Fire rescue intelligent management method and system based on multi-modal AI large model

Abstract

The invention relates to the technical field of fire control management, in particular to a fire rescue intelligent management method and system based on a multi-mode AI large model. The method comprises the following steps: acquiring real-time environment monitoring data of a fire scene; carrying out environmental parameter analysis on the fire scene real-time environmental monitoring data, and carrying out gas change trend prediction to generate a scene gas parameter change trend; acquiring a fire scene thermal imaging image; performing temperature distribution visual identification and continuous frame temperature change rate calculation according to the fire scene thermal imaging image so as to generate a fire source area temperature change rate; performing multi-time ignition trend prediction according to the temperature change rate of the fire source area and the on-site gas parameter change trend so as to generate a multi-time ignition trend prediction map; and identifying a to-be-rescued area point based on the fire scene thermal imaging image. According to the invention, real-time and accurate distribution of on-site fire rescue resources is realized, and the rescue management efficiency and safety are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of fire management, and in particular to a fire rescue intelligent management method and system based on a multimodal AI large model. Background Art

[0002] As an important means to protect the lives and property of the people, firefighting and rescue work has always faced a complex and high-risk working environment. With the acceleration of urbanization and the frequent occurrence of natural disasters, firefighting and rescue tasks have become increasingly arduous and difficult. In traditional firefighting and rescue management, manual command, equipment dispatching and on-site judgment are relied on. Although these methods were able to meet certain needs in the past, there is still much room for improvement in efficiency, accuracy and emergency response speed.

[0003] Especially in sudden disasters such as fires, rescue missions often require rapid response and real-time adjustment of rescue strategies. Traditional methods cannot accurately integrate and process various complex information on site, such as fire development, building structure, rescue personnel location, meteorological data, etc., which often delays rescue decisions and affects the efficiency and safety of fire rescue. Therefore, there is an urgent need for a new intelligent method to achieve comprehensive and real-time analysis and management of the fire rescue process to improve rescue efficiency, optimize resource allocation, and ensure personnel safety. Summary of the invention

[0004] In order to solve the above-mentioned technical problems, the present invention proposes a fire rescue intelligent management method and system based on a multimodal AI large model to solve at least one of the above-mentioned technical problems.

[0005] To achieve the above object, the present invention provides a fire rescue intelligent management method based on a multimodal AI large model, comprising the following steps: Step S1: Acquire real-time environmental monitoring data of the fire scene; perform environmental parameter analysis on the real-time environmental monitoring data of the fire scene, and predict the gas change trend to generate the on-site gas parameter change trend; Step S2: Acquire a thermal imaging image of the fire scene; perform visual recognition of temperature distribution and calculation of temperature change rate of consecutive frames based on the thermal imaging image of the fire scene, thereby generating a temperature change rate of the fire source area; Step S3: Predict the fire intensity trend at multiple points in time according to the temperature change rate of the fire source area and the change trend of the on-site gas parameters, thereby generating a multi-point fire intensity trend prediction graph; Step S4: Identify the area to be rescued based on the thermal imaging image of the fire scene; analyze the optimal rescue route for each area to be rescued based on the multi-time point fire trend prediction map, and generate multiple regional rescue tasks; Step S5: Identify firefighting resources at the fire scene; dynamically allocate resources to multiple regional rescue tasks according to the firefighting resources at the fire scene, and perform real-time rescue monitoring to obtain real-time rescue monitoring data; Step S6: Extract instant feedback information and optimize intelligent resource allocation based on real-time rescue monitoring data, thereby building an intelligent fire rescue optimization strategy.

[0006] The present invention obtains real-time environmental monitoring data, making the information in the fire rescue process more timely and accurate. By analyzing environmental parameters, the change trend of harmful gases at the fire scene can be identified, the gas concentration and diffusion trend can be predicted in time, and a critical warning can be provided for the safety of rescue personnel. The prediction of gas change trend provides a scientific basis for fire command decision-making, avoids rescue personnel from entering high-risk areas, and ensures the efficient execution of rescue tasks. Thermal imaging images provide real-time temperature data at the fire scene, which can help rescue personnel accurately understand the location of the fire source and its temperature changes. By calculating the temperature change rate of continuous frames, the change speed of the fire can be captured, the spread trend of the fire can be predicted, and real-time dynamic guidance can be provided for on-site rescue. Monitoring the temperature change rate helps to identify the hotspot area of ​​the fire and guide the reasonable allocation of fire resources. Combining the temperature change rate of the fire source area with the gas change trend for fire prediction can provide a more comprehensive and accurate fire development trend. Through multi-time point prediction, the fire command center can clearly understand the future development direction of the fire, formulate a response plan in advance, and reduce uncertainty and risk in rescue. The fire trend prediction map provides firefighters with the priority sorting of rescue tasks to ensure that resources are allocated to the most needed places first. Thermal imaging image analysis can accurately identify the areas to be rescued at the fire scene, especially those areas with high temperatures and severe fires near the fire source. The optimal rescue route analysis can prevent rescuers from entering dangerous areas, ensure that they can complete the task through the safest and fastest route, and reduce the risk and time consumption during the rescue process. The optimization of the rescue route greatly improves the rescue efficiency, especially in complex and uncertain fire scenes. By identifying the firefighting resources available at the scene (such as fire extinguishers, fire trucks, firefighters, etc.), resources can be allocated in real time and accurately to ensure that every rescue mission can be supported. Dynamic resource allocation is adjusted according to the changes in the fire scene, effectively avoiding resource waste and unnecessary delays. Real-time rescue monitoring can feedback the progress of the rescue, ensure the safety of firefighters, and make timely adjustments to the situation on the scene, making the entire rescue process more flexible and efficient.

[0007] In this specification, a fire rescue intelligent management system based on a multimodal AI big model is provided, which is used to execute the fire rescue intelligent management method based on a multimodal AI big model as described above, including: The gas trend prediction module is used to obtain real-time environmental monitoring data at the fire scene; analyze environmental parameters of the real-time environmental monitoring data at the fire scene, and predict gas change trends to generate on-site gas parameter change trends; The temperature distribution recognition module is used to obtain thermal imaging images of the fire scene; perform visual recognition of temperature distribution and calculation of the temperature change rate of consecutive frames based on the thermal imaging images of the fire scene, thereby generating the temperature change rate of the fire source area; The fire trend prediction module is used to predict the fire trend at multiple points in time according to the temperature change rate of the fire source area and the change trend of the on-site gas parameters, thereby generating a multi-point fire trend prediction graph; The rescue route analysis module is used to identify the points of the area to be rescued based on the thermal imaging images of the fire scene; analyze the optimal rescue route for each area to be rescued based on the multi-time point fire trend prediction map, and generate multiple regional rescue tasks; Dynamic resource allocation module, used to identify fire-fighting resources at the fire scene; dynamically allocate resources to multiple regional rescue tasks based on the fire-fighting resources at the fire scene, and conduct real-time rescue monitoring to obtain real-time rescue monitoring data; The resource allocation optimization module is used to extract instant feedback information and optimize intelligent resource allocation based on real-time rescue monitoring data, thereby building an intelligent fire rescue optimization strategy.

[0008] The present invention ensures that the command center and rescue personnel can obtain the changes in gas composition and concentration on site in the first time through the collection of real-time environmental monitoring data, and provide data support for safety decision-making. By predicting the trend of gas changes, it is possible to timely warn of the accumulation of harmful gases, such as carbon monoxide, nitrogen oxides, etc., so as to avoid high-risk areas in advance and protect the safety of rescue personnel. Gas trend prediction helps commanders to more scientifically evaluate the changes in the scope of fire expansion, fire source intensity and dangerous areas, so as to formulate more effective rescue and evacuation strategies. Through temperature distribution recognition, the heat source area of ​​the fire can be confirmed in real time, helping rescue personnel to lock the main direction of the fire source and fire development in time. By calculating the temperature change rate of continuous frames, the speed of fire spread is evaluated, which helps to predict the development trend of the fire, so as to make timely responses when the fire spreads rapidly. Monitoring the temperature change rate of the fire source area enables the on-site commander to flexibly adjust resources and rescue strategies to cope with changes in the fire. Combining the fire source temperature and gas changes, a more comprehensive fire prediction can be provided, which not only focuses on the temperature of the fire source itself, but also takes into account gas diffusion and fire spread speed. By predicting the multi-time trend of the fire, it is possible to understand in advance how the fire may develop at different time points, provide more forward-looking information for fire commanders, and support rescue decisions. The fire trend chart helps the command center to clarify the direction of the fire, allocate fire resources and deploy rescue personnel in advance, and ensure the timeliness and effectiveness of the response. Through thermal imaging images, it is possible to clearly identify which areas have higher temperatures and which areas have trapped people, so as to quickly identify areas that need priority rescue. Based on the fire prediction, the rescue route analysis can calculate the shortest and safest path to prevent rescue personnel from entering areas that are too dangerous or where the fire is rapidly spreading, thereby improving rescue efficiency and safety. In complex fire scenes, rescue tasks for multiple areas can be generated, and each task can be carried out in coordination to ensure the orderly conduct of rescue operations. According to the changes in the fire scene, various types of fire resources (such as fire extinguishers, fire trucks, personnel, etc.) are dynamically allocated to ensure that resources are used most effectively. As the situation at the fire scene changes, the allocation of resources can be flexibly adjusted to ensure that rescue forces can cover the most needed areas at different stages. Real-time rescue monitoring data can provide key information such as the use of fire resources and changes in the fire scene, helping commanders to respond quickly. Using AI analysis algorithms, the current resource allocation is optimized based on real-time data, and resource allocation is adjusted to adapt to the latest dynamics at the fire scene. Through intelligent decision-making, it is possible to avoid waste of resources or unreasonable allocation due to human misjudgment, and ensure that each resource is used as efficiently as possible. With the continuous update of fire scene information, the resource allocation optimization module can continuously adjust the optimization strategy according to the actual situation to ensure the efficiency and flexibility of the rescue process. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1A schematic diagram of the steps of a fire rescue intelligent management method based on a multimodal AI large model of the present invention; Figure 2 Detailed implementation flow chart of step S1; Figure 3 Detailed implementation flow chart of step S2; Figure 4 Detailed implementation flow chart of step S3. DETAILED DESCRIPTION

[0010] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0011] The example of this application provides a fire rescue intelligent management method and system based on a multimodal AI big model. The execution subjects of the fire rescue intelligent management method and system based on a multimodal AI big model include but are not limited to: mechanical equipment, data processing platform, cloud server node, network upload equipment, etc. equipped with the system can be regarded as general computing nodes of this application, and the data processing platform includes but is not limited to: at least one of an audio image management system, an information management system, and a cloud data management system.

[0012] See also Figures 1 to 4 The present invention provides a fire rescue intelligent management method based on a multimodal AI big model, and the fire rescue intelligent management method based on a multimodal AI big model comprises the following steps: Step S1: Acquire real-time environmental monitoring data of the fire scene; perform environmental parameter analysis on the real-time environmental monitoring data of the fire scene, and predict the gas change trend to generate the on-site gas parameter change trend; Step S2: Acquire a thermal imaging image of the fire scene; perform visual recognition of temperature distribution and calculation of temperature change rate of consecutive frames based on the thermal imaging image of the fire scene, thereby generating a temperature change rate of the fire source area; Step S3: Predict the fire intensity trend at multiple points in time according to the temperature change rate of the fire source area and the change trend of the on-site gas parameters, thereby generating a multi-point fire intensity trend prediction graph; Step S4: Identify the points of the area to be rescued based on the thermal imaging image of the fire scene; analyze the optimal rescue route for each area to be rescued based on the multi-time point fire trend prediction map, and generate multiple regional rescue tasks; Step S5: Identify firefighting resources at the fire scene; dynamically allocate resources to multiple regional rescue tasks according to the firefighting resources at the fire scene, and perform real-time rescue monitoring to obtain real-time rescue monitoring data; Step S6: Extract instant feedback information and optimize intelligent resource allocation based on real-time rescue monitoring data, thereby building an intelligent fire rescue optimization strategy.

[0013] The present invention obtains real-time environmental monitoring data, making the information in the fire rescue process more timely and accurate. By analyzing environmental parameters, the change trend of harmful gases at the fire scene can be identified, the gas concentration and diffusion trend can be predicted in time, and a critical warning can be provided for the safety of rescue personnel. The prediction of gas change trend provides a scientific basis for fire command decision-making, avoids rescue personnel from entering high-risk areas, and ensures the efficient execution of rescue tasks. Thermal imaging images provide real-time temperature data at the fire scene, which can help rescue personnel accurately understand the location of the fire source and its temperature changes. By calculating the temperature change rate of continuous frames, the change speed of the fire can be captured, the spread trend of the fire can be predicted, and real-time dynamic guidance can be provided for on-site rescue. Monitoring the temperature change rate helps to identify the hotspot area of ​​the fire and guide the reasonable allocation of fire resources. Combining the temperature change rate of the fire source area with the gas change trend for fire prediction can provide a more comprehensive and accurate fire development trend. Through multi-time point prediction, the fire command center can clearly understand the future development direction of the fire, formulate a response plan in advance, and reduce uncertainty and risk in rescue. The fire trend prediction map provides firefighters with the priority sorting of rescue tasks to ensure that resources are allocated to the most needed places first. Thermal imaging image analysis can accurately identify the areas to be rescued at the fire scene, especially those areas with high temperatures and severe fires near the fire source. The optimal rescue route analysis can prevent rescuers from entering dangerous areas, ensure that they can complete the task through the safest and fastest route, and reduce the risk and time consumption during the rescue process. The optimization of the rescue route greatly improves the rescue efficiency, especially in complex and uncertain fire scenes. By identifying the firefighting resources available at the scene (such as fire extinguishers, fire trucks, firefighters, etc.), resources can be allocated in real time and accurately to ensure that every rescue mission can be supported. Dynamic resource allocation is adjusted according to the changes in the fire scene, effectively avoiding resource waste and unnecessary delays. Real-time rescue monitoring can feedback the progress of the rescue, ensure the safety of firefighters, and make timely adjustments to the situation on the scene, making the entire rescue process more flexible and efficient.

[0014] In the embodiment of the present invention, refer to Figure 1 , is a schematic flow chart of the steps of a fire rescue intelligent management method based on a multimodal AI large model of the present invention. In this example, the steps of the fire rescue intelligent management method based on a multimodal AI large model include: Step S1: Acquire real-time environmental monitoring data of the fire scene; perform environmental parameter analysis on the real-time environmental monitoring data of the fire scene, and predict the gas change trend to generate the on-site gas parameter change trend; In this embodiment, suitable environmental monitoring equipment is selected, such as multi-gas detectors, temperature and humidity sensors, and smoke sensors. These devices can monitor the environmental parameters of the fire scene in real time, including temperature, humidity, oxygen concentration, carbon monoxide concentration, and volatile organic compounds (VOCs). Ensure the calibration and maintenance of the monitoring equipment to ensure the accuracy of the data. For example, the calibration cycle of the gas sensor should be set to once a month to ensure that the sensor meets the standard before use. Deploy monitoring equipment at key locations at the fire scene, such as near the fire source, smoke diffusion area, and possible trapped personnel area. Ensure that the equipment can cover the entire scene and can transmit data in real time. Set the data collection frequency, such as collecting data every 1 second, to ensure a rapid response to changes in the development of the fire. The data is transmitted to the data processing system in real time via a wireless network or wired connection. Use a data management system to record and store real-time monitoring data. The data management system should have data backup and recovery functions to ensure the security and integrity of the data. Regularly check the integrity of data records to ensure that there is no data loss or abnormality, and record the working status and data flow of each sensor. Preprocess the collected real-time monitoring data, including denoising, missing value filling, and outlier detection. Simple mean substitution or median substitution can be used to fill missing values ​​to ensure data continuity. Ensure that the timestamps of the data are consistent for subsequent analysis. For example, convert all data to UTC time format to avoid data confusion caused by time zone issues. Extract key environmental parameters such as temperature, humidity, oxygen concentration, and harmful gas concentration from the preprocessed data. Use statistical analysis methods to calculate the mean, standard deviation, and range of each parameter to understand the basic characteristics of the on-site environment. Set an analysis cycle, such as summarizing and analyzing environmental parameters every 5 minutes, and record the changing trends and fluctuations of environmental parameters. Perform trend analysis on the extracted environmental parameters, especially gas concentration data. Time series analysis methods can be used to identify the trend of gas concentration changes over time. Apply sliding average or exponential smoothing to smooth the data to reduce the impact of short-term fluctuations on trend identification. Set the smoothing window size, such as a 5-minute window, to better observe the changing trend of gas concentration. Select a suitable prediction model, such as an autoregressive integrated moving average (ARIMA) model or a long short-term memory (LSTM) network. These models can effectively capture the changing pattern of gas concentration and make future trend predictions. Set the parameters of the model, such as the autoregressive order and the moving average order in the ARIMA model, and usually choose the optimal parameters based on historical data. Use historical monitoring data to train the selected prediction model. Make sure the time span of the training data is long enough to capture the changing trend of gas concentrations. Cross-validate the model to ensure its predictive ability on different data sets. You can use 70% of the data for training and 30% of the data for validation to evaluate the performance of the model.Use the trained prediction model to predict future changes in gas concentration. Set the prediction time range, such as predicting changes in gas concentration within the next 30 minutes. Record the prediction results, including the predicted gas concentration value and its confidence interval, for reference in subsequent decision-making. Generate a prediction report that details the trend of gas concentration changes and its potential impact on fire scene safety.

[0015] Step S2: Acquire a thermal imaging image of the fire scene; perform visual recognition of temperature distribution and calculation of temperature change rate of consecutive frames based on the thermal imaging image of the fire scene, thereby generating a temperature change rate of the fire source area; In this embodiment, a high-quality thermal imaging camera is selected to ensure that it has sufficient resolution and sensitivity. Generally speaking, a thermal imaging device with a resolution of 640x480 pixels is selected to capture clear temperature distribution images at the fire scene. The device is calibrated to ensure that the accuracy of its temperature measurement is checked before use. The operating temperature range of the device is set, such as -20°C to +1200°C, to meet the needs of different fire scenes. A thermal imaging camera is set at the fire scene to ensure that it can cover the fire source and the surrounding area. According to the actual situation of the fire scene, a suitable shooting angle and height are selected to obtain the best viewing angle. The frequency of image acquisition is set, such as one frame per second, to capture the dynamic changes of the fire source area. The image is transmitted to the data processing center in real time via a wireless network or wired connection. A data management system is established to store and manage the acquired thermal imaging images. Ensure the security and integrity of the data and set a regular backup mechanism. The metadata such as the timestamp, shooting location and environmental conditions of each frame of the image are recorded for reference in subsequent analysis. The acquired thermal imaging image is preprocessed, including denoising, contrast enhancement and color mapping. Gaussian filtering can be used to remove random noise in the image and improve the visualization effect of temperature distribution. Set image processing parameters, such as the standard deviation and enhancement level of the filter, to ensure that the preprocessed image is clear and recognizable. Apply computer vision technology for visual recognition of temperature distribution. Deep learning models (such as convolutional neural networks) can be used to classify and mark temperature distribution. Use thermal imaging datasets containing different fire sources and temperature distributions when training the model. Set recognition thresholds, such as marking areas with temperatures above 60°C as fire source areas for subsequent analysis. Organize the identified fire source areas and their corresponding temperature values ​​into a report, describing the temperature distribution and fire source location in detail. Generate a temperature distribution map to intuitively display the temperature characteristics of the fire source area. Record the key parameters and results of the recognition process to provide a basis for subsequent temperature change rate calculations. Extract temperature data of the fire source area from continuous thermal imaging images. For each frame of the image, record the temperature value of the fire source area and generate time series data. Set the time interval for data extraction, such as extracting temperature data once per second, so as to analyze the temperature change of the fire source. Calculate the temperature change rate of the fire source area based on the extracted temperature data. A simple difference method can be used to calculate the temperature change between adjacent frames. For example, temperature change rate = (current frame temperature - previous frame temperature) / time interval. Set a threshold for the change rate. For example, a temperature change rate exceeding 5°C / second is considered a high-risk fire source for key monitoring. The calculated temperature change rate is compiled into a report, which describes the temperature change in the fire source area in detail, identifies possible high-temperature areas and their change trends. Generate a temperature change rate graph to intuitively display the temperature changes at different time points, help decision makers quickly understand the dynamics of the fire source, and provide a basis for subsequent rescue and control measures.

[0016] Step S3: Predict the fire intensity trend at multiple points in time according to the temperature change rate of the fire source area and the change trend of the on-site gas parameters, thereby generating a multi-point fire intensity trend prediction graph; In this embodiment, the temperature change rate data and on-site gas parameter change trend data of the fire source area are collected. These data should include temperature changes, oxygen concentrations, carbon monoxide concentrations and other related gas concentration change records at multiple time points. Ensure that the timestamps of the data are consistent for subsequent analysis. For example, the temperature change rate and gas parameter data are unified into the UTC time format to facilitate the merging of different data sources. The collected temperature change rate and gas parameter data are cleaned to remove outliers and missing values. The mean filling method can be used to handle missing values ​​to ensure the integrity of the data. The data is processed using a standardized method to convert data of different dimensions to the same scale, such as standardizing gas concentration and temperature data to a range of 0 to 1, so as to facilitate subsequent model training. Before data analysis, a preliminary visualization chart of the temperature change rate and gas parameters is generated. These charts can include temperature change trend charts and gas concentration change curves to intuitively display the basic characteristics and change trends of the data. Set visualization parameters, such as a time window of 5 minutes, to better observe changes in a short period of time. Select a suitable fire trend prediction model, such as a multiple linear regression model, an ARIMA model, or a long short-term memory (LSTM) model. According to the nature and needs of the data, select a model that can capture the characteristics of the time series. Set the input parameters of the model, including temperature change rate, gas concentration and other related factors, to ensure that the model can fully reflect the factors affecting the change of fire intensity. Use historical data to train the selected prediction model. Ensure that the training data has a sufficient time span to capture the law of fire change. For example, use the temperature change rate and gas parameter data of the past 24 hours for training. Cross-validate the model to ensure its predictive ability on different data sets. You can choose 70% of the data for training and 30% of the data for validation to evaluate the accuracy and robustness of the model. Use the trained model to predict the fire trend at multiple time points in the future. Set the time range of the prediction, such as predicting the change of fire intensity every 5 minutes in the next 1 hour. Record the prediction results at each time point, including fire intensity, possible fire spread direction and related gas concentration. These results will be used for subsequent decision support. Organize the results of the multi-time point fire trend prediction into a report, with a detailed description of the fire intensity and gas concentration prediction at each time point. Ensure the integrity and clarity of the information for reference by decision makers. Generate a forecast data table that lists the fire intensity, temperature, and main gas concentration at each time point to help decision makers quickly obtain key information. Generate a multi-time point fire trend forecast chart based on the forecast results to intuitively show the trend of future fire changes. These charts can be in the form of line charts or heat maps to clearly show the changes in fire intensity and gas concentration. Mark the key time points and change ranges in the chart to help decision makers quickly understand the dynamic characteristics of fire development.

[0017] Step S4: Identify the points of the area to be rescued based on the thermal imaging image of the fire scene; analyze the optimal rescue route for each area to be rescued based on the multi-time point fire trend prediction map, and generate multiple regional rescue tasks; In this embodiment, the thermal imaging image of the fire scene is preprocessed, including denoising and image enhancement. Gaussian filtering or median filtering can be used to remove background noise, and the contrast of the image can be improved by histogram equalization to make the area to be rescued more obvious. Set processing parameters, such as the standard deviation of the filter and the enhancement strength, to ensure that the image quality is high enough for subsequent area identification. Apply image recognition algorithms, such as deep learning-based target detection technology (such as YOLO or Faster R-CNN), to analyze the preprocessed thermal imaging image to identify the area to be rescued. These areas usually show higher temperatures and may contain trapped people or fire sources. Set detection thresholds, such as areas with temperatures above 70°C are marked as areas to be rescued that require attention, to ensure the accuracy and reliability of the identification process. Extract the fire change information of each area to be rescued from the multi-time point fire trend prediction map, including fire intensity, possible diffusion direction, and gas concentration changes. These data will be used to assess the risk level of each area. Ensure that the timestamp of the fire data is consistent with the identification time of the area to be rescued for effective comparison and analysis. Select an appropriate optimal rescue route analysis algorithm, such as the A* search algorithm or the Dijkstra algorithm, to plan routes based on the risk level, distance, and available resources of each area to be rescued. Set analysis parameters, including the weight of each path, and consider factors such as fire intensity, access barriers, and resource availability to ensure that the safest and most effective rescue route is calculated. For each area to be rescued, use the selected algorithm to analyze the optimal rescue route. Record the starting point, end point, nodes passed, and estimated travel time of each path. Set the tolerance of the path analysis, such as allowing the path error to be within 1 meter, to ensure that the identified path is feasible and safe. Ensure that the path of each area can be quickly adjusted to respond to emergencies. Organize the optimal rescue route and related information for each area into a report, listing in detail the rescue tasks for each area to be rescued, including the required resources, estimated time, and potential risks. Generate a rescue task list to ensure that the information is clear and easy to read and provide decision support for on-site commanders. Ensure that the task list includes the rescue priority of each area so that resources can be allocated reasonably.

[0018] Step S5: Identify firefighting resources at the fire scene; dynamically allocate resources to multiple regional rescue tasks according to the firefighting resources at the fire scene, and perform real-time rescue monitoring to obtain real-time rescue monitoring data; In this embodiment, a list of firefighting resources is prepared, including all available personnel, equipment and supplies. Resource classification should include firefighters, fire trucks, fire extinguishers, rescue equipment and logistical support. Set resource identification standards, for example, each firefighter should have the corresponding qualifications and experience, and the equipment should meet national safety standards. Ensure the accuracy and traceability of resource information. Evaluate the status and availability of firefighting resources through on-site surveys and real-time monitoring systems (such as drones and sensors). Record the location, quantity and working status of each resource. Set evaluation parameters, such as the health status of firefighters and the functional integrity of equipment, to ensure that resources can be effectively used in emergencies. Establish a firefighting resource database and enter the identified resource information. The database should include basic information, status, historical usage records, etc. of the resources to ensure systematic management of information. Update the resource database regularly to ensure the timeliness and accuracy of the data. For example, update the resource status information every hour so that the on-site situation can be grasped at any time. Set priorities for rescue tasks in each area according to the urgency and complexity of the rescue tasks. Risk assessment models can be used to classify tasks into high, medium and low priorities. Set evaluation parameters, such as the number of trapped people, fire intensity, and resource requirements, to ensure the scientific nature of priority evaluation. Establish a dynamic resource allocation model and select a suitable optimization algorithm (such as linear programming, dynamic programming, or genetic algorithm) for resource allocation. The model should consider factors such as resource availability, task priority, and response time. Set the model's input parameters, including the number of resources, task requirements, and priority, to ensure that the model can generate the optimal resource allocation plan. Run the resource allocation model and make dynamic adjustments based on real-time data and task requirements. Prioritize resources to high-priority tasks to ensure that resources are used reasonably. Record the results of each resource allocation, including the number, area, and time of allocation, to ensure the transparency and traceability of the allocation process. Establish a real-time rescue monitoring system, integrate on-site monitoring equipment (such as cameras, sensors, and drones), and obtain real-time data. These data include the action status of firefighters, changes in fire intensity, and the status of on-site personnel. Determine the monitoring frequency, such as updating the data every 1 minute to ensure timely response to on-site conditions. Collect and analyze the obtained real-time rescue monitoring data to evaluate the rescue effect and resource utilization. Use data analysis tools to generate real-time monitoring reports, including rescue progress, resource usage, and changes in fire intensity. Set analysis parameters, such as rescuer efficiency, resource utilization, etc., to evaluate dynamic changes on site. Adjust rescue strategies and resource allocation in a timely manner based on real-time monitoring data to ensure the flexibility and effectiveness of rescue operations. Record key parameters and decision-making basis during the adjustment process for subsequent evaluation and improvement. Generate real-time feedback reports to provide the command center and on-site commanders with the latest rescue status information to ensure scientific and timely decision-making.

[0019] Step S6: Extract instant feedback information and optimize intelligent resource allocation based on real-time rescue monitoring data, thereby building an intelligent fire rescue optimization strategy.

[0020] In this embodiment, real-time rescue data is collected from the on-site monitoring system, including the location information of firefighters, equipment status, fire changes, gas concentration, etc. These data are transmitted to the central command system in real time through sensors and monitoring equipment. Integrate data from different sources, such as image information obtained by IoT devices and drones, to ensure the comprehensiveness and accuracy of the data. Set the frequency of data collection, such as updating every 5 minutes, to ensure the timeliness of information. Use data processing algorithms to analyze the collected real-time monitoring data to extract key information, such as the rate of change of the fire, the number of trapped people, the use of resources, and the working status of rescue personnel. Set analysis parameters, such as when the rate of change of the fire exceeds a certain threshold (such as 5℃ / minute), trigger an alarm mechanism to remind the commander to respond quickly. Use data mining technology to identify potential risk points and bottlenecks. Organize the extracted instant feedback information into a report, describing the real-time situation on the scene in detail, including changes in the fire, rescue progress, and resource usage. The report should contain charts and visual information to help commanders quickly understand the current situation. Set the report update frequency, such as generating an updated report every 30 minutes, to ensure that the command center can obtain dynamic information on the scene in a timely manner. Based on real-time monitoring data, build an intelligent resource allocation optimization model and select appropriate algorithms, such as linear programming, genetic algorithms, or deep learning methods, to achieve dynamic resource allocation. Set the model's input parameters, including task priority, available resources, fire change rate, and rescue goals, to ensure that the model can fully reflect the on-site situation. Use historical rescue data to train the resource allocation model to ensure that the model can make effective predictions in different situations. For example, use data from past fire rescues to train the model to identify the optimization strategy for resource allocation. Cross-validate the model to ensure its predictive ability on different data sets. Set training parameters, such as training cycle and learning rate, to ensure that the model can achieve optimal performance. Run the optimization model to dynamically adjust resource allocation based on real-time data and task requirements. Prioritize resources to high-priority task areas to ensure that resources are used reasonably. Record the results of each allocation, including the number, area, and estimated rescue time of resource allocation, to ensure the transparency and traceability of the allocation process. Develop an intelligent fire rescue optimization strategy based on real-time feedback information and resource allocation results. The strategy should cover multiple aspects such as resource allocation, rescue steps, and emergency response mechanisms. Set strategy evaluation criteria, such as rescue efficiency, resource utilization, and safety of trapped people, and evaluate the effectiveness of the strategy through quantitative indicators. During the implementation process, monitor the rescue effect in real time and adjust the optimization strategy in time according to changes in the on-site situation. For example, if the fire spreads faster, resources should be invested in high-risk areas immediately. Set monitoring parameters, such as resource usage in each area and the rate of change of the fire, to ensure that the rescue strategy can flexibly respond to emergencies.

[0021] In this embodiment, refer to Figure 2 , is a flowchart of detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include: Step S11: acquiring real-time environmental monitoring data of the fire scene based on sensors; Step S12: performing environmental parameter analysis on the real-time environmental monitoring data of the fire scene to generate real-time parameter features of the fire scene; Step S13: Analyze gas composition information according to the real-time parameter characteristics of the fire scene to extract environmental gas composition information; Step S14: Analyze the change of the ambient gas composition information to obtain the characteristics of the change of the gas composition; Step S15: performing multi-dimensional gas concentration calculation according to the real-time parameter characteristics of the fire scene to generate multiple gas concentration time series curves; Step S16: Predicting the gas change trend based on the gas composition change characteristics and multiple gas concentration time series curves to generate the on-site gas parameter change trend.

[0022] In this embodiment, at the fire scene, the sensors are first arranged and selected. Sensors suitable for fire monitoring are selected, such as temperature sensors, smoke sensors, gas sensors (such as CO, CO 2 , O 2 、NO 2, etc.), to ensure that environmental changes can be fully monitored. Determine the installation location of the sensor, giving priority to areas where fires may occur, such as flammable material storage areas and vents. Ensure that the sensor can quickly capture environmental changes when a fire occurs. Build a real-time data acquisition system to connect the data of each sensor to the central data processing unit. Select high-frequency data acquisition equipment and set the sampling frequency to 1Hz to ensure that changes in environmental parameters can be captured in real time. Ensure the stability of data transmission. Wireless transmission technology (such as Zigbee and LoRa) can be used to ensure effective connection at the fire scene. Start the data acquisition system to monitor the environmental parameters of the fire scene in real time. Record the output data of each sensor, including temperature, humidity, gas concentration, etc., to ensure the integrity and accuracy of the data. Set up a data storage mechanism to store the real-time monitoring data on the server or cloud for subsequent analysis and processing. Ensure the security and traceability of the data. Preprocess the acquired real-time environmental monitoring data, including denoising, smoothing, and outlier detection. Use the moving average method to smooth the data to reduce fluctuations caused by environmental interference. Set thresholds to identify and remove abnormal data that does not conform to reality. For example, if the reading of a temperature sensor exceeds the set maximum value, it needs to be marked as an outlier. Extract key features from the processed environmental monitoring data, including statistical features such as average, maximum, minimum, and standard deviation. These features will be used to describe the environmental conditions at the fire scene. Combined with time series analysis, extract the changing trends and periodic characteristics of the data, and record the changes in environmental parameters in different time periods. Organize the extracted environmental parameter features into a report, describing in detail the real-time environmental status of the fire scene, including changes in parameters such as temperature, humidity, and gas concentration. Generate visual charts, such as line charts and bar charts, to intuitively display the changing trends of parameter features and provide support for subsequent analysis. Extract relevant data from gas sensors from real-time environmental monitoring data, including carbon dioxide (CO 2 ), carbon monoxide (CO), oxygen (O 2) and other concentration values ​​of harmful gases. Set the time range for data extraction, such as extracting gas composition data once a minute to form time series data of gas composition. Select an appropriate gas composition analysis method, such as principal component analysis (PCA) or cluster analysis, to identify the relationship between different gas components. This method can help extract representative gas composition characteristics. Set analysis parameters, such as selecting the first two principal components to explain the main reasons for the change in gas composition. Organize the results of gas composition analysis into a report, recording the concentration changes of each gas component and its corresponding environmental parameter characteristics. Generate a visual chart to show the trend of different gas components over time, to provide support for subsequent gas composition change analysis. Perform change analysis on the extracted gas composition information. Calculate the change rate of each gas component and analyze its growth or decrease trend over time. Set the calculation formula for change characteristics, such as change rate = (current concentration - previous moment concentration) / previous moment concentration, to quantify the change characteristics of gas composition. Use time series analysis methods to perform trend analysis on gas composition changes. Use the autoregressive moving average (ARMA) model to evaluate the change pattern of gas composition over time. Record the change characteristics, including peak values, valley values ​​and their corresponding time points, to identify the key moments of gas composition changes. Organize the gas composition change characteristics into a report, describing in detail the change patterns of different gas components and their potential impact on the fire scene environment. Generate a visual chart to show the trend of gas composition change characteristics and provide data support for subsequent gas concentration calculations. According to real-time monitoring data, select an appropriate gas concentration calculation method, such as using the ideal gas state equation or a linear regression model based on gas sensor output. Set the calculation formula to ensure that it can accurately reflect the concentration changes of each gas. Implement multi-dimensional gas concentration calculations and perform independent calculations for different gas components. Record the changes in the concentration of each gas over time to form multiple gas concentration time series curves. Set a time window, such as recording the concentration value once a minute, to ensure the timeliness and accuracy of the data. Generate a time series curve from the calculated gas concentration data to intuitively show the trend of different gas concentrations over time. Use visualization software to generate charts to ensure that the charts are clear and easy to read. Record the key features of the time series curve, such as the maximum concentration, minimum concentration and their corresponding time points, to provide a reference for the prediction of subsequent gas change trends. Select an appropriate gas trend prediction model, such as a time series prediction model (such as ARIMA) or a machine learning model (such as support vector machine, neural network). Set model parameters to ensure that the trend of gas concentration changes can be accurately captured. Use historical gas concentration data to train the selected prediction model. Divide the data set into a training set and a validation set to ensure the accuracy and generalization ability of the model after training. Record the prediction results of the model, including the predicted gas concentration value and its change trend, and compare them with the actual monitoring data to evaluate the accuracy of the model.The prediction results are compiled into a report, detailing the gas change trend and its potential impact on the fire scene environment. The key parameters of the prediction are recorded, such as the maximum and minimum gas concentrations and their changing speed. Visual charts are generated to show the predicted trend of gas changes, providing support for on-site safety monitoring and decision-making.

[0023] In this embodiment, refer to Figure 3 , is a flowchart of detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include: Step S21: Acquire a thermal imaging image of the fire scene based on the drone; Step S22: remapping the pixel grayscale values ​​of the fire scene thermal imaging image to construct a brightness optimized thermal imaging image; Step S23: performing visual recognition of temperature distribution on the brightness optimized thermal imaging image, thereby generating an on-site temperature distribution field; Step S24: accurately identify hot spots in the on-site temperature distribution field and mark the on-site fire source points; Step S25: performing fire source spatial positioning calculation on the on-site fire source point to generate each fire source spatial coordinate; Step S26: Calculate the temperature change rate of consecutive frames according to each fire source spatial coordinate, so as to generate the temperature change rate of the fire source area.

[0024] In this embodiment, a suitable drone is selected to ensure that it has the ability to carry a thermal imaging camera. The drone should have good flight stability and a long endurance time to enable effective thermal imaging monitoring at the fire scene. A high-resolution thermal imaging camera is configured to ensure that it can capture subtle temperature changes. The sensitivity of the camera should reach 0.1°C to accurately record the heat distribution at the fire scene. A flight plan for the drone is formulated, including flight altitude, speed, and path. Usually, a cruise at an altitude of 30 to 50 meters is selected to obtain a wide coverage range and detailed thermal imaging images. At the fire scene, the drone is started to fly to ensure the stability of the camera during the flight. The flight status of the drone is monitored in real time to ensure that it can complete the thermal imaging task safely and effectively. During the flight, thermal imaging images are collected in real time. The drone should take thermal images regularly and set to save an image every 5 seconds to ensure that the dynamic changes of the fire scene are captured. The collected thermal imaging images are stored in the drone's built-in memory or external storage device for subsequent processing and analysis. First, the collected thermal imaging images are preprocessed, including denoising and contrast enhancement. Use filtering algorithms (such as Gaussian filtering) to remove noise from the image to improve image quality. Ensure image clarity and details, especially in the heat source area of ​​the fire scene, for subsequent analysis. Perform pixel grayscale value remapping to adjust the grayscale values ​​in the thermal imaging image linearly or nonlinearly to optimize the brightness and contrast of the image. Set the target grayscale range, such as mapping the grayscale value from 0-255 to 100-255 to highlight the heat source area. Apply color mapping technology to convert the optimized grayscale value into a pseudo-color image to improve visual effects and readability. This helps to quickly identify the heat source area. Generate a thermal imaging image with optimized brightness and save it in a suitable image format (such as TIFF or PNG) to ensure that the image quality is not lost. Record the image processing parameters and conversion method for subsequent analysis and verification of the image processing effect. Extract temperature data from the brightness optimized thermal imaging image. According to the calibration data of the thermal imaging equipment, convert the optimized pixel value into an actual temperature value to ensure that the temperature corresponding to each pixel is accurate. Set the temperature range, which usually includes the lowest and highest temperatures at the fire scene, to facilitate subsequent temperature distribution analysis. Construct a temperature distribution field based on the extracted temperature data. Use a gridding method to divide the thermal imaging image into multiple grids, each grid corresponding to a temperature value. Generate a temperature distribution map, use isotherms or heat maps to show the temperature changes in different areas, and intuitively present the temperature distribution characteristics of the fire scene. Verify the generated temperature distribution field and compare it with the actual temperature values ​​measured on site to ensure the accuracy and reliability of the temperature distribution field. Record the verification results and adjust the temperature data extraction and conversion methods as needed to improve the accuracy of the temperature distribution field.Select an appropriate hotspot identification algorithm, such as a threshold-based method or a cluster analysis method (such as K-means clustering), to accurately identify the hotspot area in the temperature distribution field. Set identification parameters, such as the temperature threshold of the hotspot. Usually, areas that are 10°C higher than the ambient temperature are selected as hotspots. Apply the selected hotspot identification algorithm to analyze the temperature distribution field, identify the hotspot area, and mark it. Mark the identified hotspot areas on the image with different colors or symbols. Record the temperature value of each hotspot and its position in the image for subsequent fire source location and analysis. Verify the marked hotspot area to ensure that it is consistent with the actual fire source location. Verification can be performed by comparing the field measured data to ensure the accuracy of hotspot identification. According to the verification results, adjust the parameters and algorithms of hotspot identification to improve the identification effect and accuracy. Select an appropriate fire source spatial positioning method, such as geometric positioning method or three-dimensional reconstruction technology based on multi-angle thermal imaging data. Ensure that the selected method can accurately calculate the spatial coordinates of the fire source. Determine the required input data, including the image coordinates of the hotspot and the flight altitude of the drone. Perform spatial positioning calculations on the marked fire source points according to the selected method. Convert the two-dimensional coordinates in the thermal imaging image into three-dimensional spatial coordinates, taking into account the flight parameters and viewing angle of the drone. Record the spatial coordinates of each fire source point, including its X, Y, and Z coordinate values, to ensure the accuracy of the coordinates. Arrange the calculated spatial coordinates of the fire source and generate a positioning report of the fire source point, which describes in detail the spatial position of each fire source and its corresponding temperature value. Record the parameters and methods of spatial positioning calculation for subsequent analysis and verification. Collect multiple frames of thermal imaging images and extract the temperature values ​​of each fire source point in different time frames. Ensure that the collected images cover the change process of the fire source point. Set the time interval for data collection, such as collecting data every 5 seconds, to ensure that the temperature change in the fire source area can be captured. Analyze the temperature data of each fire source point and calculate its temperature change rate. Change rate = ΔT / Δt, where ΔT is the temperature change and Δt is the time interval. Record the temperature change rate of each fire source point to ensure the accuracy and consistency of the calculation. Arrange the calculated temperature change rate and generate a temperature change rate report of the fire source area, which describes in detail the temperature change of each fire source point and its potential impact on the development of the fire. Record the parameters and methods for calculating the temperature change rate to provide a basis for subsequent fire monitoring and emergency response.

[0025] In this embodiment, the specific steps of step S22 are: Perform image noise detection on thermal imaging images of fire scenes and mark abnormal image noise points; Adaptively filter abnormal noise points in the image to generate a filtered and denoised thermal imaging image; Calculate the grayscale histogram distribution of the filtered and denoised thermal imaging image to obtain the grayscale histogram distribution value; Performing nonlinear grayscale range stretching on the grayscale histogram distribution value to obtain grayscale stretching parameters; The grayscale value of the filtered and denoised thermal imaging image is remapped pixel by pixel based on the grayscale stretching parameter to construct a brightness optimized thermal imaging image.

[0026] In this embodiment, a suitable noise detection algorithm is selected, such as median filtering or local variance analysis. These algorithms can effectively identify and mark abnormal noise in thermal imaging images. Set detection parameters, such as noise threshold. Typically, the threshold is set to twice the standard deviation of the temperature value in the image to determine which pixel values ​​are considered abnormal. Apply the selected noise detection algorithm to the thermal imaging image. First, calculate the statistical characteristics of the neighborhood around each pixel, such as the mean and standard deviation. Mark those pixels that exceed the set threshold as abnormal noise. Different colors or symbols can be used to mark on the image for subsequent processing and analysis. Record the number and location of the detected abnormal noise points and generate a noise detection report. This will provide a basis for subsequent filtering and noise reduction processing. Perform a preliminary analysis to evaluate the impact of noise on the overall image quality to ensure that important heat source information is not missed during the processing. Select a suitable adaptive filtering algorithm, such as adaptive median filtering or Wiener filtering. These algorithms can dynamically adjust the filtering parameters according to the local image characteristics, thereby effectively removing noise. Determine the filter window size, usually a 3x3 or 5x5 neighborhood is chosen to balance computational efficiency and filtering effect. Apply an adaptive filter to the thermal image, traverse each pixel and calculate the statistical characteristics of the surrounding neighborhood. Dynamically adjust the filter parameters based on these characteristics to remove abnormal noise. Record the results of each filtering operation to ensure that the filtering process can effectively reduce noise while retaining heat source information. Verify the generated filtered and denoised thermal imaging image and compare it with the original image to ensure that the noise is effectively removed and the heat source characteristics are retained. Based on the verification results, adjust the filter parameters to improve the filtering effect. Record the optimized parameters for subsequent analysis and application. Perform grayscale value statistics on the filtered and denoised thermal imaging image. Traverse each pixel in the image and count its grayscale value into the corresponding histogram bucket. Usually set the grayscale value range to 0-255 to cover all possible pixel values. Select 256 buckets to ensure that each grayscale value has a corresponding statistic. Calculate the frequency of occurrence of each grayscale value and generate a grayscale histogram. Record the frequency of each grayscale value for subsequent analysis and processing. Calculate the characteristic parameters of the histogram, such as mean, variance, and kurtosis, to describe the overall grayscale distribution characteristics of the image. Generate a visualization chart of the histogram to intuitively display the distribution of grayscale values. Make sure the chart is clear and easy to read, and mark the frequency of each grayscale value. Record the calculation results and visualization chart of the histogram for subsequent analysis and optimization. Select a nonlinear grayscale range stretching method, such as gamma correction or logarithmic transformation. This method can effectively enhance the contrast of the image and highlight important temperature features. Set the stretching parameters, such as the gamma value is usually set between 0.5 and 2, in order to find the optimal contrast enhancement effect. Process the grayscale histogram distribution values ​​according to the selected nonlinear stretching method. Apply the formula to convert the grayscale values, record the stretching results of each grayscale value, generate a new grayscale histogram, and compare and analyze it with the original histogram.Verify the stretched grayscale histogram to ensure that it can effectively enhance the contrast of the image. Observe whether the distribution of the histogram is more concentrated and whether it can better reflect the temperature characteristics in the image. Select an appropriate grayscale value remapping method and map the pixels one by one according to the grayscale stretching parameters obtained in the previous step. Determine the mapping formula, such as linear mapping or nonlinear mapping based on gamma correction, to ensure that the image brightness is optimized. Iterate over each pixel in the filtered and denoised thermal imaging image and remap the grayscale value according to the grayscale stretching parameters. Record the new grayscale value of each pixel during the mapping process. Generate a thermal imaging image with optimized brightness and save it in a high-quality image format to ensure that image information is not lost. Verify the generated brightness-optimized thermal imaging image to ensure that it is better than the original image in terms of contrast and details. It can be evaluated by visual inspection and computer analysis methods. Generate a visual report of the optimized image, showing the comparison before and after optimization, and record the key parameters and results of the optimization process for subsequent application and analysis.

[0027] In this embodiment, refer to Figure 4 , is a flowchart of detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include: Step S31: Evolving the fire spread path of the on-site fire source point to obtain the fire spread path; Step S32: fitting the fire spread distribution according to the temperature change rate of the fire source area and the fire spread path, and constructing a fire spread distribution change diagram; Step S33: performing fire situation evolution mining on the fire spread distribution change graph to obtain the fire situation evolution law; Step S34: Simulate the evolution of fire spread based on the fire situation evolution law and the change trend of on-site gas parameters based on the preset multimodal AI large model to generate fire spread evolution simulation data; Step S35: Perform multi-time point fire trend prediction on the fire spread evolution simulation data, thereby generating a multi-time point fire trend prediction graph.

[0028] In this embodiment, a suitable fire spread model is selected, such as a thermal diffusion model or a fluid dynamics model. These models can simulate the diffusion behavior of flames under different environmental conditions, taking into account factors such as wind speed, humidity and temperature. Determine the input parameters of the model, such as the initial temperature of the fire source, the temperature of the surrounding environment, wind speed and wind direction, etc. Usually, the wind speed is set to 5 meters per hour and the humidity is 30%. Based on the selected diffusion model, the fire source is simulated and calculated. Numerical methods (such as finite difference method or finite element method) are used to solve the equation to obtain the diffusion path of the fire at different time points. The fire spread at each time step (for example, every minute) is recorded, and a fire spread path diagram is generated to show the change of the fire over time. The calculated fire spread path is analyzed to identify the main direction, speed and possible affected area of ​​the fire spread. Ensure that the path diagram can clearly reflect the dynamic characteristics of the fire spread. Generate a visual chart to show the fire spread path and its changes, and provide an intuitive basis for the subsequent fire spread distribution fitting. Collect the temperature change rate data of the fire source area on site, including the temperature change at different time points. These data can be obtained through thermal imaging monitoring systems to ensure their accuracy. Set the data extraction time interval, such as recording the temperature change rate every 5 minutes to capture the changes in the fire spread process. Use statistical analysis methods or machine learning techniques (such as regression analysis or cluster analysis) to fit the fire spread distribution. Combine the temperature change rate with the fire spread path to establish a mathematical model of fire spread. Set fitting parameters, such as the influence weight of the temperature change rate, to ensure that the model can reasonably reflect the characteristics of fire spread. Generate a fire spread distribution change map based on the fitting results to intuitively display the distribution of the fire at different time points. The areas with large temperature changes and the main direction of fire spread should be marked in the map. Record the key parameters and results of the fitting process to provide a basis for subsequent fire situation evolution mining. Select a suitable fire situation evolution analysis method, such as time series analysis or state transition model. These methods can help identify the key change points and evolution laws in the fire spread process. Set analysis parameters, such as time windows (for example, 5 minutes), to analyze the evolution trend and change characteristics of the fire. Conduct in-depth analysis of the fire spread distribution change map to identify patterns and laws in the fire spread process. Use graph algorithms to analyze the path, speed, and influencing factors of fire spread. Record the key evolution laws found, including the acceleration period, deceleration period, and possible turning points of fire spread to ensure the integrity and accuracy of the information. Based on the analysis results, generate a report on the evolution of the fire situation, detailing the changes and potential influencing factors during the fire spread process. Record the key parameters of the evolution law to provide a reference for subsequent simulation and prediction. Select a suitable multimodal AI large model, such as a deep learning-based image recognition model combined with a gas parameter analysis model, to comprehensively simulate the spread of fire.Configure the model's input parameters, including the evolution of the fire situation, on-site gas parameters, and historical data, to ensure that the model can fully reflect the dynamic changes at the fire scene. Input the collected evolution of the fire situation and gas parameters into the AI ​​model to simulate the evolution of the fire spread. Set the simulation time range, such as simulating the changes in the fire situation in the next hour. Record key data during the simulation process, including the speed of fire spread, temperature changes, and changes in gas concentration, to ensure the accuracy and real-time nature of the data. Analyze the generated simulated data on the evolution of the fire spread to ensure its rationality and effectiveness. Compare the simulation results with the actual monitoring data to evaluate the model's predictive ability. Select a suitable trend prediction model, such as the ARIMA model or the long short-term memory (LSTM) network. These models can make trend predictions based on historical data and take into account the characteristics of time series. Set the model's input parameters, including previous simulation data, gas concentration changes, and fire spread path data, to make accurate trend predictions. Use the selected trend prediction model to analyze the simulated data on the evolution of the fire spread and generate fire trend prediction results at multiple time points in the future. Set a forecast time range, such as predicting the fire dynamics in the next 30 minutes to 1 hour. Record the forecast results at each time point, including the speed of fire spread, temperature changes, and potential impact areas, to provide data support for decision-making. Organize the forecast results into a multi-time point fire trend forecast chart to intuitively display the changing trend of the fire and the expected impact area. Make sure the chart is clear and easy to read, and mark key data and time points.

[0029] In this embodiment, step S4 includes the following steps: Step S41: Identify the area to be rescued based on the thermal imaging image of the fire scene; Step S42: Detect trapped persons at the points in the area to be rescued, and obtain persons to be rescued in each area; Step S43: performing a regional rescue priority assessment based on the persons to be rescued in each area, thereby obtaining a rescue priority for each area; Step S44: identifying available rescue paths based on the fire scene thermal imaging image, and extracting multiple available rescue routes; Step S45: Analyze the optimal rescue route for each area of ​​multiple available rescue routes according to the multi-time point fire trend prediction map, so as to obtain the optimal rescue route for each area; Step S46: Generate multiple regional rescue tasks according to the rescue priority of each area and the optimal rescue route of each area.

[0030] In this embodiment, the thermal imaging image of the fire scene is preprocessed, including denoising and contrast enhancement, to ensure that the image quality is high enough for subsequent analysis. Median filtering or Gaussian filtering algorithms can be used to remove noise. Denoising parameters, such as the filter window size of 3x3, are set to balance processing speed and image quality. A suitable image recognition algorithm is selected, such as a target detection algorithm based on deep learning (such as YOLO or Faster R-CNN) to identify the area to be rescued. A thermal imaging data set containing different fire scenes is used when training the model to improve recognition accuracy. Threshold parameters are set, such as the confidence threshold of target detection is set to above 0.5 to ensure that only credible points in the area to be rescued are identified. The trained model is used to infer the processed thermal imaging image to identify the area to be rescued. The location coordinates of each area and its corresponding temperature value are recorded to help with subsequent analysis. Generate an area recognition report, listing in detail the coordinates, features and related environmental information of each area to be rescued to ensure the scientificity and systematicness of subsequent rescue work. Select a suitable target detection model specifically for identifying trapped persons. Convolutional neural network (CNN) or improved YOLO model can be used to ensure that the model can effectively identify trapped persons in complex fire environments. Set a training data set, including thermal images with trapped persons and without people, to improve the robustness and accuracy of the model. Perform target detection on the identified rescue areas and extract information about trapped persons in each area. Record the coordinates, size and temperature value of each target in the thermal image. Set the confidence threshold of target detection, for example, set it above 0.6 to ensure that only credible trapped persons are identified. Organize the information of the detected trapped persons into a report, listing the number, location, status and temperature information of the rescued persons in each area. Ensure the integrity and accuracy of the information. Record the parameters and results of the detection process to provide reliable data support for the subsequent rescue priority assessment. Determine the criteria for regional rescue priority assessment, including the number of trapped persons, status (such as conscious or not), distance from the fire source and the degree of danger of the surrounding environment. Set evaluation parameters, such as giving a higher weight (1 to 5 points) to the status of trapped persons and a relatively lower weight (1 to 3 points) to the degree of environmental danger. Calculate the priority of each area to be rescued according to the set evaluation criteria. Consider various factors and calculate the overall rescue priority score for each area. Record the priority evaluation results of each area to ensure the accuracy and consistency of the data for subsequent rescue plan formulation. Organize the priority evaluation results into a report, listing the rescue priority, status of the rescued personnel and related environmental information of each area in detail. Ensure that the information is clear and easy to read for subsequent decision-making. Generate a priority chart to intuitively display the rescue priority of each area, providing a basis for subsequent rescue path identification and task allocation.Select a suitable path identification algorithm, such as the A* algorithm or the Dijkstra algorithm, which can calculate the best rescue route based on environmental data. Determine the algorithm input parameters, including the map of the fire scene, the location of obstacles (such as walls, fire sources, etc.), and the walkable area. Use the selected algorithm to identify available rescue paths based on the environmental information identified in the thermal imaging image. Record the starting point, end point, and nodes passed by each path. Set the tolerance for path identification, such as allowing the path error to be within 1 meter to ensure that the identified path is feasible and safe. Organize the multiple available rescue routes identified into a report, describing the characteristics, length, and potential risks of each path in detail. Generate a visual chart to show the location and risk assessment of each path in the fire scene. Use a multi-time point fire trend prediction chart to analyze the impact of fire changes on each available rescue route. Identify the speed, direction, and possible danger areas of fire spread. Set the analysis time window, such as evaluating the impact of the fire on the rescue route every 5 minutes to ensure the timeliness of the data. Perform the optimal rescue route analysis for each available rescue route area by area. Comprehensively consider the changes in fire, the location of trapped people and the rescue priority, and calculate the safety and effectiveness of each path. Record the evaluation results of each path to ensure the scientificity and accuracy of the analysis process. Organize the analysis results of the optimal rescue route into a report, and list the optimal path, potential risks and status of trapped people in each area in detail. Ensure the integrity and clarity of information. Generate an optimal path map to intuitively display the optimal rescue route for each area, providing a basis for the subsequent allocation of rescue tasks. etc. Set allocation strategies to ensure that high-priority areas can be rescued in a timely manner. Set task parameters, such as each rescue team is responsible for 1-2 areas, and consider the staffing and professional skills of the rescue team. Generate specific rescue tasks based on the rescue priority and optimal rescue route of each area. Ensure that each task contains information such as the target area, task description and execution time. Record the details of each rescue task to ensure the accuracy and consistency of the information and provide support for subsequent implementation. Organize the generated multiple regional rescue tasks into a task list, and list the target, priority, executor and route information of each task in detail. Ensure that the task list is clear and easy to read. Generate rescue mission reports to display the allocation of various tasks and potential risk assessments, providing decision support for on-site commanders.

[0031] In this embodiment, step S5 includes the following steps: Step S51: Identify firefighting resources at the fire scene; perform personnel allocation and equipment status analysis on the firefighting resources at the fire scene to obtain an assessment value of the firefighting and rescue resources at the scene; Step S52: dynamically allocating resources to multiple regional rescue tasks according to the on-site fire rescue resource evaluation value, thereby obtaining dynamic rescue resource allocation data; Step S53: Make rescue decisions based on the dynamic rescue resource allocation data, perform real-time rescue monitoring, and obtain real-time rescue monitoring data.

[0032] In this embodiment, available firefighting resources are identified through on-site surveys and monitoring systems (such as drones and thermal imaging equipment). This includes firefighters, fire trucks, fire extinguishers, rescue equipment, etc. Ensure that each resource is recorded in detail, including quantity, location and status. Establish resource identification standards, classify resources, and set identification conditions for each type of resource. For example, firefighters should have corresponding qualifications and the equipment status must meet safety standards. Analyze the configuration of on-site firefighters, including the number of people in each team, professional skills and task allocation. Ensure the accuracy of information by retrieving on-site monitoring data and personnel registration information. Set evaluation parameters such as personnel skill level, work experience and health status to ensure that each team can effectively perform tasks. Conduct a detailed analysis of the status of on-site equipment and check the availability and functional status of fire extinguishers, fire trucks and other rescue equipment. Record the working conditions and maintenance records of each equipment to ensure that it can be effectively used in an emergency. Combine personnel configuration and equipment status to calculate the evaluation value of on-site firefighting and rescue resources. The evaluation value can be quantitatively evaluated by factors such as personnel skills, equipment status and quantity to generate a comprehensive score. According to the evaluation value of on-site fire rescue resources, a dynamic resource allocation model is established. Select an appropriate optimization algorithm, such as linear programming or genetic algorithm, to achieve the optimal allocation of resources. Determine the input parameters of the model, including the rescue mission priority of each area, the type and quantity of required resources, and the evaluation value of available resources. Run the resource allocation model to calculate the amount of fire resources required for each area and dynamically adjust it according to the evaluation value. For example, for areas with high priority, more firefighters and equipment are allocated first. Record the resource allocation of each area to ensure the transparency and accuracy of the allocation process. Dynamically adjust the evaluation value and resource allocation to cope with changes in the on-site situation. Organize the dynamic rescue resource allocation data into a report, which lists the resource allocation of each area in detail, including personnel, equipment and their status. Ensure the integrity and traceability of information. Generate a resource allocation chart to intuitively display the resource allocation of each area and provide data support for subsequent rescue decisions. Make rescue decisions based on the dynamic rescue resource allocation data. Determine the rescue strategy for each area taking into account the rescue priority and resource allocation of each area. Set decision parameters, such as rescue goals, time limits, and resource utilization efficiency, to ensure the scientificity and rationality of the decision. Establish a real-time rescue monitoring system and integrate on-site monitoring equipment (such as cameras, drones, and sensors) to obtain real-time data. This data includes the action status of firefighters, changes in the fire, and the status of personnel on site. Set the monitoring frequency, such as updating the data every 1 minute, to ensure timely response to on-site conditions. Analyze the obtained real-time rescue monitoring data to evaluate the rescue effect and resource utilization. Use data analysis tools to generate real-time monitoring reports, including rescue progress and resource utilization. According to the analysis results, timely adjust rescue decisions and resource allocation to ensure the flexibility and effectiveness of rescue operations.Record key parameters and decision-making basis during the adjustment process for subsequent evaluation and improvement.

[0033] In this embodiment, step S6 includes the following steps: Step S61: extracting instant feedback information based on real-time rescue monitoring data to obtain real-time rescue feedback information; Step S62: identifying emergency situations based on the real-time rescue feedback information and generating emergency situation data; Step S63: positioning the emergency area based on the emergency situation data to obtain emergency situation area positioning information; Step S64: Perform intelligent resource allocation optimization based on the emergency situation area positioning information, thereby constructing an intelligent fire rescue optimization strategy.

[0034] In this embodiment, a field monitoring system (such as a camera, a sensor, a drone, etc.) is used to collect real-time rescue monitoring data. These data include a variety of information such as the activity status of firefighters, changes in the fire, and the status of trapped persons. The frequency of data collection is set, for example, once every 1 minute, to ensure the timeliness and accuracy of the information. This is crucial for emergency response because the situation at the fire scene changes rapidly. The collected real-time monitoring data is preliminarily processed, including denoising and data cleaning. Data cleaning techniques are used to remove incomplete or abnormal data points to improve data quality. Data mining techniques are used to extract key information from the processed data to generate real-time rescue feedback information. This information may include the work efficiency of firefighters, the speed of fire spread, and the number of trapped persons. The extracted real-time rescue feedback information is organized into a report that describes the current rescue progress and on-site conditions in detail. The report should include the fire situation, personnel status, and resource usage in each area. Establish standards for emergency situation identification to identify which situations require special attention. Standards may include rapid spread of fire, increase in the number of trapped persons, and shortage of resources. Set identification parameters, such as when the fire spread rate exceeds a certain threshold (e.g., more than 5 meters per minute) or the number of trapped people exceeds a set value (e.g., 10 people), to trigger emergency identification. Use data analysis technology to identify real-time rescue feedback information to determine whether an emergency exists. Machine learning methods, such as decision trees or support vector machines, can be used to train models to identify emergency situations. Record the results of each identification to ensure the accuracy and completeness of the data. Generate emergency data, including the type of emergency identified, the time of occurrence, and the affected area. Organize the emergency data into reports, detailing the identified emergency situations and their potential impact on rescue work. Ensure that the information is clear and easy to read so that relevant personnel can quickly understand the situation. Select appropriate regional positioning algorithms, such as cluster analysis or spatial analysis, to determine the areas where emergencies occur. These algorithms can help identify the main impact areas of fire and trapped people. Set analysis parameters, such as cluster radius and minimum sample number, to accurately identify emergency areas. Perform regional positioning analysis on the scene based on the emergency data to identify the most severely affected areas. K-means clustering algorithm can be used to divide the monitoring data into multiple clusters to identify high-risk areas. Record the location information, impact level and related data of each emergency area to help with subsequent resource allocation and rescue decision-making. For example, linear programming or genetic algorithms can ensure that resource allocation can be dynamically adjusted according to real-time conditions. Determine the input parameters of the model, including resource requirements, available resources and priority of each emergency area. Run the resource allocation optimization model to allocate resources according to the location information of the emergency area. Prioritize resources to high-priority emergency areas to ensure that resources are used reasonably. Record the results of each allocation to ensure the transparency and accuracy of information. Dynamically adjust resource allocation to respond to changes in on-site conditions.

[0035] In this embodiment, a fire rescue intelligent management system based on a multimodal AI big model is provided, which is used to execute the fire rescue intelligent management method based on a multimodal AI big model as described above, including: The gas trend prediction module is used to obtain real-time environmental monitoring data at the fire scene; analyze environmental parameters of the real-time environmental monitoring data at the fire scene, and predict gas change trends to generate on-site gas parameter change trends; The temperature distribution recognition module is used to obtain thermal imaging images of the fire scene; perform visual recognition of temperature distribution and calculation of the temperature change rate of consecutive frames based on the thermal imaging images of the fire scene, thereby generating the temperature change rate of the fire source area; The fire trend prediction module is used to predict the fire trend at multiple points in time according to the temperature change rate of the fire source area and the change trend of the on-site gas parameters, thereby generating a multi-point fire trend prediction graph; The rescue route analysis module is used to identify the points of the area to be rescued based on the thermal imaging images of the fire scene; analyze the optimal rescue route for each area to be rescued based on the multi-time point fire trend prediction map, and generate multiple regional rescue tasks; Dynamic resource allocation module, used to identify fire-fighting resources at the fire scene; dynamically allocate resources to multiple regional rescue tasks based on the fire-fighting resources at the fire scene, and conduct real-time rescue monitoring to obtain real-time rescue monitoring data; The resource allocation optimization module is used to extract instant feedback information and optimize intelligent resource allocation based on real-time rescue monitoring data, thereby building an intelligent fire rescue optimization strategy.

[0036] The present invention ensures that the command center and rescue personnel can obtain the changes in gas composition and concentration on site in the first time through the collection of real-time environmental monitoring data, and provide data support for safety decision-making. By predicting the trend of gas changes, it is possible to timely warn of the accumulation of harmful gases, such as carbon monoxide, nitrogen oxides, etc., so as to avoid high-risk areas in advance and protect the safety of rescue personnel. Gas trend prediction helps commanders to more scientifically evaluate the changes in the scope of fire expansion, fire source intensity and dangerous areas, so as to formulate more effective rescue and evacuation strategies. Through temperature distribution recognition, the heat source area of ​​the fire can be confirmed in real time, helping rescue personnel to lock the main direction of the fire source and fire development in time. By calculating the temperature change rate of continuous frames, the speed of fire spread is evaluated, which helps to predict the development trend of the fire, so as to make timely responses when the fire spreads rapidly. Monitoring the temperature change rate of the fire source area enables the on-site commander to flexibly adjust resources and rescue strategies to cope with changes in the fire. Combining the fire source temperature and gas changes, a more comprehensive fire prediction can be provided, which not only focuses on the temperature of the fire source itself, but also takes into account gas diffusion and fire spread speed. By predicting the multi-time trend of the fire, it is possible to understand in advance how the fire may develop at different time points, provide more forward-looking information for fire commanders, and support rescue decisions. The fire trend chart helps the command center to clarify the direction of the fire, allocate fire resources and deploy rescue personnel in advance, and ensure the timeliness and effectiveness of the response. Through thermal imaging images, it is possible to clearly identify which areas have higher temperatures and which areas have trapped people, so as to quickly identify areas that need priority rescue. Based on the fire prediction, the rescue route analysis can calculate the shortest and safest path to prevent rescue personnel from entering areas that are too dangerous or where the fire is rapidly spreading, thereby improving rescue efficiency and safety. In complex fire scenes, rescue tasks for multiple areas can be generated, and each task can be carried out in coordination to ensure the orderly conduct of rescue operations. According to the changes in the fire scene, various types of fire resources (such as fire extinguishers, fire trucks, personnel, etc.) are dynamically allocated to ensure that resources are used most effectively. As the situation at the fire scene changes, the allocation of resources can be flexibly adjusted to ensure that rescue forces can cover the most needed areas at different stages. Real-time rescue monitoring data can provide key information such as the use of fire resources and changes in the fire scene, helping commanders to respond quickly. Using AI analysis algorithms, the current resource allocation is optimized based on real-time data, and resource allocation is adjusted to adapt to the latest dynamics at the fire scene. Through intelligent decision-making, it is possible to avoid waste of resources or unreasonable allocation due to human misjudgment, and ensure that each resource is used as efficiently as possible. With the continuous update of fire scene information, the resource allocation optimization module can continuously adjust the optimization strategy according to the actual situation to ensure the efficiency and flexibility of the rescue process.

[0037] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0038] The above is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A fire rescue intelligent management method based on a multimodal AI large model, characterized in that: The following steps are involved: Step S1: Acquire real-time environmental monitoring data of the fire scene; Analyze environmental parameters of real-time environmental monitoring data at the fire scene and predict gas change trends to generate on-site gas parameter change trends; Step S2: Acquire a thermal imaging image of the fire scene; perform visual recognition of temperature distribution and calculation of temperature change rate of consecutive frames based on the thermal imaging image of the fire scene, thereby generating a temperature change rate of the fire source area; Step S3: Predict the fire intensity trend at multiple points in time according to the temperature change rate of the fire source area and the change trend of the on-site gas parameters, thereby generating a multi-point fire intensity trend prediction graph; Step S4: Identify the area to be rescued based on the thermal imaging image of the fire scene; Based on the multi-time point fire trend prediction map, the optimal rescue route is analyzed for each area to be rescued, and multiple regional rescue tasks are generated; Step S5: Identify firefighting resources at the fire scene; Dynamically allocate resources to multiple regional rescue tasks based on fire scene firefighting resources, conduct real-time rescue monitoring, and obtain real-time rescue monitoring data; Step S6: Extract instant feedback information and optimize intelligent resource allocation based on real-time rescue monitoring data, thereby building an intelligent fire rescue optimization strategy.

2. The fire rescue intelligent management method based on multimodal AI big model according to claim 1 is characterized in that: The specific steps of step S1 are: Step S11: acquiring real-time environmental monitoring data of the fire scene based on sensors; Step S12: performing environmental parameter analysis on the real-time environmental monitoring data of the fire scene to generate real-time parameter features of the fire scene; Step S13: Analyze gas composition information according to the real-time parameter characteristics of the fire scene to extract environmental gas composition information; Step S14: Analyze the change of the ambient gas composition information to obtain the characteristics of the change of the gas composition; Step S15: performing multi-dimensional gas concentration calculation according to the real-time parameter characteristics of the fire scene to generate multiple gas concentration time series curves; Step S16: Predicting the gas change trend based on the gas composition change characteristics and multiple gas concentration time series curves to generate the on-site gas parameter change trend.

3. The fire rescue intelligent management method based on multimodal AI big model according to claim 1 is characterized in that: The specific steps of step S2 are: Step S21: Acquire a thermal imaging image of the fire scene based on the drone; Step S22: remapping the pixel grayscale values ​​of the fire scene thermal imaging image to construct a brightness optimized thermal imaging image; Step S23: performing visual recognition of temperature distribution on the brightness optimized thermal imaging image, thereby generating an on-site temperature distribution field; Step S24: accurately identify hot spots in the on-site temperature distribution field and mark the on-site fire source points; Step S25: performing fire source spatial positioning calculation on the on-site fire source point to generate each fire source spatial coordinate; Step S26: Calculate the temperature change rate of consecutive frames according to each fire source spatial coordinate, so as to generate the temperature change rate of the fire source area.

4. The fire rescue intelligent management method based on multimodal AI big model according to claim 3 is characterized in that: The specific steps of step S22 are: Perform image noise detection on thermal imaging images of fire scenes and mark abnormal image noise points; Adaptively filter abnormal noise points in the image to generate a filtered and denoised thermal imaging image; Calculate the grayscale histogram distribution of the filtered and denoised thermal imaging image to obtain the grayscale histogram distribution value; Performing nonlinear grayscale range stretching on the grayscale histogram distribution value to obtain grayscale stretching parameters; The grayscale value of the filtered and denoised thermal imaging image is remapped pixel by pixel based on the grayscale stretching parameter to construct a brightness optimized thermal imaging image.

5. The fire rescue intelligent management method based on multimodal AI big model according to claim 1 is characterized in that: The specific steps of step S3 are: Step S31: Evolving the fire spread path of the on-site fire source point to obtain the fire spread path; Step S32: fitting the fire spread distribution according to the temperature change rate of the fire source area and the fire spread path, and constructing a fire spread distribution change diagram; Step S33: performing fire situation evolution mining on the fire spread distribution change graph to obtain the fire situation evolution law; Step S34: Simulate the evolution of fire spread based on the fire situation evolution law and the change trend of on-site gas parameters based on the preset multimodal AI large model to generate fire spread evolution simulation data; Step S35: Perform multi-time point fire trend prediction on the fire spread evolution simulation data, thereby generating a multi-time point fire trend prediction graph.

6. The fire rescue intelligent management method based on multimodal AI big model according to claim 1 is characterized in that: The specific steps of step S4 are: Step S41: Identify the area to be rescued based on the thermal imaging image of the fire scene; Step S42: Detect trapped persons at the points in the area to be rescued, and obtain persons to be rescued in each area; Step S43: performing a regional rescue priority assessment based on the persons to be rescued in each area, thereby obtaining a rescue priority for each area; Step S44: identifying available rescue paths based on the fire scene thermal imaging image, and extracting multiple available rescue routes; Step S45: Analyze the optimal rescue route for each area of ​​multiple available rescue routes according to the multi-time point fire trend prediction map, so as to obtain the optimal rescue route for each area; Step S46: Generate multiple regional rescue tasks according to the rescue priority of each area and the optimal rescue route of each area.

7. The fire rescue intelligent management method based on multimodal AI big model according to claim 1 is characterized in that: The specific steps of step S5 are: Step S51: Identify firefighting resources at the fire scene; perform personnel allocation and equipment status analysis on the firefighting resources at the fire scene to obtain an assessment value of the firefighting and rescue resources at the scene; Step S52: dynamically allocating resources to multiple regional rescue tasks according to the on-site fire rescue resource evaluation value, thereby obtaining dynamic rescue resource allocation data; Step S53: Make rescue decisions based on the dynamic rescue resource allocation data, perform real-time rescue monitoring, and obtain real-time rescue monitoring data.

8. The fire rescue intelligent management method based on multimodal AI big model according to claim 1 is characterized in that: The specific steps of step S6 are: Step S61: extracting instant feedback information based on real-time rescue monitoring data to obtain real-time rescue feedback information; Step S62: identifying emergency situations based on the real-time rescue feedback information and generating emergency situation data; Step S63: positioning the emergency area based on the emergency situation data to obtain emergency situation area positioning information; Step S64: Perform intelligent resource allocation optimization based on the emergency situation area positioning information, thereby constructing an intelligent fire rescue optimization strategy.

9. A fire rescue intelligent management system based on a multimodal AI large model, characterized in that: The method for executing the fire rescue intelligent management method based on the multimodal AI big model as claimed in claim 1 comprises: The gas trend prediction module is used to obtain real-time environmental monitoring data at the fire scene; analyze environmental parameters of the real-time environmental monitoring data at the fire scene, and predict gas change trends to generate on-site gas parameter change trends; The temperature distribution recognition module is used to obtain thermal imaging images of the fire scene; perform visual recognition of temperature distribution and calculation of the temperature change rate of consecutive frames based on the thermal imaging images of the fire scene, thereby generating the temperature change rate of the fire source area; The fire trend prediction module is used to predict the fire trend at multiple points in time according to the temperature change rate of the fire source area and the change trend of the on-site gas parameters, thereby generating a multi-point fire trend prediction graph; The rescue route analysis module is used to identify the points of the area to be rescued based on the thermal imaging images of the fire scene; analyze the optimal rescue route for each area to be rescued based on the multi-time point fire trend prediction map, and generate multiple regional rescue tasks; Dynamic resource allocation module, used to identify fire-fighting resources at the fire scene; dynamically allocate resources to multiple regional rescue tasks according to the fire-fighting resources at the fire scene, and conduct real-time rescue monitoring to obtain real-time rescue monitoring data; The resource allocation optimization module is used to extract instant feedback information and optimize intelligent resource allocation based on real-time rescue monitoring data, thereby building an intelligent fire rescue optimization strategy.

Images