Disaster-based emergency refuge evacuation method based on spatial analysis algorithm

Abstract

The invention discloses a disaster-based emergency refuge evacuation method based on a spatial analysis algorithm, and belongs to the technical field of evacuation path planning. Establishing a road structure damage prediction model; determining an affected population gathering area and demand needing to be transferred; defining a search range by taking the disaster victim gathering point as a center, and determining a shelter meeting the evacuation demand; generating a spatial topological relation graph; constructing a disaster event dynamic evacuation model; and continuously accessing a base station positioning data flow, and dynamically triggering path re-planning. According to the emergency evacuation path selection scheme designed with multiple disaster types as the background, the complex and changeable multi-disaster type superposition situation can be effectively dealt with, meanwhile, the method is completely suitable for emergency response under the single-disaster type background, evacuation priority grading of the evacuation path is achieved, it is ensured that evacuation personnel can safely reach the evacuation destination, and the evacuation efficiency is improved. Optimization calculation is carried out based on personnel dynamic data, and the dynamic nature and catastrophe adaptability of an evacuation path planning model can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of evacuation route planning, and particularly to a multi-disaster type emergency shelter evacuation method based on a spatial analysis algorithm. Background Art

[0002] While the urban system is suffering from the direct damage of earthquake disasters, it is often accompanied by secondary disasters such as urban waterlogging caused by the rupture of underground pipe networks and landslides and mudslides caused by the instability of geological structures. The traditional disaster prevention plans for single disaster types are difficult to meet the actual needs. During the process of organizing the affected people to transfer to emergency shelters, if there is a lack of accurate evacuation route guidance, it may lead to the masses straying into areas threatened by secondary disasters, exacerbating the consequences of the disaster. Therefore, constructing an optimized system for the emergency shelter evacuation routes of the masses for different disaster types has become a key measure to enhance the disaster prevention resilience of cities.

[0003] After retrieval, the Chinese patent with the publication number CN117196128A: An emergency evacuation route planning method, device and electronic device, the technical solution of which Figure 1 is as follows. First, based on the evacuation network, an initial evacuation route is determined. Secondly, real-time environmental information is obtained and it is judged whether the initial route is affected by the disaster, and a feasible route is searched according to the disaster situation. Finally, the initial route is replaced and updated with the feasible route to generate an optimized route.

[0004] The following deficiencies exist in the existing emergency shelter evacuation methods: Most of the existing evacuation route planning is limited to a single disaster scenario, without considering dynamic factors such as road failure and secondary risks caused by the superposition of multiple disasters, and overly relies on the shortest path or time optimization, ignoring the real-time changes in the road passing capacity threshold, congestion probability and environmental risks during the evacuation process; Most of the existing evacuation route planning adopts a point-to-point mode, without considering the upper limit of the capacity of the emergency shelter. Continuing to evacuate when overloaded is likely to cause potential safety hazards, and it is easy to lead to low efficiency and unbalanced resource allocation in large-scale disasters; In the existing technology, the evacuation route planning is carried out based on the simulation and analysis of historical data or static data. When a disaster occurs, the road conditions often change rapidly. The lag of static data makes it difficult to adjust the planning scheme in time, affecting the evacuation efficiency and safety.

[0005] In view of the above problems, a multi-disaster type emergency shelter evacuation method based on a spatial analysis algorithm is proposed. Summary of the Invention

[0006] The purpose of the present invention is to provide a multi-disaster type emergency shelter evacuation method based on a spatial analysis algorithm. By using this device for work, the problems in the above background are solved.

[0007] To achieve the above purpose, the present invention provides the following technical solution: A multi-disaster type emergency shelter evacuation method based on a spatial analysis algorithm, including the following steps:

[0008] S1: Determine the types of disasters and their interaction patterns, obtain disaster characteristic parameters, quantify the comprehensive risk level of single disasters or multiple disasters based on geographic information system spatial analysis, and generate dynamic risk distribution maps;

[0009] S2: Collect the first-level index parameters such as geological structure, road grade, construction age, and seismic resistance level, use the hierarchical analysis method to determine the weight coefficients of the second-level index parameters, establish a road structure damage prediction model, obtain the road structure damage degree score, and output the road residual capacity coefficient;

[0010] S3: Integrate mobile phone and base station data to monitor population distribution and migration in real time, identify the affected population concentration areas and scale, divide evacuation priorities based on risk maps, and determine the affected population concentration areas and needs that need to be relocated;

[0011] S4: Define the search area with the gathering point of the victims as the center, screen the surrounding emergency shelters, match the number of victims through capacity demand analysis, and finally determine the shelters that meet the evacuation needs;

[0012] S5: Generate a spatial topology relationship diagram using a spatial topology analysis algorithm based on the preset vector geographic data and the evacuation road distribution of the emergency shelter;

[0013] S6: Based on the spatial topological relationship diagram, the real-time road capacity data, the disaster risk probability and the shelter capacity are introduced, and a dynamic evacuation model of disaster events is constructed using a dynamic evacuation model of five-fold costs;

[0014] S7: Continuously access base station positioning data streams, monitor actual evacuation progress and population distribution changes, and dynamically trigger path replanning.

[0015] Furthermore, the comprehensive hazard level calculation method described in step S1 is: integrating historical disaster data and real-time crowd intelligence perception information, combining the hierarchical analysis method to quantify the weights of the three major indicators of "disaster hazard-vulnerability of disaster-bearing bodies-disaster reduction capabilities", and constructing a multi-disaster coupling evaluation model. Based on the spatial analysis technology of the geographic information system, the disaster-stricken area is rasterized, and the disaster site data, geographic environment parameters and dynamic disaster indicators are superimposed to generate a disaster hazard zoning map, and finally output the comprehensive regional hazard level.

[0016] Furthermore, the secondary indicators corresponding to the geological structure in step S2 are rock type and terrain characteristics, the secondary indicators corresponding to the road grade are road length, road width, road surface condition and road surface material, the secondary indicator corresponding to the construction age is the construction year, and the secondary indicator corresponding to the seismic resistance grade is the road surface seismic resistance grade.

[0017] Further, the method for constructing the road structure damage prediction model in step S2 is as follows: First, integrate data such as geological structure, road attributes, construction age, and seismic resistance level and perform standardization processing. Then, determine the weights of each index through the analytic hierarchy process. Next, use a graph neural network to extract the node features of the geological structure and the edge features of the road attributes, and combine a time series model to process the dynamic change features of the construction age and seismic resistance level. Finally, fuse the weighted features to construct a road structure damage prediction model, and output the damage score and the residual traffic capacity coefficient.

[0018] Further, the calculation formula for the residual traffic capacity coefficient of the road in step S2 is: Residual traffic capacity coefficient of the road = 1 - Degree of road structure damage / Maximum bearing capacity.

[0019] Further, the method for identifying the disaster-affected population gathering area in step S3 is: Construct a deep learning model, use mobile phone user density data and geospatial information as inputs, accurately classify the population heat distribution. After training and optimization with a large amount of sample data, the model can accurately mark the high-density areas as "disaster-affected population gathering areas".

[0020] Further, the spatial topology relationship graph in step S5 includes network nodes composed of disaster-affected population gathering points, emergency shelters, and intersections in the road network, and edges composed of road segments in the road network. Mark the predicted damaged road segments as disabled edges, and dynamically adjust the edge weights of the damaged road segments according to the residual traffic capacity.

[0021] Further, the method for constructing the disaster event dynamic evacuation model in step S6 is: Take minimizing the evacuation time, minimizing the road disaster risk probability, maximizing the use capacity of the shelter, maximizing the path structure redundancy, and dynamically adapting the weight adjustment as the optimization objectives, and take the road traffic efficiency, disaster risk probability, and shelter capacity limit as the constraint conditions. According to the optimization objectives and constraint conditions, construct a multi-objective function F(X) = min(T(N), R(N), Cc(N), Cr(N), Cy(N)), where N is the total number of evacuees in the multi-objective function, F(X) is the evacuation path optimization objective function, T(N) is the total evacuation time objective function, R(N) is the disaster risk probability objective function, Cc(N) is the evacuation flow capacity objective function (to avoid exceeding the shelter capacity), Cr(N) is the shelter use capacity objective function, and Cy(N) is the path structure redundancy objective function.

[0022] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0023] 1. Incorporate multiple disaster types into the background consideration, comprehensively consider the impact of different disaster types on the evacuation path. The obtained evacuation plan and system are applicable to both single-disaster scenarios and multi-disaster compound situations, and have broad applicability and practicability.

[0024] 2. Taking road capacity, shelter capacity, and path safety risk factors as evacuation road priority ranking indicators, realizing the classification of evacuation priority for evacuation paths, ensuring smooth traffic and road safety during the evacuation process, guaranteeing sufficient resettlement space for evacuees, and greatly improving the evacuation efficiency and safety.

[0025] 3. Considering the prediction of the damage degree of disasters such as earthquakes to the road itself and the impact on passability, multi-objective comprehensive optimization can be given to the evacuation path.

[0026] 4. Using the mobile hotspot data within the evacuation area as the shelter demand data, which can clearly reflect the characteristics of the crowd in the actual situation and provide more accurate data support for the planning of evacuation paths. At the same time, using the personnel positioning data of communication base stations and performing optimization calculations based on the dynamic personnel data can effectively improve the dynamic performance and disaster adaptation of the evacuation path planning model.

[0027] 5. For the system constructed according to the method of the present invention, only by inputting the initial data, the optimal evacuation path plan can be automatically calculated, which can significantly improve the emergency response speed and decision-making efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is a schematic flow chart of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0029] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0030] An emergency shelter evacuation method for different disaster types based on spatial analysis algorithms, comprising the following steps:

[0031] Step 1: Determine the disaster types and their interaction modes, obtain disaster characteristic parameters, including disaster types, danger levels, and intensity indicators, quantify the comprehensive danger level of single or multiple disaster superpositions based on the spatial analysis of geographic information systems, and generate a dynamic risk distribution map;

[0032] Step 2: Collect first-level index parameters such as geological structure, road grade, construction year, and seismic grade, use the analytic hierarchy process to determine the weight coefficients of second-level index parameters, establish a road structure damage prediction model, obtain the score of the road structure damage degree, and output the road residual traffic capacity coefficient;

[0033] Step 3: Integrate mobile phone and base station data to monitor population distribution and migration in real time, identify the gathering areas and scale of affected populations, combine with the risk map to divide the evacuation priorities, and determine the gathering areas and needs of affected populations to be transferred;

[0034] Step 4: Define a search scope centered on the gathering points of affected people, screen the surrounding emergency shelters, match the number of affected people through capacity demand analysis, and finally determine the shelters that meet the evacuation needs. The location allocation can be solved by using the newly built location allocation tool in NetworkAnalyst in ArcGIS. In the model parameter settings, the actual travel distance of the road network is used as the impedance parameter, and the "maximize coverage with capacity constraints" allocation mode is adopted. Set the impedance interruption value to ensure that the path length between the demand point and the facility point does not exceed the service radius threshold. The specific location allocation solving process is as follows:

[0035] (1) Construct a network dataset: Integrate road data and municipal traffic control information to construct a road network dataset containing traffic directions, one-way street restrictions, and dynamic risk attributes;

[0036] (2) Load constraint conditions: Associate the maximum effective evacuation number of facility points and the population statistics of demand points to the attribute table and embed them into the location allocation tool;

[0037] (3) Run the solver: Adopt the "maximize coverage with capacity constraints" mode, use the actual travel distance as the impedance parameter, and generate an allocation plan that maximizes the coverage of the total population through iterative optimization;

[0038] Step 5: Generate a spatial topological relationship diagram by using the spatial topological analysis algorithm based on the preset vector geographic data and the evacuation road distribution of emergency shelters;

[0039] Step 6: Based on the spatial topological relationship diagram, introduce the real-time road capacity data, disaster risk probability, and shelter capacity, and use the dynamic evacuation model with five-fold costs to construct a dynamic evacuation model for disaster events;

[0040] Step 7: Continuously access the base station positioning data stream, monitor the actual evacuation progress and changes in population distribution, and dynamically trigger path replanning.

[0041] The calculation method of the comprehensive disaster risk level in Step 1 is as follows: Integrate historical disaster data and real-time crowd-sourced perception information, combine the analytic hierarchy process to quantify the weights of the three major indicators of "disaster hazard - vulnerability of disaster-bearing bodies - disaster reduction capacity", construct a multi-hazard coupling evaluation model, rasterize the affected area based on the spatial analysis technology of geographic information system, overlay the disaster site data, geographical environment parameters, and dynamic disaster situation indicators, generate a disaster hazard zoning map, and finally output the regional comprehensive disaster risk level.

[0042] Specifically, this calculation model comprehensively considers the multi-hazard risk levels of "earthquake - urban waterlogging", "earthquake - geological disasters", and "earthquake - urban waterlogging - geological disasters". The calculation method for the comprehensive disaster risk level is as follows:

[0043] Obtain historical disaster data of the region, including disaster type, level, location, affected area, number of casualties, etc.;

[0044] Integrate the natural attributes and socio-economic attributes of disasters, and use the analytic hierarchy process to obtain the influencing factors of "disaster hazard - vulnerability of disaster-bearing bodies - disaster reduction and relief capabilities", and further construct a multi-hazard evaluation model;

[0045] Based on crowd-sourced sensing for disaster site data collection, the data includes information such as disaster type, rescue situation at the work site, personnel search and rescue and casualties, on-site evacuation situation, and damage to infrastructure, and collect disaster-related information data and geographical information feedback by the online group;

[0046] From the disaster site information data feedback by the network, select three indicator data representing the disaster situation of the disaster, namely disaster hazard, vulnerability of disaster-bearing bodies, and disaster reduction and relief capabilities. The evaluation process is to divide the affected area into multiple grid cells, and conduct evaluations on disaster hazard, vulnerability of disaster-bearing bodies, and disaster reduction and relief capabilities respectively. The ArcGIS software can be used to overlay the indicator data, conduct spatial analysis, and comprehensively consider the results of the three indicators to generate a disaster hazard zoning map of the affected area;

[0047] Select indicators representing the disaster-affected area according to geographical information, and overlay the geographical information with the disaster hazard zoning map through a geographic information system to obtain the comprehensive disaster risk level of the region. The indicators representing the disaster-affected area refer to natural conditions such as the topography, geological structure, and water system environment of the affected area.

[0048] By clarifying the disaster types of earthquakes and the coupling of earthquakes with other secondary disasters, obtaining the parameter of disaster characteristics, performing network analysis of the disaster-affected area, and quantifying the comprehensive risk level of a single disaster or the superposition of multiple disasters. The emergency evacuation route selection plan designed with multi-hazards as the background can not only effectively respond to the complex and changeable multi-hazard superposition situation, but also be fully applicable to the emergency response in the context of a single disaster.

[0049] The secondary indicators corresponding to the geological structure in step two are rock type and terrain characteristics, the secondary indicators corresponding to the road grade are road length, road width, road surface condition, and road surface material, the secondary indicator corresponding to the construction year is the construction year, and the secondary indicator corresponding to the seismic grade is the road surface seismic grade.

[0050] The construction method of the road structure damage prediction model in Step 2 is as follows: First, integrate data such as geological structure, road attributes, construction age, and seismic resistance level and perform standardization processing. Then, determine the weights of each index through the analytic hierarchy process. Next, use a graph neural network to extract the node features of the geological structure and the edge features of the road attributes, and combine with a time series model to process the dynamic change features of the construction age and seismic resistance level. Finally, fuse the weighted features to construct a road structure damage prediction model, and output the damage score and the residual traffic capacity coefficient.

[0051] The calculation formula for the residual traffic capacity coefficient of the road in Step 2 is: Residual traffic capacity coefficient of the road = 1 - Degree of road structure damage / Maximum bearing capacity.

[0052] Specifically, first collect data on geological structure, road grade, construction age, and seismic resistance level, and perform data standardization and normalization processing. Then, use the analytic hierarchy process to determine the weight coefficients of each secondary index parameter. Then, use parameters such as geological structure, road attributes, and construction age as the input features of the model. Use a graph neural network and a graph convolutional layer to extract the node features from the geological structure data and the edge features from the road attribute data. Use a time series to process parameters such as construction age and seismic resistance level, which can be used as time encoding features, and extract long-term dependence information through a time gating network. Assign the determined weight coefficients to each layer of features to establish a road structure damage prediction model. Finally, by inputting the data of the 4 indexes of geological structure, road attributes, construction age, and seismic resistance level, obtain the score of the degree of road structure damage and the residual traffic capacity coefficient of the road.

[0053] The identification method of the disaster-affected population gathering area in Step 3 is: Construct a deep learning model, use mobile phone user density data and geospatial information as inputs, and accurately classify the population heat distribution. After training and optimization with a large number of sample data, the model can accurately mark the high-density areas as "disaster-affected population gathering areas".

[0054] Specifically, obtain the mobile hotspot data of the public through relevant departments, including timestamps, specific locations (latitude and longitude), and the number of mobile phone users. Obtain the base station location and coverage data from communication operators, including timestamps, base station geographical locations (latitude and longitude), and the number of mobile phone users. Register the mobile hotspot data and communication base station location data according to the same time interval, delete invalid or duplicate data to ensure the accuracy and uniqueness of the data. Use the kernel density estimation method to process the registered data. By setting a certain range of bandwidth parameters, identify the locations of disaster-stricken population gathering areas. Combine spatial analysis techniques to calculate the population density of each disaster-stricken area. Use the movement path data of mobile phone users, that is, the trajectory information from one base station to another. Utilize time series analysis to track the base station handover situation of mobile phone users in different time periods and extract the complete migration trajectories. Use the mobile phone user density data and geographical spatial information as inputs to accurately classify the population heat distribution. After training and optimization with a large number of sample data, the model can accurately mark high-density areas as "disaster-stricken population gathering areas". By calculating the number of mobile phone users entering and leaving a certain area within a certain time interval, evaluate the population mobility of the area. Observe the stay situation of mobile phone users in a certain area over a long period of time to judge the population stability of the area. Combine the population migration trajectory data extracted in the third step. Through time series analysis, calculate the population density change trend in each time period. Based on historical disaster population gathering, migration data, and population distribution data as training samples, build a population migration model based on long short-term memory networks and optimize the model parameters through cross-validation.

[0055] In the spatial topological relationship diagram in step five, it includes network nodes composed of disaster-stricken population gathering points, emergency shelters, and intersections in the road network, and edges composed of road segments in the road network. Mark the predicted damaged road segments as disabled edges and dynamically adjust the edge weights of the damaged road segments according to the remaining traffic capacity.

[0056] Specifically, dynamically adjusting the edge weights of the damaged road segments according to the remaining traffic capacity can be achieved through the ArcGIS Network Analyst module. Focus on repairing breaks, overlaps, and connectivity errors in the road network. According to the urban traffic guidance requirements, reconstruct the topological relationship of vulnerable road segments. Use a combination of spatial joining and field calculation for association. Dynamically update the traffic status and impedance weights of the road network according to the simulation model with dynamic risk parameters. Establish a multi-state road network topology (normal / partially damaged / completely damaged). Among them, the algorithm for the spatial topological relationship diagram of the emergency evacuation network is as follows:

[0057] Determine the evacuation area of the disaster event;

[0058] Obtain the number of people to be evacuated in the evacuation area and the distribution of the gathering points of the affected population. According to the distribution of the gathering points of the affected population, determine the evacuation traffic distribution in the evacuation area;

[0059] Based on the spatial analysis system, generate a path network spatial topology model according to the preset vector geographic data and the evacuation traffic distribution in the evacuation area. The path network spatial topology model includes network nodes composed of the gathering points of the affected population, emergency shelter points, and intersections in the road network, and edges composed of road segments in the road network;

[0060] The ArcGIS Network Analyst module can be used to mark the predicted damaged sections as disabled edges according to the information of disaster risk points such as earthquakes, geological disasters, and urban waterlogging points, dynamically adjust the edge weights of the damaged sections according to the residual traffic capacity, and reconstruct the topological relationship of the vulnerable sections according to the urban traffic guidance requirements;

[0061] Adopt a method combining spatial join and field calculation for association. The dynamic risk parameters dynamically update the traffic state and impedance weights of the road network according to the simulation model, and establish a multi-state road network topology (normal / partially damaged / fully damaged).

[0062] The construction method of the disaster event dynamic evacuation model in step six is as follows: taking minimizing the evacuation time, minimizing the road disaster risk probability, maximizing the use capacity of the shelter, maximizing the path structure redundancy, and dynamically adapting the weight adjustment as the optimization objectives, and taking the road traffic efficiency, disaster risk probability, and shelter capacity limit as the constraint conditions. According to the optimization objectives and constraint conditions, construct a multi-objective function F(X)=min(T(N),R(N),Cc(N),Cr(N),Cy(N)). In the multi-objective function, N is the total number of evacuees, F(X) is the evacuation path optimization objective function, T(N) is the total evacuation time objective function, R(N) is the disaster risk probability objective function, Cc(N) is the evacuation throughput objective function (to avoid exceeding the shelter capacity), Cr(N) is the shelter use capacity objective function, and Cy(N) is the path structure redundancy objective function.

[0063] Specifically, considering the requirements for timeliness and safety in the actual process of emergency evacuation, determine the objectives of minimizing the evacuation time, minimizing the road disaster risk probability, maximizing the use capacity of the shelter, maximizing the path structure redundancy, and dynamically adapting the weight adjustment, and determine the constraints of road traffic efficiency (not exceeding the preset maximum value), disaster risk probability (not exceeding the preset threshold), and shelter capacity limit (not exceeding the number of people that the shelter can accommodate);

[0064] Collect data on population distribution, distribution and capacity of shelters, disaster risks, etc. Based on the path network spatial topology model generated by the GIS system, set capacity attributes for emergency shelter points, and set four attributes for the edges composed of road segments in the road network, namely capacity, passing time, disaster risk probability, and path structure redundancy;

[0065] Introduce the Non-dominated Sorting Genetic Algorithm II to randomly generate an initial population that meets the constraint conditions, calculate the performance of each individual in five objective functions, sort the population according to the Pareto optimality principle, retain all non-dominated solutions, perform crossover and mutation operations to generate a new offspring population, repeat the fitness calculation, non-dominated sorting, and genetic operations until the convergence condition is met, collect all Pareto optimal solutions, analyze the trade-off relationships of each objective function, and select the optimal or sub-optimal path according to actual requirements.

[0066] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device.

[0067] Although the 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 disaster-based emergency evacuation method based on a spatial analysis algorithm, characterized in that: The following steps are involved: S1: Determine the types of disasters and their interaction patterns, obtain disaster characteristic parameters, quantify the comprehensive risk level of single disasters or multiple disasters based on geographic information system spatial analysis, and generate dynamic risk distribution maps; S2: Collect the first-level index parameters such as geological structure, road grade, construction age, and seismic resistance level, use the hierarchical analysis method to determine the weight coefficients of the second-level index parameters, establish a road structure damage prediction model, obtain the road structure damage degree score, and output the road residual capacity coefficient; S3: Integrate mobile phone and base station data to monitor population distribution and migration in real time, identify the affected population concentration areas and scale, divide evacuation priorities based on risk maps, and determine the affected population concentration areas and needs that need to be relocated; S4: Define the search area with the gathering point of the victims as the center, screen the surrounding emergency shelters, match the number of victims through capacity demand analysis, and finally determine the shelters that meet the evacuation needs; S5: Generate a spatial topology relationship diagram using a spatial topology analysis algorithm based on the preset vector geographic data and the evacuation road distribution of the emergency shelter; S6: Based on the spatial topological relationship diagram, the real-time road capacity data, the disaster risk probability and the shelter capacity are introduced, and a dynamic evacuation model of disaster events is constructed using a dynamic evacuation model of five-fold costs; S7: Continuously access base station positioning data streams, monitor actual evacuation progress and population distribution changes, and dynamically trigger path replanning.

2. The method for emergency evacuation based on spatial analysis algorithm according to claim 1, characterized in that: The calculation method of the comprehensive hazard level described in step S1 is: integrating historical disaster data and real-time crowd intelligence perception information, combining the hierarchical analysis method to quantify the weights of the three major indicators of "disaster hazard-disaster-bearing body vulnerability-disaster reduction capacity", building a multi-disaster coupling evaluation model, and rasterizing the disaster-stricken area based on the spatial analysis technology of the geographic information system, superimposing disaster site data, geographic environment parameters and dynamic disaster indicators, generating a disaster hazard zoning map, and finally outputting the comprehensive regional hazard level.

3. The method for emergency evacuation based on spatial analysis algorithm according to claim 1, characterized in that: The secondary indicators corresponding to the geological structure in step S2 are rock type and terrain characteristics, the secondary indicators corresponding to the road grade are road length, road width, road surface condition and road surface material, the secondary indicator corresponding to the construction age is the construction year, and the secondary indicator corresponding to the seismic resistance grade is the road surface seismic resistance grade.

4. The method for emergency evacuation based on disaster type based on spatial analysis algorithm according to claim 1, characterized in that: The method for constructing the road structure damage prediction model described in step S2 is: first, integrate and standardize data such as geological structure, road attributes, construction age and seismic resistance level, then determine the weight of each indicator through the hierarchical analysis method, then use the graph neural network to extract the node characteristics of the geological structure and the edge characteristics of the road attributes, and combine the time series model to process the dynamic change characteristics of the construction age and seismic resistance level, and finally integrate the weighted features to construct a road structure damage prediction model, and output the damage score and residual capacity coefficient.

5. The method for emergency evacuation based on spatial analysis algorithm according to claim 1, characterized in that: The calculation formula of the road residual capacity coefficient in step S2 is: road residual capacity coefficient=1-road structure damage degree / maximum bearing capacity.

6. The method for emergency evacuation based on different disaster types based on spatial analysis algorithm according to claim 1, characterized in that: The method for identifying disaster-affected population clusters in step S3 is to build a deep learning model, use mobile phone user density data and geographic spatial information as input, and accurately classify the thermal distribution of the population. After training and optimization with a large amount of sample data, the model can accurately mark high-density areas as "disaster-affected population clusters." 7. The method for emergency evacuation based on spatial analysis algorithm according to claim 1, characterized in that: The spatial topological relationship diagram in step S5 includes network nodes composed of disaster-stricken population gathering points, emergency shelters, and intersections in the road network, and edges composed of road sections in the road network. The predicted damaged sections are marked as disabled edges, and the edge weights of the damaged sections are dynamically adjusted according to the residual traffic capacity.

8. The method for emergency evacuation based on different disaster types based on spatial analysis algorithm according to claim 1, characterized in that: The method for constructing the dynamic evacuation model of disaster events in step S6 is: taking minimizing evacuation time, minimizing road disaster risk probability, maximizing shelter utilization capacity, maximizing path structure redundancy and dynamic adaptation weight adjustment as optimization objectives, taking road traffic efficiency, disaster risk probability and shelter capacity limit as constraints, and constructing a multi-objective function F(X)=min(T(N), R(N), Cc(N), Cr(N), Cy(N)) according to the optimization objectives and constraints, where N is the total number of evacuees, F(X) is the evacuation path optimization objective function, T(N) is the total evacuation time objective function, R(N) is the disaster risk probability objective function, Cc(N) is the evacuation flow objective function, Cr(N) is the shelter utilization capacity objective function, and Cy(N) is the path structure redundancy objective function.

Images