In this example, its value range is [0, 1].

[0108] e is a natural constant.

[0109] ψ represents the fire emergency simulation evaluation index for the pre-managed educational institution area. In this example, to determine whether the simulated fire protection of the educational institution area exceeds the prescribed effective simulation process, a quantitative analysis of the simulation process data is required. If the response time of the fire-fighting equipment is long during an accident, it will increase the spread of the accident. At the same time, if personnel receive the instruction to evacuate to the safe area late, there is a possibility that some personnel will not evacuate safely according to the instructions. This increases the evacuation time, meaning that the simulated evacuation time accounts for too large a proportion of the total fire protection time. This not only increases the possibility of personnel being in danger, but also leads to the ineffective implementation of subsequent emergency work. That is, the extinguishing agent is not effectively aimed at the fire source, and the amount of extinguishing agent used is higher than the predicted reference amount, making the fire emergency simulation inefficient and reducing its effectiveness. Furthermore, if the amount of extinguishing agent used is lower than the predicted reference amount, there is a possibility that the fire source is not completely extinguished, which also makes the fire emergency simulation inefficient. In summary, the response time of the fire-fighting equipment, the proportion of evacuation time, and the amount of extinguishing agent used can comprehensively reflect the effectiveness of this fire emergency simulation.

[0110] In one specific embodiment, the present invention conducts fire emergency simulation on the pre-managed educational institution area and acquires fire emergency simulation data of the pre-managed educational institution area. By comparing the evaluated fire emergency simulation index of the pre-managed educational institution area with the preset fire emergency simulation evaluation reference index, the fire emergency simulation process of the pre-managed educational institution area is finally input into the big data fire education cloud platform and visualized. This makes the big data fire education cloud platform an efficient and intelligent fire management system. Once an abnormal situation or fire signal is detected, the big data fire education cloud platform can immediately activate the emergency simulation plan and respond to the accident safely and accurately, thereby improving the management of fire emergency.

[0111] Fire emergency management feedback: The fire emergency simulation evaluation index of the pre-managed educational institution area is compared with the preset fire emergency simulation evaluation reference index, and finally the fire emergency simulation process of the pre-managed educational institution area is managed and feedback is provided.

[0112] Specifically, the management feedback process for the fire emergency simulation of the pre-managed educational institution area is as follows:

[0113] The fire emergency simulation evaluation index of the pre-managed educational institution area is compared with the fire emergency simulation evaluation reference index preset in the fire emergency simulation database. This reference index is a benchmark or target value set based on industry standards, historical accident analysis, and multiple practical applications, representing an ideal or expected level of fire emergency capability. It is used to assess and compare the fire emergency preparedness of different areas. If the fire emergency simulation evaluation index of the pre-managed educational institution area is greater than the preset reference index, it indicates that the area's fire emergency preparedness and response capability exceeds a certain standard or expectation. In other words, the area performs better overall in responding to fires or other emergencies, achieving higher levels in areas such as personnel evacuation speed, fire equipment response time, and emergency resource allocation efficiency. Therefore, by conducting fire emergency simulations on the pre-managed educational institution area and extracting the fire emergency simulation process, this process is input into the big data fire education cloud platform for visualization. The aim is to present the entire fire emergency process intuitively and comprehensively, including but not limited to... The process involves multiple stages, including fire detection, alarm, personnel evacuation, fire equipment response, and dispatch and coordination by the emergency command center. The visualization aims to remind relevant personnel in educational institutions to follow the simulated fire emergency procedures during a fire. If the fire emergency simulation evaluation index of the pre-managed educational institution area is equal to or less than the fire emergency simulation evaluation reference index, it indicates that the area's fire emergency preparedness and response capabilities have failed to meet the preset standards or expectations. This signifies deficiencies or inefficiencies in fire prevention, alarm response, personnel evacuation, and fire equipment operation. In this case, management feedback is provided to the fire emergency simulation process of the pre-managed educational institution area. Management feedback, rather than visualization, is used because the fire emergency simulation system requires certain simulation resources to transmit the simulation process. This feedback aims to prevent the simulation resources from being underutilized and to avoid misleading relevant personnel in the educational institution. Visualizing a poorly evaluated or erroneous process with significant casualties could lead some to mistakenly believe that the simulated operation is correct and efficient, which would be detrimental to fire emergency response in the event of an actual accident. The specific feedback process is as follows:

[0114] First, if the big data fire safety education cloud platform detects that the fire emergency simulation evaluation index is equal to or less than the fire emergency simulation evaluation reference index, it directly sends an early warning signal to the fire emergency simulation system indicating that the simulation process has not met the standard, causing the system to immediately stop the simulation. Simultaneously, the platform identifies reasons such as equipment malfunction or inefficient processes that could cause the low evaluation index. Based on these findings, specific improvement measures and plans are developed, which may include equipment maintenance and updates, optimization of emergency procedures, and strengthened daily management and supervision. These improvement plans are then implemented (the platform sends the plans and measures back to the fire emergency simulation system for a new fire emergency simulation of the pre-managed educational institution area), and the effectiveness is continuously monitored during the simulation to ensure its effectiveness. After the simulation is complete, the platform reassesses the fire emergency simulation evaluation index, comparing it with the reference value to confirm the improvement effect for further adjustments and optimizations. Through this series of management feedback processes, the fire emergency response capabilities of the pre-managed educational institution area can be effectively improved, ensuring a rapid and effective response to actual fires and other emergencies, thus protecting the lives of personnel.

[0115] In one specific embodiment, the present invention provides a fire emergency management method for a big data education platform for educational institutions. This method quantitatively compares the structural data of the educational institution's area with the inspection and management data of the big data fire safety education cloud platform. By integrating quantitative analysis of data from fire equipment, sensors, and cameras, more accurate inspection index values ​​for the educational institution's area can be determined. Fire emergency simulations are then performed on the pre-managed educational institution area, and a fire emergency simulation evaluation index for the pre-managed area is assessed. This significantly reduces the possibility of inaccurate pre-disaster predictions. The simulation results are compared with a preset fire emergency simulation evaluation reference index. The fire emergency simulation process of the pre-managed educational institution area is input into the big data fire safety education cloud platform and visualized, thereby improving the emergency response capability to real fire events. This enables efficient fire emergency response during fire accidents, ultimately improving the overall fire safety management level of educational institutions.

[0116] The above description is merely an example and illustration of the structure of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the structure of the invention or exceed the scope defined by the present invention, and all such modifications and additions should fall within the protection scope of the present invention.

Claims

1. A fire emergency management method for a big data education platform of an educational institution, characterized in that, include: Inspection and management judgment: Collect structural data of the area where the educational institution is located and inspection and management data of the big data fire safety education cloud platform to determine the inspection index value of the area where the educational institution is located, and compare it with the preset inspection index threshold. The specific process for determining the inspection indicator values ​​for the area to which the educational institution belongs is as follows: The monitoring coverage area of ​​fire cameras in various areas is compared with the functional coverage area of ​​each area to obtain the monitoring coverage area ratio of each area. The building volume of each type of area is matched with the number of qualified fire sensors corresponding to each pre-set building volume interval to obtain the number of qualified fire sensors for each type of area. Based on the monitoring coverage area ratio of various regions, the number of qualified fire sensors in various regions, and the reference number of qualified fire sensors in various regions, the first inspection characteristic index of various regions is determined by comprehensive processing. Obtain historical fault data for each type of fire-fighting equipment in various regions, including the number of faults and the duration of each fault. Based on the online duration, memory usage, minimum screen output resolution of each fire camera in various regions, as well as the number of faults and duration of each fault of each fire equipment in various regions, the second inspection characteristic index of each region is determined by comprehensive processing. By combining the first and second inspection characterization indicators of various regions, the inspection index values ​​of the regions where educational institutions are located are obtained through data processing. These inspection index values ​​are used to characterize the management level of the regions where educational institutions are located and to provide data basis for fire emergency simulation of pre-managed educational institution regions. Fire emergency simulation assessment: The area where the educational institution belongs to the inspection indicator value is greater than the inspection indicator threshold is marked as the pre-managed educational institution area. Fire emergency simulation is carried out on the pre-managed educational institution area to obtain the fire emergency simulation data of the pre-managed educational institution area and evaluate the fire emergency simulation evaluation index of the pre-managed educational institution area. The assessment process for the fire emergency simulation evaluation index of the pre-managed educational institution area is as follows: The evacuation time of the pre-managed educational institution area is compared with the total fire simulation time to obtain the evacuation time ratio of the pre-managed educational institution area. The response times of each fire-fighting device in the pre-managed educational institution area are summed and averaged sequentially to obtain the average response time of the fire-fighting devices in the pre-managed educational institution area. Therefore, based on the evacuation time ratio of the pre-managed educational institution area, the average response time of the fire-fighting equipment in the pre-managed educational institution area, and the total amount of fire extinguishing agent used in the pre-managed educational institution area, a fire emergency simulation evaluation index for the pre-managed educational institution area is comprehensively evaluated. The fire emergency simulation evaluation index for the pre-managed educational institution area is used to characterize the degree of evaluation of the fire emergency simulation in the pre-managed educational institution area. The fire emergency management feedback is obtained by comparing the fire emergency simulation evaluation index of the pre-managed education institution region with a preset fire emergency simulation evaluation reference index, and finally managing the fire emergency simulation process of the pre-managed education institution region.

2. The fire emergency management method for the big data education platform of the educational institution according to claim 1, characterized in that: The structure data of the region to which the education institution belongs is collected, and the specific collection process is as follows: The region to which the education institution belongs is divided according to the function region type, and is recorded as each type of region, and the structure data of each type of region is counted; The structure data of each type of region includes the function coverage area of each type of region and the building main volume of each type of region; The structure data of each type of region is taken as the structure data of the region to which the education institution belongs.

3. The fire emergency management method for the big data education platform of the educational institution according to claim 1, characterized in that: The patrol management data of the big data fire education cloud platform includes the fire camera monitoring coverage area of each type of region, the number of qualified fire sensor patrols of each type of region, and the operation output patrol data corresponding to each fire camera of each type of region; The operation output patrol data corresponding to each fire camera of each type of region includes the online time length, memory occupation, and picture output minimum resolution of each fire camera of each type of region.

4. The fire emergency management method for the big data education platform of the educational institution according to claim 1, characterized in that: The patrol indication value of the region to which the education institution belongs is specifically expressed as: ； In the formula, is a patrol indication value of a region to which an educational institution belongs, is a first patrol representation index of the kth type of region, is a second patrol representation index of the kth type of region, is a preset weight factor corresponding to the first patrol representation index, is a preset weight factor corresponding to the second patrol representation index, and k is the number of each type of region, , and p is the total number of types of regions.

5. The fire emergency management method for the big data education platform of the educational institution according to claim 1, characterized in that: The patrol indication value of the region to which the education institution belongs is compared with a preset patrol indication threshold, and the specific comparison process is as follows: If the patrol indication value of the region to which the education institution belongs is greater than the preset patrol indication threshold, the fire emergency simulation of the region to which the education institution belongs is performed, and if the patrol indication value of the region to which the education institution belongs is less than or equal to the preset patrol indication threshold, the patrol indication values of each type of region are extracted to obtain the arrangement order of the patrol indication values, which is taken as the fire inspection and investigation order, and the fire inspection and investigation order is transmitted to the big data fire education cloud platform for management prompt.

6. The fire emergency management method for the big data education platform of the educational institution according to claim 1, characterized in that: The fire emergency simulation data of the pre-managed education institution region includes the total simulation time, the evacuation time, the response time of each fire equipment, and the total amount of fire extinguishing agent used.

7. The fire emergency management method for the big data education platform of the educational institution according to claim 1, characterized in that: The fire emergency simulation evaluation index of the pre-managed education institution region is specifically expressed as: ； In the formula, is a fire emergency simulation evaluation index for pre-managing an educational institution area, is a pre-set evacuation time ratio, is an average response time of fire-fighting equipment for pre-managing an educational institution area, is a total amount of fire extinguishing agent for pre-managing an educational institution area, is a pre-set reference total amount of fire extinguishing agent, is an influence factor corresponding to a pre-set evacuation time ratio unit value, is an influence factor corresponding to a pre-set average response time of fire-fighting equipment unit value, and e is a natural constant.

8. The fire emergency management method for the big data education platform for educational institutions of claim 1, wherein: The management feedback of the fire emergency simulation process of the pre-managed education institution region is specifically as follows: The fire emergency simulation evaluation index of the pre-managed education institution region is compared with a preset fire emergency simulation evaluation reference index, if the fire emergency simulation evaluation index of the pre-managed education institution region is greater than the preset fire emergency simulation evaluation reference index, the fire emergency simulation process of the pre-managed education institution region is extracted by performing the fire emergency simulation of the pre-managed education institution region, and the fire emergency simulation process of the pre-managed education institution region is input into the big data fire education cloud platform and visualized displayed, and if the fire emergency simulation evaluation index of the pre-managed education institution region is equal to or less than the fire emergency simulation evaluation reference index, the management feedback of the fire emergency simulation process of the pre-managed education institution region is performed.

Images