Evaluation method, device and equipment for fire-fighting power deployment and storage medium

Abstract

The invention discloses an evaluation method, device and equipment for fire fighting power deployment and a storage medium. The method comprises the following steps: acquiring fire accident associated data, constructing a fire accident scene model based on the fire accident associated data, and executing at least one fire-fighting power deployment scheme on the fire accident scene model to obtain multiple groups of fire-fighting feedback data, the fire accident scene model is a three-dimensional model for dynamically simulating a fire accident space layout, a fire environment and a disaster situation trend; for each group of fire-fighting feedback data, inputting the fire-fighting feedback data into a pre-trained fire-fighting evaluation model, and determining an evaluation index corresponding to the fire-fighting strength deployment scheme based on a model output result; and evaluating the fire-fighting power deployment scheme based on the evaluation index and a preset index threshold. And the accuracy and the reliability of the evaluation of the fire-fighting power deployment scheme are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of fire simulation and deduction, and in particular to an evaluation method, device, equipment and storage medium for fire fighting force deployment. Background Art

[0002] Fires are characterized by rapid spread, high difficulty in extinguishing, and high rescue risks. After a fire accident occurs, how to optimize the reasonable deployment of firefighting forces as much as possible to reduce rescue casualties and economic losses has become a hot topic in the global fire safety and firefighting field.

[0003] Current research on firefighting force deployment primarily relies on intelligent optimization algorithms such as genetic algorithms and ant colony algorithms. While these algorithms can achieve optimal resource allocation solutions through simulation, they suffer from high computational complexity and lack of real-time performance. Predictive models based on deep learning and reinforcement learning can dynamically predict fire activity and optimize deployment strategies, but they are limited by a scarcity of training data. Summary of the Invention

[0004] The present invention provides a method, device, equipment and storage medium for evaluating the deployment of fire fighting forces, so as to solve the problem of high computational complexity of the deployment of fire fighting forces.

[0005] According to one aspect of the present invention, a method for evaluating firefighting force deployment is provided, the method comprising:

[0006] Obtaining fire accident related data, constructing a fire accident scenario model based on the fire accident related data, and executing at least one firefighting force deployment plan on the fire accident scenario model to obtain multiple sets of firefighting feedback data, wherein the fire accident scenario model is a three-dimensional model that dynamically simulates the spatial layout, fire environment, and disaster trend of the fire accident;

[0007] For each set of firefighting feedback data, the firefighting feedback data is input into a pre-trained firefighting assessment model, and based on the model output, an evaluation index corresponding to the firefighting force deployment plan is determined;

[0008] The firefighting force deployment plan is evaluated based on the evaluation indicators and preset indicator thresholds.

[0009] According to another aspect of the present invention, there is provided a device for evaluating the deployment of fire fighting forces, the device comprising:

[0010] a firefighting force deployment module, configured to obtain fire accident related data, construct a fire accident scenario model based on the fire accident related data, and execute at least one firefighting force deployment plan on the fire accident scenario model to obtain multiple sets of firefighting feedback data, wherein the fire accident scenario model is a three-dimensional model that dynamically simulates the spatial layout, fire environment, and disaster trends of the fire accident;

[0011] An evaluation index determination module is used to input each set of fire feedback data into a pre-trained fire assessment model and determine an evaluation index corresponding to the fire force deployment plan based on the model output results;

[0012] The deployment plan evaluation module is used to evaluate the firefighting force deployment plan based on the evaluation index and the preset index threshold.

[0013] According to another aspect of the present invention, an electronic device is provided, comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the fire fighting force deployment assessment method described in any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the fire fighting force deployment assessment method described in any embodiment of the present invention when executed.

[0018] The technical solution of the embodiment of the present invention obtains fire accident related data, constructs a fire accident scenario model based on the fire accident related data, executes at least one firefighting force deployment plan on the fire accident scenario model to obtain multiple sets of firefighting feedback data; constructs a three-dimensional fire accident scenario model that can accurately simulate the development dynamics of the fire. Then, for each set of firefighting feedback data, the firefighting feedback data is input into a pre-trained firefighting assessment model, and the evaluation index corresponding to the firefighting force deployment plan is determined based on the model output result; the firefighting operation data is converted into a quantifiable evaluation index through the firefighting assessment model; finally, the firefighting force deployment plan is evaluated based on the evaluation index and the preset index threshold. The problem of high computational complexity of firefighting force deployment is solved, and the accuracy and reliability of the firefighting force deployment operation evaluation and the accuracy and scientific nature of the firefighting deployment plan are improved.

[0019] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 This is a flow chart of a method for evaluating fire fighting force deployment according to the first embodiment of the present invention;

[0022] Figure 2 This is a flow chart of a method for evaluating fire fighting force deployment according to the second embodiment of the present invention;

[0023] Figure 3 This is a schematic structural diagram of a fire fighting force deployment assessment device provided in accordance with a third embodiment of the present invention;

[0024] Figure 4 It is a structural diagram of an electronic device for implementing the method for evaluating the deployment of fire fighting forces according to an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] Example 1

[0028] Figure 1A flowchart of a method for evaluating the deployment of fire fighting forces is provided for the first embodiment of the present invention. This embodiment is applicable to the evaluation of the deployment of fire fighting forces. The method can be executed by an evaluation device for the deployment of fire fighting forces. The evaluation of the deployment of fire fighting forces can be implemented in the form of hardware and / or software. The evaluation of the deployment of fire fighting forces can be configured in an electronic device. Figure 1 As shown, the method includes:

[0029] S110 . Obtain fire accident related data, construct a fire accident scenario model based on the fire accident related data, and execute at least one firefighting force deployment plan on the fire accident scenario model to obtain multiple sets of firefighting feedback data.

[0030] The fire accident scene model is a three-dimensional model that dynamically simulates the spatial layout, fire environment, and disaster trend of a fire accident. Fire accident-related data can be understood as data related to a fire accident.

[0031] For example, fire accident-related data may include accident scene identification data, fire type data, accident attribute data, main pipe network water supply data, foam mixture supply data, wind direction data, and wind speed data. Specifically, accident scene identification data is used to identify the specific scene of the fire accident, such as crude oil tank fire, forest fire, and factory workshop fire. Fire type data describes the specific type and characteristics of the fire. Different types of fire require different fire extinguishing methods and agents. Accident attribute data reflects the basic attributes and characteristics of the fire accident and is used for fire severity assessment, statistics, and analysis. Accident attribute data may include the time of fire occurrence, location of fire, cause of fire, and fire losses, including casualties and property damage. Main pipe network water supply data represents the total amount of water that the fire water supply network can provide during a fire and is an important indicator of fire water supply capacity. Foam mixture supply data is used in situations where foam is used for firefighting, such as fires involving liquids or meltable solids. Foam mixture supply data includes data such as the type of foam, mixing ratio, and supply flow rate. Wind direction data refers to the direction of the wind, and wind speed data refers to the horizontal distance the air flows in unit time.

[0032] Specifically, fire accident-related data for the required fire incidents can be obtained from a pre-established fire database. Pre-set 3D modeling software can be used to construct a 3D model of the fire incident scene, including buildings, facilities, and terrain. The fire-related data can then be input into pre-set fire simulation software to simulate the fire process. The pre-set 3D modeling software and pre-set fire simulation software can be selected based on needs and are not limited in this embodiment.

[0033] Optionally, the firefighting force deployment plan includes at least one firefighting force deployment operation; the firefighting force deployment operation includes placing a command center, placing at least one type of firefighting vehicle, and selecting a target firefighting mode for buildings around the fire.

[0034] Optionally, the fire accident associated data includes three-dimensional scene data and fire simulation data; the fire simulation data includes fire spread data, thermal radiation intensity data and smoke diffusion data; accordingly, constructing a fire accident scene model based on the fire accident associated data includes: constructing a target scene model based on the three-dimensional scene data; dynamically simulating the fire scene on the target scene model based on the fire spread data, the thermal radiation intensity data and the smoke diffusion data to obtain the fire accident scene model.

[0035] Fire spread data can be understood as the spatial and temporal expansion of a fire. Thermal radiation intensity data can be understood as the intensity of heat transferred from a high-temperature object in a fire to the surrounding space through thermal radiation. Smoke dispersion data can be understood as the spatial distribution, movement, and dissipation of smoke generated by a fire. The target scene model can be understood as a three-dimensional spatial environment model.

[0036] Specifically, the heat conduction equation is used to calculate the temperature change inside a solid object during a fire, thereby predicting the spread of fire within the object. The Stefan-Boltzmann radiation heat transfer model is used to calculate the intensity of heat radiation from a high-temperature object in a fire to the surrounding environment. The Navier-Stokes equations are used to simulate the flow of smoke and hot gases in a fire, calculating the smoke's diffusion range and trajectory.

[0037] Specifically, a three-dimensional spatial environment model is constructed based on the fire accident related data. The fire spread data (spread range, speed, direction, etc.) is integrated into the target scene model to dynamically simulate the expansion process of the fire in the target environment. According to the actual situation of the fire spread, the fire source position and spread range in the model are dynamically updated. The thermal radiation intensity data is used to calculate the distribution of thermal radiation intensity of high-temperature objects in the fire to the surrounding environment. The smoke diffusion data (smoke concentration, diffusion direction, diffusion speed, etc.) is incorporated into the model to simulate the distribution and movement of smoke in the target environment. Numerical methods (such as finite difference method, finite element method, finite volume method, etc.) can be used to solve the fire accident scene model to obtain the dynamic development process of the fire in the target environment. By dynamically simulating the fire accident scene model, the disaster evolution process under different fire scales, spread speeds and meteorological conditions can be simulated.

[0038] Optionally, the three-dimensional scene data includes point cloud data, accident environment aerial photography data and accident scene mapping data; accordingly, constructing a target scene model based on the three-dimensional scene data includes: generating a first scene model based on the point cloud data, and constructing a target three-dimensional geometric body in the first scene model based on a preset geometric modeling tool to obtain a second scene model; wherein the target three-dimensional geometric body includes at least one of a fire facility, a fire truck and building facilities around the fire facility; generating a normal map and a reflectivity map of the target three-dimensional geometric body through texture mapping technology, generating a three-dimensional terrain height map based on the accident environment aerial photography data and the accident scene mapping data, and applying the normal map, the reflectivity map and the three-dimensional terrain height map to the second scene model; determining an orthophoto map of the accident scene based on the accident environment aerial photography data, applying the orthophoto map as a texture map to the second scene model and adding target environment element data to obtain the target scene model.

[0039] The first scene model can be understood as an initial three-dimensional environment model, and the second scene model can be understood as an optimized three-dimensional environment model.

[0040] Specifically, the fire scene is scanned using a device such as a laser scanner to generate point cloud data containing a large number of spatial points. These points contain 3D coordinate information about the object's surface. Point cloud processing software is used to convert the processed point cloud data into a triangular mesh model, the first scene model. This model provides a preliminary representation of the 3D spatial structure of the fire scene. Based on the specific circumstances of the fire, a 3D model of the burning facilities, such as buildings, (crude oil) tanks, and warehouses, is created within the first scene model. This can be done manually, through parametric modeling, or by importing existing models. A 3D model of the fire truck is added. Surrounding structures, such as adjacent buildings, walls, and roads, are constructed to fully represent the accident scene. The constructed target 3D geometry is integrated into the first scene model to form the second scene model. Texture mapping software is used to generate a normal map for the target 3D geometry. Normal maps simulate the microscopic details of an object's surface, enhancing the model's realism. Texture mapping software is also used to generate a reflectance map, which defines the light reflectance characteristics of an object's surface, making the model appear more realistic under different lighting conditions. Based on aerial photography of the accident environment and accident scene mapping data, a 3D terrain height map is generated using GIS software or specialized terrain modeling software to reflect the topographical undulations at the accident scene. The generated normal map, reflectivity map, and 3D terrain height map are applied to the second scene model, making the model more visually realistic while accurately representing the topographical features of the accident scene. The aerial photography of the accident environment is processed, and an orthophoto of the accident scene is generated through operations such as orthorectification and image stitching. The orthophoto is applied as a texture map to the second scene model, ensuring that the model's appearance is more consistent with the actual accident scene.

[0041] Specifically, based on the specific circumstances of the fire accident, other target environmental element data is added, such as surface vegetation, soil material, etc. Ultimately, a target scene model containing rich information and realistic effects is obtained.

[0042] S120. For each set of firefighting feedback data, the firefighting feedback data is input into a pre-trained firefighting assessment model, and an evaluation index corresponding to the firefighting force deployment plan is determined based on the model output result.

[0043] The fire assessment model can be understood as a neural network model pre-trained based on sample fire rescue data, and the evaluation index can be understood as the rescue evaluation score.

[0044] Optionally, the firefighting feedback data includes firefighting deployment execution sequence data, firefighting cost data and firefighting time data; the firefighting cost data includes the total number of firefighting vehicles, water spraying volume data, water spraying height data and location data of the firefighting vehicles.

[0045] Firefighting deployment execution sequence data can be understood as the sequence of operations required to execute the firefighting force deployment plan. Firefighting cost data can be understood as the resource costs consumed in executing the firefighting force deployment plan. Firefighting duration data records the time elapsed from the start to the end of the firefighting operation. Position data can be understood as the position of the fire truck relative to the fire facility. For example, the fire truck is located upwind of the fire facility.

[0046] Specifically, the system can receive firefighting force deployment actions triggered by users on the interactive interface, such as dragging a command center into the fire accident scene model, dragging at least one model of fire truck and foam truck into the fire accident scene model, and selecting the target firefighting mode for buildings and facilities surrounding the fire as cooling mode or extinguishing mode. Once placed, the fire trucks simulate spraying water on the fire until the preset firefighting duration is reached or the fire is successfully extinguished, generating firefighting feedback data.

[0047] Optionally, before inputting the fire feedback data into a pre-trained fire assessment model, it also includes: constructing a sample fire data set, dividing the sample fire data set into a training set and a test set; iteratively training a pre-established initial neural network model based on the training set, calculating the predicted value through forward propagation, updating the model parameters through back propagation, calculating the loss function in each iteration, and adjusting the model parameters according to the value of the loss function; after the training is completed, performing a performance evaluation on the trained model based on the test set to obtain a model performance indicator, and determining the fire assessment model based on at least one model performance indicator.

[0048] Specifically, various relevant data are collected from past fire and firefighting cases, including fire accident characteristics such as fire type, cause, size, and burning materials; firefighting deployment and operational information, such as firefighting force deployment, firefighting strategy selection, and equipment use; and corresponding historical firefighting feedback data, such as firefighting time and property damage extent. The collected data is labeled to clearly define the firefighting effectiveness level or specific evaluation metric value corresponding to each data sample, providing labels for subsequent model training. The sample firefighting dataset is divided into training and test sets in a specific ratio (e.g., 7:3). Based on the characteristics and requirements of the fire rescue assessment problem, an appropriate neural network architecture is designed and the model parameters are initialized. Sample data from the training set is input into the initial neural network model, and predictions are calculated through each layer of the model. The loss function between the predicted values and the true labels is calculated. Based on the loss function value, the gradients of the model parameters are calculated using the backpropagation algorithm. Sample data from the test set is input into the trained model to obtain the model's prediction results. Performance evaluation metrics are calculated based on the predicted results and the true labels. A comprehensive consideration of multiple performance metrics is used to select the model with the best overall performance.

[0049] S130. Evaluate the firefighting force deployment plan based on the evaluation index and the preset index threshold.

[0050] The preset indicator threshold can be preset based on experience, and this embodiment does not limit it.

[0051] Specifically, the output of the evaluation model includes multiple evaluation indicators. A comprehensive evaluation indicator corresponding to the firefighting force deployment operation is determined based on the multiple evaluation indicators and preset weights corresponding to each evaluation indicator. The firefighting force deployment operation is evaluated based on the comprehensive evaluation indicator and a preset indicator threshold.

[0052] Optionally, the model output results include a firefighting process rationality index, a firefighting cost-effectiveness index and a firefighting efficiency index; the determination of the evaluation index corresponding to the firefighting force deployment operation based on the model output results includes: determining the evaluation index corresponding to the firefighting force deployment operation based on the firefighting process rationality index, the first preset weight corresponding to the firefighting process rationality index, the firefighting cost-effectiveness index, the second preset weight corresponding to the firefighting cost-effectiveness index, the firefighting efficiency index and the third preset weight corresponding to the firefighting efficiency index.

[0053] The firefighting process rationality index can be understood as an indicator of the rationality of the order in which firefighting force deployment is executed. The firefighting cost-effectiveness index can be understood as an indicator of the cost of rescue operations. The firefighting efficiency index can be understood as an indicator of the speed and effectiveness of rescue operations.

[0054] The first preset weight, the second preset weight, and the third preset weight can be preset based on experience, and this embodiment does not limit them.

[0055] Specifically, the firefighting process rationality index, firefighting cost-effectiveness index, and firefighting efficiency index are standardized. The standardized firefighting process rationality index, firefighting cost-effectiveness index, and firefighting efficiency index are weighted and summed to obtain a fire rescue evaluation index corresponding to the firefighting force deployment operation.

[0056] For example, the evaluation index is calculated based on the normalized value of each index and the corresponding preset weight. The calculation formula is as follows:

[0057] E=w1×R+w2×C+w3×Ef

[0058] Among them, E is the evaluation index, w1 is the first preset weight, R is the standardized fire protection process rationality index value, w2 is the second preset weight, C is the standardized fire protection cost-effectiveness index value, w3 is the third preset weight, and Ef is the standardized fire extinguishing efficiency index value.

[0059] The technical solution of the embodiment of the present invention obtains fire accident related data, constructs a fire accident scenario model based on the fire accident related data, executes at least one firefighting force deployment plan on the fire accident scenario model to obtain multiple sets of firefighting feedback data; constructs a three-dimensional fire accident scenario model that can accurately simulate the development dynamics of the fire. Then, for each set of firefighting feedback data, the firefighting feedback data is input into a pre-trained firefighting assessment model, and the evaluation index corresponding to the firefighting force deployment plan is determined based on the model output result; the firefighting operation data is converted into a quantifiable evaluation index through the firefighting assessment model; finally, the firefighting force deployment plan is evaluated based on the evaluation index and the preset index threshold. The problem of high computational complexity of firefighting force deployment is solved, and the accuracy and reliability of the firefighting force deployment operation evaluation and the accuracy and scientific nature of the firefighting deployment plan are improved.

[0060] Example 2

[0061] Figure 2 This is a flowchart of a method for evaluating firefighting force deployment in a fire, provided in Example 2 of the present invention. This embodiment further optimizes the above-mentioned embodiment. Optionally, evaluating the firefighting force deployment plan based on the evaluation index and the preset index threshold includes: determining that the firefighting force deployment plan is qualified if the evaluation index is not less than the preset index threshold; and determining that the firefighting force deployment plan is unqualified if the evaluation index is less than the preset index threshold.

[0062] like Figure 2 As shown, the method includes:

[0063] S210: Obtain fire accident related data, construct a fire accident scenario model based on the fire accident related data, and execute at least one firefighting force deployment plan on the fire accident scenario model to obtain multiple sets of firefighting feedback data.

[0064] S220. For each set of firefighting feedback data, input the firefighting feedback data into a pre-trained firefighting assessment model, and determine an evaluation index corresponding to the firefighting force deployment plan based on the model output result.

[0065] S230: When the evaluation index is not less than the preset index threshold, determine that the firefighting force deployment plan is qualified.

[0066] The preset indicator threshold can be preset based on experience, and this embodiment does not limit it.

[0067] Specifically, if the firefighting process rationality indicator contributes significantly to the comprehensive evaluation and the overall evaluation index meets the standards, it indicates that the various links in the firefighting force deployment process flow smoothly, tasks are allocated rationally, and there are no significant process disruptions or delays. For example, after the fire broke out, the deployment of firefighting forces, the coordination of on-site command, and the cooperation of various teams were all carried out in an orderly manner according to the predetermined plan. Firefighting operations achieved relatively good firefighting results at a reasonable cost. This means that firefighting resources were utilized efficiently, without excessive waste or a significant imbalance between input and output. For example, during the firefighting process, fire extinguishing agents and equipment were used rationally, controlling the fire at a low cost and minimizing property losses. Firefighting operations were swift and effective, completing key firefighting tasks such as rapidly extinguishing the fire and promptly rescuing trapped personnel in a short period of time.

[0068] Optionally, when there are multiple qualified firefighting force deployment plans, the firefighting force deployment plan with the highest evaluation index can be determined as the optimal firefighting force deployment plan.

[0069] S240: When the evaluation index is less than the preset index threshold, determine that the firefighting force deployment plan is unqualified.

[0070] Specifically, if the evaluation indicators do not meet the standards, it may indicate that there are serious problems with the firefighting process. For example, firefighting forces are not dispatched in a timely manner, resulting in missing the best time to extinguish the fire; on-site command is chaotic, coordination between teams is poor, and there are overlapping tasks or blank areas, which affects the efficiency of firefighting. Or the cost input of firefighting operations does not match the output. It may be that fire extinguishing agents and equipment are overused during the firefighting process, resulting in a waste of resources; or firefighting operations fail to effectively reduce fire losses, such as casualties and property losses are still serious, reflecting inefficient resource utilization. The speed of action is slow, and the fire cannot be controlled in time or trapped people cannot be rescued. For example, the firefighting time is too long, and the fire spreads and expands; rescuing trapped people takes too long, increasing the risk of casualties.

[0071] Optionally, if firefighting force deployment operations fail, specific failure indicators can be determined based on the firefighting process rationality indicator, preset process indicator threshold, firefighting cost-effectiveness indicator, preset cost indicator threshold, firefighting efficiency indicator, and preset efficiency indicator threshold. By identifying specific failure indicators, problematic links in firefighting force deployment operations can be accurately identified. For example, if the firefighting process rationality indicator fails, further analysis can be conducted to determine which link is faulty, such as the failure to establish an on-site command center first. Based on the failure indicators, targeted improvement recommendations can be formulated. If the firefighting cost-effectiveness indicator fails, analysis can be conducted to determine which resource allocations are inappropriate, thereby optimizing resource allocation and improving cost-effectiveness. After implementing corrective measures, these indicators can be re-evaluated. Comparing the values before and after the improvements allows for a visual assessment of the effectiveness of the improvements and determines whether firefighting force deployment operations have been effectively improved. Optionally, when multiple failure indicators occur, the correlation and impact between the indicators should be comprehensively considered, with priority given to addressing the indicators that have the greatest impact on firefighting effectiveness. For example, if both the firefighting process rationality index and the firefighting efficiency index are unqualified, and the unreasonable firefighting force deployment process is the main reason for the low firefighting efficiency, then the firefighting force deployment process should be optimized first.

[0072] The technical solution of the embodiments of the present invention determines that the firefighting force deployment operation is qualified if the evaluation indicator is not less than the preset indicator threshold; and determines that the firefighting force deployment operation is unqualified if the evaluation indicator is less than the preset indicator threshold. This ensures that the system can respond to different working mode requirements in a timely and accurate manner, providing users with a stable and efficient user experience. This improves the accuracy of the firefighting force deployment operation assessment.

[0073] As an optional example of the first embodiment of the present invention, the fire fighting force deployment assessment method of this embodiment specifically includes the following steps:

[0074] The four-layer collaborative architecture of "data-model-interaction-hardware" achieves digital mapping of the entire crude oil tank fire emergency response process through multi-level data coupling and real-time feedback mechanisms. This architecture supports the parallel simulation of multiple scenarios, dynamic resource scheduling, and tactical effectiveness evaluation, providing a highly immersive and interactive decision-making sandbox for intensive crude oil fire training and actual combat command.

[0075] 1. System Architecture

[0076] The system architecture of the three-dimensional simulation system based on the deployment of fire fighting forces in crude oil storage tanks includes a data input and algorithm support layer, a three-dimensional modeling and database interaction layer, a rendering engine and user interaction layer, and a hardware and network support layer.

[0077] 1. Data input and algorithm support layer

[0078] The data input and algorithm support layer provides the fundamental data and core algorithms for the entire system. It not only collects initial data on the accident scenario and storage tanks but also executes calculation algorithms related to fire spread and extinguishing strategies. This provides accurate input for subsequent simulation calculations, ensuring the scientific and reliable results.

[0079] 2. 3D modeling and database interaction layer

[0080] The 3D modeling and database interaction layer creates a realistic 3D model of the tank farm and a simulated environment, providing an intuitive interface between the user and the simulation system. This layer manages and stores data on tanks, firefighting equipment, and accident scenarios, ensuring that users can view and modify relevant information at any time during the simulation. The precision of the model and the efficient database storage ensure the accuracy and real-time updating of simulation data.

[0081] 3. Rendering engine and user interaction layer

[0082] The rendering engine and user interaction layer utilize powerful rendering capabilities to present 3D modeling and real-time simulation results to users. Users can adjust firefighting strategies in real time by dragging and dropping. Their interactive commands drive the back-end simulation computing layer through a bidirectional data coupling mechanism, enabling real-time visualization of fire spread and the performance of firefighting equipment, ensuring maximum firefighting efficiency.

[0083] 4. Hardware and network support layer

[0084] The hardware and network support layers ensure stable system operation and smooth data transmission. The system is deployed through independent servers and local area networks, combined with high-performance computing resources to ensure real-time simulation calculations and rendering, avoiding calculation delays that affect simulation results.

[0085] 2. Implementation Process

[0086] Step 1. Create a 3D model

[0087] Building a 3D model is the cornerstone of a 3D simulation system. The geometric accuracy and authenticity of its physical properties directly affect the simulation credibility of the accident scene and the user's immersion.

[0088] For example, in the data collection stage: a multispectral LiDAR and a five-lens oblique photography unit are installed on an unmanned aerial vehicle platform to achieve efficient acquisition of large-scale geographic information; ultra-high-resolution photogrammetry is based on a structure-from-motion algorithm, and a texture mesh is generated through multi-view geometric reconstruction to retain the surface material properties of the accident scene; a multi-source heterogeneous data fusion framework integrates LiDAR point cloud, infrared thermal imaging, and multispectral images to construct a multi-dimensional scene representation system with both geometric accuracy and semantic information.

[0089] Reconstruction and optimization stage: Scan and reconstruct the collected data, extract point cloud features, generate a first scene model, reconstruct the three-dimensional geometry of key facilities such as storage tanks and fire trucks in the first scene model based on preset geometric modeling tools, and perform detail repair and optimization to obtain a second scene model; generate normal maps and reflectivity maps of the target three-dimensional geometry through texture mapping technology, and generate normal maps and reflectivity maps with details such as surface burns and chemical corrosion to achieve physically consistent expression of material properties and optimize visual effects.

[0090] Step 2: Build the accident scene

[0091] The spatial layout of the accident scene is reproduced through a real three-dimensional environment, providing users with an immersive interactive experience.

[0092] A three-dimensional terrain height map is generated based on the aerial photography data of the accident environment and the surveying data of the accident site, accurately presenting the ground slope and undulation changes; the orthophoto image generated by the shooting is then applied to the terrain model as a texture map to accurately restore the original terrain appearance; finally, environmental elements such as surface vegetation and soil material are added, and the scene realism is enhanced through texture mapping and lighting simulation to obtain the target scene model, providing a reliable geographic space foundation for fire-fighting tactical deduction.

[0093] By recreating the actual scene layout at a 1:1 ratio, we ensure the scientific deployment of firefighting forces within the 3D scene. Parameters such as road width and turning radius are set in accordance with national fire regulations, with a focus on optimizing fire lane design to ensure fire truck routes meet actual combat requirements. Optionally, a rendering engine can be used to render flames, smoke, explosions, wind direction, water jets, mist, and foam within the 3D scene. This realistic firefighting rendering enhances the fidelity of the scene, strengthens the user's sense of immersion, and facilitates subsequent scoring.

[0094] Step 3: Develop relevant logic code

[0095] C++ can be used to develop related algorithm logic, such as wind speed and direction algorithm, foam liquid total amount calculation, fire force deployment algorithm, etc., so that fire accident scenes and fire extinguishing feedback can be dynamically displayed.

[0096] Blueprints are a visual scripting system suitable for rapidly developing interactive logic and UIs. By dragging and dropping nodes and setting parameters, logical flows can be intuitively presented. Blueprints can also call algorithms implemented in C++. Therefore, using Unreal Engine's Blueprint system allows for developing interactive logic such as UIs and function menus. Users can simulate firefighting with the help of a keyboard and mouse, improving their ability to handle emergencies.

[0097] Step 4 System Test

[0098] By designing multiple test cases, each module and functional point of the system is tested one by one to ensure that they can produce expected outputs and behaviors under different inputs and conditions, and to find system defects or loopholes.

[0099] The technical solution of the embodiment of the present invention, through the construction of a four-layer collaborative architecture of "data-model-interaction-hardware", realizes the digital mapping of the entire process of emergency response to crude oil storage tank fires through multi-level data coupling and real-time feedback mechanisms. It provides a highly immersive and highly interactive decision-making sandbox for intensive training and actual combat command of crude oil fires. Combining the three-dimensional simulation technology of crude oil storage tank fires with fire deployment algorithms and applying them to fire training and tactical deductions can not only be used for accident analysis and the formulation of emergency response strategies, but also as an education and training tool to help users understand the dangers of crude oil storage tank fires and how to safely and effectively respond to fire accidents. It is of great significance to emergency rescue.

[0100] Example 3

[0101] Figure 3 This is a schematic diagram of a fire fighting force deployment assessment device provided by the third embodiment of the present invention. Figure 3 As shown, the device includes: a fire force deployment module 310, an evaluation index determination module 320 and a deployment plan evaluation module 330.

[0102] Among them, the fire force deployment module 310 is used to obtain fire accident related data, construct a fire accident scene model based on the fire accident related data, and execute at least one fire force deployment plan on the fire accident scene model to obtain multiple groups of fire feedback data, wherein the fire accident scene model is a three-dimensional model that dynamically simulates the spatial layout, fire environment and disaster trend of the fire accident; the evaluation index determination module 320 is used to input the fire feedback data into a pre-trained fire evaluation model for each group of fire feedback data, and determine the evaluation index corresponding to the fire force deployment plan based on the model output result; the deployment plan evaluation module 330 is used to evaluate the fire force deployment plan based on the evaluation index and the preset index threshold.

[0103] The technical solution of the embodiment of the present invention obtains fire accident related data, constructs a fire accident scenario model based on the fire accident related data, executes at least one firefighting force deployment plan on the fire accident scenario model to obtain multiple sets of firefighting feedback data; constructs a three-dimensional fire accident scenario model that can accurately simulate the development dynamics of the fire. Then, for each set of firefighting feedback data, the firefighting feedback data is input into a pre-trained firefighting assessment model, and the evaluation index corresponding to the firefighting force deployment plan is determined based on the model output result; the firefighting operation data is converted into a quantifiable evaluation index through the firefighting assessment model; finally, the firefighting force deployment plan is evaluated based on the evaluation index and the preset index threshold. The problem of high computational complexity of firefighting force deployment is solved, and the accuracy and reliability of the firefighting force deployment operation evaluation and the accuracy and scientific nature of the firefighting deployment plan are improved.

[0104] Optionally, the fire accident related data includes three-dimensional scene data and fire simulation data; the fire simulation data includes fire spread data, heat radiation intensity data, and smoke diffusion data; accordingly, the firefighting force deployment module includes:

[0105] A scene model construction unit, configured to construct a target scene model based on the three-dimensional scene data;

[0106] A fire simulation unit is used to dynamically simulate a fire scene on the target scene model based on the fire spread data, the thermal radiation intensity data and the smoke diffusion data to obtain the fire accident scene model.

[0107] Optionally, the three-dimensional scene data includes point cloud data, accident environment aerial photography data, and accident scene mapping data; accordingly, the scene model construction unit includes:

[0108] a scene model generation subunit, configured to generate a first scene model based on the point cloud data, and construct a target three-dimensional geometric body in the first scene model using a preset geometric modeling tool to obtain a second scene model; wherein the target three-dimensional geometric body includes at least one of a fire facility, a fire truck, and buildings surrounding the fire facility;

[0109] a mapping subunit, configured to generate a normal map and an albedo map of the target three-dimensional geometric body using texture mapping technology, generate a three-dimensional terrain height map based on the accident environment aerial photography data and the accident scene mapping data, and apply the normal map, the albedo map, and the three-dimensional terrain height map to the second scene model;

[0110] The environmental element adding subunit is used to determine the orthophoto image of the accident scene based on the accident environment aerial photography data, apply the orthophoto image as a texture map to the second scene model and add target environmental element data to obtain the target scene model.

[0111] Optionally, the firefighting force deployment plan includes at least one firefighting force deployment operation; the firefighting force deployment operation includes placing a command center, placing at least one type of firefighting vehicle, and selecting a target firefighting mode for buildings around the fire.

[0112] Optionally, the device further includes:

[0113] A data set construction module is used to construct a sample fire and firefighting data set before inputting the firefighting feedback data into a pre-trained fire assessment model, and divide the sample fire and firefighting data set into a training set and a test set;

[0114] A model training module is used to iteratively train a pre-established initial neural network model based on the training set, calculate prediction values through forward propagation, update model parameters through backpropagation, calculate a loss function in each iteration, and adjust the model parameters according to the value of the loss function;

[0115] The performance evaluation module is used to perform performance evaluation on the trained model based on the test set after the training is completed to obtain a model performance index, and determine the fire protection evaluation model based on at least one model performance index.

[0116] Optionally, the model output results include a fire protection process rationality index, a fire protection cost-effectiveness index, and a fire extinguishing efficiency index; accordingly, the evaluation index determination module is specifically used to:

[0117] An evaluation index corresponding to the firefighting force deployment operation is determined based on the firefighting process rationality index, the first preset weight corresponding to the firefighting process rationality index, the firefighting cost-effectiveness index, the second preset weight corresponding to the firefighting cost-effectiveness index, the firefighting efficiency index and the third preset weight corresponding to the firefighting efficiency index.

[0118] Optionally, the deployment solution evaluation module includes:

[0119] A first evaluation unit is configured to determine that the firefighting force deployment plan is qualified if the evaluation index is not less than the preset index threshold;

[0120] The second evaluation unit is used to determine that the firefighting force deployment plan is unqualified when the evaluation index is less than the preset index threshold.

[0121] The firefighting force deployment operation evaluation device provided in the embodiment of the present invention can execute the firefighting force deployment operation evaluation method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0122] Example 4

[0123] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0124] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0125] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0126] The processor 11 can be various general-purpose and / or specialized processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the method for assessing firefighting force deployment.

[0127] In some embodiments, the method for assessing the deployment of firefighting forces may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method for assessing the deployment of firefighting forces described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the method for assessing the deployment of firefighting forces via any other suitable means (e.g., via firmware).

[0128] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0129] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0130] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0131] To provide interaction with a service acquirer, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the service acquirer; and a keyboard and pointing device (e.g., a mouse or trackball), through which the service acquirer can provide input to the electronic device. Other types of devices can also be used to provide interaction with the service acquirer; for example, the feedback provided to the service acquirer can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the service acquirer can be received in any form (including acoustic input, voice input, or tactile input).

[0132] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a service acquirer computer having a graphical service acquirer interface or a web browser through which a service acquirer can interact with embodiments of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0133] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0134] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0135] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for evaluating the deployment of fire fighting forces, characterized in that: include: Obtaining fire accident related data, constructing a fire accident scenario model based on the fire accident related data, and executing at least one firefighting force deployment plan on the fire accident scenario model to obtain multiple sets of firefighting feedback data; wherein the fire accident scenario model is a three-dimensional model that dynamically simulates the spatial layout, fire environment, and disaster trends of the fire accident; For each set of firefighting feedback data, the firefighting feedback data is input into a pre-trained firefighting assessment model, and based on the model output, an evaluation index corresponding to the firefighting force deployment plan is determined; The firefighting force deployment plan is evaluated based on the evaluation indicators and preset indicator thresholds.

2. The method according to claim 1, characterized in that The fire accident related data includes three-dimensional scene data and fire simulation data; the fire simulation data includes fire spread data, heat radiation intensity data and smoke diffusion data; The constructing of a fire accident scenario model based on the fire accident associated data includes: Constructing a target scene model based on the three-dimensional scene data; A fire scene is dynamically simulated on the target scene model based on the fire spread data, the heat radiation intensity data and the smoke diffusion data to obtain the fire accident scene model.

3. The method according to claim 2, characterized in that The three-dimensional scene data includes point cloud data, accident environment aerial photography data, and accident scene mapping data; and constructing a target scene model based on the three-dimensional scene data includes: Generate a first scene model based on the point cloud data, and construct a target three-dimensional geometric body in the first scene model using a preset geometric modeling tool to obtain a second scene model; wherein the target three-dimensional geometric body includes at least one of a burning facility, a fire truck, and buildings and facilities surrounding the burning facility; generating a normal map and an albedo map of the target three-dimensional geometric body by using texture mapping technology, generating a three-dimensional terrain height map based on the accident environment aerial photography data and the accident scene mapping data, and applying the normal map, the albedo map, and the three-dimensional terrain height map to the second scene model; An orthophoto image of the accident scene is determined based on the accident environment aerial photography data, the orthophoto image is applied as a texture map to the second scene model and target environment element data is added to obtain the target scene model.

4. The method according to claim 1, wherein The firefighting force deployment plan includes at least one firefighting force deployment operation; the firefighting force deployment operation includes placing a command center, placing at least one type of firefighting vehicle, and selecting a target firefighting mode for buildings around the fire.

5. The method according to claim 1, wherein Before inputting the fire feedback data into the pre-trained fire assessment model, the method further includes: Constructing a sample fire and firefighting dataset, and dividing the sample fire and firefighting dataset into a training set and a test set; Iteratively training a pre-established initial neural network model based on the training set, calculating a predicted value through forward propagation, updating model parameters through backpropagation, calculating a loss function in each iteration, and adjusting the model parameters according to the value of the loss function; After the training is completed, the performance of the trained model is evaluated based on the test set to obtain a model performance index, and the fire assessment model is determined based on at least one model performance index.

6. The method according to claim 1, characterized in that The model output results include a firefighting process rationality index, a firefighting cost-effectiveness index, and a firefighting efficiency index; the evaluation index corresponding to the firefighting force deployment operation determined based on the model output results includes: An evaluation index corresponding to the firefighting force deployment operation is determined based on the firefighting process rationality index, the first preset weight corresponding to the firefighting process rationality index, the firefighting cost-effectiveness index, the second preset weight corresponding to the firefighting cost-effectiveness index, the firefighting efficiency index and the third preset weight corresponding to the firefighting efficiency index.

7. The method according to claim 1, characterized in that The evaluating the firefighting force deployment plan based on the evaluation index and the preset index threshold includes: If the evaluation index is not less than the preset index threshold, the firefighting force deployment plan is determined to be qualified; When the evaluation index is less than the preset index threshold, it is determined that the firefighting force deployment plan is unqualified.

8. A fire fighting force deployment assessment device, characterized in that: include: A firefighting force deployment module is configured to obtain fire accident related data, construct a fire accident scenario model based on the fire accident related data, and execute at least one firefighting force deployment plan on the fire accident scenario model to obtain multiple sets of firefighting feedback data; wherein the fire accident scenario model is a three-dimensional model that dynamically simulates the spatial layout, fire environment, and disaster trends of the fire accident; An evaluation index determination module is used to input each set of fire feedback data into a pre-trained fire assessment model and determine an evaluation index corresponding to the fire force deployment plan based on the model output results; The deployment plan evaluation module is used to evaluate the firefighting force deployment plan based on the evaluation index and the preset index threshold.

9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the method for evaluating the deployment of fire fighting forces according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for evaluating the deployment of fire fighting forces according to any one of claims 1 to 7 when executed.

Images