A method and system for managing dispatch information based on fire truck fire

Abstract

The application discloses a kind of based on fire truck fire fighting's dispatch information management method and system, it is related to intelligent fire dispatch technical field, including, receiving fire alarm information, and based on preliminary fire assessment result, real-time fire ground data are collected;Real-time fire ground data collected are combined with historical fire data, and the trend of fire spread is analyzed by AI fire prediction model;According to the trend of fire spread and the equipment state of fire truck, dynamically allocate fire truck resources, plan optimal driving route;Real-time monitoring fire truck driving state, based on road condition and equipment information are dynamically adjusted, according to real-time fire ground situation update fire truck's task allocation;In the process of extinguishing fire, according to the material consumption condition of fire truck real-time scheduling resource is supplied.The application is by real-time monitoring the material consumption condition of fire truck, intelligent dispatch supply resource, ensure the continuity and efficiency of extinguishing fire action.

Description

Technical Field

[0001] This invention relates to the field of intelligent fire dispatching technology, and in particular to a method and system for managing dispatching information based on fire truck firefighting. Background Technology

[0002] With the acceleration of urbanization and the increase in building density, the frequency and complexity of fire accidents are increasing, especially in high-rise buildings and densely populated urban areas, posing unprecedented challenges to fire rescue work. In traditional fire dispatch, fire trucks, as the main firefighting force, are typically dispatched based on manual decision-making and experience from the command center. Due to the lack of real-time dynamic fire scene information, the resource allocation efficiency of fire trucks is often low, making it difficult to make flexible adjustments according to the actual situation at the fire scene. In addition, the planning of fire truck routes mostly relies on predefined static paths, which cannot respond promptly to complex and changing traffic conditions and the spread of fire. This results in the arrival time of fire trucks, resource allocation, and operational command not reaching the optimal state in actual fire rescue, affecting firefighting efficiency and rescue effectiveness.

[0003] Although the introduction of smart technologies in recent years has brought some improvements to fire dispatching, such as the Internet of Things (IoT) for real-time monitoring of fire truck status and drones for real-time collection of fire scene information, there are still many shortcomings. First, existing dispatching methods often lack the ability to dynamically allocate fire truck resources based on the fire scene situation, failing to fully utilize the fusion analysis of real-time fire scene data and historical fire data. Second, during fire truck travel, existing technologies fail to effectively combine real-time traffic information and fire truck equipment status to dynamically optimize travel routes. Furthermore, existing management of fire scene material consumption and replenishment is relatively lagging, making it difficult to achieve timely and accurate replenishment during firefighting, thus affecting the stability and efficiency of continuous rescue efforts. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a method for managing dispatch information based on fire truck firefighting to solve the problem of insufficient intelligence and real-time dispatch of fire truck resources.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, the present invention provides a dispatch information management method based on fire truck firefighting, which includes receiving fire alarm information and collecting real-time fire scene data based on preliminary fire assessment results;

[0008] By combining real-time fire data with historical fire data, the fire spread trend is analyzed using an AI fire prediction model.

[0009] Based on the fire spread trend and the equipment status of fire trucks, dynamically allocate fire truck resources and plan the optimal driving routes;

[0010] Real-time monitoring of fire truck driving status, dynamic adjustments based on road conditions and equipment information, and updating of fire truck task allocation according to real-time fire situation;

[0011] During the firefighting process, resources are replenished in real time based on the consumption of materials by the fire trucks.

[0012] As a preferred embodiment of the fire truck-based dispatch information management method of the present invention, the specific steps of receiving fire alarm information and collecting real-time fire scene data based on preliminary fire assessment results are as follows:

[0013] Receive fire alarm information and format it.

[0014] Kalman filtering is used to remove noise from fire alarm information;

[0015] Set a fire threshold, use a Bayesian inference model to calculate the probability of a fire, and conduct a preliminary fire assessment when the probability of a fire exceeds the threshold.

[0016] Real-time environmental data of the fire site is acquired, and a fire prediction model combining convolutional neural networks and long short-term memory networks is used to output preliminary fire assessment results.

[0017] Based on the initial assessment of the fire, flight missions were assigned to drones;

[0018] The drone's flight path is optimized using an ant colony algorithm to reach the fire site and collect real-time fire data.

[0019] As a preferred embodiment of the fire truck-based dispatch information management method of the present invention, the specific steps of combining the collected real-time fire data with historical fire data and analyzing the fire spread trend through an AI fire prediction model are as follows:

[0020] Real-time and historical fire data are represented in quantum states, and multidimensional data are processed using quantum superposition and entanglement.

[0021] Based on multidimensional data, high-dimensional data is mapped to the frequency domain through quantum Fourier transform, expressed as:

[0022] ;

[0023] in, Indicates time The quantum state fusion model at the current moment, This indicates the number of dimensions involved in fire prediction. The ordinal number represents the weight of the dimensional data. Indicates the first Weights of dimensional data Indicates the first The quantum state of real-time fire scene data in dimensionality. This indicates that the data is collected in real time. Indicates the first The quantum state of historical data in dimensions This indicates that the data originates from historical records. Represents the tensor product;

[0024] Based on quantum data fusion, nonlinear dynamic fuzzy logic is introduced to fuzzify real-time fire data;

[0025] By performing fuzzy set analysis on each parameter and combining it with a system of nonlinear differential equations, the change of fire intensity over time is dynamically described, and the expression is:

[0026] ;

[0027] in, Indicates the trend of the fire spreading. Over time The first derivative, This indicates the amount of real-time fire data. Index variables representing real-time fire data. For each environmental parameter Fuzzy membership function, Indicates the first Real-time fire data Over time rate of change Indicates a point in time in the past. Weighting function for historical data, Represents the exponentially decaying function. The parameter that controls the decay rate. This represents the exponential decay coefficient that controls the impact of historical data on current forecasts. Indicates time a tiny increment, Indicates past time A tiny increment;

[0028] The fire spreads rapidly Over time The first derivative analysis outputs the fire's spread rate, direction, and extent.

[0029] As a preferred embodiment of the dispatch information management method based on fire truck firefighting described in this invention, the method involves introducing nonlinear dynamic fuzzy logic to fuzzify real-time fire scene data based on quantum data fusion. The specific steps are as follows:

[0030] For the fused quantum data, define fuzzy sets and set membership functions for the fuzzy sets;

[0031] Real-time fire data collected in real time is converted into fuzzy values ​​using a membership function.

[0032] By using a fuzzy reasoning mechanism and combining it with a fuzzy rule base, the activation level of each rule is calculated, and a fuzzy output of the fire spread trend is derived.

[0033] As a preferred embodiment of the fire truck-based dispatch information management method of the present invention, the specific steps of dynamically allocating fire truck resources and planning optimal driving routes according to the fire spread trend and the equipment status of the fire trucks are as follows:

[0034] The status information of each fire truck is monitored in real time through vehicle-to-everything (V2X) communication.

[0035] By combining the speed, direction, and extent of fire spread, deep reinforcement learning is used to intelligently dispatch fire truck resources.

[0036] By using spatiotemporal graph convolutional networks combined with real-time traffic data and geographic information, the optimal driving route for fire trucks can be planned.

[0037] As a preferred embodiment of the fire truck-based dispatch information management method of the present invention, the steps of real-time monitoring of fire truck driving status, dynamic adjustment based on road conditions and equipment information, and updating fire truck task allocation according to the real-time fire situation are as follows:

[0038] By combining fire truck status information obtained from the Internet of Vehicles and real-time traffic conditions provided by the traffic management platform, road traffic conditions are predicted through a spatiotemporal graph convolutional network.

[0039] If abnormal road conditions occur, the fire truck's route will be dynamically adjusted using an adaptive dynamic programming model.

[0040] The speed, direction, and extent of the fire's spread are obtained in real time through drones and monitoring equipment.

[0041] By combining the status of fire trucks and the fire situation, a multi-objective optimization method is used to adjust the task allocation of each fire truck.

[0042] As a preferred embodiment of the fire truck-based firefighting dispatch information management method of the present invention, wherein: during the firefighting process, resources are dispatched in real time for replenishment based on the material consumption of the fire truck, specifically through the following steps:

[0043] The remaining amount of fire-fighting supplies in fire trucks is monitored in real time, and the data is transmitted to the central control platform via wireless network.

[0044] The central control platform preprocesses the received data on the remaining quantity of fire-fighting supplies.

[0045] Based on the pre-processed remaining data of fire-fighting supplies, a material consumption prediction model is constructed using deep learning to predict the consumption rate of supplies in the future. The expression is as follows:

[0046] ;

[0047] in, for The current rate of material consumption by fire trucks The density of the extinguishing agent. The velocity vector of the extinguishing agent injection. Let be the divergence of the velocity field. For the velocity field, The volume of the spray area. It is the gravitational acceleration vector. For the spray angle, Indicates the time decay coefficient. This represents a tiny increase in the volume of the sprayed area;

[0048] Based on the consumption rate derived from the material consumption prediction model, and combined with the location of fire trucks, the fire scene conditions, and the material reserves at the supply station, particle swarm optimization is used to dynamically find supply routes and timing.

[0049] Secondly, the present invention provides a dispatch information management system based on fire truck firefighting, including a fire assessment module, a trend prediction module, a resource allocation module, a route planning module, and a material supply module;

[0050] The fire assessment module is used to receive fire alarm information and collect real-time fire scene data based on the preliminary fire assessment results.

[0051] The trend prediction module is used to combine the collected real-time fire data with historical fire data and analyze the fire spread trend through an AI fire prediction model.

[0052] The resource allocation module is used to dynamically allocate fire truck resources and plan the optimal driving route based on the fire spread trend and the equipment status of the fire trucks.

[0053] The route planning module is used to monitor the driving status of fire trucks in real time, make dynamic adjustments based on road conditions and equipment information, and update the task allocation of fire trucks according to the real-time fire situation.

[0054] The material supply module is used to dispatch resources in real time to replenish supplies based on the material consumption of the fire truck during the firefighting process.

[0055] Thirdly, the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the dispatch information management method based on fire truck firefighting as described in the first aspect of the present invention.

[0056] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the dispatch information management method based on fire truck firefighting as described in the first aspect of the present invention.

[0057] The beneficial effects of this invention are as follows: By introducing real-time fire scene data collection by drones, combining it with an AI fire prediction model based on historical fire data, and employing methods such as quantum data fusion and dynamic fuzzy logic, this invention accurately predicts the spread trend of fires and dynamically optimizes the resource scheduling and driving routes of fire trucks based on their equipment status and real-time road conditions. Simultaneously, during firefighting, it can monitor the material consumption of fire trucks in real time, intelligently scheduling replenishment resources to ensure the continuity and efficiency of firefighting operations. Overall, it significantly improves the intelligence level of fire truck dispatching, shortens rescue response time, and enhances the coordination efficiency of fire rescue. Attached Figure Description

[0058] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0059] Figure 1 This is a flowchart of the dispatch information management method based on fire truck firefighting in Example 1.

[0060] Figure 2 This is a module diagram of the dispatch information management system based on fire truck firefighting in Example 1. Detailed Implementation

[0061] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0062] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0063] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0064] Example 1, referring to Figure 1 and Figure 2 This is the first embodiment of the present invention, which provides a method for managing dispatch information based on fire truck firefighting, including the following steps:

[0065] S1. Receive fire alarm information and collect real-time fire scene data based on preliminary fire assessment results.

[0066] Furthermore, it receives fire alarm information from multiple data sources and performs formatting processing;

[0067] The system uses multiple data sources, including data from fire detectors, manual alarms, and satellite thermal imaging, and unifies key information such as timestamps and geographic coordinates.

[0068] Kalman filtering is used to remove noise from fire alarm information, eliminating random errors and noise in the data and improving data reliability.

[0069] Set a preset fire threshold, use a Bayesian inference model to calculate the probability of a fire occurring, and confirm the fire alarm is valid when the probability of a fire occurring exceeds the preset threshold, and conduct a preliminary fire assessment.

[0070] The system acquires real-time environmental data (including temperature, humidity, wind speed, wind direction, etc.) of the fire location and outputs preliminary fire assessment results (including predictions of the fire's spread range, direction, and speed) through a fire prediction model that combines a convolutional neural network (CNN) and a long short-term memory network (LSTM).

[0071] Based on the initial assessment of the fire, flight missions were assigned to drones;

[0072] The drone's flight path is optimized using an ant colony algorithm to reach the fire site and collect real-time fire data.

[0073] The real-time fire data includes information such as fire temperature distribution, fire spread, and wind speed. The data is preprocessed through edge computing nodes and transmitted to the command center in real time using a 5G network to assist in further decision-making and fire assessment.

[0074] S2. Combine the collected real-time fire data with historical fire data, and analyze the fire spread trend through an AI fire prediction model.

[0075] Furthermore, real-time fire scene data and historical data are represented in quantum states, and multidimensional data are processed using quantum superposition and entanglement.

[0076] It should be noted that traditional fire prediction models (such as CNN and LSTM) rely on classical computing architectures, and computation time increases exponentially with the increase of data dimensionality. Quantum computing, on the other hand, can process large amounts of data in parallel, greatly improving computational efficiency and solving the computational bottleneck in traditional prediction models. Especially when processing the fusion of real-time fire data and historical data, the superior parallelism and entangled states of quantum computing enable it to find the optimal data fusion strategy in a very short time.

[0077] Based on multidimensional data, high-dimensional data is mapped to the frequency domain through quantum Fourier transform (QFT), as expressed by:

[0078] ;

[0079] in, Indicates time The quantum state fusion model at the current moment, This indicates the number of dimensions involved in fire prediction. The weight ordinal number represents the weight of the dimension data, used to control the weight of the first dimension. The extent to which real-time and historical fire data from different dimensions affect the overall quantum state fusion. Indicates the first The weights of dimensional data are used to control the degree of influence from different data sources. Indicates the first The quantum state of real-time fire scene data in dimensionality. This indicates that the data is collected in real time. Indicates the first The quantum state of historical data in dimensions This indicates that the data originates from historical records. Represents the tensor product;

[0080] Based on quantum data fusion, nonlinear dynamic fuzzy logic is introduced to fuzzify real-time fire data (such as wind speed, temperature, and humidity). The specific steps are as follows:

[0081] For the fused quantum data, define fuzzy sets (such as low wind speed, medium wind speed, and high wind speed) and set membership functions for the fuzzy sets;

[0082] Real-time fire data collected in real time is converted into fuzzy values ​​using a membership function to represent the degree of membership of each parameter in different fuzzy sets.

[0083] By using a fuzzy reasoning mechanism and combining it with a fuzzy rule base, the activation level of each rule is calculated, and a fuzzy output of the fire spread trend is derived.

[0084] It should be noted that fire spread is a highly nonlinear and dynamically changing process, and traditional linear models struggle to capture this complexity. We employ Dynamic Nonlinear Fuzzy Logic System (DNFLLS) to handle the uncertainties and fuzziness in the fire spread process; by fuzzifying different environmental parameters (such as wind speed, humidity, and temperature), we can effectively address the uncertainties in the fire spread trend.

[0085] By performing fuzzy set analysis on each parameter and combining it with a system of nonlinear differential equations, the change of fire intensity over time is dynamically described, and the expression is:

[0086] ;

[0087] in, Indicates the trend of the fire spreading. Over time The first derivative of the fire describes the rate at which the fire spreads over time. This indicates the amount of real-time fire data (such as wind speed, humidity, etc.). Index variables representing real-time fire data. For each environmental parameter The fuzzy membership function is used to represent the degree of influence of this parameter on the fire. Indicates the first Real-time fire data Over time rate of change Indicates a point in time in the past. Weighting function for historical data, Represents the exponentially decaying function. The parameter that controls the decay rate. This represents the exponential decay coefficient that controls the impact of historical data on current forecasts. Indicates time a tiny increment, Indicates past time A tiny increment;

[0088] Preferably, by introducing a system of nonlinear differential equations, the transformation process between various fuzzy sets can be dynamically described. For example, when humidity decreases and wind speed increases, the trend of fire spread will intensify nonlinearly. Through nonlinear dynamic modeling, this complex change process can be accurately captured.

[0089] The fire spreads rapidly Over time The first derivative analysis outputs the fire's spread rate, direction, and extent.

[0090] S3. Based on the fire spread trend and the equipment status of the fire trucks, dynamically allocate fire truck resources and plan the optimal driving route.

[0091] Furthermore, the vehicle network can monitor the status information of each fire truck in real time, including its location, speed, equipment integrity, material reserves (such as water, fuel, etc.), and power level.

[0092] By combining the speed, direction, and extent of fire spread, deep reinforcement learning is used to intelligently dispatch fire truck resources.

[0093] Specifically, the decision-making process considers the direction of fire spread, the status of fire trucks, and geographical and traffic information, and finds the optimal resource allocation scheme by maximizing the cumulative reward function.

[0094] Using a spatiotemporal graph convolutional network (ST-GCN) that combines real-time traffic data and geographic information, the optimal route for fire trucks is planned.

[0095] Specifically, by representing the road network as a graph structure, ST-GCN predicts future traffic congestion and combines Dijkstra's or A* algorithms to calculate the shortest travel path.

[0096] Preferably, the Spatiotemporal Graph Convolutional Network (ST-GCN) is a deep learning model for processing spatiotemporal data. It can combine real-time traffic data (such as congestion, road closures, etc.) and geographic information (such as road networks, terrain, etc.) to plan the optimal route for each fire truck, ensuring that the fire truck can reach the fire scene as quickly as possible.

[0097] S4. Monitor the driving status of fire trucks in real time, make dynamic adjustments based on road conditions and equipment information, and update the task allocation of fire trucks according to the real-time fire situation.

[0098] Furthermore, by combining fire truck status information obtained from the Internet of Vehicles, including location, speed, water tank capacity, equipment status, and fuel / electricity, with real-time traffic conditions provided by the traffic management platform, road traffic conditions are predicted through a spatiotemporal graph convolutional network (ST-GCN).

[0099] It should be noted that Spatiotemporal Graph Convolutional Networks (ST-GCN) are deep learning models used for modeling spatiotemporal data, and are particularly suitable for handling complex systems with spatiotemporal dependencies, such as traffic networks. It represents road networks as graph structures and extracts spatial features through convolutional operations on the graph, combining this with time-series data to predict future traffic conditions.

[0100] Furthermore, ST-GCN uses a graph to represent the connections between road segments and roads in the transportation network. The graph consists of nodes and edges:

[0101] Nodes: Nodes in the diagram represent road segments, intersections, or other traffic-related physical locations in the transportation network.

[0102] Edges: Edges between nodes represent the transmission paths of traffic flow, i.e., the connections between roads. Edges can be directed (representing the direction of traffic flow) or undirected (representing bidirectional connections between road segments).

[0103] In a specific traffic scenario, the road network can be represented by a map. express:

[0104] Node set: Represents all road segments or traffic critical points in the road network.

[0105] Edge set: Represents the connection between road segments (such as intersections, traffic flow direction).

[0106] Each node (road segment) has different information such as traffic flow, speed, and vehicle density at different times. This information can be represented as time series data, that is, at each time step, the state of the node is the traffic characteristics of that node (such as traffic flow, vehicle speed, etc.).

[0107] Therefore, the input data can be represented as a spatiotemporal feature matrix, where each row represents the state of a node and the columns represent the feature values ​​at each time step.

[0108] In ST-GCN, graph convolution is used to capture spatial dependencies, i.e., the mutual influence between different road segments. Compared to traditional CNNs that perform convolutions on two-dimensional plane pixels, graph convolution is performed on the nodes of a graph, and the features of each node are updated using information from its neighboring nodes.

[0109] In each layer, the node's features are updated by weighted summation of the features of its neighboring nodes using the adjacency matrix A. This process captures spatial traffic flow relationships.

[0110] In addition to spatial dimensions, traffic data also exhibits temporal dependencies. For example, the current traffic conditions are often closely related to the traffic conditions of the past few minutes or hours. Therefore, ST-GCN also captures the temporal dependencies of traffic flow through temporal convolution.

[0111] Temporal convolution typically uses one-dimensional convolution (1D-CNN) to process time-series data. For each node, a sliding window operation is performed along the time dimension using one-dimensional convolution to extract patterns of change over time.

[0112] ST-GCN gradually extracts the spatial and temporal dynamic dependencies between nodes in a traffic network by alternating between hierarchical structures of graph convolution and temporal convolution. After multiple layers of convolutional operations, ST-GCN can learn complex spatiotemporal features, which are ultimately used for traffic state prediction.

[0113] The last layer is typically a fully connected layer or a one-dimensional convolution, used to output predictions of future traffic conditions, such as traffic flow and vehicle speed in the next few minutes.

[0114] If abnormal road conditions occur, the fire truck's route will be dynamically adjusted using an adaptive dynamic programming model, with the goal of minimizing travel time and resource consumption.

[0115] By using drones and monitoring equipment to obtain real-time information on the spread speed, direction, and extent of the fire, and combining this with the status of fire trucks and the fire situation, a multi-objective optimization method is used to adjust the task allocation of each fire truck to ensure that the fire trucks perform the optimal tasks based on the latest fire situation.

[0116] For example, when the fire in a certain area subsides, nearby fire trucks can be relocated to provide support to other more urgent areas.

[0117] S5. During the firefighting process, resources are dispatched in real time to replenish supplies based on the consumption of materials by the fire trucks.

[0118] Furthermore, with the support of Internet of Things (IoT) technology, sensors installed on fire trucks can monitor the remaining amount of fire-fighting supplies (such as water and foam) in real time and send the data to the central control platform.

[0119] The central control platform preprocesses the received data on the remaining quantity of fire-fighting supplies, including data cleaning and formatting, to ensure data quality and availability.

[0120] Based on the pre-processed remaining data of fire-fighting supplies, a material consumption prediction model is constructed using deep learning to predict the consumption rate of supplies in the future. The expression is as follows:

[0121] ;

[0122] in, for The rate of fire extinguishing agent consumption per unit time indicates the mass of extinguishing agent consumed by the fire truck. Density is the density of the extinguishing agent, representing the mass of the extinguishing agent per unit volume. Let be the velocity vector of the extinguishing agent injection, representing the velocity and direction of the extinguishing agent injection. The divergence of the velocity field represents the degree of diffusion in fluid flow, i.e., the net outflow of fluid per unit volume. The velocity field represents the velocity distribution of the fluid in space. The volume of the spray area represents the spatial extent covered by the extinguishing agent. Let be the gravitational acceleration vector, representing the effect of gravity on the extinguishing agent injection. The spray angle represents the angle between the direction of the extinguishing agent spray and the horizontal plane. This represents the time decay coefficient, indicating the natural decreasing trend of the rate of resource consumption as time increases. This represents a tiny increase in the volume of the sprayed area;

[0123] Based on the consumption rate derived from the material consumption prediction model, and combined with the location of fire trucks, the fire scene conditions, and the material reserves of supply stations, particle swarm optimization is used to dynamically find supply paths and timing.

[0124] Specifically, the steps for dynamically finding supply routes and timing are as follows:

[0125] First, the real-time location of each fire truck is obtained through vehicle-to-everything (V2X) communication, and the real-time situation of the fire scene is collected simultaneously, including the speed and direction of fire spread and the danger zones. In addition, the location, material reserves, and resupply capacity of each supply station must be obtained. Simultaneously, combined with a material consumption prediction model, the material consumption rate and remaining material quantity of each fire truck are dynamically calculated.

[0126] Secondly, the optimization objective must be defined. The core objective is to ensure that fire trucks can be resupplyed in a timely manner before supplies run out, and to find the optimal route to complete resupply in the shortest possible time. This means finding reasonable resupply times and planning the optimal route for fire trucks from their current location to the resupply station. During this process, the danger zone of the fire scene, real-time traffic conditions, and the urgency of the firefighting mission should be fully considered.

[0127] Furthermore, the particle swarm optimization (PSO) algorithm is used to dynamically optimize the resupply scheme. The specific steps are as follows:

[0128] Initialize the particle swarm: Each particle represents a possible resupply plan, which includes two key elements: resupply timing (when to resupply) and resupply path (the optimal route from the fire truck's current location to the resupply station).

[0129] Fitness evaluation: The fitness function is used to evaluate the merits of each solution. The fitness function considers the following factors:

[0130] Resupply time: The round-trip time for the fire truck from its current location to the resupply station, including traffic conditions inside and outside the fire scene.

[0131] Risk of depletion of supplies: Will the rate of consumption of supplies cause the fire truck to run out of supplies before it can be resupplyed?

[0132] Impact of the fire situation: Will the departure of fire trucks from the fire scene for resupply affect firefighting operations or cause the fire to get out of control?

[0133] Particle swarm iteration update: By iteratively updating the particle swarm, the timing and path of each particle's replenishment are dynamically adjusted to gradually approach the optimal solution.

[0134] Ultimately, the particle swarm optimization algorithm outputs the optimal resupply timing, ensuring that fire trucks receive timely resupply before supplies run out. Simultaneously, it provides the optimal resupply route, ensuring fire trucks complete resupply missions in the shortest possible time, minimizing interruptions and impacts on firefighting operations.

[0135] This embodiment also provides a dispatch information management system based on fire truck firefighting, including: a fire assessment module, a trend prediction module, a resource allocation module, a route planning module, and a material supply module; the fire assessment module is used to receive fire alarm information and collect real-time fire scene data based on the preliminary fire assessment results; the trend prediction module is used to combine the collected real-time fire scene data with historical fire data and analyze the fire spread trend through an AI fire prediction model; the resource allocation module is used to dynamically allocate fire truck resources and plan the optimal driving route according to the fire spread trend and the equipment status of the fire trucks; the route planning module is used to monitor the driving status of fire trucks in real time, make dynamic adjustments based on road conditions and equipment information, and update the task allocation of fire trucks according to the real-time fire scene situation; the material supply module is used to dispatch resources for replenishment in real time according to the material consumption of fire trucks during the firefighting process.

[0136] This embodiment also provides a computer device applicable to the dispatch information management method based on fire truck firefighting, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the dispatch information management method based on fire truck firefighting proposed in the above embodiment.

[0137] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0138] This embodiment also provides a storage medium storing a computer program, which, when executed by a processor, implements the dispatch information management method based on fire truck firefighting as proposed in the above embodiment. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0139] In summary, this invention accurately predicts the spread of fire by introducing real-time fire scene data collection by drones, combining it with an AI fire prediction model based on historical fire data, and employing methods such as quantum data fusion and dynamic fuzzy logic. Furthermore, it dynamically optimizes fire truck resource allocation and routes based on equipment status and real-time road conditions. Simultaneously, during firefighting, it can monitor fire truck material consumption in real time and intelligently allocate replenishment resources, ensuring the continuity and efficiency of firefighting operations. Overall, it significantly improves the intelligence level of fire truck dispatching, shortens rescue response time, and enhances the coordination efficiency of fire rescue.

[0140] Example 2, referring to Table 1, is the second embodiment of the present invention. To further verify the technical solution of the present invention, experimental simulation data of the dispatch information management method based on fire truck fire fighting are given.

[0141] The experiment simulates a fire scenario to evaluate whether the proposed method can demonstrate significant performance advantages in multi-source data access and drone scheduling. The experiment compares the proposed method with existing traditional fire monitoring methods, focusing on key indicators such as preliminary fire assessment, drone scheduling efficiency, response time, and accuracy of fire scene data acquisition and analysis.

[0142] In the experiment, traditional fire monitoring methods relied on a single data source for fire detection and response. They typically depended on fixed fire detectors (such as smoke sensors and temperature sensors) for alarms and determined the occurrence of a fire based on simple logical conditions (such as temperature or smoke concentration exceeding a set threshold). Traditional methods depend on data from these fixed sensors, failing to dynamically capture the complex changes in the fire scene. Furthermore, they lack efficient fusion and processing mechanisms when dealing with multi-source data (such as manual alarms and satellite thermal imaging). In addition, drone scheduling in traditional methods usually uses preset flight paths and does not optimize based on the actual fire situation, resulting in long response times.

[0143] The experimental group employed the multi-source data fusion fire monitoring method proposed in this paper, capable of receiving data from multiple sources including fire detectors, manual alarms, and satellite thermal imaging. In the experimental group, this data underwent noise reduction using Kalman filtering, and timestamps and geographic coordinates were standardized. After formatting the data, a Bayesian inference model was used to calculate the probability of a fire. When the probability exceeded a preset threshold, the fire alarm was confirmed as valid, and a preliminary fire assessment was conducted.

[0144] Next, the experiment simulated real-time environmental data (including temperature, humidity, wind speed, and wind direction) at the fire scene. The experimental method used a fire prediction model combining convolutional neural networks (CNN) and long short-term memory networks (LSTM) to output the range, direction, and speed of fire spread. Simultaneously, based on the fire assessment results, the experimental method deployed drones with sufficient battery power and optimized their flight paths using an ant colony algorithm to collect real-time fire scene data. After arriving at the fire scene, the drones collected information such as temperature distribution and fire spread, preprocessed the data using edge computing nodes, and transmitted it in real-time to the command center via a 5G network.

[0145] In the experiment, the experimental group's method utilized quantum state representation to combine real-time fire data with historical fire data, and then mapped the data to the frequency domain using quantum Fourier transform (QFT) to predict fire spread trends. Compared with traditional fire monitoring methods, the experimental group's method demonstrated extremely high parallel processing efficiency, especially when processing multi-source data with complex dimensions.

[0146] After the experiment, the performance of the experimental group and traditional fire monitoring methods was compared in terms of data processing efficiency, drone dispatch response time, and accuracy of fire scene data collection.

[0147] The details are shown in Table 1 below:

[0148] Table 1 Comparison of Experimental Data

[0149]

[0150] The experimental data clearly demonstrates that the multi-source data fusion fire monitoring method proposed in this paper has significant advantages over traditional fire monitoring methods in several key indicators. Firstly, in terms of data processing efficiency, the experimental method achieves 90 MB / s, almost twice that of traditional methods. This is attributed to the noise reduction through Kalman filtering and the preprocessing of multi-source data, which avoids redundancy and interference from noisy data, greatly improving the processing speed. In contrast, traditional methods rely on a single data source and lack effective processing capabilities for multi-source data, resulting in lower data processing efficiency.

[0151] Secondly, regarding the drone dispatch response time, the experimental method performed exceptionally well, with a response time of only 5 seconds, compared to 12 seconds for the traditional method. Traditional drone dispatch methods often rely on pre-set flight paths and cannot dynamically adjust to changes in the fire situation, resulting in a slow response. The experimental method, however, combines fire assessment results with an ant colony algorithm to dynamically optimize drone flight paths, ensuring that drones can be rationally dispatched to the fire scene in the shortest possible time.

[0152] Regarding the accuracy of fire scene data collection, the experimental group's real-time data collected by the drones achieved a 95% match with the actual fire situation, significantly outperforming the traditional method's 78%. Traditional methods typically cannot effectively integrate multi-source data (such as satellite thermal imaging and environmental sensors), relying solely on a single data source for fire assessment, resulting in lower data collection accuracy. The experimental group's method preprocesses the drone-collected data through edge computing nodes and deeply integrates it with historical fire data, making the collected data more accurate and reliable.

[0153] Regarding the error in fire spread prediction, the experimental group's error was 6%, significantly lower than the 15% of traditional methods. Traditional methods typically rely on simple linear models or rules based on historical experience for fire spread prediction, which are unable to cope with complex fire environments. The experimental group's method, through quantum state data fusion and quantum Fourier transform (QFT), effectively improved the accuracy of fire spread prediction. The parallel processing capabilities of quantum computing demonstrate a significant advantage when dealing with high-dimensional data, while traditional methods struggle to handle such complex, multi-dimensional data.

[0154] Finally, regarding real-time fire scene data transmission latency, the experimental method achieved a latency of 2 seconds, significantly lower than the traditional method's 8 seconds. Traditional methods, employing lower bandwidth network transmission technologies and lacking edge computing support, result in slower data transmission speeds. In contrast, the experimental method, leveraging 5G networks and edge computing nodes, ensured rapid transmission of fire scene data to the command center, aiding in further decision-making.

[0155] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for managing dispatch information based on fire truck firefighting, characterized in that: include, Receive fire alarm information and collect real-time fire scene data based on preliminary fire assessment results; The collected real-time fire data is combined with historical fire data, and the fire spread trend is analyzed using an AI fire prediction model. The specific steps are as follows: Real-time and historical fire data are represented in quantum states, and multidimensional data are processed using quantum superposition and entanglement. Based on multidimensional data, high-dimensional data is mapped to the frequency domain through quantum Fourier transform, expressed as: in, Indicates time The quantum state fusion model at the current moment, This indicates the number of dimensions involved in fire prediction. The ordinal number represents the weight of the dimensional data. Indicates the first Weights of dimensional data Indicates the first The quantum state of real-time fire scene data in dimensionality. This indicates that the data is collected in real time. Indicates the first The quantum state of historical data in dimensions This indicates that the data originates from historical records. Represents the tensor product; Based on quantum data fusion, nonlinear dynamic fuzzy logic is introduced to fuzzify real-time fire data; By performing fuzzy set analysis on each parameter and combining it with a system of nonlinear differential equations, the change of fire intensity over time is dynamically described, and the expression is: in, Indicates the trend of the fire spreading. Over time The first derivative, This indicates the amount of real-time fire data. Index variables representing real-time fire data. For each environmental parameter Fuzzy membership function, Indicates the first Real-time fire data Over time rate of change, Indicates a point in time in the past. Weighting function for historical data, Represents the exponentially decaying function. The parameter that controls the decay rate. This represents the exponential decay coefficient that controls the impact of historical data on current forecasts. Indicates time a tiny increment, Indicates past time A tiny increment; The fire spreads rapidly Over time The first derivative analysis outputs the fire's spread rate, direction, and extent. Based on the fire spread trend and the equipment status of fire trucks, dynamically allocate fire truck resources and plan the optimal driving routes; Real-time monitoring of fire truck driving status, dynamic adjustments based on road conditions and equipment information, and updating of fire truck task allocation according to real-time fire situation; During the firefighting process, resources are replenished in real time based on the consumption of materials by the fire trucks.

2. The dispatch information management method based on fire truck firefighting as described in claim 1, characterized in that: The specific steps for receiving fire alarm information and collecting real-time fire scene data based on preliminary fire assessment results are as follows: Receive fire alarm information and format it. Kalman filtering is used to remove noise from fire alarm information; Set a fire threshold, use a Bayesian inference model to calculate the probability of a fire, and conduct a preliminary fire assessment when the probability of a fire exceeds the threshold. Real-time environmental data of the fire site is acquired, and a fire prediction model combining convolutional neural networks and long short-term memory networks is used to output preliminary fire assessment results. Based on the initial assessment of the fire, flight missions were assigned to drones; The drone's flight path is optimized using an ant colony algorithm to reach the fire site and collect real-time fire data.

3. The dispatch information management method based on fire truck firefighting as described in claim 2, characterized in that: Based on quantum data fusion, nonlinear dynamic fuzzy logic is introduced to fuzzify real-time fire scene data. The specific steps are as follows: For the fused quantum data, define fuzzy sets and set membership functions for the fuzzy sets; Real-time fire data collected in real time is converted into fuzzy values ​​using a membership function. By using a fuzzy reasoning mechanism and combining it with a fuzzy rule base, the activation level of each rule is calculated, and a fuzzy output of the fire spread trend is derived.

4. The dispatch information management method based on fire truck firefighting as described in claim 3, characterized in that: The process involves dynamically allocating fire truck resources and planning optimal routes based on the fire's spread and the equipment status of the fire trucks. The specific steps are as follows: The status information of each fire truck is monitored in real time through vehicle-to-everything (V2X) communication. By combining the speed, direction, and extent of fire spread, deep reinforcement learning is used to intelligently dispatch fire truck resources. By using spatiotemporal graph convolutional networks combined with real-time traffic data and geographic information, the optimal driving route for fire trucks can be planned.

5. The dispatch information management method based on fire truck firefighting as described in claim 4, characterized in that: The real-time monitoring of fire truck driving status, dynamically adjusted based on road conditions and equipment information, and updated fire truck task allocation according to the real-time fire situation, involves the following steps: By combining fire truck status information obtained from the Internet of Vehicles and real-time traffic conditions provided by the traffic management platform, road traffic conditions are predicted through a spatiotemporal graph convolutional network. If abnormal road conditions occur, the fire truck's route will be dynamically adjusted using an adaptive dynamic programming model. The speed, direction, and extent of the fire's spread are obtained in real time through drones and monitoring equipment. By combining the status of fire trucks and the fire situation, a multi-objective optimization method is used to adjust the task allocation of each fire truck.

6. The dispatch information management method based on fire truck firefighting as described in claim 5, characterized in that: During the firefighting process, resources are replenished in real time based on the consumption of materials by the fire trucks. The specific steps are as follows: The remaining amount of fire-fighting supplies in fire trucks is monitored in real time, and the data is transmitted to the central control platform via wireless network. The central control platform preprocesses the received data on the remaining quantity of fire-fighting supplies. Based on the pre-processed remaining data of fire-fighting supplies, a material consumption prediction model is constructed using deep learning to predict the consumption rate of supplies in the future. The expression is as follows: ； in, for The current rate of material consumption by fire trucks The density of the extinguishing agent. The velocity vector of the extinguishing agent injection. Let be the divergence of the velocity field. For the velocity field, The volume of the spray area. It is the gravitational acceleration vector. For the spray angle, Indicates the time decay coefficient. This represents a tiny increase in the volume of the sprayed area; Based on the consumption rate derived from the material consumption prediction model, and combined with the location of fire trucks, the fire scene conditions, and the material reserves at the supply station, particle swarm optimization is used to dynamically find supply routes and timing.

7. A dispatch information management system based on fire truck firefighting, based on the dispatch information management method based on fire truck firefighting as described in any one of claims 1 to 6, characterized in that: It includes a fire assessment module, a trend prediction module, a resource allocation module, a route planning module, and a material supply module; The fire assessment module is used to receive fire alarm information and collect real-time fire scene data based on the preliminary fire assessment results. The trend prediction module is used to combine the collected real-time fire data with historical fire data and analyze the fire spread trend through an AI fire prediction model. The resource allocation module is used to dynamically allocate fire truck resources and plan the optimal driving route based on the fire spread trend and the equipment status of the fire trucks. The route planning module is used to monitor the driving status of fire trucks in real time, make dynamic adjustments based on road conditions and equipment information, and update the task allocation of fire trucks according to the real-time fire situation. The material supply module is used to dispatch resources in real time to replenish supplies based on the material consumption of the fire truck during the firefighting process.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the dispatch information management method based on fire truck firefighting as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the dispatch information management method based on fire truck firefighting as described in any one of claims 1 to 6.

Images