Disaster rescue path planning and mode optimization method and system based on large model

Abstract

The invention relates to the technical field of disaster relief path planning, in particular to a disaster relief path planning and mode optimization method and system based on a large model, and the method comprises the following steps: collecting and preprocessing data; constructing a prediction model; planning and optimizing a path; a decision support system; real-time adjustment and feedback are carried out; the method has the beneficial effects that the disaster condition and the influence thereof can be quickly analyzed by using big data and a machine learning technology, so that the time required by traditional rescue path planning is greatly shortened, and the emergency response speed is improved. Within golden 72 hours of post-disaster rescue, each second is crucial. The system can provide an optimal rescue path and a resource allocation scheme in an extremely short time, help rescue workers to quickly arrive at a disaster area, and save more lives.

Description

Technical Field

[0001] The present invention relates to the technical field of disaster relief rescue path planning, and specifically provides a method and system for optimizing disaster relief rescue path planning and methods based on a large model. Background Art

[0002] Limitations of traditional disaster relief rescue path planning and method optimization:

[0003] Difficulties in information acquisition and integration: Traditional disaster relief rescue relies on single data sources such as manual reporting and satellite remote sensing, which have problems such as information lag, limited coverage, and inconsistent data formats, making it difficult to comprehensively and timely grasp the dynamics of the disaster area in real time. There is a lack of an effective integration mechanism for data from different sources (such as meteorology, traffic, social media), resulting in information silos and affecting the accuracy of decision-making.

[0004] Insufficient disaster trend prediction ability: Traditional methods rely on historical experience or simple statistical models and are difficult to capture the complex evolution laws of disasters (such as secondary disaster chain reactions and dynamic changes in resource requirements). There is a lack of accurate prediction of the disaster impact range and duration, leading to unreasonable allocation of rescue resources and delaying the best rescue opportunity.

[0005] Low path planning efficiency: Traditional path planning relies on static maps and cannot respond in real time to changes in road conditions (such as road damage and traffic control), resulting in detours and congestion of rescue vehicles and reducing rescue efficiency. There is a lack of multi-objective optimization ability (such as time, cost, safety), and it is difficult to generate the optimal path under complex constraints (such as limited resources and prioritizing the rescue of high-risk areas).

[0006] The decision support system has a single function: Traditional decision support systems are mostly based on rule bases or simple models and lack intelligent analysis capabilities, making it difficult to handle complex and dynamic disaster relief scenarios. There is a lack of a visual interface and simulation function, and it is difficult for decision-makers to intuitively understand the disaster situation and evaluate the effectiveness of the plan, resulting in a decline in decision-making quality.

[0007] The feedback mechanism and dynamic adjustment are lagging: Traditional systems lack a real-time data monitoring and feedback mechanism and cannot timely perceive changes in the disaster area (such as new disaster points and resource exhaustion), resulting in a disconnect between rescue strategies and actual needs. Dynamic adjustment relies on manual intervention, with a slow response speed and difficulty in adapting to the rapidly changing disaster relief environment. Summary of the Invention

[0008] The purpose of the present invention is to provide a method and system for optimizing disaster relief rescue path planning and methods based on a large model to solve the problems raised in the above background art.

[0009] To achieve the above purpose, the present invention provides the following technical solution: A method for optimizing disaster relief rescue path planning and methods based on a large model, including the following steps:

[0010] (1) Data collection and preprocessing;

[0011] (2) Construction of prediction model;

[0012] (3) Path planning and optimization;

[0013] (4) Decision support system;

[0014] (5) Real-time adjustment and feedback.

[0015] Preferably, step (1) specifically includes the following steps:

[0016] Multi-source data collection: Collect data related to disasters and rescue from multiple channels, including but not limited to satellite images, drone reconnaissance, ground sensor networks, meteorological station data, social media information, and reports from government and rescue agencies; these data provide rich inputs for subsequent analysis;

[0017] Data cleaning and integration: Clean the collected data to remove noise and irrelevant information, ensuring data accuracy and consistency. Integrate data from different sources to form a unified data

[0018] Data preprocessing: Preprocess the data, including format conversion, normalization, and feature extraction, to meet the requirements of subsequent modeling and analysis.

[0019] Preferably, step (2) specifically includes the following steps:

[0020] Historical data analysis: Use historical disaster data and rescue records to analyze the occurrence patterns, development trends of disasters, and influencing factors of rescue effects. Through statistical analysis and machine learning algorithms, discover the patterns and correlations hidden in the data;

[0021] Disaster trend prediction: Based on the results of historical data analysis and combined with the current disaster situation, construct a prediction model to estimate the development trend and impact scope of the disaster;

[0022] Risk assessment: Conduct risk assessment on the predicted disaster trends to determine the risk levels that different regions and populations may face.

[0023] Preferably, step (3) specifically includes the following steps:

[0024] Application of geographic information system: Use GIS technology to combine the geographical information of the disaster area with the location and quantity information of rescue resources to form a detailed geographical database; through GIS analysis, identify the traffic arteries, obstacles, and potential dangerous areas in the disaster area, providing a basis for path planning;

[0025] Optimal path search: Use graph theory algorithms to search for the optimal path from the rescue starting point to the end point in the geographical database, considering factors such as distance, travel time, road conditions, and traffic restrictions to ensure the feasibility and efficiency of the path;

[0026] Optimization of resource allocation: According to the results of path planning and the location and quantity information of rescue resources, optimize the rescue resource allocation plan to ensure that rescue supplies and personnel are prioritized to be sent to the places where they are most needed, and improve the utilization efficiency of resources;

[0027] Dynamic adjustment strategy: During the rescue process, dynamically adjust the path planning and resource allocation plans based on real-time data and information to ensure that the rescue operation is always consistent with the actual situation and improve the flexibility and adaptability of the rescue.

[0028] Preferably, step (4) specifically includes the following steps: Visual interface design: Develop a user-friendly visual interface to display the path planning results, resource allocation plans, and disaster trend information. Decision-makers can understand the disaster situation and rescue situation through intuitive charts, maps, and data tables, and thus make more informed decisions; Simulation and emulation: Provide simulation and emulation functions to allow decision-makers to test different rescue plans and strategies in a virtual environment, which helps to evaluate the effects and potential risks of various plans and provides more options and bases for decision-makers; Intelligent advice and auxiliary decision-making: Based on the prediction model and the results of path planning, provide intelligent advice and auxiliary decision-making support for decision-makers;

[0029] Step (5) specifically includes the following steps: Real-time data monitoring: During the rescue process, the system monitors the changes in the disaster area and the progress of the rescue operation in real time, collects real-time data through sensor networks, drone reconnaissance means, and updates the system database in a timely manner; Dynamic path adjustment: According to real-time data and information, dynamically adjust the rescue path to adapt to new situations and needs; Establishment of a feedback mechanism: Establish an effective feedback mechanism to allow rescue personnel and affected people to report the situation and needs on the spot. The system adjusts the rescue strategy and resource allocation plan in a timely manner according to the feedback information to ensure the pertinence and effectiveness of the rescue operation.

[0030] A system for a disaster relief rescue path planning and method optimization method based on a large model, including:

[0031] Data collection and preprocessing module, used to collect data related to disasters and rescues from multiple channels, clean, integrate, and preprocess the collected data to meet the subsequent modeling and analysis requirements;

[0032] Prediction model construction module, used to construct a prediction model based on historical data and the current disaster situation for disaster trend prediction and risk assessment;

[0033] Path planning and optimization module, which is used to plan and optimize rescue paths and optimize the allocation of rescue resources by combining geographic information system technology;

[0034] Decision support system module, used to provide decision makers with intuitive disaster and rescue situation display, simulation and emulation functions, as well as intelligent suggestions and auxiliary decision support;

[0035] The real-time adjustment and feedback module is used to monitor changes in the disaster area and the progress of rescue operations in real time during the rescue process, dynamically adjust rescue routes and resource allocation plans, and establish a feedback mechanism.

[0036] Preferably, the data collection and preprocessing module specifically includes:

[0037] A multi-source data collection unit to gather disaster and relief-related data from satellite imagery, drone reconnaissance, ground sensor networks, weather station data, social media information, and reports from government and relief agencies;

[0038] Data cleaning and integration unit, used to clean the collected data, remove noise and irrelevant information, ensure data accuracy and consistency, and integrate data from different sources to form a unified data set;

[0039] The data preprocessing unit is used to perform format conversion, normalization, and feature extraction preprocessing operations on the integrated data to meet subsequent modeling and analysis requirements.

[0040] Preferably, the prediction model building module specifically includes:

[0041] The historical data analysis unit is used to use historical disaster data and rescue records to analyze the occurrence patterns and development trends of disasters and the factors affecting rescue effectiveness through statistical analysis and machine learning algorithms, and to discover the patterns and associations hidden in the data;

[0042] Disaster trend prediction unit, which is used to build a prediction model based on the results of historical data analysis and the current disaster situation to estimate the development trend and impact range of disasters;

[0043] The risk assessment unit is used to conduct risk assessments on predicted disaster trends and determine the risk levels that different regions and populations may face.

[0044] Preferably, the path planning and optimization module specifically includes:

[0045] A Geographic Information System (GIS) application unit that uses GIS technology to combine the geographical information of the disaster area with the location and quantity information of rescue resources, forming a detailed geographical database. Through GIS analysis, it identifies the main traffic routes, obstacles, and potential danger areas in the disaster area, providing a basis for route planning.

[0046] An optimal path search unit that uses graph theory algorithms to search for the optimal path from the rescue starting point to the end point in the geographical database, considering distance, travel time, road conditions, and traffic restrictions to ensure the feasibility and efficiency of the path.

[0047] A resource allocation optimization unit that optimizes the rescue resource allocation plan based on the results of route planning and the location and quantity information of rescue resources, ensuring that rescue supplies and personnel are preferentially sent to the places where they are most needed and improving the utilization efficiency of resources.

[0048] A dynamic adjustment strategy unit that dynamically adjusts the route planning and resource allocation plan during the rescue process based on real-time data and information, ensuring that the rescue operation always conforms to the actual situation and improving the flexibility and adaptability of the rescue.

[0049] Preferably, the decision support system module specifically includes:

[0050] A visualization interface design unit that develops a user-friendly visualization interface to display the route planning results, resource allocation plan, and disaster trend information. Decision-makers can understand the disaster situation and rescue status through intuitive charts, maps, and data tables, thereby making more informed decisions.

[0051] A simulation and emulation unit that provides simulation and emulation functions, allowing decision-makers to test different rescue plans and strategies in a virtual environment, evaluate the effects and potential risks of various plans, and provide more options and bases for decision-makers.

[0052] An intelligent advice and auxiliary decision-making unit that provides intelligent advice and auxiliary decision-making support for decision-makers based on prediction models and the results of route planning.

[0053] The real-time adjustment and feedback module specifically includes:

[0054] A real-time data monitoring unit that, during the rescue process, the system monitors the changes in the disaster area and the progress of the rescue operation in real-time, collects real-time data through sensor networks and drone reconnaissance means, and updates the system database in a timely manner.

[0055] A dynamic route adjustment unit that dynamically adjusts the rescue route according to real-time data and information to adapt to new situations and requirements.

[0056] A feedback mechanism establishment unit is used to establish an effective feedback mechanism, allowing rescue workers and affected people to report the situation and needs at the scene. The system adjusts the rescue strategy and resource allocation plan in a timely manner according to the feedback information, ensuring the pertinence and effectiveness of the rescue operation.

[0057] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0058] The method and system for optimizing the disaster relief rescue path planning and method based on a large model proposed by the present invention utilize big data and machine learning technologies to quickly analyze the disaster situation and its impacts, thereby greatly shortening the time required for traditional rescue path planning and improving the speed of emergency response. In the golden 72 hours after a disaster, every second is crucial. The system can provide the optimal rescue path and resource allocation plan within an extremely short time, helping rescue workers quickly reach the disaster area and save more lives. The system integrates multiple technologies such as geographic information system (GIS), real-time data analysis, machine learning, and prediction models, providing comprehensive decision-making support for decision-makers. This helps reduce mistakes in subjective judgment and improve the success rate of rescue operations. It enables decision-makers to more intuitively understand the disaster situation and rescue needs based on the visual data and analysis reports provided by the system, and thus make more scientific and reasonable decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 It is the flowchart of fine-tuning the large model of the present invention;

[0060] Figure 2 It is the functional structure diagram of the present invention;

[0061] Figure 3 It is the flowchart of the method of the present invention. SPECIFIC EMBODIMENTS

[0062] In order to clearly and completely describe the objectives, technical solutions of the present invention, and make the advantages more clear, the following further details the embodiments of the present invention with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are part of the embodiments of the present invention, rather than all of the embodiments. They are merely used to explain the embodiments of the present invention and are not used to limit the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of the present invention.

[0063] Embodiment 1. Please refer to Figures 1 to 3 , the present invention provides a technical solution: A method for optimizing the disaster relief rescue path planning and method based on a large model, including the following steps:

[0064] (1) Data collection and preprocessing; specifically including the following steps

[0065] 1) Multi-source data collection: Collect data related to disasters and rescue from multiple channels, including but not limited to satellite images, drone reconnaissance, ground sensor networks, meteorological station data, social media information, and reports from government and rescue agencies. This data provides rich input for subsequent analysis. For example, satellite images can provide a wide-area view of the disaster area, helping to identify the scope and severity of the affected areas; social media information can reflect the needs and situations of the victims in real time.

[0066] 2) Data cleaning and integration: Clean the collected data to remove noise and irrelevant information, ensuring data accuracy and consistency. Integrate data from different sources to form a unified data set for subsequent analysis and processing.

[0067] 3) Data preprocessing: Preprocess the data, including format conversion, normalization, feature extraction, etc., to meet the requirements of subsequent modeling and analysis. For example, convert satellite images into a digital elevation model (DEM) for analysis, or extract keywords and sentiment tendencies from social media information.

[0068] (2) Build a prediction model; specifically including the following steps

[0069] 1) Historical data analysis: Use historical disaster data and rescue records to analyze the occurrence patterns, development trends of disasters, and influencing factors of rescue effects. Through statistical analysis and machine learning algorithms, discover the patterns and correlations hidden in the data.

[0070] 2) Disaster trend prediction: Based on the results of historical data analysis and combined with the current situation of the disaster, build a prediction model to estimate the development trend and impact scope of the disaster. For example, use time series analysis or deep learning models to predict weather changes, water level rises, or fire spread in the disaster area in the next period of time.

[0071] 3) Risk assessment: Conduct a risk assessment on the predicted disaster trends to determine the risk levels that different regions and populations may face. This helps to formulate targeted rescue measures and plans in advance and reduce the losses caused by disasters.

[0072] (3) Route planning and optimization; specifically including the following steps

[0073] 1) Application of Geographic Information System (GIS): Use GIS technology to combine the geographical information of the disaster area with information such as the location and quantity of rescue resources to form a detailed geographical database. Through GIS analysis, identify the main traffic roads, obstacles, and potential dangerous areas in the disaster area, providing a basis for route planning.

[0074] 2) Optimal path search: Use graph theory algorithms (such as Dijkstra algorithm, A* algorithm, etc.) to search for the optimal path from the rescue starting point to the end point in the geographic database. Consider factors including distance, travel time, road conditions, traffic restrictions, etc. to ensure the feasibility and efficiency of the path.

[0075] 3) Optimization of resource allocation: According to the results of path planning and information such as the location and quantity of rescue resources, optimize the rescue resource allocation plan. Ensure that rescue supplies and personnel can be preferentially sent to the places where they are most needed, and improve the utilization efficiency of resources.

[0076] 4) Dynamic adjustment strategy: During the rescue process, dynamically adjust the path planning and resource allocation plan according to real-time data and information (such as changes in road conditions, new development of disasters, etc.). This ensures that the rescue operation is always consistent with the actual situation and improves the flexibility and adaptability of the rescue.

[0077] (4) Decision support system; specifically includes the following steps

[0078] 1) Visual interface design: Develop a user-friendly visual interface to display information such as path planning results, resource allocation plans, and disaster trends. Decision-makers can understand the disaster situation and rescue situation through intuitive charts, maps, and data tables, so as to make more informed decisions.

[0079] 2) Simulation and emulation: Provide simulation and emulation functions, allowing decision-makers to test different rescue plans and strategies in a virtual environment. This helps to evaluate the effects and potential risks of various plans and provides more choices and bases for decision-makers.

[0080] 3) Intelligent advice and auxiliary decision-making: Based on the prediction model and the results of path planning, provide intelligent advice and auxiliary decision-making support for decision-makers. For example, when the demand in a certain area increases or the traffic condition deteriorates, the system can automatically propose suggestions for adjusting the rescue path and resource allocation.

[0081] (5) Real-time adjustment and feedback; specifically includes the following steps

[0082] 1) Real-time data monitoring: During the rescue process, the system monitors the changes in the disaster area and the progress of the rescue operation in real time. Collect real-time data through sensor networks, drone reconnaissance, etc. and update the system's database in a timely manner.

[0083] 2) Dynamic path adjustment: According to real-time data and information, dynamically adjust the rescue path to adapt to new situations and requirements. For example, when a certain road is impassable due to landslides or floods, the system can quickly re-plan other feasible paths.

[0084] 3) Establishment of feedback mechanism: Establish an effective feedback mechanism to allow rescue workers and affected people to report the situation and needs at the scene. The system adjusts rescue strategies and resource allocation plans in a timely manner based on the feedback information to ensure the pertinence and effectiveness of rescue operations.

[0085] Embodiment 2, based on Embodiment 1, proposes a system for the disaster relief rescue path planning and method optimization method according to Claim 5, including:

[0086] Data collection and preprocessing module, which is used to collect data related to disasters and rescues from multiple channels, clean, integrate and preprocess the collected data to meet the subsequent modeling and analysis requirements; specifically including: multi-source data collection unit, which is used to collect data related to disasters and rescues from multiple channels such as satellite images, drone reconnaissance, ground sensor networks, weather station data, social media information, and reports from government and rescue agencies; data cleaning and integration unit, which is used to clean the collected data, remove noise and irrelevant information, ensure the accuracy and consistency of the data, and integrate data from different sources to form a unified data set; data preprocessing unit, which is used to perform format conversion, normalization, and feature extraction preprocessing operations on the integrated data to meet the subsequent modeling and analysis requirements.

[0087] Prediction model construction module, which is used to construct a prediction model based on historical data and the current disaster situation for disaster trend prediction and risk assessment; specifically including: historical data analysis unit, which is used to analyze the occurrence patterns, development trends, and influencing factors of rescue effects of disasters through statistical analysis and machine learning algorithms using historical disaster data and rescue records, and to discover patterns and associations hidden in the data; disaster trend prediction unit, which is used to construct a prediction model based on the results of historical data analysis and in combination with the current disaster situation to estimate the development trend and impact range of the disaster; risk assessment unit, which is used to conduct risk assessment on the predicted disaster trends to determine the risk levels that different regions and populations may face.

[0088] The path planning and optimization module is used to plan and optimize the rescue path by combining geographic information system technology and optimize the allocation plan of rescue resources; specifically including: a geographic information system application unit, which is used to combine the geographic information of the disaster area with the location and quantity information of rescue resources by using GIS technology to form a detailed geographic database, and through GIS analysis, identify the traffic arteries, obstacles and potential dangerous areas in the disaster area to provide a basis for path planning; an optimal path search unit, which is used to search for the optimal path from the rescue starting point to the end point in the geographic database by using graph theory algorithms, considering factors such as distance, travel time, road conditions, and traffic restrictions to ensure the feasibility and efficiency of the path; a resource allocation optimization unit, which is used to optimize the allocation plan of rescue resources according to the results of path planning and the location and quantity information of rescue resources to ensure that rescue supplies and personnel are sent to the places where they are most needed first and improve the utilization efficiency of resources;

[0089] The dynamic adjustment strategy unit is used to dynamically adjust the path planning and resource allocation plan according to real-time data and information during the rescue process to ensure that the rescue operation is always consistent with the actual situation and improve the flexibility and adaptability of the rescue.

[0090] The decision support system module is used to provide intuitive disaster situation and rescue situation display, simulation and emulation functions as well as intelligent suggestions and auxiliary decision support for decision makers; specifically including: a visualization interface design unit, which is used to develop a user-friendly visualization interface to display the results of path planning, resource allocation plan and disaster trend information. Decision makers can understand the disaster situation and rescue situation through intuitive charts, maps and data tables to make more informed decisions; a simulation and emulation unit, which is used to provide simulation and emulation functions, allowing decision makers to test different rescue plans and strategies in a virtual environment, evaluate the effects and potential risks of various plans, and provide more choices and bases for decision makers; an intelligent suggestion and auxiliary decision unit, which is used to provide intelligent suggestions and auxiliary decision support for decision makers based on the prediction model and the results of path planning.

[0091] The real-time adjustment and feedback module is used to monitor the changes in the disaster area and the progress of the rescue operation in real time during the rescue process, dynamically adjust the rescue path and resource allocation plan, and establish a feedback mechanism; specifically including: a real-time data monitoring unit, which is used to monitor the changes in the disaster area and the progress of the rescue operation in real time during the rescue process, collect real-time data through sensor networks and drone reconnaissance means, and update the system database in a timely manner; a dynamic path adjustment unit, which is used to dynamically adjust the rescue path according to real-time data and information to adapt to new situations and needs; a feedback mechanism establishment unit, which is used to establish an effective feedback mechanism, allowing rescue personnel and affected people to report the situation and needs on the spot, and the system adjusts the rescue strategy and resource allocation plan in a timely manner according to the feedback information to ensure the pertinence and effectiveness of the rescue operation.

[0092] Although embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A large-scale model-based disaster relief and rescue path planning and mode optimization method, characterized by: The following steps are involved: (1) Data collection and preprocessing; (2) Build a prediction model; (3) Path planning and optimization; (4) Decision support system; (5) Real-time adjustment and feedback.

2. The method for disaster relief route planning and mode optimization based on a large model according to claim 1, characterized in that: Step (1) specifically includes the following steps: Multi-source data collection: Collecting disaster and relief-related data from multiple sources, including but not limited to satellite imagery, drone reconnaissance, ground sensor networks, weather station data, social media information, and reports from government and relief agencies; this data provides rich input for subsequent analysis; Data cleaning and integration: Clean the collected data, remove noise and irrelevant information, and ensure the accuracy and consistency of the data. Integrate data from different sources to form a unified data Data preprocessing: Preprocess the data, including format conversion, normalization, and feature extraction, to meet subsequent modeling and analysis requirements.

3. The method for disaster relief route planning and mode optimization based on a large model according to claim 2, characterized in that: Step (2) specifically includes the following steps: Historical data analysis: Utilizing historical disaster data and rescue records, we analyze the patterns and trends of disasters, as well as the factors influencing rescue effectiveness. Through statistical analysis and machine learning algorithms, we can uncover patterns and associations hidden in the data. Disaster trend prediction: Based on the results of historical data analysis and combined with the current disaster situation, a prediction model is constructed to estimate the development trend and impact range of disasters; Risk assessment: Conduct risk assessments on predicted disaster trends to determine the risk levels that different regions and populations may face.

4. The method for disaster relief route planning and mode optimization based on a large model according to claim 3, characterized in that: Step (3) specifically includes the following steps: Geographic Information System Application: Utilizing GIS technology, the geographical information of the disaster area is combined with the location and quantity of rescue resources to form a detailed geographic database. Through GIS analysis, traffic arteries, obstacles, and potential danger zones in the disaster area are identified, providing a basis for route planning. Optimal Path Search: Use graph theory algorithms to search for the optimal path from the rescue starting point to the destination in the geographic database, taking into account factors such as distance, travel time, road conditions, and traffic restrictions to ensure the feasibility and efficiency of the path; Resource allocation optimization: Based on the results of path planning and the location and quantity of rescue resources, the rescue resource allocation plan is optimized to ensure that rescue supplies and personnel are sent to the places where they are most needed, thereby improving resource utilization efficiency; Dynamically adjust strategies: During the rescue process, path planning and resource allocation plans are dynamically adjusted based on real-time data and information to ensure that rescue operations are always consistent with actual conditions and improve the flexibility and adaptability of the rescue.

5. The method for disaster relief route planning and mode optimization based on a large model according to claim 4, characterized in that: Step (4) specifically includes the following steps: Visual interface design: developing a user-friendly visual interface to display path planning results, resource allocation plans, and disaster trend information. Decision makers can understand the disaster situation and rescue status through intuitive charts, maps, and data tables, thereby making more informed decisions; Simulation and simulation: providing simulation and simulation functions, allowing decision makers to test different rescue plans and strategies in a virtual environment, helping to evaluate the effectiveness and potential risks of various plans, and providing decision makers with more options and basis; Intelligent suggestions and auxiliary decision-making: providing intelligent suggestions and auxiliary decision-making support to decision makers based on the prediction model and path planning results; Step (5) specifically includes the following steps: real-time data monitoring: during the rescue process, the system monitors the changes in the disaster area and the progress of the rescue operation in real time, collects real-time data through sensor networks and drone reconnaissance, and updates the system database in a timely manner; dynamic path adjustment: based on real-time data and information, the rescue path is dynamically adjusted to adapt to new situations and needs; feedback mechanism establishment: an effective feedback mechanism is established to allow rescue personnel and disaster-stricken people to report on-site conditions and needs. The system adjusts the rescue strategy and resource allocation plan in a timely manner based on the feedback information to ensure the pertinence and effectiveness of the rescue operation.

6. A system for the large-scale model-based disaster relief and rescue path planning and mode optimization method according to claim 5, characterized in that: include: The data collection and preprocessing module is used to collect disaster and rescue-related data from multiple channels, and clean, integrate and preprocess the collected data to meet subsequent modeling and analysis needs; The prediction model building module is used to build a prediction model based on historical data and current disaster conditions to predict disaster trends and conduct risk assessments; Path planning and optimization module, which is used to plan and optimize rescue paths and optimize the allocation of rescue resources by combining geographic information system technology; Decision support system module, used to provide decision makers with intuitive disaster and rescue situation display, simulation and emulation functions, as well as intelligent suggestions and auxiliary decision support; The real-time adjustment and feedback module is used to monitor changes in the disaster area and the progress of rescue operations in real time during the rescue process, dynamically adjust rescue routes and resource allocation plans, and establish a feedback mechanism.

7. A system according to claim 6, characterized in that: The data collection and preprocessing module specifically includes: A multi-source data collection unit to gather disaster and relief-related data from satellite imagery, drone reconnaissance, ground sensor networks, weather station data, social media information, and reports from government and relief agencies; Data cleaning and integration unit, used to clean the collected data, remove noise and irrelevant information, ensure data accuracy and consistency, and integrate data from different sources to form a unified data set; The data preprocessing unit is used to perform format conversion, normalization, and feature extraction preprocessing operations on the integrated data to meet subsequent modeling and analysis requirements.

8. A system according to claim 7, characterized in that: The prediction model building module specifically includes: The historical data analysis unit is used to use historical disaster data and rescue records to analyze the occurrence patterns and development trends of disasters and the factors affecting rescue effectiveness through statistical analysis and machine learning algorithms, and to discover the patterns and associations hidden in the data; Disaster trend prediction unit, which is used to build a prediction model based on the results of historical data analysis and the current disaster situation to estimate the development trend and impact range of disasters; The risk assessment unit is used to conduct risk assessments on predicted disaster trends and determine the risk levels that different regions and populations may face.

9. A system according to claim 8, characterized in that: The path planning and optimization module specifically includes: The Geographic Information System Application Unit uses GIS technology to combine the geographical information of the disaster area with the location and quantity of rescue resources to form a detailed geographic database. GIS analysis is used to identify traffic arteries, obstacles, and potential danger areas in the disaster area, providing a basis for route planning. The optimal path search unit is used to use graph theory algorithms to search for the optimal path from the rescue starting point to the end point in the geographic database, taking into account distance, travel time, road conditions, and traffic restrictions to ensure the feasibility and efficiency of the path; The resource allocation optimization unit is used to optimize the allocation of rescue resources based on the results of path planning and the location and quantity of rescue resources, ensuring that rescue materials and personnel are given priority and sent to where they are most needed, thereby improving resource utilization efficiency; The dynamic adjustment strategy unit is used to dynamically adjust the path planning and resource allocation plan according to real-time data and information during the rescue process, ensuring that the rescue operation is always consistent with the actual situation and improving the flexibility and adaptability of the rescue.

10. A system according to claim 9, characterized in that: The decision support system modules specifically include: The visualization interface design unit is used to develop user-friendly visualization interfaces to display path planning results, resource allocation plans, and disaster trend information. Decision makers can understand the disaster situation and rescue status through intuitive charts, maps, and data tables, thereby making more informed decisions. The simulation and emulation unit is used to provide simulation and emulation functions, allowing decision makers to test different rescue plans and strategies in a virtual environment, evaluate the effectiveness and potential risks of various plans, and provide decision makers with more options and basis; Intelligent suggestion and decision support unit, which provides intelligent suggestions and decision support to decision makers based on the prediction model and path planning results; The real-time adjustment and feedback module specifically includes: The real-time data monitoring unit is used to monitor the changes in the disaster area and the progress of the rescue operation in real time during the rescue process. It collects real-time data through sensor networks and drone reconnaissance, and promptly updates the system database. Dynamic path adjustment unit, used to dynamically adjust the rescue path to adapt to new situations and needs based on real-time data and information; The feedback mechanism establishment unit is used to establish an effective feedback mechanism, allowing rescue workers and disaster-stricken people to report on-site conditions and needs. The system adjusts rescue strategies and resource allocation plans in a timely manner based on feedback information to ensure the targetedness and effectiveness of rescue operations.

Images