Smart fire emergency management method and system

Abstract

The present invention relates to the field of smart fire technology, and in particular to a smart fire emergency management method and system. The method comprises the following steps: obtaining environmental perception data, fire equipment status data, crowd monitoring data and fire emergency resource data of the fire management area of ​​the fire monitoring cloud platform; performing fire status fire scene situation assessment processing according to the environmental perception data and the fire equipment status data, and generating fire status fire scene situation assessment data; performing fire emergency scene data analysis based on the fire scene situation assessment data and crowd monitoring data, and generating fire emergency scene data; performing fire emergency resource intelligent scheduling priority analysis on the fire emergency scene data based on the fire emergency resource data, and generating fire emergency resource intelligent scheduling priority data. The present invention realizes efficient intelligent emergency dispatch of fire resources by analyzing the linkage management of fire scene risk assessment and emergency resource dispatch.

Description

Technical Field

[0001] The present invention relates to the field of smart firefighting technology, and in particular to a smart firefighting emergency management method and system. Background Art

[0002] Smart fire emergency management is an innovative solution that uses cutting-edge technologies such as the Internet of Things, big data, and artificial intelligence to upgrade the fire emergency management model to an intelligent and digital one. With the acceleration of modern urbanization, the density of urban buildings and population continues to increase, and the probability and complexity of fires are also increasing. Traditional fire emergency management has been unable to cope with the current complex and changeable fire emergency situation. By introducing the Internet of Things technology, the smart fire emergency management method can collect and monitor multi-source data in the fire management area in real time, identify fire hazards more accurately, and conduct intelligent analysis and prediction of the situation of fire occurrence. The application of big data and artificial intelligence technology enables the smart fire emergency management method to build a dynamic prediction and evaluation model for fire emergency scenarios, provide accurate emergency resource scheduling strategies, and improve the speed and efficiency of fire emergency response. However, the existing smart fire emergency management methods still have some shortcomings. In terms of related information processing, it is difficult to integrate multi-source data in a timely manner, resulting in a slow response speed for emergency prediction and the inability to achieve real-time warning and rapid response; the linkage effect in fire emergency management is poor, and it is impossible to conduct efficient dynamic weight analysis between the fire scene situation and emergency resource scheduling, which in turn affects the accuracy and effectiveness of emergency decision-making; there is still much room for improvement in the accuracy and efficiency of fire prevention and control, especially in the linkage management of emergency resource scheduling and fire scene risk assessment, and there is a lack of sufficient intelligent processing means. Summary of the invention

[0003] Based on this, the present invention provides a smart fire emergency management method and system to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a smart fire emergency management method includes the following steps:

[0005] Step S1: Obtain fire management area data; perform regional fire emergency global data integration processing on the pre-stored fire monitoring cloud platform according to the fire management area data to generate regional fire emergency global data, wherein the regional fire emergency global data includes environmental perception data of the fire management area, fire equipment status data, crowd monitoring data and fire emergency resource data;

[0006] Step S2: Perform multi-source fire intelligent monitoring and processing in the fire management area according to the environmental perception data to generate real-time multi-source fire data;

[0007] Step S3: Performing fire scene situation assessment processing on a fire status according to real-time multi-source fire data and fire equipment status data to generate fire scene situation assessment data;

[0008] Step S4: performing fire emergency scene data analysis based on the fire scene situation assessment data and the crowd monitoring data to generate fire emergency scene data; performing fire emergency scene dynamic weight analysis based on the fire emergency scene data to generate fire emergency scene dynamic weight data;

[0009] Step S5: Based on the fire emergency resource data and the fire emergency scenario dynamic weight data, the fire emergency resource intelligent scheduling priority analysis is performed on the fire emergency scenario data to generate fire emergency resource intelligent scheduling priority data; and the fire emergency resource intelligent scheduling operation is executed through the fire emergency resource intelligent scheduling priority data.

[0010] The present invention can fully understand the current situation of the fire management area by acquiring multi-source data (such as environmental perception data, fire equipment status data, crowd monitoring data, and fire emergency resource data) in the fire management area. After integrated processing, these data form regional fire emergency global data, which helps to provide a reliable data basis for subsequent intelligent monitoring, scene evaluation, and emergency resource scheduling, realizes the unified management of multi-source heterogeneous data, breaks the information islands between various fire subsystems, improves the efficiency and accuracy of data processing, and lays a solid foundation for subsequent intelligent decision-making. Through the analysis of environmental perception data, intelligent monitoring of fires can be achieved. The system can monitor fire risks in real time and generate multi-source fire data. Multi-source fire intelligent monitoring improves the accuracy and speed of fire risk identification, effectively reduces the false alarm rate or missed alarm rate, ensures the early detection of fires, and uses the Internet of Things sensor network and big data analysis to achieve accurate identification and real-time monitoring of fire hazards, greatly improving the intelligence level of fire warning. Comprehensive analysis of real-time multi-source fire data and fire equipment status data accurately evaluates the current fire scene situation and generates fire scene situation assessment data to help the system quickly determine the development trend of the fire and take targeted emergency measures in a timely manner. The fusion analysis of fire equipment status and fire scene information greatly improves the accuracy of the assessment, allowing firefighters to make more accurate emergency decisions based on real-time scene situation. Combining fire scene assessment data with crowd monitoring data can accurately analyze the dynamic situation of crowds within the fire impact area, helping the system generate comprehensive fire emergency scene data. Through dynamic weight analysis, risks in different areas can be prioritized to ensure that emergency resources are allocated to the most urgent areas, effectively improving the analysis ability and accuracy of fire emergency scenes, ensuring that the situation in densely populated areas can be fully considered during emergency response, and minimizing the risk of casualties. Based on intelligent scheduling priority analysis of fire emergency scene data and dynamic weight data, the system can reasonably allocate emergency resources to ensure that resources are preferentially dispatched to the areas with the greatest risks. This intelligent scheduling mechanism can greatly improve resource utilization efficiency and avoid resource waste, while maximizing the timeliness and effectiveness of emergency response, ensuring that fire emergency resources can be dispatched in the best way in complex fire scenarios, reducing emergency response time and improving overall rescue efficiency.

[0011] This specification provides a smart fire emergency management system for executing the smart fire emergency management method as described above. The smart fire emergency management system includes:

[0012] A fire emergency global data integration module is used to obtain fire management area data; perform regional fire emergency global data integration processing on the pre-stored fire monitoring cloud platform according to the fire management area data to generate regional fire emergency global data, wherein the regional fire emergency global data includes environmental perception data of the fire management area, fire equipment status data, crowd monitoring data and fire emergency resource data;

[0013] Multi-source fire monitoring module, used to perform multi-source fire intelligent monitoring and processing in the fire management area based on environmental perception data, and generate real-time multi-source fire data;

[0014] A fire status fire scene situation assessment module is used to perform fire status fire scene situation assessment processing based on real-time multi-source fire data and fire equipment status data to generate fire status fire scene situation assessment data;

[0015] The fire emergency scene dynamic weight analysis module is used to analyze the fire emergency scene data based on the fire scene situation assessment data and the crowd monitoring data to generate the fire emergency scene data; perform the fire emergency scene dynamic weight analysis based on the fire emergency scene data to generate the fire emergency scene dynamic weight data;

[0016] The fire emergency resource intelligent scheduling execution module is used to perform fire emergency resource intelligent scheduling priority analysis on fire emergency scenario data based on fire emergency resource data and fire emergency scenario dynamic weight data, generate fire emergency resource intelligent scheduling priority data; and execute fire emergency resource intelligent scheduling operations through fire emergency resource intelligent scheduling priority data.

[0017] The beneficial effect of the present application is that the present application collects and integrates the environmental perception data, fire equipment status data, crowd monitoring data and fire emergency resource data of the fire management area in real time, and performs intelligent monitoring and evaluation processing of the fire scene based on these data, thereby overcoming the problem of untimely integration of multi-source data in the prior art, and realizing real-time early warning and rapid response. In particular, through the design of the adaptive multi-source abnormal perception signal monitoring engine, it is possible to monitor abnormal information of fire in real time, and effectively improve the reaction speed of emergency prejudgment. Through the combination of fire scene situation assessment data and crowd monitoring data, the dynamic weight analysis of the fire emergency scene is realized. Through the dynamic weight analysis of the fire emergency scene of the fire scene risk data and the crowd behavior characteristic data, the emergency resource scheduling is made more accurate and effective, and the problem of poor linkage effect in the prior art is improved, so that the relationship between the fire scene situation and the emergency resource scheduling is closer, ensuring the accuracy and efficiency of emergency decision-making. Fire emergency resources are allocated through the dynamic weight of the fire emergency scene, and the scheduling status of the scheduling resources is intelligently updated, which further improves the accuracy of fire prevention and control. Through the intelligent scheduling priority analysis, it is ensured that the fire emergency resources are reasonably scheduled according to the real-time updated scene dynamic weight data, which effectively solves the problem of insufficient resource scheduling optimization in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic diagram of the steps of a smart fire emergency management method of the present invention;

[0019] Figure 2 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0020] Figure 3 for Figure 1 Detailed implementation steps of step S5;

[0021] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0022] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0023] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0024] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0025] To achieve this, please refer to Figures 1 to 3 The present invention provides a smart fire emergency management method, comprising the following steps:

[0026] Step S1: Obtain fire management area data; perform regional fire emergency global data integration processing on the pre-stored fire monitoring cloud platform according to the fire management area data to generate regional fire emergency global data, wherein the regional fire emergency global data includes environmental perception data of the fire management area, fire equipment status data, crowd monitoring data and fire emergency resource data;

[0027] Step S2: Perform multi-source fire intelligent monitoring and processing in the fire management area according to the environmental perception data to generate real-time multi-source fire data;

[0028] Step S3: Performing fire scene situation assessment processing on a fire status according to real-time multi-source fire data and fire equipment status data to generate fire scene situation assessment data;

[0029] Step S4: performing fire emergency scene data analysis based on the fire scene situation assessment data and the crowd monitoring data to generate fire emergency scene data; performing fire emergency scene dynamic weight analysis based on the fire emergency scene data to generate fire emergency scene dynamic weight data;

[0030] Step S5: Based on the fire emergency resource data and the fire emergency scenario dynamic weight data, the fire emergency resource intelligent scheduling priority analysis is performed on the fire emergency scenario data to generate fire emergency resource intelligent scheduling priority data; and the fire emergency resource intelligent scheduling operation is executed through the fire emergency resource intelligent scheduling priority data.

[0031] The present invention can fully understand the current situation of the fire management area by acquiring multi-source data (such as environmental perception data, fire equipment status data, crowd monitoring data, and fire emergency resource data) in the fire management area. After integrated processing, these data form regional fire emergency global data, which helps to provide a reliable data basis for subsequent intelligent monitoring, scene evaluation, and emergency resource scheduling, realizes the unified management of multi-source heterogeneous data, breaks the information islands between various fire subsystems, improves the efficiency and accuracy of data processing, and lays a solid foundation for subsequent intelligent decision-making. Through the analysis of environmental perception data, intelligent monitoring of fires can be achieved. The system can monitor fire risks in real time and generate multi-source fire data. Multi-source fire intelligent monitoring improves the accuracy and speed of fire risk identification, effectively reduces the false alarm rate or missed alarm rate, ensures the early detection of fires, and uses the Internet of Things sensor network and big data analysis to achieve accurate identification and real-time monitoring of fire hazards, greatly improving the intelligence level of fire warning. Comprehensive analysis of real-time multi-source fire data and fire equipment status data accurately evaluates the current fire scene situation and generates fire scene situation assessment data to help the system quickly determine the development trend of the fire and take targeted emergency measures in a timely manner. The fusion analysis of fire equipment status and fire scene information greatly improves the accuracy of the assessment, allowing firefighters to make more accurate emergency decisions based on real-time scene situation. Combining fire scene assessment data with crowd monitoring data can accurately analyze the dynamic situation of crowds within the fire impact area, helping the system generate comprehensive fire emergency scene data. Through dynamic weight analysis, risks in different areas can be prioritized to ensure that emergency resources are allocated to the most urgent areas, effectively improving the analysis ability and accuracy of fire emergency scenes, ensuring that the situation in densely populated areas can be fully considered during emergency response, and minimizing the risk of casualties. Based on intelligent scheduling priority analysis of fire emergency scene data and dynamic weight data, the system can reasonably allocate emergency resources to ensure that resources are preferentially dispatched to the areas with the greatest risks. This intelligent scheduling mechanism can greatly improve resource utilization efficiency and avoid resource waste, while maximizing the timeliness and effectiveness of emergency response, ensuring that fire emergency resources can be dispatched in the best way in complex fire scenarios, reducing emergency response time and improving overall rescue efficiency.

[0032] As an embodiment of the present invention, refer to Figure 1The above is a schematic diagram of the steps of a smart fire emergency management method of the present invention. In this embodiment, the smart fire emergency management method includes the following steps:

[0033] Step S1: Obtain fire management area data; perform regional fire emergency global data integration processing on the pre-stored fire monitoring cloud platform according to the fire management area data to generate regional fire emergency global data, wherein the regional fire emergency global data includes environmental perception data of the fire management area, fire equipment status data, crowd monitoring data and fire emergency resource data;

[0034] In an embodiment of the present invention, environmental perception data is obtained by deploying a variety of sensor devices (such as temperature sensors, smoke detectors, CO2 concentration sensors, etc.) in the fire management area, and the maximum operating status data of the fire equipment is collected at the same time. The maximum operating status data of the fire equipment refers to the operating capacity of the equipment under normal circumstances, such as the upper limit of the water pressure of the fire pump, the maximum spray time of the fire extinguisher, etc. Through the deployed monitoring equipment, the crowd monitoring data is used to track the dense areas and flow directions of personnel in real time. The fire emergency resource data in the fire management area is obtained and uploaded to the cloud platform. All of these data are transmitted to the fire monitoring cloud platform through the Internet of Things devices. The platform integrates and processes different types of data (environmental perception data, maximum operating status data of fire equipment, crowd monitoring data, fire emergency resource data) to generate regional fire emergency global data. This global data provides a unified and integrated data basis for subsequent fire monitoring, risk assessment and equipment scheduling.

[0035] Step S2: Perform multi-source fire intelligent monitoring and processing in the fire management area according to the environmental perception data to generate real-time multi-source fire data;

[0036] In the embodiment of the present invention, based on the environmental perception data, the system uses the built-in fire monitoring algorithm to conduct a comprehensive analysis of different data sources. For example, when the smoke sensor, temperature sensor and gas sensor detect anomalies at the same time, the system will trigger the intelligent monitoring process to generate real-time multi-source fire data. The generation of multi-source fire data depends on the joint analysis of multiple sensor data and is optimized through machine learning models. The model can combine historical sensor data and real-time data to intelligently evaluate fire risks and reduce false alarm rates. For example, a sharp rise in temperature and smoke indicates a fire, but it may also be other non-fire events. The system improves the accuracy of fire warnings by intelligently screening multi-source data.

[0037] Step S3: Performing fire scene situation assessment processing on a fire status according to real-time multi-source fire data and fire equipment status data to generate fire scene situation assessment data;

[0038] In the embodiment of the present invention, the fire scene situation assessment is performed using real-time multi-source fire data and fire equipment status data. The fire equipment status data here is no longer a simple monitoring of whether the equipment is in good condition, but refers to the key data of the actual operating capacity of the equipment when a fire occurs. For example, when a fire occurs, it is assessed whether the fire pump can reach its maximum water pressure under the current fire situation, or the remaining amount of spraying time of the intelligent fire extinguisher after use is assessed. The system evaluates the actual response capability of the fire equipment at the fire scene based on the real-time operating data of these fire equipment and the fire situation data. The fire scene situation assessment data of the fire state is a comprehensive analysis result, which takes into account the relationship between the fire development situation (such as the direction and intensity of the fire spread) and the maximum operating capacity of the fire equipment. For example, in a scene where the fire is large and spreads quickly, the assessment result may show that the current equipment is difficult to control the fire and more resources need to be deployed for fire extinguishing. This assessment data provides an important reference for subsequent resource scheduling and emergency decision-making.

[0039] Step S4: performing fire emergency scene data analysis based on the fire scene situation assessment data and the crowd monitoring data to generate fire emergency scene data; performing fire emergency scene dynamic weight analysis based on the fire emergency scene data to generate fire emergency scene dynamic weight data;

[0040] In an embodiment of the present invention, based on the fire scene situation assessment data and crowd monitoring data of the fire status, the system analyzes the entire emergency scene. The fire emergency scene data includes areas with relatively high current fire risks, crowded areas, working conditions of firefighting equipment, etc., to identify the most dangerous areas and places with the highest density of people. Through dynamic weight analysis, the system assigns weights to different areas to determine which areas have the greatest fire risks and which areas are most urgent to evacuate people. For example, if a high-risk area is also densely populated and the maximum operating capacity of the firefighting equipment is close to its limit, the system will assign a higher weight to the area to ensure that resources are allocated to the area first. Dynamic weight analysis ensures the accuracy and real-time nature of resource scheduling. As the fire develops, the system can adjust the weights of each area based on the real-time monitored data, dynamically update the fire emergency scene, and ensure that the most needed areas receive the most timely support.

[0041] Step S5: Based on the fire emergency resource data and the fire emergency scenario dynamic weight data, the fire emergency resource intelligent scheduling priority analysis is performed on the fire emergency scenario data to generate fire emergency resource intelligent scheduling priority data; and the fire emergency resource intelligent scheduling operation is executed through the fire emergency resource intelligent scheduling priority data.

[0042] In the embodiment of the present invention, intelligent scheduling priority analysis is performed based on the analysis results of fire emergency scene data, dynamic weight data and fire equipment operation capacity. Identify currently available fire emergency resources, such as fire extinguishers, fire pumps, fire fighting vehicles and firefighters. Based on real-time dynamic weight data, the system evaluates and sorts the resource requirements of each area to ensure that areas with high fire risk and areas where equipment capacity is close to the limit are given priority to obtain resources, and automatically dispatches fire resources by generating fire emergency resource scheduling priority data. For example, if the fire in a certain area is large and the existing fire fighting equipment cannot effectively control the fire, the system will dispatch fire fighting vehicles, additional equipment and personnel to the area first. In addition, the system continuously adjusts the priority of resource scheduling by real-time monitoring of the status of the equipment and the development trend of the fire to ensure the efficient use of emergency resources. The execution of intelligent scheduling operations can be achieved through automation. For example, the system directly transmits the ratio of firefighters to the terminal device of the responsible personnel; the human-machine interface can be used to provide real-time monitoring information to ensure that the dispatching command center has a real-time grasp of the fire situation and adjusts the scheduling direction and priority of resources as needed.

[0043] Preferably, step S2 comprises the following steps:

[0044] Step S21: Analyze historical multi-source baseline perception signals according to environmental perception data to generate historical multi-source baseline perception signals;

[0045] Step S22: Designing an adaptive monitoring engine for multi-source abnormal perception signals based on historical multi-source baseline perception signals to generate an adaptive multi-source abnormal perception signal monitoring engine;

[0046] Step S23: performing real-time multi-source abnormal perception signal monitoring and processing on the environmental perception data based on the adaptive multi-source abnormal perception signal detection engine to generate a real-time multi-source abnormal perception signal;

[0047] Step S24: Perform real-time multi-source fire data analysis based on the real-time multi-source abnormal perception signal to generate real-time multi-source fire data.

[0048] The present invention establishes a baseline model under normal firefighting conditions through baseline analysis of historical environmental perception data. This baseline signal can be used as a comparison standard for subsequent fire monitoring and anomaly detection, effectively distinguishing between normal and abnormal conditions, and can help the system extract the laws and features in historical data, provide a reference basis for the intelligentization of fire monitoring, reduce the possibility of false alarms and missed alarms, and establish a historical baseline of multi-source data to help improve the accuracy of abnormal monitoring and enhance the reliability of the fire risk warning system. Based on the design of an adaptive monitoring engine based on historical multi-source baseline signals, it is possible to achieve dynamic adjustment of fire monitoring signals. The engine can adjust the monitoring standards in real time according to environmental changes to maintain the sensitivity and accuracy of the monitoring system. The adaptive monitoring engine can automatically optimize the monitoring rules according to different scenarios and time periods, enhance the system's adaptability to various complex scenarios, and improve the intelligent level of fire monitoring. The system's ability to process abnormal perception signals is improved, the dynamic monitoring function of fire hazards is enhanced, and the necessity of manual intervention is reduced. The adaptive detection engine can quickly identify abnormal situations, such as changes in multi-source sensing signals such as temperature and smoke density, and generate real-time abnormal sensing signals by monitoring environmental sensing data in real time. Real-time monitoring enables the system to capture fire precursors in a timely manner, reduce response delays, and effectively improve the response speed of fire warnings, enhancing the timeliness and accuracy of fire monitoring, ensuring that warnings can be issued at the earliest time point when a fire occurs to avoid the expansion of the fire. By analyzing real-time abnormal sensing signals, accurate multi-source fire data can be generated to identify the specific location and development trend of the fire. Real-time fire data analysis can refine fire hazards into multiple dimensions, such as the speed of fire development and the scope of influence, providing detailed data support for emergency management, ensuring the real-time and accuracy of fire data, helping the emergency command center to make more scientific and accurate decisions, and improving the efficiency and accuracy of fire handling.

[0049] In an embodiment of the present invention, historical perception data is obtained from environmental perception devices (such as temperature sensors, humidity sensors, smoke detectors, CO2 sensors, etc.). These data may include environmental parameters of multiple dimensions, such as normal temperature range, air humidity, gas composition, etc. in the area. The system summarizes these environmental data collected over a long period of time and generates a baseline signal of the environment based on a statistical analysis method. Specifically, the baseline perception signal refers to the normal environmental characteristic value in the absence of a fire. For example, the temperature of an office building in a normal state may be between 18°C ​​and 25°C, and the humidity is maintained between 30% and 50%. By analyzing data from different time periods, the system can summarize the baseline perception characteristics of different types of areas at different time periods. The baseline signal is not only a single static data, but a data set that changes dynamically over time, which can reflect characteristics such as day and night cycles and seasonal changes. Based on these data, the system generates a set of historical multi-source baseline perception signals. After obtaining the historical multi-source baseline perception signals, the system will design an adaptive monitoring engine through a machine learning algorithm. The design goal of this engine is to be able to automatically adjust the monitoring rules according to the changes in the baseline signal and detect abnormal situations. First, the machine learning model is trained using historical data to generate an algorithm that is sensitive to different abnormal perception signals. For example, the system will compare and analyze environmental data under normal conditions and known fire data to establish a set of identification standards for multi-source abnormal perception signals. After that, the system designs an adaptive monitoring engine with flexible adjustment capabilities, which can automatically adjust the monitoring thresholds and weights to adapt to changes in different time, location, equipment and environmental conditions. The adaptive engine also has learning capabilities. As time goes by, the system will continue to acquire new data, and the monitoring engine can automatically learn new environmental signal characteristics and optimize the monitoring strategy for sensing abnormal signals. For example, when the ambient temperature varies greatly between day and night, the monitoring engine can automatically adjust the temperature threshold to avoid false alarms. After the adaptive monitoring engine is designed and deployed, the system will use it to monitor real-time environmental perception data. When a fire scene occurs, environmental data (such as temperature, humidity, smoke concentration, etc.) will deviate from the range of historical baseline signals. At this time, the adaptive monitoring engine can identify these abnormal signals and generate real-time multi-source abnormal perception signals, and conduct a comprehensive analysis of data sources from different sensors. Suppose the smoke detector in a certain area detects an increase in smoke concentration, and the temperature sensor detects an abnormal temperature rise at the same time, the monitoring engine will compare these signals with the baseline perception signal. If these values ​​exceed the adaptive threshold, the system will mark these signals as abnormal and generate corresponding abnormal signal data. In addition, the monitoring engine can monitor the changing trends of multiple sensor data in real time and quickly identify small abnormal changes in the environment. For example, when a sensor detects an abnormality alone, the monitoring engine will combine other data sources for further analysis to avoid false alarms from a single signal.After generating real-time multi-source abnormal perception signals, the system will conduct further fire analysis on these signals. At this time, the system uses multi-source data fusion technology to combine multiple abnormal signals to generate real-time multi-source fire data. It is not limited to the judgment of a single sensor, but confirms the specific status and development trend of the fire through comprehensive analysis of multiple data. Valuable fire indicators are extracted from abnormal signals. The simultaneous increase in smoke concentration and temperature may indicate that the fire has spread. The system summarizes this information into a set of real-time fire data, including the intensity of the fire, the direction of spread, the scope of influence, etc. In addition, the system will also combine the fire equipment status data for auxiliary judgment. For example, when the fire sprinkler equipment automatically starts and the water pressure is abnormal in the area where the abnormal signal is detected, the severity of the fire is further confirmed and a more detailed fire data report is generated. Through real-time multi-source fire data, the system can provide immediate and comprehensive information support for fire emergency response. These data not only help identify the location of the fire, but also predict the speed of fire spread and the possible affected areas, providing a decision-making basis for the subsequent dispatch of fire equipment.

[0050] Preferably, step S3 comprises the following steps:

[0051] Step S31: extracting abnormal perception signal space nodes according to real-time multi-source abnormal perception signals to generate abnormal perception signal space node data;

[0052] Step S32: performing spatial multi-source fire node identification processing on the corresponding real-time multi-source fire data through the abnormal sensing signal spatial node data to generate real-time spatial multi-source fire data;

[0053] Step S33: analyzing the equipment fire emergency mobilization status according to the fire equipment status data, and generating equipment fire emergency mobilization status data;

[0054] Step S34: performing fire state space fire joint feature analysis based on the equipment fire emergency mobilization state data and the real-time spatial multi-source fire data to generate fire state space fire joint feature data;

[0055] Step S35: performing local spatial node division processing on the fire status spatial fire joint characteristic data to generate fire status local spatial fire joint characteristic data;

[0056] Step S36: Perform fire scene situation assessment processing on the fire state based on the fire state local space fire joint feature data to generate fire scene situation assessment data on the fire state.

[0057] The present invention extracts spatial nodes from multi-source abnormal sensing signals and accurately locates the occurrence location of abnormal sensing signals, which helps to accurately determine the potential occurrence point or high-risk area of ​​fire, enhances the spatial analysis capability of abnormal signals, and makes fire monitoring not only limited to data changes, but also can track the specific spatial location of abnormal signals, improves the accuracy of fire monitoring, and the extraction of spatial nodes helps to divide the key areas within the monitoring range, which is convenient for further fire situation analysis and resource scheduling. Through spatial node identification, fire data is associated with specific spatial locations, which helps to more intuitively understand the propagation path and impact range of fire. The generated real-time spatial multi-source fire data can provide detailed spatial information for subsequent decision support, facilitate fire commanders to make accurate scheduling and emergency decisions, effectively improve the visualization capability of fire data, and help relevant departments to grasp the dynamic development of fire in a timely manner. By analyzing the status of firefighting equipment, the system can understand the availability, location and mobilization of the current equipment, ensure that the emergency equipment is in the best condition, quickly respond to the needs of the fire scene, optimize the mobilization and management of equipment, and prevent emergency response delays caused by poor equipment status or unreasonable location. It can automatically generate mobilization suggestions based on the status data of the equipment, reduce human judgment errors, and improve the scientificity and rationality of equipment mobilization. By combining the equipment mobilization status and real-time fire data for analysis, the relationship between the spatial characteristics of the current fire situation and equipment mobilization is understood, thereby generating more accurate joint feature data. By jointly analyzing the fire spatial characteristics and equipment status, the system can provide a more reasonable emergency response strategy, making equipment scheduling and fire response measures more coordinated. This joint feature analysis improves the adaptability and flexibility of equipment mobilization and fire situation in fire scenarios, and ensures the fire simulation status of firefighting equipment during the development of the fire. The local spatial division of the joint feature data can further refine the analysis of the fire scene and decompose the fire situation into smaller and manageable local nodes, which is convenient for formulating more accurate emergency measures. This division helps to highlight the most urgent areas of the fire, help decision makers concentrate resources and forces where they are most needed, and improve the efficiency of fire disposal. Through local node division, the system can analyze the risk characteristics of each node more carefully, analyze the probabilistic spatial relationship of fire evolution, identify the degree of fire risk in each local space, and formulate targeted fire extinguishing or evacuation plans. The fire scene state assessment based on the local spatial joint feature data can accurately predict the future development trend of the fire and help emergency management personnel formulate scientific disposal strategies. The state assessment enables the system to dynamically track the spread and changes of the fire, timely discover potential high-risk areas, and provide timely decision support for emergency resource dispatch. By evaluating the fire state, the predictability and accuracy of the emergency response are improved, ensuring that firefighting resources can be efficiently invested in fire disposal and reducing the losses and impacts of the fire.

[0058] As an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 FIG. 1 is a flow chart of detailed implementation steps of step S3 in FIG. 1 . In this embodiment, step S3 includes:

[0059] Step S31: extracting abnormal perception signal space nodes according to real-time multi-source abnormal perception signals to generate abnormal perception signal space node data;

[0060] In an embodiment of the present invention, spatial nodes are extracted based on real-time multi-source abnormal perception signals. The purpose of spatial node extraction is to locate the fire risk to a specific physical location, such as a floor of a building or an area in a room, by matching the location information of multiple sensors, and using the sensor location corresponding to the abnormal perception signal as a "spatial node". For example, when the temperature sensor and smoke detector on a certain floor detect an abnormality at the same time, the system will associate these abnormal signals with specific spatial nodes (such as the floor and room number) and generate abnormal perception signal spatial node data at that location. Through spatial node extraction, the abnormal signal is linked to the actual geographic location, which facilitates subsequent fire assessment and emergency response.

[0061] Step S32: performing spatial multi-source fire node identification processing on the corresponding real-time multi-source fire data through the abnormal sensing signal spatial node data to generate real-time spatial multi-source fire data;

[0062] In an embodiment of the present invention, based on the spatial node data of the abnormal perception signal, the real-time multi-source fire data is associated with these spatial nodes, and the fire data is identified through the spatial positioning information of the abnormal perception signal obtained in the previous step. For example, different sensors will capture a variety of perception signals of fire (such as abnormal temperature and abnormal smoke concentration). The system associates these fire perception data with specific spatial nodes to generate real-time spatial multi-source fire data that identifies the spatial position. These identification processes can not only accurately locate the specific location of the fire, but also identify the spread of the fire between different nodes.

[0063] Step S33: analyzing the equipment fire emergency mobilization status according to the fire equipment status data, and generating equipment fire emergency mobilization status data;

[0064] In the embodiment of the present invention, the current operating status and maximum operating capacity of the fire equipment in the fire scenario will be determined by analyzing the status data of the fire equipment. The system can obtain status information from the fire equipment in real time, including water pressure of the water pump, flow rate of the fire sprinkler system, remaining capacity of the fire extinguisher, etc. For example, the system will evaluate the mobilization capacity of equipment such as fire extinguishers and fire pumps in the current fire scenario, and analyze whether it can cover the required area or whether more equipment is needed. By analyzing the current working status of these devices, the system generates equipment fire emergency mobilization status data to provide a basis for subsequent equipment scheduling decisions.

[0065] Step S34: performing fire state space fire joint feature analysis based on the equipment fire emergency mobilization state data and the real-time spatial multi-source fire data to generate fire state space fire joint feature data;

[0066] In an embodiment of the present invention, by combining the equipment fire emergency mobilization status data and real-time spatial multi-source fire data, a joint feature analysis of the fire scene is performed, and the current fire development trend (such as fire intensity, spread direction) is combined with the maximum operating capacity of the equipment to analyze the effectiveness of the existing equipment in responding to the current fire. For example, in a certain area, the system may find that the water pressure of the fire-fighting equipment is close to the maximum operating state, while the fire is still spreading. At this time, the system evaluates whether the existing equipment is sufficient to control the fire through a comprehensive analysis of the equipment status and the fire situation, and generates fire joint feature data in the fire status space. This data includes joint information on fire intensity, equipment emergency response capabilities, and other aspects, which is convenient for decision makers to make the next response strategy.

[0067] Step S35: performing local spatial node division processing on the fire status spatial fire joint characteristic data to generate fire status local spatial fire joint characteristic data;

[0068] In an embodiment of the present invention, the fire status spatial fire joint feature data is refined, the local nodes are divided according to the spatial characteristics of the fire, and different areas are distinguished according to the actual development trend of the fire, and multiple local spatial nodes are divided, and the data of these nodes are further refined. For example, in a large building, a fire may affect multiple floors or rooms at the same time. The system will independently analyze the fire characteristics of each floor or room and generate fire status data for each local area. Through this local division processing, the system generates more accurate fire status local spatial fire joint feature data, providing detailed information for emergency response to different spatial nodes.

[0069] Step S36: Perform fire scene situation assessment processing on the fire state based on the fire state local space fire joint feature data to generate fire scene situation assessment data on the fire state.

[0070] In the embodiment of the present invention, by analyzing the joint characteristic data of local space fires in the fire state, the overall situation of the fire scene is evaluated, not only considering the current situation of the fire, but also combining the characteristics of each local area to predict the possible further development trend of the fire. Combined with data such as the spread direction of the fire, the maximum operating capacity of the equipment, and the intensity of the fire, the fire scene situation evaluation data of the fire state is generated. For example, in a certain area, the fire may soon spread to adjacent floors, and the existing equipment capacity is insufficient to control the fire. On this basis, the system generates an evaluation report to help decision makers quickly determine the trend of fire development and formulate emergency plans.

[0071] Preferably, step S36 includes the following steps:

[0072] Step S361: Acquire fire joint evolution data of historical fire status scenes;

[0073] Step S362: establishing a probability distribution mapping relationship between the fire mobilization state and the fire situation evolution based on a preset Bayesian structural time series model, so as to obtain a fire situation prediction model framework in the fire state space;

[0074] Step S363: Performing model training processing on the fire state space fire trend prediction model architecture based on the historical fire state scene fire joint evolution data to generate a fire state space fire trend prediction model;

[0075] Step S364: Perform fire state fire scene trend assessment processing on the fire state local space fire joint feature data through the fire state space fire trend prediction model to generate fire state fire scene trend assessment data.

[0076] The present invention can build a comprehensive understanding of the laws of fire development by acquiring data on historical firefighting status and fire evolution. These historical data provide rich basic data for the establishment and training of subsequent fire prediction models, and provide a priori probability characteristics of fire impact and fire evolution. Historical fire evolution data helps the system identify the patterns and characteristics of fire development, helps to predict the fire situation that may occur in the future in advance, improves the predictability of the system, provides historical samples for the fire scene state prediction model, ensures the accuracy and reliability of subsequent models, and reduces the uncertainty in fire scene prediction. Using the Bayesian structural time series model, the relationship between the fire mobilization state and the fire development trend is established to form a scientific probability distribution mapping relationship, enhance the prediction ability of the fire situation, enable the system to handle uncertainty and time series characteristics, especially the dynamic fire mobilization state and the time dependence of fire development evolution, ensure the dynamic and flexibility of fire situation prediction, and continuously update the prediction results according to real-time data by establishing an accurate model architecture, so that emergency response is more intelligent and the efficiency of fire scene response is improved. By training the model on historical data, the system can continuously improve the accuracy and stability of fire situation prediction, ensuring that the prediction model can effectively adapt to different fire scenarios. Model training can make fire dispatch and fire situation analysis more intelligent and data-driven, reduce human intervention, and optimize the emergency decision-making process. With the enrichment of training data, the prediction accuracy of the model will continue to improve, helping emergency personnel to predict the expansion trend of fire, risk areas and mobilization needs in advance, and improve the efficiency of emergency management. By applying the trained fire situation prediction model, the real-time local fire scene feature data can be evaluated and predicted, thereby generating high-precision fire scene situation assessment data, improving the real-time and accuracy of fire scene assessment, ensuring that emergency personnel can know the development trend of the fire in advance and make a quick and accurate emergency response. Based on the fire situation assessment results, the system can provide targeted fire resource dispatch suggestions, further optimize the dispatch efficiency of fire equipment and personnel, and improve the success rate of fire disposal.

[0077] In the embodiment of the present invention, historical data related to fire are extracted from historical fire records. These data include the state changes of fire equipment during the development of the fire, the fire spread path, the fire extinguishing time, and the equipment scheduling, etc. The data sources come from the logs, monitoring records, and sensor data collected by the fire protection system. For example, the system reviews past fire cases in a building, analyzes the spread of fires at different time points, the mobilization and operation status of fire protection equipment (such as fire pumps, fire extinguishers, automatic sprinkler systems, etc.), and the specific details of how the fire was finally controlled. These historical data are integrated into historical fire protection state scene fire joint evolution data, including the time of fire occurrence, development speed, fire extinguishing effect, fire protection equipment response status, etc. Using the preset Bayesian structure time series model, a probability distribution mapping relationship between the fire equipment mobilization state and the fire state evolution is established, that is, the time series probability space when different scenes send fires. The Bayesian structure time series model is used to process the fire evolution process with high uncertainty in the time dimension, and predict the future fire situation in combination with historical data. Based on historical fire evolution data and equipment mobilization data, a multivariate time series model is constructed. The model considers the temporal characteristics of fire (such as spread speed, intensity change) and the mobilization and response of firefighting equipment (such as the impact on fire control when the fire pump is started). By correlating the fire development trend with the mobilization of firefighting equipment, the system establishes a probability distribution mapping relationship. This mapping relationship helps predict the future changes of the fire situation under specific equipment mobilization conditions and generates a fire state space fire state prediction model architecture. By using the acquired historical fire state scene fire joint evolution data, the fire state space fire state prediction model architecture is trained. The training process aims to optimize the model so that it can more accurately predict the future evolution of the fire scene. Using the supervised learning method, the firefighting equipment mobilization status in the historical data and the actual results of fire evolution are used as training samples. By adjusting the model parameters, the prediction results are closer to the historical evolution results. For example, the system can adjust the probability distribution weights in the Bayesian model according to the fire spread speed in the historical data to make it more consistent with the actual fire development trend. Through repeated training, the system generates an optimized fire status spatial fire state prediction model, which can provide accurate fire state prediction based on real-time data. Using the trained fire status spatial fire state prediction model, the local spatial fire joint feature data of the fire status is processed to evaluate the fire scene state. The data of the current local spatial node is input through the prediction model. The model will predict the possible further development of the fire based on the comparison of historical data and current real-time data. Through this prediction, the system can derive the possible path of fire spread, changes in fire intensity, and risk levels of different spatial nodes. For example, the fire data in a certain area shows that the temperature and smoke concentration are continuing to rise, while the status of the fire-fighting equipment in the area shows insufficient water pressure.The model predicts through calculations that the fire in the area may further expand and affect adjacent areas. Based on this, the system generates fire scene situation assessment data for firefighting status, which provides decision support for subsequent emergency response and resource allocation.

[0078] Preferably, step S363 includes the following steps:

[0079] Perform fire evolution time series feature analysis of historical fire state scenarios based on the fire joint evolution data of historical fire state scenarios to generate fire evolution time series feature data of historical fire state scenarios;

[0080] Performing fire evolution time series distribution evaluation processing of historical fire state scenarios according to fire evolution time series characteristic data of historical fire state scenarios to generate fire evolution time series distribution evaluation data of historical fire state scenarios;

[0081] Perform a fire state scenario fire evolution time series prior distribution analysis based on historical fire state scenario fire evolution time series distribution assessment data to generate fire state scenario fire evolution time series prior distribution data;

[0082] The fire state space fire trend prediction model architecture is trained through the fire state scenario time series fire evolution prior distribution data to generate a fire state space fire trend prediction model.

[0083] The present invention analyzes the time series characteristics of historical fire evolution, extracts the key nodes and trends of fire development, identifies the typical time series patterns of fire occurrence and spread, helps the system establish a time series model of fire development laws, clarifies the initiation, development and spread of fire, and provides accurate time series feature data support for subsequent fire prediction. This time series feature analysis enhances the system's understanding of the dynamic evolution of fire, can predict the possible time points and situation changes of fire development in advance, and helps optimize fire emergency strategies. Through time series distribution evaluation processing, the system can quantitatively analyze the time distribution of fire evolution, identify the time series characteristics of different fire evolution stages and their influencing factors, and the generated time series distribution evaluation data helps the system identify key information such as high-risk periods of fire and time nodes of accelerated fire spread, thereby providing more targeted time windows and preventive measures for emergency response, ensuring that the time characteristics of fire evolution are accurately evaluated, and making the prediction model more refined and dynamic. By analyzing the prior distribution of the fire evolution time series, the system can determine the probability range of fire occurrence and the key distribution characteristics in the time series based on historical data, provide prior information for the prediction model, improve the prediction accuracy of the model, and enable the system to better cope with complex fire evolution situations based on the prior distribution, reduce the uncertainty in the prediction, and make more effective inferences when facing new fire scenes. By training the model with prior distribution data, a more accurate fire situation prediction model can be constructed, which has the ability to make accurate predictions based on historical evolution laws and real-time data. The model training process is based on prior data, which can continuously optimize and adjust the performance of the model, improve the prediction accuracy and reliability of the fire situation, and ensure that accurate decisions can be made quickly in emergency response. The generated fire situation prediction model can provide dynamic situation predictions during the development of the fire, ensuring that firefighting equipment and resources can be reasonably allocated and respond to the fire in a timely manner.

[0084] In the embodiment of the present invention, fire joint evolution data is extracted from the historical fire state scene database, including key parameters of the fire at different times, such as flame spread speed, temperature change, smoke concentration change, equipment response time, etc. The system performs time series feature analysis on these data to determine the development characteristics and laws of the fire at different times, performs time series analysis on each historical fire, and decomposes the key stages in the fire evolution process, such as initial combustion, spread, extinguishing, etc. Through these analyses, the system generates historical fire state scene fire evolution time series feature data, which describes in detail the characteristics of the entire process of the fire from the starting point to the end point, and can be used to analyze the evolution law of the fire in different types of buildings. The previously generated historical fire state scene fire evolution time series feature data is statistically and distributedly evaluated, and the distribution characteristics of each stage in the fire evolution process are evaluated by analyzing the time series change pattern in the historical data. For example, the time distribution of a fire from initial combustion to its spread, or the time interval distribution from the initial stage of a fire to the response of firefighting equipment, uses time series analysis tools to model historical data and identify high-frequency distribution patterns of fire evolution. Through this evaluation, the system can generate historical fire state scenario fire evolution time series distribution evaluation data, which describes the distribution characteristics of fire on the time axis, including important characteristics such as fire development speed and response time. Based on the historical fire state scenario fire evolution time series distribution evaluation data, the time series prior distribution analysis of fire evolution is performed. The purpose of the prior distribution analysis is to provide a probabilistic basis for future fire situation prediction, and to infer the future evolution trend of fire by combining historical evolution data. The time series characteristic distribution of fire is modeled as a probability distribution. For example, the spread speed of a fire in the initial stage is a normal distribution, or the distribution of equipment response time may conform to a certain prior probability model. Through this prior analysis, the system generates fire evolution time series prior distribution data for fire state scenarios, which provide preliminary probability input for subsequent prediction models. The designed fire state prediction model is trained using the fire evolution time series prior distribution data for fire state scenarios. The purpose of model training is to be able to identify the probability of future fire evolution and dynamically adjust the prediction results based on real-time input data. The fire evolution prior distribution in historical data is used as the initial parameter of the model, and the model is adjusted in combination with multi-source data in actual fire scenes (such as temperature, smoke concentration, and equipment status). Through multiple iterative training, the system can continuously optimize the prediction accuracy of the model and generate a fire state space fire situation prediction model, which can receive the latest data of the fire scene in real time and provide accurate fire situation prediction.

[0085] Preferably, step S364 includes the following steps:

[0086] The local space fire joint characteristic data of the fire state is transmitted to the fire state space fire trend prediction model to perform the fire state local space fire probability analysis and generate the fire state local space fire probability data;

[0087] Perform local space probability correlation feature analysis based on local space fire probability data of fire fighting status to generate local space probability correlation feature data;

[0088] Perform time series probability evolution analysis based on local space fire probability data of fire status to generate local space fire time series probability data of fire status;

[0089] Based on the local space probability association feature data and the local space fire time series probability data of the fire state, the local space fire probability data of the fire state is processed for fire scene situation assessment to generate fire scene situation assessment data of the fire state.

[0090] The present invention inputs the local space fire joint feature data into the prediction model, accurately analyzes the probability of fire when the fire fighting equipment is applied, identifies the possibility of fire at different spatial nodes, provides an important probability basis for fire emergency decision-making, identifies the high-risk areas of fire in the local space, helps decision makers give priority to areas with greater risks, and optimizes resource scheduling. The local fire probability analysis enhances the prediction ability of the system, helps to refine and differentiate emergency response strategies, and enables the system to perform risk assessment with higher accuracy. By analyzing the correlation characteristics of the local space fire probability data, the correlation between the spatial nodes is found, the potential paths for the fire to spread and spread in different areas are identified, and the spatial propagation pattern of the fire is identified through the probability space correlation relationship, so that the prediction model can not only evaluate the fire risk of a single node, but also reveal the correlation risk between different nodes, further improving the comprehensiveness of the fire situation analysis. Time series probability evolution analysis can dynamically track the evolution of fires, predict the changing trends of fires at different time nodes, and better judge the speed and direction of fire spread based on the analysis results. It can accurately predict the evolution of fires in the future, ensuring that emergency responders can deploy corresponding prevention and control measures in advance. The generation of time series probability data further improves the timeliness and accuracy of fire prediction, ensuring that the fire emergency management system can respond promptly and effectively according to real-time changes. By combining local spatial probability association characteristics and time series probability data, the overall situation of the current fire scene can be comprehensively and dynamically evaluated, ensuring that decision makers can obtain accurate fire situation assessment results. This evaluation process enables the system to make comprehensive judgments on complex fire scenes, providing more valuable analysis data for the emergency command center, facilitating the scientific and efficient allocation of resources and firefighters. The fire scene situation assessment data improves the overall situation awareness of the fire system, enabling the system to adjust the emergency response strategy in real time and dynamically to adapt to the actual situation of fire development.

[0091] In an embodiment of the present invention, the acquired local space fire joint feature data of the fire state is transmitted to the trained fire state space fire state prediction model. The model calculates the probability of fire occurrence at the local space node by analyzing the input multi-source feature data (such as the temperature, smoke concentration, fire equipment status, etc. of the fire occurrence area). The model generates a probability value based on the input data to indicate the possibility of fire occurrence or continued spread in the local space. Assuming that the temperature and smoke concentration in a certain area rise sharply and the working capacity of the equipment is close to saturation, the model may calculate that the probability of further expansion of the fire in the area is high. The system generates local space fire probability data of the fire state based on these calculation results and records it for further analysis. By further analyzing the correlation characteristics of the local space fire probability data of the fire state, the correlation between the fires in different space nodes is evaluated, that is, if a fire occurs in a space node, whether it will cause fire risks in the surrounding areas. By analyzing the physical adjacent relationship and fire spread characteristics (such as wind direction, building structure) between each local space node, a correlation model of fire probability is established. For example, if the probability of fire in a room is high, and the room is connected to another room through a ventilation system, the system may identify that the fire probabilities of the two rooms are correlated. Based on these association analyses, the system generates local spatial probability association feature data, revealing the potential connection between different spatial nodes in the spread of fire. Based on the local spatial fire probability data of the fire status, the temporal probability evolution analysis is performed. The purpose of this analysis is to predict the evolution trend of the fire at different times, that is, the speed and direction of the fire expansion, and to evaluate its possibility in the future by combining the time factor. The probability change of the fire in the local space is modeled using time series analysis technology. For example, if the current probability of fire in a certain area is gradually increasing, and the temperature and smoke concentration in the surrounding area are also increasing, the system may predict that the fire will spread to the adjacent area in the next few minutes. By analyzing the time series data of fire occurrence and expansion, the local spatial fire time series probability data of the fire status is generated, which can provide accurate time warning for the fire brigade. The local spatial probability association feature data is combined with the local spatial fire time series probability data of the fire status to evaluate the overall fire scene situation. By comprehensively considering the fire probability, spatial correlation and time series changes in the local area, and based on the local spatial fire probability data of the fire status, the overall fire scene situation analysis is performed. For example, if the fire probability in multiple adjacent spaces is high and the fire spreads rapidly in the time series, the system will assess that the fire may spread rapidly to a larger area. The generated fire status and fire scene situation assessment data will include the overall situation of fire development, the affected area, and the effectiveness of equipment response, which will be directly used in the emergency command system to help decision makers formulate more effective response strategies.

[0092] Preferably, step S4 comprises the following steps:

[0093] Step S41: performing fire status fire scene risk analysis according to the fire status fire scene situation assessment data to generate fire status fire scene risk data;

[0094] Step S42: extracting target fire scene data from the fire scene risk data of the fire state based on a preset fire hazard risk threshold, and generating target fire scene data;

[0095] Step S43: Analyze crowd flow behavior characteristics according to crowd flow monitoring data to generate crowd flow behavior characteristic data;

[0096] Step S44: Analyze the crowd fire scene data according to the crowd behavior characteristic data to generate crowd fire scene data;

[0097] Step S45: Perform fire emergency scene data analysis based on the target fire scene data and the crowd fire scene data to generate fire emergency scene data;

[0098] Step S46: Performing a fire emergency scene dynamic weight analysis on the fire emergency scene data based on the fire status fire scene risk data of the target fire scene data and the crowd behavior characteristic data of the crowd fire scene data to generate fire emergency scene dynamic weight data.

[0099] Through risk analysis of fire scene situation assessment data, the present invention can accurately identify the potential risks of the current fire scene, determine the threats and impact areas that may be caused by the fire, help the system quickly lock in areas and locations with higher fire risks, provide effective early warning information, help formulate emergency plans in advance and optimize the allocation of fire resources, improve the fire situation awareness ability, help decision makers scientifically evaluate the risks brought by fire, and make corresponding response measures according to the risk level. By setting the threshold of fire hazard risk, the system can automatically screen out high-risk fire scenes that exceed the risk threshold, as well as scenes that do not have fires after firefighting by firefighting equipment, ensure that the areas with the greatest fire hazards are monitored, simplify the data extraction process in complex fire scenes, and enable the system to efficiently identify and extract key target fire scenes, which helps to optimize the accuracy of fire emergency response, give priority to the most dangerous fire scenes, reduce resource waste, and improve the efficiency and accuracy of emergency decision-making. Through the analysis of crowd monitoring data, the system can grasp the dynamics of people at the fire scene or in the affected area in real time, provide detailed information on the density of people, the direction and speed of people flow, understand the distribution of people at the fire scene, and facilitate the formulation of evacuation strategies and the optimization of the design of evacuation channels to ensure the safe evacuation of people. The generation of crowd behavior feature data improves the system's perception of people's behavior, and can more accurately predict the behavior patterns of people flow, reducing the risk of confusion and casualties in emergency situations. Through in-depth analysis of crowd behavior feature data, it is possible to accurately grasp the densely populated areas and evacuation directions in the fire scene, generate targeted fire scene data, and help optimize fire emergency measures, so that emergency response can fully consider the flow of people, and ensure that resources and evacuation paths can be reasonably arranged in the fire scene. The crowd fire scene data makes the system more flexible and accurate in the fire emergency process, improves the effectiveness of emergency response, and ensures that people can safely and quickly evacuate dangerous areas. By combining the target fire scene and crowd flow data, the system can generate more complete fire emergency scene data, comprehensively reflect the fire situation and crowd behavior, provide all-round data support for emergency response, and enhance the system's ability to grasp the overall emergency scene. It ensures that fire emergency measures can be dynamically adjusted according to the development of the fire and changes in population density. The generation of fire emergency scene data helps the system optimize emergency response strategies, ensure the rational allocation and use of personnel, equipment, and resources, and improve overall emergency efficiency.By performing dynamic weight analysis on fire scene risk data and crowd behavior characteristic data, it is possible to give priority to areas with higher risk levels and dense populations, thereby improving the accuracy of emergency response. Dynamic weight analysis enables the system to flexibly adjust the allocation of emergency resources according to real-time changes in the fire, ensuring that emergency resources and equipment are allocated to the locations where they are most needed, reducing fire losses, and making the system adaptive and flexible. It can dynamically adjust emergency strategies according to on-site fire scenes and personnel, ensuring the effective execution and response speed of the overall emergency action.

[0100] In the embodiment of the present invention, the risk analysis of the fire scene is performed based on the fire scene state assessment data of the fire state, and the potential risk of fire spread is analyzed, including the impact of the fire on the building structure, the speed and direction of the fire spread, and the response capability of the equipment. By analyzing the burning intensity, spread speed and possible diffusion path of the fire in different areas, the risk level of each area is calculated, and the fire prediction model is combined with the maximum operating capacity of the equipment to generate the fire scene risk data of the fire state, which includes the fire risk level of each area and the possible resource mobilization information. The risk data is screened by the preset fire hazard risk threshold. The threshold represents an acceptable upper limit of the fire risk. According to this threshold, the high-risk fire scene is extracted, the fire risk data of each area is analyzed, and the areas exceeding the risk threshold are screened and marked as target fire scenes. These areas are usually large fires and fast spreading areas. According to these data, target fire scene data is generated, and a basis is provided for subsequent emergency response. The crowd monitoring data is extracted from the monitoring equipment deployed in the crowded area, and the crowd behavior characteristics are analyzed. The system analyzes the key behavior characteristics of the crowd such as the flow direction, density, and residence time, and identifies the behavior characteristics of the personnel by analyzing the dynamic information in the crowd monitoring data. For example, when a fire occurs, the flow direction and speed of people will be detected to identify whether there are crowds or blocked escape routes. Based on these analyses, the system generates crowd behavior feature data to provide information for evacuation and emergency response. The crowd behavior feature data is combined with the current fire scene to analyze the crowd fire scene data, analyze the relationship between the spread of the fire and the crowd behavior, evaluate the impact of the fire on people, identify the high-risk areas where people are trapped by evaluating the intersection of the fire spread path and the crowd flow direction, and evaluate the effectiveness of the existing evacuation routes. The system generates crowd fire scene data, which includes information such as personnel distribution, flow trend, and evacuation pressure, to facilitate subsequent emergency response. The target fire scene data and the crowd fire scene data are combined for comprehensive analysis, the overlap between the risk area of ​​the fire and the crowded area is analyzed, the threat level of the fire to people is evaluated, and the fire emergency scene data is generated. By analyzing the density of people in the high-risk area of ​​the fire, the priority of the emergency response is determined. For example, if a large number of people are stranded in a high-risk fire area, the area will be marked as an emergency priority response area. The system generates fire emergency scenario data, providing a priority reference for fire resource dispatch and personnel evacuation. Dynamic weight analysis is performed on target fire scenario data, fire status fire scenario risk data, and crowd fire scenario data. The priority of emergency response is determined by calculating the comprehensive weight of fire risk and crowd evacuation pressure in each emergency scenario.Based on factors such as the severity of fire spread, population density, and equipment response capability, dynamic weights are assigned to each area. High-risk areas with dense populations will receive higher weights, and firefighting equipment and emergency resources will be prioritized. Dynamic weight data for fire emergency scenarios will be generated to provide a basis for the rational allocation of resources and emergency decision-making.

[0101] Preferably, step S5 comprises the following steps:

[0102] Step S51: performing fire emergency scene resource demand analysis processing according to the fire emergency scene data to generate fire emergency scene resource demand data, wherein the fire emergency scene resource demand data includes fire emergency scene resource demand scheduling data and fire emergency scene resource demand node data;

[0103] Step S52: establishing a fire emergency scenario demand node map based on the fire emergency scenario resource demand node data and the corresponding fire emergency scenario dynamic weight data, and transmitting the fire emergency scenario resource demand scheduling data to the fire emergency scenario demand node map for demand scheduling mapping, thereby generating a fire emergency scenario demand map;

[0104] Step S53: performing a fire emergency resource intelligent scheduling priority analysis on the fire emergency scenario demand map based on the fire emergency resource data to generate fire emergency resource intelligent scheduling priority data;

[0105] Step S54: Execute the fire emergency resource intelligent scheduling operation through the fire emergency resource intelligent scheduling priority data.

[0106] The present invention can accurately identify the types and quantities of emergency resources required in fire scenes by analyzing the resource requirements of fire emergency scene data, ensure that resource allocation is more reasonable and effective, optimize resource scheduling, avoid resource waste or shortage, ensure that the equipment, personnel and materials required in the emergency response process can be in place in time, and improve the efficiency of emergency disposal. The resource demand data of the fire emergency scene provides detailed demand scheduling information, which lays a data foundation for subsequent resource scheduling and priority analysis, making the emergency response process more scientific and reasonable. The demand node data is combined with the dynamic weight data to establish a complete demand node map, which helps to identify the demand priority and resource distribution of each node, ensure that resource scheduling can be carried out according to actual needs, and generate a demand map through scheduling mapping, so that the system can clearly understand each resource demand point in the fire emergency scene, realize accurate scheduling of emergency resources, and improve the rationality and efficiency of scheduling. The demand node map helps to realize the optimization of resource allocation under complex emergency scenes, ensure that key nodes get resource support first, and improve the coordination and execution effect of the overall emergency response. Through intelligent scheduling priority analysis, it is possible to determine which resources need to be allocated first according to the actual needs and resource conditions of the emergency scenario, thereby optimizing the emergency response speed and effect, significantly improving the accuracy and real-time nature of resource scheduling, ensuring that key areas and high-risk nodes can get emergency support first, and avoiding delays in the best time for emergency response. The priority data of intelligent scheduling of fire emergency resources provides a scientific scheduling basis for emergency commanders, reduces errors in human decision-making, and ensures the efficiency and rationality of resource allocation. By performing intelligent scheduling operations based on scheduling priority data, the system can automatically and quickly deploy emergency resources, reduce delays in the manual scheduling process, improve the efficiency of emergency response, ensure the automation and intelligence of emergency resource scheduling, reduce human intervention, and enhance the system's autonomous scheduling capabilities, so that resources can reach the most needed locations in the shortest time. Through intelligent scheduling operations, scheduling strategies can be dynamically adjusted to ensure the optimal use of resources, further improving the response speed and accuracy of fire emergency management.

[0107] As an embodiment of the present invention, refer to Figure 3 As shown, Figure 1 FIG. 5 is a flow chart of detailed implementation steps of step S5, in this embodiment, step S5 includes:

[0108] Step S51: performing fire emergency scene resource demand analysis processing according to the fire emergency scene data to generate fire emergency scene resource demand data, wherein the fire emergency scene resource demand data includes fire emergency scene resource demand scheduling data and fire emergency scene resource demand node data;

[0109] In the embodiment of the present invention, the resource demand analysis of the fire emergency scene is performed based on the previously generated fire emergency scene data. It is necessary to analyze factors such as the risk level of the fire, the density of the flow of people, and the current status of the equipment to determine the types of resources required for the emergency and their scheduling priorities. According to the fire situation of the scene, the types of emergency resources that need to be deployed are evaluated, such as fire extinguishing equipment (fire pumps, fire extinguishers), firefighters, protective equipment, etc. According to the expansion path of the fire and the density of the flow of people, it is analyzed at which nodes the resources need to be deployed, and the fire emergency scene resource demand node data is generated. These node data represent the specific location and the required resource type. For example, in a commercial building fire scene, multiple resource demand nodes are identified, including the core area of ​​the fire, the key nodes on the evacuation path (such as the staircase), and the refuge places where the flow of people is concentrated. Each node will require different resources according to the fire risk and the evacuation of the crowd, such as high-pressure fire hoses, smoke removal equipment, or additional personnel guidance resources. The system generates fire emergency scene resource demand scheduling data based on these node data to provide accurate demand guidance for subsequent resource scheduling.

[0110] Step S52: establishing a fire emergency scenario demand node map based on the fire emergency scenario resource demand node data and the corresponding fire emergency scenario dynamic weight data, and transmitting the fire emergency scenario resource demand scheduling data to the fire emergency scenario demand node map for demand scheduling mapping, thereby generating a fire emergency scenario demand map;

[0111] In an embodiment of the present invention, a fire emergency scene demand node map is established by combining the fire emergency scene resource demand node data and the fire emergency scene dynamic weight data, and all resource demand nodes and their dynamic weights are spatially laid out to display each resource demand point and its corresponding dynamic weight in the emergency scene in a visual form. The resource demand nodes are mapped for demand scheduling, and the weight of the positional relationship of each node in the emergency scene and the resource scheduling requirements are displayed. These resource demand nodes are matched with the fire emergency scene resource demand scheduling data to generate a complete fire emergency scene demand map, which not only displays the resource demand nodes, but also indicates the scheduling priority according to the dynamic weights of different nodes. For example, in the core area of ​​the fire, fire-fighting equipment is dispatched first, while in the evacuation passages where people are concentrated, evacuation personnel are dispatched first.

[0112] Step S53: performing a fire emergency resource intelligent scheduling priority analysis on the fire emergency scenario demand map based on the fire emergency resource data to generate fire emergency resource intelligent scheduling priority data;

[0113] In an embodiment of the present invention, the fire emergency scenario demand map is further analyzed, and the fire emergency resource data is combined to calculate and allocate intelligent scheduling priorities to ensure that existing resources can be efficiently scheduled according to reasonable priorities. All available fire emergency resource data are obtained, including status information of equipment, vehicles, personnel, etc. For example, the existing fire resources (such as the available number of fire trucks, the status of fire pumps, and the real-time distribution of firefighters) are analyzed. Then, according to the node priority in the demand map, the available resources are allocated according to demand. For example, if the node weight in a certain fire core area is high, fire trucks and high-pressure water guns and other equipment will be dispatched first. Use machine learning algorithms or optimization algorithms to perform intelligent scheduling priority analysis to determine the deployment order of each emergency resource, and generate fire emergency resource intelligent scheduling priority data, which can determine which resources need to be mobilized first and which resources can be deployed secondary according to changes in the fire situation.

[0114] Step S54: Execute the fire emergency resource intelligent scheduling operation through the fire emergency resource intelligent scheduling priority data.

[0115] In the embodiment of the present invention, the actual dispatching task of firefighting resources is performed through the intelligent dispatching priority data of firefighting emergency resources, and resources are allocated in the order of priority to ensure that emergency resources can be quickly deployed to the most needed nodes, and firefighting equipment and personnel are automatically commanded and dispatched. For example, when a fire spreads to a high-risk area, the system will automatically dispatch nearby fire trucks and fire-fighting equipment to the area according to the intelligent dispatching priority to ensure that the fire can be controlled in time. At the same time, the system commands firefighters to quickly enter the high-priority area of ​​the fire scene through the emergency communication system to ensure the orderly conduct of firefighting operations. In addition, the system can also automatically perform some firefighting tasks through technologies such as drones and remote control devices. For example, drones can quickly reach the fire scene for real-time monitoring and information collection, or put in fire-fighting devices. Automated firefighting equipment (such as fire-fighting robots) can quickly reach high-risk areas of fire under the command of the dispatching system, perform firefighting tasks, and dynamically adjust dispatching operations. As firefighting emergency firefighting develops, the dispatching priority is adjusted according to real-time feedback. For example, if the fire in a certain area is controlled, the system will automatically reallocate equipment and personnel, and deploy resources to other areas with higher risks or adjacent areas to ensure that emergency resources are optimally utilized. Through intelligent scheduling operations, the system can significantly improve the response speed and resource utilization efficiency of fire emergencies, ensuring rapid control of fires.

[0116] Preferably, step S53 includes the following steps:

[0117] Perform a fire emergency resource dispatch priority analysis on the fire emergency scenario demand map based on the fire emergency resource data to generate fire emergency resource dispatch priority data;

[0118] The fire emergency scenario dynamic weight data of the fire emergency scenario demand map is updated and monitored in real time, and the fire emergency resource scheduling priority data is intelligently adjusted according to the fire emergency scenario demand map corresponding to the real-time updated fire emergency scenario dynamic weight data to generate fire emergency resource intelligent scheduling priority data.

[0119] By analyzing the emergency resource data and the scene demand map, the present invention can determine which resources need to be allocated first, ensure that key areas can obtain emergency support in time, improve the efficiency of emergency response, avoid errors and unreasonable scheduling caused by human judgment, ensure that resource allocation is more scientific and accurate, and improve the coordination of overall resource management, especially in multi-point emergencies, it can reasonably balance resource allocation to avoid the situation where resources are concentrated in one place while other areas are limited. By real-time monitoring of scene dynamic weight data, it is possible to grasp the changes in fire scenes in a timely manner, especially in complex and dynamically changing emergency scenes, ensure that priority data is adjusted synchronously with actual needs, and intelligently adjust resource scheduling priorities to ensure that emergency resources can be quickly reallocated according to the latest weight data, thereby maximizing the flexibility and timeliness of emergency response. The real-time intelligent adjustment mechanism significantly enhances the adaptive ability of resource scheduling, so that resource allocation can quickly respond to sudden changes, avoid emergency lag problems caused by fixed scheduling strategies, and improve the response ability of the overall fire emergency management system.

[0120] In an embodiment of the present invention, priority analysis is performed on resources in a fire emergency scenario based on fire emergency resource data. Fire emergency resource data includes real-time status information of currently available firefighters and materials. For example, real-time status data of various firefighting materials, such as the available water pressure of fire pumps, the remaining spraying time of fire extinguishers, the location of fire trucks, and the distribution and action capabilities of firefighters, are obtained from sensors and IoT devices. By matching these resource data with the previously generated fire emergency scenario demand map, the dispatchability of each resource is evaluated. For example, if a certain area has a large fire, it is marked as a dispatch point with a higher priority, and the available firefighting equipment and personnel around it are matched according to the resource requirements of the area. The matching of resource availability and demand is analyzed by an algorithm to generate fire emergency resource dispatch priority data, taking into account the arrival time of fire emergency resources, the current state of fire emergency resources, and the urgency of the fire. In addition, considering the dispatch efficiency of resources, equipment with a short distance is dispatched first to reduce the dispatch time, and the response time, working capacity and other factors of the equipment are comprehensively analyzed to generate fire emergency resource dispatch priority data, in which the dispatch order of each resource is subjected to intelligent analysis of the system to ensure that the resources can be efficiently deployed to the most needed nodes in the shortest time. Through sensors and data monitoring equipment, the fire emergency scene demand map is continuously monitored in real time, especially the dynamic weight data in the scene. The dynamic weight reflects the changes in factors such as fire risk, equipment status, crowd density, and fire spread speed of each node in the scene. When the fire situation changes, the weight of each node needs to be adjusted in time. According to the real-time updated sensor data, fire spread speed, and the actual working status of fire-fighting equipment, the dynamic weight data in the scene is updated. For example, assuming that a fire node has been gradually controlled due to the effective response of fire-fighting equipment, the weight of this node will gradually decrease. If the fire in the adjacent area begins to spread, the weight may increase rapidly. Not only is the weight data simply updated, but the priority data of fire emergency resource scheduling is also intelligently adjusted based on this data. The key to intelligent adjustment is to consider the dynamic correlation of adjacent nodes. For example, when the fire of a high-weight node (such as the fire center area) is effectively controlled, the system will automatically reduce the scheduling priority of the node. However, the system will also evaluate the adjacent nodes at the same time. If the fire risk of adjacent nodes increases, the system will give priority to transferring resources to these adjacent areas. The specific intelligent adjustment process is achieved through the following methods: Real-time feedback mechanism: The system monitors the changes in the fire through real-time feedback from fire-fighting equipment (such as water pressure, smoke concentration, etc.). When the fire is under control, the system will automatically reduce the dynamic weight of the node and reallocate the resource to a high-weight node with greater demand.Linked scheduling of adjacent nodes: The system determines which adjacent nodes the fire may spread from by analyzing the physical correlation between adjacent nodes, such as the interaction of ventilation systems, building structures, and pedestrian channels. When the weight of a node decreases, the system will prioritize the analysis of adjacent nodes and increase the resource scheduling priority of the node based on the potential risk of the node. Dynamic priority optimization algorithm: The system runs an optimization algorithm for scheduling priorities and adjusts the priority of resources in real time based on the latest scenario requirements and dynamic weights. Assuming that the fire risk in a certain area is reduced, resources are dynamically reallocated, giving priority to mobilizing resources to other areas with larger fires and higher population density. This process ensures the rational scheduling of resources and avoids waste of resources.

[0121] This specification provides a smart fire emergency management system for executing the smart fire emergency management method as described above. The smart fire emergency management system includes:

[0122] A fire emergency global data integration module is used to obtain fire management area data; perform regional fire emergency global data integration processing on the pre-stored fire monitoring cloud platform according to the fire management area data to generate regional fire emergency global data, wherein the regional fire emergency global data includes environmental perception data of the fire management area, fire equipment status data, crowd monitoring data and fire emergency resource data;

[0123] Multi-source fire monitoring module, used to perform multi-source fire intelligent monitoring and processing in the fire management area based on environmental perception data, and generate real-time multi-source fire data;

[0124] A fire status fire scene situation assessment module is used to perform fire status fire scene situation assessment processing based on real-time multi-source fire data and fire equipment status data to generate fire status fire scene situation assessment data;

[0125] The fire emergency scene dynamic weight analysis module is used to analyze the fire emergency scene data based on the fire scene situation assessment data and the crowd monitoring data to generate the fire emergency scene data; perform the fire emergency scene dynamic weight analysis based on the fire emergency scene data to generate the fire emergency scene dynamic weight data;

[0126] The fire emergency resource intelligent scheduling execution module is used to perform fire emergency resource intelligent scheduling priority analysis on fire emergency scenario data based on fire emergency resource data and fire emergency scenario dynamic weight data, generate fire emergency resource intelligent scheduling priority data; and execute fire emergency resource intelligent scheduling operations through fire emergency resource intelligent scheduling priority data.

[0127] The beneficial effect of the present application is that the present application collects and integrates the environmental perception data, fire equipment status data, crowd monitoring data and fire emergency resource data of the fire management area in real time, and performs intelligent monitoring and evaluation processing of the fire scene based on these data, thereby overcoming the problem of untimely integration of multi-source data in the prior art, and realizing real-time early warning and rapid response. In particular, through the design of the adaptive multi-source abnormal perception signal monitoring engine, it is possible to monitor abnormal information of fire in real time, and effectively improve the reaction speed of emergency prejudgment. Through the combination of fire scene situation assessment data and crowd monitoring data, the dynamic weight analysis of the fire emergency scene is realized. Through the dynamic weight analysis of the fire emergency scene of the fire scene risk data and the crowd behavior characteristic data, the emergency resource scheduling is made more accurate and effective, and the problem of poor linkage effect in the prior art is improved, so that the relationship between the fire scene situation and the emergency resource scheduling is closer, ensuring the accuracy and efficiency of emergency decision-making. Fire emergency resources are allocated through the dynamic weight of the fire emergency scene, and the scheduling status of the scheduling resources is intelligently updated, which further improves the accuracy of fire prevention and control. Through the intelligent scheduling priority analysis, it is ensured that the fire emergency resources are reasonably scheduled according to the real-time updated scene dynamic weight data, which effectively solves the problem of insufficient resource scheduling optimization in the prior art.

[0128] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0129] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A smart fire emergency management method, characterized in that: The following steps are involved: Step S1: Obtain fire management area data; perform regional fire emergency global data integration processing on the pre-stored fire monitoring cloud platform according to the fire management area data to generate regional fire emergency global data, wherein the regional fire emergency global data includes environmental perception data of the fire management area, fire equipment status data, crowd monitoring data and fire emergency resource data; Step S2: Perform multi-source fire intelligent monitoring and processing in the fire management area according to the environmental perception data to generate real-time multi-source fire data; Step S3: Performing fire scene situation assessment processing on a fire status according to real-time multi-source fire data and fire equipment status data to generate fire scene situation assessment data; Step S4: Performing fire emergency scene data analysis based on the fire scene situation assessment data and the crowd monitoring data to generate fire emergency scene data; performing fire emergency scene dynamic weight analysis based on the fire emergency scene data to generate fire emergency scene dynamic weight data; Step S5: performing fire emergency resource intelligent dispatch priority analysis on the fire emergency scenario data based on the fire emergency resource data and the fire emergency scenario dynamic weight data, generating fire emergency resource intelligent dispatch priority data; executing the fire emergency resource intelligent dispatch operation according to the fire emergency resource intelligent dispatch priority data; Wherein, step S5 comprises the following steps: Step S51: performing fire emergency scene resource demand analysis processing according to the fire emergency scene data to generate fire emergency scene resource demand data, wherein the fire emergency scene resource demand data includes fire emergency scene resource demand scheduling data and fire emergency scene resource demand node data; Step S52: establishing a fire emergency scenario demand node map based on the fire emergency scenario resource demand node data and the corresponding fire emergency scenario dynamic weight data, and transmitting the fire emergency scenario resource demand scheduling data to the fire emergency scenario demand node map for demand scheduling mapping, thereby generating a fire emergency scenario demand map; Step S53: performing a fire emergency resource intelligent scheduling priority analysis on the fire emergency scenario demand map based on the fire emergency resource data to generate fire emergency resource intelligent scheduling priority data; Step S54: Execute the fire emergency resource intelligent scheduling operation through the fire emergency resource intelligent scheduling priority data.

2. The smart fire emergency management method according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: Analyze historical multi-source baseline perception signals according to environmental perception data to generate historical multi-source baseline perception signals; Step S22: Designing an adaptive monitoring engine for multi-source abnormal perception signals based on historical multi-source baseline perception signals to generate an adaptive multi-source abnormal perception signal monitoring engine; Step S23: performing real-time multi-source abnormal perception signal monitoring and processing on the environmental perception data based on the adaptive multi-source abnormal perception signal detection engine to generate a real-time multi-source abnormal perception signal; Step S24: Perform real-time multi-source fire data analysis based on the real-time multi-source abnormal perception signal to generate real-time multi-source fire data.

3. The intelligent fire emergency management method according to claim 2 is characterized in that: Step S3 includes the following steps: Step S31: extracting abnormal perception signal space nodes according to real-time multi-source abnormal perception signals to generate abnormal perception signal space node data; Step S32: performing spatial multi-source fire node identification processing on the corresponding real-time multi-source fire data through the abnormal sensing signal spatial node data to generate real-time spatial multi-source fire data; Step S33: analyzing the equipment fire emergency mobilization status according to the fire equipment status data, and generating equipment fire emergency mobilization status data; Step S34: performing fire state space fire joint feature analysis based on the equipment fire emergency mobilization state data and the real-time spatial multi-source fire data to generate fire state space fire joint feature data; Step S35: performing local spatial node division processing on the fire status spatial fire joint characteristic data to generate fire status local spatial fire joint characteristic data; Step S36: Perform fire scene situation assessment processing on the fire state based on the fire state local space fire joint feature data to generate fire scene situation assessment data on the fire state.

4. The intelligent fire emergency management method according to claim 3 is characterized in that: Step S36 includes the following steps: Step S361: Acquire fire joint evolution data of historical fire status scenes; Step S362: establishing a probability distribution mapping relationship between the fire mobilization state and the fire situation evolution based on a preset Bayesian structural time series model to obtain a fire situation prediction model framework in the fire state space; Step S363: performing model training processing on the fire state space fire trend prediction model architecture based on the historical fire state scene fire joint evolution data to generate a fire state space fire trend prediction model; Step S364: Perform fire state fire scene trend assessment processing on the fire state local space fire joint feature data through the fire state space fire trend prediction model to generate fire state fire scene trend assessment data.

5. The smart fire emergency management method according to claim 4 is characterized in that: Step S363 includes the following steps: Perform fire evolution time series feature analysis of historical fire state scenarios based on the fire joint evolution data of historical fire state scenarios to generate fire evolution time series feature data of historical fire state scenarios; Performing fire evolution time series distribution evaluation processing of historical fire state scenarios according to fire evolution time series characteristic data of historical fire state scenarios to generate fire evolution time series distribution evaluation data of historical fire state scenarios; Perform a fire state scenario fire evolution time series prior distribution analysis based on historical fire state scenario fire evolution time series distribution assessment data to generate fire state scenario fire evolution time series prior distribution data; The fire state space fire trend prediction model architecture is trained through the fire state scenario time series fire evolution prior distribution data to generate a fire state space fire trend prediction model.

6. The intelligent fire emergency management method according to claim 4 is characterized in that: Step S364 includes the following steps: The local space fire joint characteristic data of the fire state is transmitted to the fire state space fire trend prediction model to perform the fire state local space fire probability analysis and generate the fire state local space fire probability data; Perform local space probability correlation feature analysis based on local space fire probability data of fire fighting status to generate local space probability correlation feature data; Perform time series probability evolution analysis based on local space fire probability data of fire status to generate local space fire time series probability data of fire status; Based on the local space probability association feature data and the local space fire time series probability data of the fire state, the local space fire probability data of the fire state is processed for fire scene situation assessment to generate fire scene situation assessment data of the fire state.

7. The smart fire emergency management method according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: performing fire status fire scene risk analysis according to the fire status fire scene situation assessment data to generate fire status fire scene risk data; Step S42: extracting target fire scene data from the fire scene risk data of the fire state based on a preset fire hazard risk threshold, and generating target fire scene data; Step S43: Analyze crowd flow behavior characteristics according to crowd flow monitoring data to generate crowd flow behavior characteristic data; Step S44: Analyze the crowd fire scene data according to the crowd behavior characteristic data to generate crowd fire scene data; Step S45: Perform fire emergency scene data analysis based on the target fire scene data and the crowd fire scene data to generate fire emergency scene data; Step S46: Performing a fire emergency scene dynamic weight analysis on the fire emergency scene data based on the fire status fire scene risk data of the target fire scene data and the crowd behavior characteristic data of the crowd fire scene data to generate fire emergency scene dynamic weight data.

8. The intelligent fire emergency management method according to claim 1, characterized in that: Step S53 includes the following steps: Perform a fire emergency resource dispatch priority analysis on the fire emergency scenario demand map based on the fire emergency resource data to generate fire emergency resource dispatch priority data; The fire emergency scenario dynamic weight data of the fire emergency scenario demand map is updated and monitored in real time, and the fire emergency resource scheduling priority data is intelligently adjusted according to the fire emergency scenario demand map corresponding to the real-time updated fire emergency scenario dynamic weight data to generate fire emergency resource intelligent scheduling priority data.

9. A smart fire emergency management system, characterized in that: Used to execute the smart fire emergency management method as claimed in claim 1, the smart fire emergency management system comprises: A fire emergency global data integration module is used to obtain fire management area data; perform regional fire emergency global data integration processing on the pre-stored fire monitoring cloud platform according to the fire management area data to generate regional fire emergency global data, wherein the regional fire emergency global data includes environmental perception data of the fire management area, fire equipment status data, crowd monitoring data and fire emergency resource data; Multi-source fire monitoring module, used to perform multi-source fire intelligent monitoring and processing in the fire management area based on environmental perception data, and generate real-time multi-source fire data; A fire status fire scene situation assessment module is used to perform fire status fire scene situation assessment processing based on real-time multi-source fire data and fire equipment status data to generate fire status fire scene situation assessment data; The fire emergency scene dynamic weight analysis module is used to analyze the fire emergency scene data based on the fire scene situation assessment data and the crowd monitoring data to generate the fire emergency scene data; perform the fire emergency scene dynamic weight analysis based on the fire emergency scene data to generate the fire emergency scene dynamic weight data; The fire emergency resource intelligent scheduling execution module is used to perform fire emergency resource intelligent scheduling priority analysis on fire emergency scenario data based on fire emergency resource data and fire emergency scenario dynamic weight data, generate fire emergency resource intelligent scheduling priority data; and execute fire emergency resource intelligent scheduling operations through fire emergency resource intelligent scheduling priority data.

Images