CN119250429B

CN119250429B - Intelligent fire emergency management method and system

Info

Publication number: CN119250429B
Application number: CN202411307262.2A
Authority: CN
Inventors: 汪孝军
Original assignee: Hunan Junte Intelligent Technology Co ltd
Current assignee: Hunan Junte Intelligent Technology Co ltd
Priority date: 2024-09-19
Filing date: 2024-09-19
Publication date: 2025-03-28
Anticipated expiration: 2044-09-19
Also published as: CN119250429A

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

Intelligent fire emergency management method and system

Technical Field

The invention relates to the technical field of intelligent fire protection, in particular to an intelligent fire protection emergency management method and system.

Background

The intelligent fire emergency management is an innovative solution for performing intelligent and digital upgrading on the fire emergency management mode by utilizing the front technical means such as the Internet of things, big data, artificial intelligence and the like. With the acceleration of the modern urban process, urban building and population density are continuously increased, the occurrence probability and complexity of fire are also improved, and the traditional fire emergency management has difficulty in coping with the current complicated and changeable fire emergency situations. The intelligent fire emergency management method is capable of accurately identifying fire hazards and intelligently analyzing and predicting the situation of fire occurrence by introducing the internet of things technology and carrying out multi-source data acquisition and real-time monitoring on the fire management area. The application of big data and artificial intelligence technology enables the intelligent fire emergency management method to construct a dynamic prediction and evaluation model of a fire emergency scene, provides an accurate emergency resource scheduling strategy and improves the speed and efficiency of fire emergency response. However, the existing intelligent fire emergency management method still has some defects, in the aspect of associated information processing, the multi-source data are difficult to integrate in time, the response speed of emergency pre-judgment is low, real-time early warning and quick response cannot be achieved, the linkage effect in fire emergency management is poor, efficient dynamic weight analysis between a fire scene situation and emergency resource scheduling cannot be conducted, the accuracy and effectiveness of emergency decision are further affected, a large improvement space still remains in the aspects of fire prevention and control accuracy and efficiency, and particularly, in the aspect of linkage management of emergency resource scheduling and fire scene risk assessment, a sufficient intelligent processing means is lacked.

Disclosure of Invention

Based on the above, the present invention provides a method and a system for intelligent fire emergency management, so as to solve at least one of the above technical problems.

In order to achieve the above purpose, an intelligent fire emergency management method comprises the following steps:

the method comprises the steps of S1, acquiring fire control management area data, carrying out regional fire control emergency global data integrated processing on a pre-stored fire control monitoring cloud platform according to the fire control management area data, and generating regional fire control emergency global data, wherein the regional fire control emergency global data comprise environment sensing data, fire control equipment state data, people flow monitoring data and fire control emergency resource data of a fire control management area;

s2, performing intelligent multi-source fire disaster monitoring processing of a fire control management area according to the environment sensing data to generate real-time multi-source fire disaster data;

step S3, performing fire-fighting status fire scene state evaluation processing according to the real-time multi-source fire data and the fire-fighting equipment status data to generate fire-fighting status fire scene state evaluation data;

step S4, fire emergency scene data analysis is carried out based on fire scene potential state evaluation data and people stream monitoring data to generate fire emergency scene data;

and S5, performing fire emergency resource intelligent scheduling priority analysis on the fire emergency scene data based on the fire emergency resource data and the fire emergency scene dynamic weight data to generate fire emergency resource intelligent scheduling priority data, and executing fire emergency resource intelligent scheduling operation through the fire emergency resource intelligent scheduling priority data.

The invention can comprehensively know the condition of the current fire control management area by acquiring the multi-source data (such as environment sensing data, fire control equipment state data, people flow monitoring data and fire control emergency resource data) of the fire control management area. After the data are integrated, regional fire emergency global data are formed, a reliable data base is provided for subsequent intelligent monitoring, scene evaluation and emergency resource scheduling, unified management of multi-source heterogeneous data is realized, information islands among all fire subsystems are broken, the efficiency and accuracy of data processing are improved, and a solid base is laid for subsequent intelligent decision. Through the analysis to the environmental perception data, can realize the intelligent monitoring of conflagration, the system can real-time supervision conflagration risk and generate multisource conflagration data, multisource conflagration intelligent monitoring has improved conflagration risk identification's precision and speed, has effectively reduced false alarm rate or missing report rate, ensures the early discovery of conflagration, utilizes thing networking sensor network and big data analysis, has realized accurate discernment and the real-time supervision of conflagration hidden danger, has improved the intelligent level of conflagration early warning by a wide margin. The comprehensive analysis of the real-time multi-source fire data and the fire-fighting equipment state data accurately evaluates the situation of the current fire scene, generates fire-fighting state fire scene state evaluation data, helps a system to rapidly judge the development trend of the fire, timely takes targeted emergency measures, and performs fusion analysis on the fire-fighting equipment state and fire scene information, so that the evaluation accuracy is greatly improved, and firefighters can make more accurate emergency decisions based on the real-time scene situation. The fire scene evaluation data and the people stream monitoring data are combined, so that people stream dynamic conditions in the fire influence range can be accurately analyzed, the system is helped to generate comprehensive fire emergency scene data, risks in different areas can be prioritized through dynamic weight analysis, emergency resources are ensured to be distributed to the most urgent area, the analysis capability and accuracy of the fire emergency scene are effectively improved, the situation of the intensive areas can be fully considered during emergency treatment, and the casualties risk is furthest reduced. Based on the fire emergency scene data and the dynamic weight data, intelligent scheduling priority analysis is performed, emergency resources can be reasonably configured by the system, and the resources are ensured to be scheduled to the area with the largest risk preferentially. The intelligent scheduling mechanism can greatly improve the resource utilization efficiency, avoid resource waste, simultaneously ensure the timeliness and the effectiveness of emergency response to the greatest extent, ensure that fire emergency resources can be scheduled in an optimal mode in a complex fire scene, reduce the emergency response time and improve the overall rescue efficiency.

The present specification provides an intelligent fire emergency management system for executing the intelligent fire emergency management method as described above, the intelligent fire emergency management system comprising:

the regional fire emergency global data integration module is used for acquiring fire management regional data, carrying out regional fire emergency global data integration processing on a pre-stored fire monitoring cloud platform according to the fire management regional data, and generating regional fire emergency global data, wherein the regional fire emergency global data comprises environment sensing data, fire equipment state data, people flow monitoring data and fire emergency resource data of a fire management region;

the multi-source fire monitoring module is used for performing intelligent multi-source fire monitoring processing of the fire control management area according to the environment sensing data to generate real-time multi-source fire data;

The fire-fighting status fire scene potential state evaluation module is used for performing fire-fighting status fire scene potential state evaluation processing according to the real-time multi-source fire data and the fire-fighting equipment status data to generate fire-fighting status fire scene potential state evaluation data;

The fire emergency scene dynamic weight analysis module is used for analyzing fire emergency scene data based on fire scene potential state evaluation data and people flow monitoring data to generate fire emergency scene data;

the intelligent scheduling execution module of the fire-fighting emergency resources is used for analyzing the intelligent scheduling priority of the fire-fighting emergency resources on the basis of the fire-fighting emergency resource data and the dynamic weight data of the fire-fighting emergency scene, generating the intelligent scheduling priority data of the fire-fighting emergency resources, and executing the intelligent scheduling operation of the fire-fighting emergency resources through the intelligent scheduling priority data of the fire-fighting emergency resources.

The intelligent fire scene monitoring and evaluating system has the beneficial effects that the intelligent fire scene monitoring and evaluating system overcomes the problem of untimely multi-source data integration in the prior art by collecting and integrating the environment sensing data, the fire equipment state data, the people stream monitoring data and the fire emergency resource data of the fire management area in real time and performing intelligent monitoring and evaluating processing on the fire scene based on the data, and can realize real-time early warning and quick response. Particularly, by the design of the self-adaptive multisource anomaly perception signal monitoring engine, the anomaly information of the fire can be monitored in real time, and the response speed of emergency pre-judgment is effectively improved. The dynamic weight analysis of the fire emergency scene is realized by combining the fire scene situation evaluation data and the people stream monitoring data, and the fire emergency scene is more accurate and effective in emergency resource scheduling by analyzing the dynamic weight of the fire emergency scene of the fire scene risk data and the people stream behavior characteristic data, so that the problem of poor linkage effect in the prior art is improved, the relationship between the fire scene situation and the emergency resource scheduling is tighter, and the accuracy and the high efficiency of emergency decision are ensured. The fire emergency resources are distributed through the dynamic weight of the fire emergency scene, the scheduling state of the scheduling resources is intelligently updated, the fire prevention and control accuracy is further improved, the reasonable scheduling of the fire emergency resources according to the scene dynamic weight data updated in real time is ensured through the intelligent scheduling priority analysis, and the problem of insufficient resource scheduling optimization in the prior art is effectively solved.

Drawings

FIG. 1 is a schematic flow chart of steps of an intelligent fire emergency management method according to the present invention;

FIG. 2 is a flowchart illustrating the detailed implementation of step S3 in FIG. 1;

FIG. 3 is a flowchart illustrating the detailed implementation of step S5 in FIG. 1;

the achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.

Detailed Description

The following is a clear and complete description of the technical method of the present invention, taken in conjunction with the accompanying drawings, and it is evident that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, are intended to fall within the scope of the present invention.

Furthermore, the drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. The functional entities may be implemented in software or in one or more hardware modules or integrated circuits or in different networks and/or processor methods and/or microcontroller methods.

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

To achieve the above objective, referring to fig. 1 to 3, the present invention provides an intelligent fire emergency management method, comprising the following steps:

As an embodiment of the present invention, as described with reference to fig. 1, a schematic flow chart of steps of an intelligent fire emergency management method of the present invention is provided, in this embodiment, the intelligent fire emergency management method includes the following steps:

In the embodiment of the invention, the environment sensing data are acquired through various sensor devices (such as a temperature sensor, a smoke detector, a CO2 concentration sensor and the like) deployed in the fire control management area, and meanwhile, the maximum running state data of the fire control device are acquired. The maximum operation state data of the fire-fighting equipment refers to the operation capacity of the equipment under normal conditions, such as the upper water pressure limit of the fire pump, the maximum injection time of the fire extinguisher, etc. The people stream monitoring data are used for tracking the dense areas and the flowing directions of people in real time through the deployed monitoring equipment. And acquiring fire emergency resource data in the fire control management area and uploading the fire emergency resource data to the cloud platform. All the data are transmitted to a fire control monitoring cloud platform through the Internet of things equipment, and the platform performs integrated processing on different types of data (environment sensing data, maximum running state data of fire control equipment, people flow monitoring data and fire control emergency resource data) to generate regional fire control emergency global data. The global data provides a unified and integrated data base for subsequent fire monitoring, risk assessment and equipment scheduling.

In the embodiment of the invention, based on the environmental awareness data, the system utilizes a built-in fire monitoring algorithm to comprehensively analyze different data sources. For example, when the smoke sensor, the temperature sensor and the gas sensor detect anomalies at the same time, the system triggers an intelligent monitoring process to generate real-time multi-source fire data, the generation of which depends on joint analysis of multiple sensor data, and is optimized through a machine learning model. The model can be combined with the historical data and the real-time data of the sensor to intelligently evaluate the fire risk and reduce the false alarm rate. For example, a sharp rise in temperature and smoke is indicative of a fire, but may be other non-fire events, and the system improves the accuracy of fire early warning by intelligent screening of multi-source data.

In the embodiment of the invention, the state evaluation of the fire scene is performed by utilizing the real-time multi-source fire data and the fire equipment state data. The fire protection equipment status data here is no longer a simple monitoring of whether the equipment is in a good condition, but rather is critical data of the actual operational capabilities of the equipment in the event of a fire. For example, in the event of a fire, it is evaluated whether the fire pump can reach its maximum water pressure in the case of the current fire, or the remaining amount of the intelligent fire extinguisher's injection time after use. The system evaluates the actual response capability of the fire-fighting equipment in the fire scene according to the real-time operation data of the fire-fighting equipment and the situation data of the fire. The fire scene state evaluation data is a comprehensive analysis result, and considers the relation between the fire development situation (such as the fire spreading direction and intensity) and the maximum operation capacity of the fire-fighting equipment. For example, in a scenario where the fire is large and the propagation speed is fast, the evaluation result may show that the current device has difficulty controlling the fire, and more resources need to be allocated to extinguish the fire. This evaluation data provides an important reference basis for subsequent resource scheduling and emergency decisions.

In the embodiment of the invention, based on fire scene potential state evaluation data and people stream monitoring data in a fire state, the system analyzes the whole emergency scene, and the fire emergency scene data comprises a region with a large current fire risk, a crowd-intensive region, the working condition of fire-fighting equipment and the like, and identifies the region with the highest current risk and the place with the highest personnel concentration. Through dynamic weight analysis, the system distributes weights for different areas, and determines which areas have the greatest fire risk and which areas have the most urgent crowd evacuation. For example, if a high risk area is simultaneously personnel intensive and the maximum operational capacity of the fire apparatus has approached a limit, the system will assign a higher weight to that area, ensuring that resources are preferentially allocated to that area. The accuracy and the instantaneity of resource scheduling are ensured by dynamic weight analysis. Along with the development of fire, the system can adjust the weight of each area according to the data monitored in real time, dynamically update the fire emergency scene and ensure that the most needed place is supported most timely.

In the embodiment of the invention, the intelligent scheduling priority analysis is performed according to the fire emergency scene data, the dynamic weight data and the analysis result of the operation capability of the fire-fighting equipment. Currently available fire emergency resources such as fire extinguishers, fire pumps, fire extinguishing vehicles, firefighters, etc. are identified. Based on the real-time dynamic weight data, the system evaluates and sorts the resource demands of all areas, ensures that the areas with high risk of fire and the equipment capacity close to the limit are prioritized to obtain resources, and automatically schedules fire resources by generating fire emergency resource scheduling priority data. For example, if the fire in an area is large and existing fire equipment is not effective in controlling the fire, the system may send fire vehicles, additional equipment, and personnel to the area with priority. In addition, the system continuously adjusts the priority of resource scheduling by monitoring the state of equipment and the development situation of fire in real time, so that the high-efficiency utilization of emergency resources is ensured. Execution of the intelligently scheduled jobs may be accomplished through automated means. For example, the system directly transmits the fire fighter proportion to the terminal equipment of responsible personnel, and the unmanned and man-machine can be used for providing real-time monitoring information, ensuring that a dispatching command center grasps fire situation in real time and adjusting the dispatching direction and priority of resources according to the requirement.

Preferably, step S2 comprises the steps of:

s21, performing historical multi-source baseline sensing signal analysis according to the environmental sensing data to generate a historical multi-source baseline sensing signal;

S22, performing self-adaptive monitoring engine design of multi-source abnormal sensing signals according to the historical multi-source baseline sensing signals to generate a self-adaptive multi-source abnormal sensing signal monitoring engine;

s23, performing real-time multi-source abnormal sensing signal monitoring processing on the environment sensing data based on the self-adaptive multi-source abnormal sensing signal detection engine to generate a real-time multi-source abnormal sensing signal;

and step S24, analyzing the real-time multi-source fire data based on the real-time multi-source abnormal sensing signals to generate the real-time multi-source fire data.

According to the invention, through the baseline analysis of the historical environment sensing data, a baseline model in a normal fire-fighting state is established, the baseline signal can be used as a comparison standard for subsequent fire monitoring and abnormal detection, so that the normal and abnormal conditions can be effectively distinguished, the system can be helped to extract rules and features in the historical data, a reference basis is provided for the intellectualization of the fire monitoring, the possibility of false alarm and missing alarm is reduced, and the establishment of a historical baseline of the multi-source data is beneficial to improving the accuracy of the abnormal monitoring and the reliability of a fire risk early warning system. The self-adaptive monitoring engine is designed based on the historical multi-source baseline signals, so that the dynamic adjustment of fire monitoring signals can be realized, the monitoring standard can be adjusted in real time according to the change of the environment, and the sensitivity and the accuracy of the monitoring system are maintained. The self-adaptive monitoring engine can automatically optimize the monitoring rules according to different scenes and time periods, so that the adaptability of the system to various complex scenes is enhanced, and the intelligent level of fire monitoring is improved. The system has the advantages of improving the capability of processing abnormal sensing signals, enhancing the dynamic monitoring function of fire hazards and reducing the necessity of manual intervention. The self-adaptive detection engine can quickly identify abnormal conditions, such as changes of multisource sensing signals of temperature, smoke concentration and the like, through real-time monitoring of environment sensing data, real-time abnormal sensing signals are generated, the real-time monitoring enables the system to timely capture fire precursors, response delay is reduced, response speed of fire early warning is effectively improved, timeliness and accuracy of fire monitoring are improved, early warning can be carried out at the earliest time point when fire occurs, and expansion of the fire is avoided. Through the analysis to real-time unusual perception signal, can produce accurate multisource fire data, discernment conflagration specific position and the trend of developing take place, real-time fire data analysis can be with fire hidden danger fine into a plurality of dimensions, like fire development speed, influence scope etc. for emergency management provides the data support of detail, guaranteed fire data's instantaneity and accuracy nature, help emergent command center to make more scientific, accurate decision, improved fire handling's efficiency and accuracy.

In the embodiment of the invention, the history sensing data is obtained from environment sensing equipment (such as a temperature sensor, a humidity sensor, a smoke detector, a CO2 sensor and the like). Such data may include environmental parameters in multiple dimensions, such as normal temperature ranges within the area, air humidity, gas composition, and the like. The system aggregates these environmental data collected over a long period of time and generates a baseline signal for the environment based on statistical analysis methods. Specifically, the baseline sensor signal refers to a 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 ℃ and 25 ℃, and the humidity may be maintained between 30% and 50%. By analyzing the data for different time periods, the system can summarize the baseline perceptual features of different types of regions over different time periods. The baseline signal is not only single static data, but is a data set which dynamically changes along with time, and can reflect the characteristics of day-night period, seasonal change and the like. Based on the data, the system generates a set of historical multi-source baseline perceptual signals. After the historical multi-source baseline sensory signal is acquired, the system will design an adaptive monitoring engine through a machine learning algorithm. The design goal of the engine is to automatically adjust the monitoring rules according to the change of the baseline signal, detect abnormal conditions, firstly train a machine learning model by using historical data, and generate algorithms sensitive to different abnormal perception signals. For example, the system will perform a comparative analysis based on the environmental data under normal conditions and the known fire data, and establish a set of recognition criteria for the multisource anomaly perception signals. The system then designs an adaptive monitoring engine with flexible adjustment capability, which can automatically adjust the monitored threshold and weights to accommodate changes in different time, place, equipment and environmental conditions, and learning capability. Over time, the system will continue to acquire new data and the monitoring engine will be able to automatically learn new environmental signal characteristics and optimize the monitoring strategy for perceived abnormal signals. For example, in the case of large differences in ambient temperature between day and night, the monitoring engine can automatically adjust the temperature threshold to avoid false positives. After the adaptive monitoring engine is designed and deployed, the system monitors real-time environmental awareness data using the engine. When a fire scene occurs, environmental data (e.g., temperature, humidity, smoke concentration, etc.) may deviate from the range of the historical baseline signal. At this time, the adaptive monitoring engine may identify these anomaly signals and generate real-time multi-source anomaly-aware signals that comprehensively analyze the data sources from the different sensors. Assuming that the smoke detector in a region detects an increase in smoke concentration while the temperature sensor detects an abnormal temperature rise, the monitoring engine will compare these signals to the baseline perceived signal. If these values exceed the adaptive threshold, the system marks these signals as abnormal and generates corresponding abnormal signal data. In addition, the monitoring engine can monitor the change trend of the sensor data in real time and rapidly identify small-amplitude abnormal changes in the environment. For example, when a sensor detects an anomaly alone, the monitoring engine may combine with other data sources to further analyze, avoiding single signal false positives. After the generation of the real-time multisource anomaly-aware signals, the system will perform further fire analysis on these signals. At this time, the system uses a multi-source data fusion technology and combines a plurality of abnormal signals to generate real-time multi-source fire data, which is not limited to the judgment of a single sensor, but confirms the specific state and development situation of the fire through the comprehensive analysis of a plurality of data. extracting a valuable fire indicator from the anomaly signal, the simultaneous increase in smoke concentration and temperature may indicate that the fire has spread. The system combines this information into a set of real-time fire data, including the intensity, direction of spread, extent of impact, etc. of the fire. In addition, the system also can combine fire-fighting equipment state data to carry out auxiliary judgment. For example, when the fire sprinkler equipment is automatically activated 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. By means of real-time multi-source fire data, the system can provide immediate and comprehensive information support for fire emergency response. The data not only helps identify the place where the fire disaster occurs, but also can predict the speed of fire disaster spread and possible disaster areas, and provides decision basis for subsequent fire-fighting equipment dispatching.

Preferably, step S3 comprises the steps of:

S31, carrying out abnormal sensing signal space node extraction according to the real-time multi-source abnormal sensing signals to generate abnormal sensing signal space node data;

S32, performing space multisource fire node identification processing on corresponding real-time multisource fire data through abnormal perception signal space node data to generate real-time space multisource fire data;

S33, analyzing the fire-fighting emergency deployment state of the equipment according to the fire-fighting equipment state data, and generating the fire-fighting emergency deployment state data of the equipment;

step S34, fire control state space fire joint characteristic analysis is carried out according to the equipment fire control emergency movement state data and the real-time space multi-source fire data, and fire control state space fire joint characteristic data are generated;

Step S35, carrying out local space node division processing on the fire-fighting state space fire disaster combined characteristic data to generate fire-fighting state local space fire disaster combined characteristic data;

And step S36, carrying out fire-fighting status fire scene potential state evaluation processing based on the fire-fighting status local space fire joint characteristic data, and generating fire-fighting status fire scene potential state evaluation data.

According to the invention, the space nodes are extracted from the multisource abnormal sensing signals, so that the occurrence positions of the abnormal sensing signals are accurately positioned, the potential occurrence points or high risk areas of a fire disaster can be accurately determined, the space analysis capability of the abnormal signals is enhanced, the fire disaster monitoring is not only limited to data change, but also the specific space positions of the abnormal signals can be tracked, the accuracy of the fire disaster monitoring is improved, the extraction of the space nodes is beneficial to dividing key areas in the monitoring range, and further fire disaster situation analysis and resource scheduling are facilitated. Through space node identification, the fire data are associated with specific space positions, so that the propagation path and the influence range of the fire are more intuitively understood, the generated real-time space multi-source fire data can provide detailed space information for subsequent decision support, fire commanders can conveniently and accurately schedule and make emergency decisions, the visualization capability of the fire data is effectively improved, and relevant departments are helped to timely master the dynamic development condition of the fire. Through the analysis to the fire-fighting equipment state, the system can know availability, position and the condition of transferring of current equipment, ensures that emergency equipment is in the best state, can respond the demand on fire scene fast, optimizes the transferring and managing of equipment, prevents the emergent response delay that leads to because of equipment state is not good or the position is unreasonable, can automatically generate the suggestion of transferring according to the state data of equipment, reduces the artificial judgement error, promotes the scientificity and the rationality that equipment transferred. The spatial characteristics of the current fire situation and the relation between the fire situation are understood by combining and analyzing the equipment movement state and the real-time fire data, so that more accurate combined characteristic data is generated, a more reasonable emergency response strategy is provided by a help system through the combined analysis of the fire spatial characteristics and the equipment state, so that equipment scheduling and fire countermeasures are more coordinated and consistent, the combined characteristic analysis improves the adaptability and the flexibility of the equipment movement and the fire situation in a fire scene, and the fire simulation situation called by fire equipment in the fire development process is ensured. The combined characteristic data is subjected to local space division processing, analysis of fire scenes can be further refined, fire situations are decomposed into smaller and manageable local nodes, more accurate emergency measures can be formulated conveniently, the division processing is helpful for highlighting the most urgent areas of the fire, decision makers are helped to concentrate resources and forces to the most needed places, the efficiency of fire disposal is improved, through the local node division, the system can analyze risk characteristics of each node more carefully, probability spatial relations of fire evolution are analyzed, the risk degree of each local space fire is identified, and a targeted fire extinguishing or evacuation plan is formulated. According to the situation assessment of the fire scene, which is carried out according to the local spatial joint characteristic data, the future development trend of the fire is accurately predicted, the emergency management personnel is helped to formulate a scientific disposal strategy, the situation assessment enables the system to dynamically track the spread and change situation of the fire, a potential high-risk area is timely found, timely decision support is provided for emergency resource scheduling, the predictability and the accuracy of emergency response are improved through assessing the situation of the fire, the fire resources are ensured to be efficiently put into fire disposal, and the loss and the influence of the fire are reduced.

As an embodiment of the present invention, referring to fig. 2, a detailed implementation step flow diagram of step S3 in fig. 1 is shown, where in this embodiment, step S3 includes:

In the embodiment of the invention, the extraction of the space nodes is performed according to the real-time multisource abnormal sensing signals. The purpose of the space node extraction is to locate the fire risk to a specific physical location, for example, a certain floor of a certain building or a certain area in a room, and the sensor location corresponding to the abnormal sensing signal is used as a "space node" by matching the location information of a plurality of sensors. For example, when a temperature sensor and smoke detector at a floor detect anomalies at the same time, the system correlates these anomaly signals to specific spatial nodes (e.g., floor and room numbers) to generate anomaly-aware signal spatial node data for that location. Through space node extraction, the abnormal signal is related to the actual geographic position, so that subsequent fire evaluation and emergency response are facilitated.

In the embodiment of the invention, based on the space node data of the abnormal sensing signals, the real-time multi-source fire data are associated with the space nodes, and the fire data are identified and processed through the space positioning information of the abnormal sensing signals obtained in the previous step. For example, different sensors may capture various perceived signals of a fire (e.g., temperature anomalies, smoke concentration anomalies). The system correlates these fire awareness data with specific spatial nodes to generate real-time spatial multi-source fire data identifying spatial locations. The identification processes not only can accurately locate the specific position of the fire, but also can identify the spreading situation of the fire among different nodes.

in the embodiment of the invention, the current operation condition and the maximum operation capability of the fire-fighting equipment in a fire scene are determined by analyzing the state data of the fire-fighting equipment. The system can acquire state information from the fire-fighting equipment in real time, including water pressure of a water pump, flow rate of a fire-fighting spraying system, residual capacity of a fire extinguisher and the like. For example, the system may evaluate the mobility of fire extinguishers and fire pumps in the current fire scenario, analyze whether they are able to cover the desired area or require more equipment to participate. By analyzing the current working states of the devices, the system generates the fire emergency mobilization state data of the devices, and provides basis for subsequent device scheduling decisions.

In the embodiment of the invention, the fire scene joint feature analysis is carried out by combining the equipment fire emergency mobilization state data and the real-time space multisource fire data, the current fire development situation (such as fire intensity and spreading direction) is combined with the maximum operation capacity of the equipment, and the effectiveness of the existing equipment when the current fire is dealt with is analyzed. For example, in an area, the system may find that the water pressure of the fire apparatus has approached a maximum operating condition while the fire is still spreading. At the moment, the system evaluates whether the existing equipment is enough to control the fire through comprehensive analysis of the equipment state and the fire situation, and generates fire-fighting state space fire joint characteristic data. The data comprises combined information of fire intensity, equipment emergency response capability and the like, so that a decision maker can conveniently make a next coping strategy.

In the embodiment of the invention, the fire joint characteristic data of the fire status space is subjected to refinement treatment, the local nodes are divided according to the spatial characteristics of the fire, different areas are distinguished according to the actual development situation of the fire, a plurality of local spatial nodes are divided, and the data of the nodes are further subjected to refinement treatment. For example, in large buildings, a fire may affect multiple floors or rooms simultaneously. The system may analyze fire characteristics of each floor or room independently to generate fire status data for each local area. Through the local division processing, the system generates more accurate fire state local space fire disaster combined characteristic data, and detailed information is provided for emergency response aiming at different space nodes.

In the embodiment of the invention, the overall potential state evaluation of the fire scene is carried out by analyzing the fire joint characteristic data of the local space in the fire prevention state, so that the current situation of the fire is considered, and the characteristics of each local area are combined to predict the possible further development trend of the fire. And generating fire scene potential state evaluation data of the fire state by combining the data of the spreading direction of the fire, the maximum operation capacity of equipment, the intensity of the fire and the like. For example, in an area, a fire may be about to spread to an adjacent floor, while existing equipment capacity is insufficient to control the fire. The system generates an evaluation report on the basis, helps a decision maker to quickly judge the trend of fire development, and makes an emergency scheme.

Preferably, step S36 comprises the steps of:

Step S361, acquiring fire joint evolution data of a scene in a historical fire state;

Step S362, establishing a probability distribution mapping relation between a fire-fighting mobilization state and fire potential evolution based on a preset Bayesian structure time sequence model to obtain a fire-fighting state space fire potential prediction model framework;

Step S363 is that model training processing is carried out on the fire state space fire state prediction model framework based on the fire state scene fire joint evolution data to generate a fire state space fire state prediction model;

And S364, performing fire-fighting status fire scene potential state evaluation processing on the fire-fighting status local space fire joint characteristic data through a fire-fighting status space fire potential state prediction model to generate fire-fighting status fire scene potential state evaluation data.

According to the invention, through acquiring the data of the historical fire state and fire evolution, comprehensive cognition on the fire development rule can be constructed, the historical data provides rich basic data for building and training a subsequent fire prediction model, and the prior probability characteristics of fire influence and fire evolution are provided. The historical fire evolution data helps the system to identify the mode and the characteristic of fire development, is favorable for predicting the fire situation possibly happening in the future in advance, improves the predictability of the system, provides a historical sample for a fire scene potential state prediction model, ensures the accuracy and the reliability of a subsequent model, and reduces the uncertainty in fire scene prediction. The relation between the fire-fighting mobilization state and the fire development trend is established by utilizing a Bayesian structure time sequence model, a scientific probability distribution mapping relation is formed, the prediction capability of the fire situation is enhanced, the system can process uncertainty and time sequence characteristics, particularly the time dependence of dynamic fire-fighting mobilization state and fire development evolution is processed, the dynamics and flexibility of fire situation prediction are ensured, the prediction result is updated continuously according to real-time data by establishing an accurate model framework, the emergency response is more intelligent, and the response efficiency of a fire scene is improved. By training the model on the historical data, the accuracy and stability of fire situation prediction can be continuously improved, the prediction model can be effectively adapted to different fire scenes, the model training can enable fire control scheduling and fire situation analysis to become more intelligent and data-driven, human intervention is reduced, emergency decision flow is optimized, along with the enrichment of training data, the prediction accuracy of the model is continuously improved, emergency personnel are helped to predict the expansion trend, risk area and mobilization requirement of the fire in advance, and the emergency management efficiency is improved. By applying the trained fire situation prediction model, real-time local fire scene feature data can be evaluated and predicted, so that high-precision fire scene situation evaluation data are generated, the real-time performance and accuracy of fire scene evaluation are improved, emergency personnel are ensured to know the development trend of a fire in advance, quick and accurate emergency response is made, and based on the fire situation evaluation result, the system can provide targeted fire resource scheduling advice, the scheduling efficiency of fire equipment and personnel is further optimized, and the success rate of fire disposal is improved.

In the embodiment of the invention, the historical data related to the fire disaster are extracted from the historical fire control record, and the data comprise the state change of fire control equipment, the fire spreading path, the fire extinguishing time, the equipment scheduling condition and the like in the fire disaster development process, and the data sources are from the logs, the monitoring records and the data acquired by the sensors of the fire control system. For example, the system reviews past fire cases in a certain building, analyzes the spread of fire at various points in time, the deployment and operation status of fire-fighting equipment (e.g., fire pump, extinguisher, automatic spray system, etc.), and the specific details of the ultimate control of fire, which are integrated into historical fire status scene fire joint evolution data, including time of occurrence, rate of development, fire extinguishing effect, fire-fighting equipment response status, etc. And establishing a probability distribution mapping relation between the mobilization state of the fire-fighting equipment and the evolution of the fire potential state by using a preset Bayesian structure time sequence model, namely, a time sequence probability space when different scenes send fires, wherein the Bayesian structure time sequence model is used for processing the fire evolution process with higher uncertainty in the time dimension, and predicting the future fire situation by combining historical data. According to the historical fire evolution data and the equipment deployment data, a multivariate time sequence model is constructed, and the model considers the time sequence characteristics (such as spreading speed and intensity change) of the fire and the deployment and response of the fire-fighting equipment (such as the influence on fire control when a fire pump is started). Through carrying out association analysis on the fire development situation and the fire-fighting equipment mobilization, the system establishes a probability distribution mapping relation. The mapping relation helps to predict future changes of fire situations under the condition of specific equipment mobilization, and a fire state space fire state prediction model framework is generated. By utilizing the acquired fire joint evolution data of the historical fire scene, the fire state prediction model framework of the fire state space is trained, and the training process aims at optimizing the model, so that the future evolution of the fire scene can be predicted more accurately. The supervision learning method is used, the actual results of the fire fighting equipment movement state and the fire evolution in the historical data are used as training samples, and the prediction results are closer to the historical evolution results by adjusting model parameters. For example, the system can adjust probability distribution weights in the Bayesian model according to the fire spread speed in the historical data so as to be more in line with the actual fire development trend. By repeated training, the system generates an optimized fire state space fire state prediction model that can provide accurate fire state predictions based on real-time data. And processing the fire joint characteristic data of the local space in the fire state by using the trained fire state space fire state prediction model, evaluating the fire scene state, inputting the data of the current local space node through the prediction model, and predicting possible further development of the fire according to the comparison of the historical data and the current real-time data by the model. By means of the prediction, the system can obtain possible paths of fire spread, changes of fire intensity and risk levels of different space nodes. For example, fire data for an area indicates that temperature and smoke concentration are continuously rising, while fire equipment status for the area indicates insufficient water pressure. The model predicts that the fire in this region may expand further and affect adjacent regions by calculation. The system generates fire scene potential state evaluation data of the fire state according to the data, and the data provides decision support for subsequent emergency response and resource allocation.

Preferably, step S363 includes the steps of:

performing fire evolution time sequence characteristic analysis of the historical fire state scene according to the fire joint evolution data of the historical fire state scene to generate fire evolution time sequence characteristic data of the historical fire state scene;

Performing fire evolution time sequence distribution evaluation processing of the historical fire state scene according to the fire evolution time sequence characteristic data of the historical fire state scene to generate fire evolution time sequence distribution evaluation data of the historical fire state scene;

performing fire scene fire evolution time sequence prior distribution analysis according to historical fire scene fire evolution time sequence distribution evaluation data to generate fire scene fire evolution time sequence prior distribution data;

And carrying out model training treatment on the fire state space fire state prediction model framework through the fire state scene time sequence fire evolution priori distribution data to generate a fire state space fire state prediction model.

According to the invention, through analyzing the time sequence characteristics of the historical fire evolution, key nodes and trends of the fire development are extracted, typical time sequence modes of fire occurrence and spread are identified, a system is helped to establish a time sequence model of a fire development rule, the starting, development and spread processes of the fire are clarified, accurate time sequence characteristic data support is provided for subsequent fire prediction, the time sequence characteristic analysis enhances the understanding of the system on the dynamic fire evolution, possible time points and situation changes of the fire development can be prejudged in advance, and the optimization of a fire emergency strategy is facilitated. Through time sequence distribution evaluation processing, the system can quantitatively analyze time distribution of fire evolution, time sequence characteristics and influence factors thereof of different fire evolution stages are identified, and generated time sequence distribution evaluation data help the system to identify key information such as high-risk time intervals of fire and time nodes of fire acceleration and spread, so that a more targeted time window and preventive measures are provided for emergency response, accurate evaluation of the time characteristics of fire evolution is ensured, and a prediction model is more refined and dynamic. By analyzing the prior distribution of the fire evolution time sequence, the system can determine the probability range of fire occurrence and key distribution characteristics in the time sequence based on historical data, provide prior information for a prediction model, improve the prediction precision of the model, enable the system to better cope with complex fire evolution conditions based on the prior distribution, reduce uncertainty in prediction and effectively infer when facing new fire scenes. By training the model through prior distribution data, a more accurate fire situation prediction model can be built, the model has the capability of accurately predicting according to historical evolution rules and real-time data, the model training process is based on prior data, the performance of the model can be continuously optimized and adjusted, the prediction precision and reliability of fire situations are improved, accurate decisions can be rapidly made in emergency response, the generated fire situation prediction model can provide dynamic situation prediction in the fire development process, and fire equipment and resources can be reasonably distributed and timely cope with fires.

In the embodiment of the invention, the fire joint evolution data is extracted from the historical fire state scene database, and comprises key parameters of the fire at different moments, such as flame spreading speed, temperature change, smoke concentration change, equipment response time and the like. The system determines the development characteristics and rules of the fire at different moments by analyzing the time sequence characteristics of the data, and analyzes the time sequence of each historical fire, so as to decompose key stages in the evolution process of the fire, such as initial combustion, spreading, extinguishing and the like. Through the analysis, the system generates fire evolution time sequence characteristic data of the scene of the historical fire state, wherein the data describe the overall process characteristic of the fire from the starting point to the end point in detail and can be used for analyzing the evolution rule of the fire in different types of buildings. And carrying out statistics and distribution evaluation on the previously generated time sequence characteristic data of the fire evolution of the scene of the historical fire state, and evaluating the distribution characteristic of each stage in the fire evolution process by analyzing the time sequence change mode in the historical data. For example, the time distribution of fire from initial combustion to spread, or the time interval distribution from the beginning of the fire to the response of the fire fighting equipment, using time series analysis tools to model historical data, identify high frequency distribution patterns of fire evolution, by which the system can generate historical fire status scene fire evolution time series distribution evaluation data describing the fire's distribution characteristics on the time axis, including important characteristics such as fire development speed and response time. Based on the historical fire state scene fire evolution time sequence distribution evaluation data, performing time sequence prior distribution analysis of fire evolution, wherein the prior distribution analysis aims to provide a probability basis for future fire situation prediction, and deducing the future evolution trend of the fire by combining the historical evolution data. The time series characteristic distribution of fire is modeled as a probability distribution. For example, the rate of spread of a fire in an initial stage is a normal distribution, or the distribution of device response times may conform to some prior probability model. Through the prior analysis, the system generates prior distribution data of fire evolution time sequence of the fire scene, and the data provides preliminary probability input for a subsequent prediction model. And training the designed fire potential state prediction model by utilizing the fire evolution time sequence priori distribution data of the fire state scene. The model training aims to identify the probability of future fire evolution and dynamically adjust the prediction result according to real-time input data. And using the prior distribution of fire evolution in the historical data as an initial parameter of the model, and carrying out model adjustment by combining multi-source data (such as temperature, smoke concentration and equipment state) in an actual fire scene. Through repeated iterative training, the system can continuously optimize the prediction precision of the model, and a fire state space fire state prediction model is generated, and can receive the latest data of a fire scene in real time and provide accurate fire state prediction.

Preferably, step S364 includes the steps of:

transmitting the fire-fighting state local space fire joint characteristic data to a fire-fighting state space fire potential state prediction model to analyze fire-fighting state local space fire probability, and generating fire-fighting state local space fire probability data;

Carrying out local space probability correlation characteristic analysis according to the fire state local space fire probability data to generate local space probability correlation characteristic data;

performing time sequence probability evolution analysis according to the fire state local space fire probability data to generate fire state local space fire time sequence probability data;

And carrying out fire-fighting state fire scene potential state evaluation processing on the fire-fighting state local space fire probability data based on the local space probability associated characteristic data and the fire-fighting state local space fire time sequence probability data, and generating fire-fighting state fire scene potential state evaluation data.

According to the invention, the probability of the fire disaster in the application process of the fire fighting equipment is accurately analyzed by inputting the local space fire disaster combined characteristic data into the prediction model, the probability of the fire disaster on different space nodes is identified, an important probability basis is provided for fire emergency decision, the high-risk area of the fire disaster in the local space is identified, a decision maker is helped to pay attention to the area with larger risk preferentially, and resource scheduling is optimized. The local fire probability analysis enhances the prediction capability of the system, is beneficial to the accuracy and differentiation of emergency response strategies, and enables the system to perform risk assessment with higher accuracy. Through analyzing the association characteristics of the local space fire probability data, the association among the space nodes is found, the potential paths of fire spreading and spreading in different areas are identified, and the space spreading modes of the fire are identified through the probability space association, so that the prediction model not only can evaluate the fire risk of a single node, but also can reveal the association risk among different nodes, and the comprehensiveness of fire situation analysis is further improved. The time sequence probability evolution analysis can dynamically track the evolution process of the fire disaster, forecast the change trend of the fire disaster on different time nodes, better judge the speed and direction of fire disaster spreading according to the analysis result, accurately forecast the evolution condition of the fire disaster in a period of time in the future, ensure that emergency response personnel can deploy corresponding prevention and control measures in advance, further improve the timeliness and the accuracy of fire disaster forecast by generating time sequence probability data, and ensure that the fire emergency management system can respond timely and effectively according to real-time change. By combining the local space probability correlation characteristics and the time sequence probability data, the overall potential state of the current fire scene can be comprehensively and dynamically estimated, so that a decision maker can acquire an accurate fire situation estimation result, the estimation processing enables the system to comprehensively judge the complex fire scene, the system provides analysis data with more reference value for the emergency command center, is convenient for scientifically and efficiently distributing resources and firefighters, and improves the overall situation awareness capability of the fire-fighting system by using the fire scene situation assessment data, so that the system can dynamically adjust an emergency response strategy in real time so as to adapt to the actual situation of fire development.

In the embodiment of the invention, the acquired fire-fighting status local space fire joint characteristic data are transmitted to a trained fire-fighting status space fire potential state prediction model, and the model calculates the occurrence probability of fire on the local space nodes by analyzing the input multi-source characteristic data (such as the temperature, smoke concentration, fire-fighting equipment state and the like of a fire occurrence area). The model generates a probability value based on the input data, which is used to indicate the possibility of fire occurrence or continuous spread in the local space, and the model can calculate that the probability of further expansion of the fire in a certain area is higher on the assumption that the temperature and smoke concentration in the certain area are sharply increased and the working capacity of the equipment is close to the saturated state. The system generates fire status local spatial fire probability data based on these calculations and records it for further analysis. And (3) by further carrying out correlation characteristic analysis on the local space fire probability data in the fire prevention state, evaluating the correlation of the fire among different space nodes, namely, if the fire occurs in one space node, whether the fire risk of the surrounding area can be caused or not. By analyzing the physical adjacent relation among the local space nodes and fire spread characteristics (such as wind direction and building structure), a correlation model of fire probability is established. For example, if the probability of a fire being in one room is high and the room is connected to another room by a ventilation system, the system may recognize that there is an association of the probability of a fire in both rooms. The system generates local space probability associated characteristic data according to the associated analysis, and reveals potential connection of fire spread among different space nodes. And carrying out time sequence probability evolution analysis based on the fire state local space fire probability data. The purpose of this analysis is to predict the evolution trend of the fire at different moments, i.e. the expansion speed and direction of the fire, in combination with the time factors, to evaluate its probability at future moments. The probability change of fire in the local space is modeled by using a time series analysis technique. For example, if the probability of a fire in a current area increases gradually, while the temperature and smoke concentration in surrounding areas also increase, the system may predict that the fire will spread to adjacent areas in the next few minutes. The fire disaster occurrence and expansion time sequence data are analyzed to generate fire disaster state local space fire disaster time sequence probability data, and the data can provide accurate time early warning for fire departments. The local space probability associated characteristic data is combined with the fire-fighting state local space fire time sequence probability data to carry out overall fire scene potential state evaluation, and the overall fire scene is analyzed based on the fire-fighting state local space fire probability data by comprehensively considering the fire probability, the spatial association and the time sequence change of the local area. For example, if the fire probability of multiple adjacent spaces is high and the expansion speed of the fire in the time sequence is high, the system will evaluate the fire possibly spreading to a larger extent, and the generated fire scene potential evaluation data will include the overall situation of fire development, the disaster range and the effectiveness of equipment coping, and the data will be directly used in the emergency command system to help the decision maker to make more effective coping strategies.

Preferably, step S4 comprises the steps of:

S41, performing fire scene risk analysis according to fire scene potential state evaluation data to generate fire scene risk data;

Step S42, extracting target fire scene data from fire scene risk data in a fire prevention state based on a preset fire hazard risk threshold value, and generating target fire scene data;

S43, carrying out people stream behavior feature analysis according to people stream monitoring data to generate people stream behavior feature data;

S44, analyzing the stream fire scene data according to the stream behavior characteristic data to generate stream fire scene data;

Step S45, fire emergency scene data analysis is carried out according to the target fire scene data and the people stream fire scene data, and fire emergency scene data are generated;

And S46, performing fire emergency scene dynamic weight analysis on the fire emergency scene data based on the fire scene risk data of the fire state of the target fire scene data and the people flow behavior characteristic data of the people flow fire scene data, and generating the fire emergency scene dynamic weight data.

According to the invention, through risk analysis of the fire scene potential state evaluation data, the potential risk of the current fire scene can be accurately identified, the threat and the influence area possibly caused by the fire can be determined, the system is helped to quickly lock the area and the position with higher fire risk, effective early warning information is provided, emergency schemes are helped to be formulated in advance, fire resource allocation is optimized, the fire situation sensing capability is improved, a decision maker is helped to scientifically evaluate the risk brought by the fire, and corresponding countermeasures are made according to the risk level. Through setting up the threshold value of fire control fire hazard risk, the system can automatic screening out the high-risk fire scene that surpasses the threshold value to and do not possess the scene of conflagration after carrying out the fire control through fire control equipment, ensure to monitor the biggest region of conflagration hidden danger, simplified the data extraction process in the complex fire scene, make the system can high-efficient discernment and draw key target fire scene, help optimizing the accuracy of fire control emergent response, the priority handles the most dangerous fire scene, reduce the wasting of resources, improve emergent decision's efficiency and accuracy. By analyzing the people flow monitoring data, the system can grasp the personnel dynamics in a fire scene or an affected area in real time, provide detailed information about the people flow density degree, the personnel flow direction and the speed, know the distribution condition of personnel in the fire scene, facilitate the establishment of evacuation strategies and the optimization of evacuation channels, ensure the safe evacuation of the personnel, improve the perception capability of the system to the personnel behaviors by the generation of the people flow behavior characteristic data, more accurately predict the behavior mode of the people flow, and reduce the confusion and casualties risk of the personnel in emergency. Through deep analysis of people stream behavior characteristic data, people dense areas and evacuation directions can be accurately mastered in a fire scene, targeted fire scene data are generated, and fire emergency measures are optimized, so that emergency response can fully take the flowing condition of people into consideration, reasonable arrangement of resources and evacuation paths in the fire scene is ensured, the people stream fire scene data enable the system to be more flexible and accurate in the fire emergency process, the effectiveness of emergency response is improved, and people can be ensured to safely and rapidly evacuate from dangerous areas. By combining the target fire scene and the people stream data, the system can generate more complete fire emergency scene data, comprehensively reflect fire situation and crowd behaviors, provide omnibearing data support for emergency response, enhance the grasping capability of the system on the whole emergency scene, ensure that fire emergency measures can be dynamically adjusted according to the change of fire development situation and personnel density, ensure reasonable allocation and use of personnel, equipment and resources, and promote the whole emergency efficiency. By carrying out dynamic weight analysis on fire scene risk data and people stream behavior characteristic data, areas with higher risk levels and dense personnel can be processed preferentially, the accuracy of emergency response is improved, the dynamic weight analysis enables the system to flexibly adjust the allocation scheme of emergency resources according to real-time changes of fire, the emergency resources and equipment are ensured to be allocated to the most needed places preferentially, fire loss is reduced, the system has self-adaptability and flexibility, the emergency strategy can be dynamically adjusted according to scene fire and personnel, and the effective execution and response speed of the whole emergency action are ensured.

In the embodiment of the invention, the risk analysis of the fire scene is performed based on the fire scene potential state evaluation data, and the potential risk of fire spread is analyzed, including the influence of the fire on the building structure, the speed and the direction of the fire spread and the coping capability of equipment. The fire scene risk data of the fire state is generated by analyzing the combustion intensity, the spreading speed and the possible spreading paths of the fire in different areas, calculating the risk level of each area and combining the maximum operation capacity of equipment by using a fire prediction model, wherein the data comprise the fire risk level of each area and the possible resource allocation information. And screening the risk data through a preset fire hazard risk threshold. The threshold represents an acceptable upper limit of fire risk, a high-risk fire scene is extracted according to the threshold, fire risk data of each area are analyzed, areas exceeding the risk threshold are screened out and marked as target fire scenes, the areas are usually areas with larger fire and rapid spreading speed, target fire scene data are generated according to the data, and basis is provided for subsequent emergency response. And extracting people stream monitoring data from monitoring equipment deployed in the crowd-intensive area, and performing people stream behavior feature analysis. The system can analyze key behavior characteristics such as the flow direction, the density degree, the residence time and the like of people, and identify the behavior characteristics of the people by analyzing dynamic information in the people flow monitoring data. For example, when a fire occurs, the flow direction and speed of people are detected, and whether the problems of crowd gathering, escape route blockage and the like exist is identified. Based on these analyses, the system generates people stream behavioral characteristic data that provides information for people evacuation and emergency response. And combining the people stream behavior characteristic data with the current fire scene, analyzing the people stream fire scene data, analyzing the relation between the spreading situation of the fire and the people stream behavior to evaluate the influence of the fire on the personnel, identifying the high risk area in which the personnel are trapped by evaluating the intersection situation of the fire spreading path and the crowd flowing direction, and evaluating the effectiveness of the existing evacuation route. The system generates people stream fire scene data which comprises information such as personnel distribution, flowing trend, evacuation pressure and the like, so that subsequent emergency response is facilitated. And comprehensively analyzing the target fire scene data and the people stream fire scene data, analyzing the overlapping condition of the risk area and the crowd-intensive area of the fire, evaluating the threat degree of the fire to personnel, and generating fire emergency scene data. The priority of emergency response is determined by analyzing the concentration of people in the high-risk areas of fire. For example, if a large number of people are trapped in a high risk fire area, that area may be marked as an emergency preferential response area. The system generates fire emergency scene data and provides priority references for fire resource scheduling and personnel evacuation. And carrying out dynamic weight analysis on the target fire scene data, the fire scene risk data in the fire state and the people stream fire scene data, and determining the priority of emergency response by calculating the comprehensive weight of the fire risk and the crowd evacuation pressure in each emergency scene. Based on factors such as the severity of fire spread, personnel concentration, equipment response capability and the like, dynamic weights are distributed for each area, high-risk areas with dense crowds can obtain higher weights, fire-fighting equipment and emergency resources are arranged preferentially, dynamic weight data of a fire-fighting emergency scene are generated, and basis is provided for reasonable distribution of resources and emergency decision.

Preferably, step S5 comprises the steps of:

Step S51, fire emergency scene resource demand analysis processing is carried out according to the fire emergency scene data, and fire emergency scene resource demand data is generated, wherein the fire emergency scene resource demand data comprises fire emergency scene resource demand scheduling data and fire emergency scene resource demand node data;

Step S52, a fire-fighting emergency scene demand node map is established based on the fire-fighting emergency scene resource demand node data and the corresponding fire-fighting emergency scene dynamic weight data, and fire-fighting emergency scene resource demand scheduling data are transmitted to the fire-fighting emergency scene demand node map to carry out demand scheduling mapping, so that a fire-fighting emergency scene demand map is generated;

Step S53, fire-fighting emergency resource intelligent scheduling priority analysis is carried out on the fire-fighting emergency scene demand spectrum based on the fire-fighting emergency resource data, and fire-fighting emergency resource intelligent scheduling priority data is generated;

And S54, executing the intelligent fire emergency resource scheduling operation through the intelligent fire emergency resource scheduling priority data.

According to the method, the fire emergency scene data are analyzed in terms of resource requirements, the types and the quantity of emergency resources required in a fire scene can be accurately identified, the resource allocation is more reasonable and effective, the resource scheduling is optimized, the resource waste or deficiency is avoided, equipment, personnel and materials required in an emergency response process can be timely in place, the emergency treatment efficiency is improved, detailed demand scheduling information is provided for the fire emergency scene resource requirement data, a data foundation is laid for subsequent resource scheduling and priority analysis, and the emergency response process is scientific and reasonable. The demand node data and the dynamic weight data are combined, a complete demand node map is established, the demand priority and the resource distribution condition of each node are helped to be identified, resource scheduling can be guaranteed to be carried out according to actual demands, the demand map is generated through scheduling mapping, so that a system can clearly know each resource demand point in a fire emergency scene, accurate scheduling of emergency resources is achieved, scheduling rationality and scheduling efficiency are improved, the demand node map is favorable for achieving resource allocation optimization in a complex emergency scene, resource support is guaranteed to be preferentially obtained by key nodes, and coordination and execution effects of overall emergency response are improved. Through intelligent scheduling priority analysis, which resources need to be allocated preferentially can be determined according to the actual demands and resource conditions of emergency scenes, so that emergency response speed and effect are optimized, the accuracy and instantaneity of resource scheduling are obviously improved, the critical areas and high-risk nodes can obtain emergency support preferentially, the best opportunity of delaying emergency response is avoided, the fire emergency resource intelligent scheduling priority data provides scientific scheduling basis for emergency commanders, errors of artificial decision are reduced, and the high efficiency and rationality of resource allocation are ensured. By executing intelligent dispatching operation based on dispatching priority data, the system can automatically and rapidly deploy emergency resources, delay in the manual dispatching process is reduced, emergency handling efficiency is improved, automation and intellectualization of emergency resource dispatching are ensured, manual intervention is reduced, autonomous dispatching capacity of the system is improved, resources can reach the most needed place in the shortest time, dispatching strategies can be dynamically adjusted through intelligent dispatching operation, optimal utilization of the resources is ensured, and response speed and accuracy of fire emergency management are further improved.

As an embodiment of the present invention, referring to fig. 3, a detailed implementation step flow diagram of step S5 in fig. 1 is shown, where in this embodiment, step S5 includes:

In the embodiment of the invention, the resource demand analysis of the fire emergency scene is performed based on the fire emergency scene data generated before, and factors such as the risk level of fire, the people flow concentration, the existing state of equipment and the like are required to be analyzed so as to determine the type of resources required by emergency and the scheduling priority thereof. According to the fire situation of the scene, the types of emergency resources to be allocated, such as fire extinguishing equipment (fire pump, fire extinguisher), firefighters, protective equipment and the like, are evaluated, according to the expansion path of the fire and the concentration of people flow, which nodes are required to allocate resources are analyzed, and fire emergency scene resource demand node data are generated, wherein the node data represent specific positions and the required resource types. For example, in a commercial building fire scenario, a plurality of resource demand nodes are identified, including the core area of the fire, key nodes on the evacuation path (e.g., stairs ports), and refuge sites where people flow is concentrated. Each node may require different resources, such as high pressure fire guns, smoke abatement equipment, or additional personnel evacuation resources, depending on the risk of fire and the people evacuation situation. The system generates fire emergency scene resource demand scheduling data according to the node data, and provides accurate demand guidance for subsequent resource scheduling.

In the embodiment of the invention, the fire emergency scene resource demand node data and the fire emergency scene dynamic weight data are combined, a fire emergency scene demand node map is established, all resource demand nodes and dynamic weights thereof are spatially distributed, each resource demand point and corresponding dynamic weights thereof in an emergency scene are displayed in a visual form, the resource demand nodes are subjected to demand scheduling mapping, and the weight of the position relation of each node in the emergency scene and the resource scheduling demand are displayed. The resource demand nodes are matched with fire emergency scene resource demand scheduling data to generate a complete fire emergency scene demand map, and the map not only displays the resource demand nodes, but also indicates scheduling priority according to the dynamic weights of different nodes. For example, in a fire core area, fire fighting equipment is preferentially dispatched, while on evacuation channels where people flow is concentrated, people to be dredged are preferentially dispatched.

In the embodiment of the invention, the demand spectrum of the fire emergency scene is further analyzed, and the calculation and the distribution of the intelligent scheduling priority are carried out by combining the fire emergency resource data, so that the existing resources can be efficiently scheduled according to reasonable priority. And acquiring all available fire emergency resource data, including state information of equipment, vehicles, personnel and the like. For example, existing fire resources (e.g., available number of fire engines, status of fire pumps, real-time distribution of firefighters) are analyzed. And then, according to the node priority in the demand graph, the available resources are allocated according to the demand. For example, if the node weight of a fire core area is high, equipment such as fire engines and high-pressure water guns can be preferentially allocated. The intelligent scheduling priority analysis is carried out by using a machine learning algorithm or an optimization algorithm, so that the allocation order of each emergency resource is determined, intelligent scheduling priority data of fire emergency resources are generated, which resources need to be mobilized first can be determined, and which resources can be allocated secondarily according to the change of fire situations.

According to the embodiment of the invention, the actual scheduling task of the fire-fighting resources is executed through the fire-fighting emergency resource intelligent scheduling priority data, and the resource allocation is carried out according to the priority order, so that the emergency resources can be ensured to be rapidly deployed to the most needed nodes, and the fire-fighting equipment and personnel are automatically commanded and scheduled. For example, when a fire spreads to a high risk area, the system automatically dispatches nearby fire engines and equipment to the area according to intelligent dispatch priority, ensuring timely control of the fire. Meanwhile, the system directs firefighters to quickly enter a high-priority area of a fire scene through the emergency communication system, so that orderly fire extinguishing actions are ensured. In addition, the system can automatically execute part of fire-fighting tasks through unmanned aerial vehicle, remote control equipment and other technologies. For example, the unmanned aerial vehicle can quickly reach a fire scene for real-time monitoring and information acquisition, or put in a fire extinguishing device. The automatic fire-fighting equipment (such as a fire-fighting robot) can quickly reach a fire high-risk area under the command of a dispatching system, execute fire-fighting tasks and dynamically adjust dispatching operation, and the dispatching priority is adjusted according to real-time feedback along with the development of fire-fighting emergency fire extinguishing. For example, if a fire is controlled in an area, the system automatically reassigns equipment and personnel to allocate resources to other areas or adjacent areas where there is a higher risk to ensure that emergency resources are optimally utilized. Through intelligent scheduling operation, the system can greatly improve the response speed and the resource utilization efficiency of fire emergency, and ensure the rapid control of fire.

Preferably, step S53 includes the steps of:

According to the fire emergency resource data, fire emergency resource scheduling priority analysis is carried out on the fire emergency scene demand spectrum, and fire emergency resource scheduling priority data are generated;

The method comprises the steps of carrying out real-time updating and monitoring on fire-fighting emergency scene dynamic weight data of fire-fighting emergency scene demand patterns, carrying out resource scheduling priority intelligent regulation on fire-fighting emergency resource scheduling priority data according to the fire-fighting emergency scene demand patterns corresponding to the fire-fighting emergency scene dynamic weight data updated in real time, and generating the fire-fighting emergency resource intelligent scheduling priority data.

According to the invention, by analyzing the emergency resource data and the scene demand pattern, the priority allocation of the resources can be determined, the emergency support can be timely obtained in the critical area, the emergency response efficiency is improved, the error and unreasonable scheduling caused by manual judgment are avoided, the resource allocation is ensured to be more scientific and accurate, the coordination of overall resource management is improved, and particularly in a multipoint emergency, the resource allocation can be reasonably balanced, and the condition that the resources are concentrated at a certain place and other areas are limited is avoided. The scene dynamic weight data is monitored in real time, the change condition of a fire scene can be mastered in time, particularly in complex and dynamically changed emergency scenes, priority data and actual demands are guaranteed to be synchronously adjusted, the resource scheduling priority is intelligently adjusted, emergency resources are guaranteed to be rapidly redistributed according to the latest weight data, so that the flexibility and timeliness of emergency response are improved to the greatest extent, the self-adaptive capacity of resource scheduling is obviously enhanced by a real-time intelligent adjusting mechanism, sudden changes can be rapidly responded to resource allocation, emergency hysteresis problems caused by a fixed scheduling strategy are avoided, and the coping capacity of the whole fire emergency management system is improved.

In the embodiment of the invention, the priority analysis is performed on the resources in the fire emergency scene based on the fire emergency resource data. The fire emergency resource data includes real-time status information of currently available firefighters and supplies, etc. For example, real-time status data of various fire-fighting materials, such as available water pressure of fire pumps, remaining injection time of fire extinguishers, location of fire engines, and distribution and action ability of firefighters, are obtained from sensors, internet of things equipment, and schedulability of each resource is evaluated by matching these resource data with a fire emergency scene demand pattern generated previously. For example, an area may have a fire greater, marked as a higher priority dispatch point, and may be matched to surrounding available fire equipment and personnel based on the resource requirements of the area. The matching condition of the availability and the demand of the resources is analyzed through an algorithm, the fire emergency resource scheduling priority data is generated, and the arrival time of the fire emergency resources, the current state of the fire emergency resources and the emergency degree of the fire are considered. In addition, the scheduling efficiency of the resources is considered, the equipment with the short distance is scheduled preferentially, the scheduling time is reduced, the factors such as the response time and the working capacity of the equipment are comprehensively analyzed, the fire emergency resource scheduling priority data are generated, wherein the scheduling sequence of each resource is subjected to intelligent analysis of a system, and the resources can be deployed to the most needed nodes in the shortest time efficiently. The fire emergency scene demand spectrum is continuously monitored in real time through the sensor and the data monitoring equipment, particularly, dynamic weight data in the scene reflects the change condition of factors such as fire risk, equipment state, people flow density, fire spreading speed and the like of each node in the scene, when the fire situation changes, the weight of each node is required to be adjusted in time, and the dynamic weight data in the scene is updated according to the sensor data updated in real time, the fire spreading speed, the actual working state of the fire equipment and the like. For example, assuming a fire node has been gradually controlled by the effective response of the fire equipment, the weight of the node is gradually reduced. And in the area adjacent thereto, if the fire starts to spread, the weight may rapidly increase. The weight data is updated simply, and intelligent adjustment is performed on the scheduling priority data of the fire emergency resources according to the weight data. The key to intelligent regulation is to consider the dynamic relevance of neighboring nodes. For example, when the fire of a high weight node (e.g., a fire center area) is actively controlled, the system automatically reduces the scheduling priority of that node, however, the system also simultaneously evaluates the nodes adjacent thereto. If the fire risk of neighboring nodes increases, the system may prioritize the transfer of resources to these neighboring areas. The specific intelligent regulation process is realized by a real-time feedback mechanism that the system monitors the change of fire through the real-time feedback (such as water pressure, smoke concentration and the like) of the fire-fighting equipment. When the fire is controlled, the system automatically reduces the dynamic weight of the node and redistributes the resource to the higher weight nodes that are more in need. Adjacent node linkage scheduling the system determines which adjacent nodes a fire may spread from a high weight node to by analyzing the physical association between adjacent nodes, such as by interactions of ventilation systems, building structures, and people flow paths. When the weight of a certain node is reduced, the system can analyze the adjacent node preferentially and increase the resource scheduling priority of the node according to the potential risk of the node. And the system runs a scheduling priority optimization algorithm, and adjusts the priority of the resource in real time according to the latest scene demand and the dynamic weight. Assuming that the fire risk of a certain area is reduced, the resources are dynamically reallocated, and the resources are preferentially mobilized to other areas with larger fire and higher personnel concentration. The process ensures reasonable scheduling of resources and avoids resource waste.

The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.

The foregoing is only a specific embodiment of the invention to enable those skilled in the art to understand or practice the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A smart fire emergency management method, characterized in that it includes the following steps:

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, characterized in that step S2 comprises 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 smart fire emergency management method according to claim 2, characterized in that step S3 comprises 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 space node division processing on the fire status spatial fire joint feature data to generate fire status local space fire joint feature 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 smart fire emergency management method according to claim 3, characterized in that step S36 comprises 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, so as 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, characterized in that step S363 comprises the following steps:

According to the fire joint evolution data of historical fire state scenes, the fire evolution time series characteristics of historical fire state scenes are analyzed to generate the fire evolution time series characteristic data of historical fire state scenes;

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 smart fire emergency management method according to claim 4, characterized in that step S364 comprises 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 time series probability data of local space fire 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 comprises 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: performing 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 smart fire emergency management method according to claim 1, characterized in that step S53 comprises 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 it is used to execute the smart fire emergency management method according to claim 1, and 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 scene situation assessment module for fire status is used to perform fire scene situation assessment processing based on real-time multi-source fire data and fire equipment status data to generate 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.