Post-earthquake rescue route optimization method coupling safety and efficiency

Abstract

The present application provides a post-earthquake rescue path optimization method that couples safety and efficiency, and relates to the technical field of post-earthquake rescue path optimization, including: obtaining multi-source data; constructing a road map through the multi-source data and susceptibility results; determining rescue centers and disaster-stricken points based on emergency rescue reports in the multi-source data; constructing a lightweight graph neural network; inputting the road map, rescue centers, and disaster-stricken points into the lightweight graph neural network; using the cumulative weight of each node from the rescue center to the road map as a node feature, iterating the node feature representation through the lightweight graph neural network to obtain the minimum value of the cumulative weight of the disaster-stricken point, backtracking the cumulative weight of the disaster-stricken point, and obtaining the optimal rescue path from the rescue center to the disaster-stricken point, thereby achieving efficient emergency rescue path optimization in a large-scale and complex road network in a wide-area strong earthquake zone.

Description

Technical Field

[0001] The present application relates to the technical field of post-earthquake rescue path optimization, and in particular to a post-earthquake rescue path optimization method that couples safety and efficiency. Background Art

[0002] The main challenges in optimizing rescue routes after a major earthquake currently lie in the inefficiency of path optimization over complex, wide-area road networks and the failure to consider safety along the roads (susceptibility to co-seismic disasters), making it inadequate for emergency rescue efforts. Finding a fast route for emergency vehicles from a rescue center to the disaster site after an earthquake is a shortest path problem within path optimization. Traditional global search path optimization algorithms traverse all edges and nodes to find the shortest path from the starting point to the target node. Dijkstra's algorithm traverses all nodes to find the shortest path from each node to the starting point, and then searches for the shortest path from the starting point to the target point. The A* algorithm uses the physical distance from neighboring nodes as a criterion for selecting neighboring nodes. By incorporating this heuristic metric, the A* algorithm can theoretically find the optimal path faster than Dijkstra's algorithm. Because traditional global search algorithms perform global searches, they can generally find an optimal path from the starting point to the target point (if one exists), making them relatively stable. However, their global traversal nature results in relatively low search efficiency, limiting their application in large-scale, strong earthquake zones.

[0003] Inspired by animal flocking behavior, microbial foraging behavior, and natural phenomena, heuristic optimization algorithms have recently begun to be applied to path optimization. These methods employ local search and gradually iterate to converge to a global optimum. After defining a path based on node IDs or node attributes (path encoding), the node attributes are iterated multiple times and the top-k solutions are selected, gradually converging to a global optimum. Finally, the shortest path is obtained according to the path definition. Genetic algorithms (GAs) mimic the laws of genetic inheritance (recombination and mutation produce new genes, and fitness functions eliminate poorly performing genes) to optimize solutions. However, unlike other problems such as the Traveling Salesman Problem (TSP), the number of nodes within a single solution in metaheuristic algorithms for path optimization is not fixed (path length is uncertain), and gene crossover and mutation require a new definition. Unlike GA path optimization methods, particle swarm optimization (PSO) does not redefine particle behavior. Instead, it converts path solutions (variable-length solutions) into node attributes (fixed-length solutions). Specifically, PSO optimizes node priorities in the graph and selects node IDs based on these priorities to form a path. The Pulse Coupled Neural Network (PCNN), Rapid Physarum Algorithm (RPA), and Ripple Spread Algorithm (RSA) methods simulate the information transmission and connectivity of the primate visual system (pulse signals), the foraging process of Physarum fungi, and the diffusion of ripples on a liquid surface (ripple relay race), respectively, to optimize paths. Similar to PCNN, the Rosenance algorithm also optimizes paths based on signal transmission. A node is activated when a signal is first transmitted to that node. The shortest path is determined by superimposing the forward transmission of the starting signal and the reverse transmission of the ending signal.

[0004] At present, path optimization has made important progress and a large number of excellent results have emerged. However, there are still the following limitations: (1) The current path optimization algorithm mainly performs well on small-scale graphs (the number of nodes is less than or equal to 2000). However, earthquake rescue is often a large-scale complex road network. In real earthquake scenarios, the number of nodes may be greater than 10,000, or even reach 100,000. Due to the global traversal characteristics and the unreasonable solution regularization method, the current shortest path optimization algorithm has low computational efficiency on large-scale graphs, which limits its application in large-scale earthquake rescue road network graphs. (2) The current emergency rescue route optimization does not consider the path safety issues caused by the distribution of coseismic landslides, which is very detrimental to the smooth progress of emergency rescue and the safety of rescue workers. (3) The current coseismic landslide susceptibility evaluation usually uses all coseismic landslide training models and landslide susceptibility assessment. However, there are many coseismic landslides and they are distributed over a wide area. The complete and accurate interpretation of these landslides usually takes weeks to months, which is difficult to support the 72-hour golden rescue and has limited practicality. Summary of the Invention

[0005] The purpose of the present invention is to provide a post-earthquake rescue route optimization method that couples safety and efficiency in order to solve the problem that the existing emergency rescue route optimization does not consider the path safety caused by the co-seismic landslide distribution.

[0006] The above-mentioned purpose of this application is achieved through the following technical solutions:

[0007] S1: Acquire multi-source data; use the multi-source data in combination with the CGBoost algorithm to predict the susceptibility of co-seismic landslides, obtain susceptibility results, and verify them; the multi-source data include: topographic data, geological data, human engineering activity data, environmental data, rainfall data, and earthquake data;

[0008] S2: Construct a road map using multi-source data and susceptibility results;

[0009] S3: Determine rescue centers and disaster-affected areas based on emergency rescue reports from multi-source data;

[0010] S4: Building a lightweight graph neural network;

[0011] S5: Input the road map, rescue centers, and disaster-affected areas into the lightweight graph neural network;

[0012] The cumulative weight of each node from the rescue center to the road graph is used as the node feature to perform node feature characterization;

[0013] Through the lightweight graph neural network iterative node feature representation, the minimum value of the cumulative weight of the disaster-stricken point is obtained. By backtracing the cumulative weight of the disaster-stricken point, the optimal rescue path from the rescue center to the disaster-stricken point is obtained.

[0014] An electronic device includes a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device performs a post-earthquake rescue path optimization method that couples safety and efficiency.

[0015] A computer-readable storage medium stores instructions. When the instructions are executed, a post-earthquake rescue route optimization method that couples safety and efficiency is implemented.

[0016] The beneficial effects of the technical solution provided by this application are:

[0017] 1. LGNN (Light Graph Neural Network) node-parallel representation offers high efficiency when applied to large-scale, complex road networks. Earthquake rescue operations often involve large, complex road networks. In real-world earthquake scenarios, the number of nodes may exceed 10,000 or even 100,000. Current shortest path optimization algorithms suffer from low computational efficiency on large graphs due to their global traversal nature and the inadequate solution regularization methods used in heuristic optimization algorithms, which make it difficult to find the optimal path. The LGNN algorithm formulates rescue path optimization as a problem of minimizing the cumulative road weights from the rescue center. For each node (intersection) in the road network, the LGNN uses the cumulative weights of all roads from the rescue center (starting point) to that node (referred to as the node cumulative weight) as the node feature. Leveraging node topology and GNN message passing and feature aggregation mechanisms, the LGNN parallelizes the node features of each node and then backtracks to obtain the optimal path. Due to the high efficiency of LGNN parallel representation, efficient emergency rescue path optimization can be achieved across large, complex road networks in wide-area strong earthquake zones.

[0018] 2. The susceptibility of co-seismic landslides along the road is included as one of the road indicators to be considered in route optimization, which improves the rationality of route optimization. Emergency rescue route optimization is to find a safe route for rescue vehicles to quickly reach the rescue point. However, these high-risk landslide areas along the road are dangerous areas for emergency rescue. The cracked rock and soil and loose deposits may cause emergency rescue personnel or vehicles to be buried or injured, seriously threatening the safety of rescue workers and rescued personnel. Therefore, the present invention takes into account the safety along the road and uses the susceptibility of co-seismic landslides along the road to measure the safety of the rescue road; quantify the road safety and traffic efficiency (vehicle travel time) according to the landslide susceptibility level, road grade and road length, and couple them to carry out emergency rescue route optimization and improve the rationality of route optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The present application will be further described below with reference to the accompanying drawings and embodiments, in which:

[0020] Figure 1 It is a step diagram in the embodiment of the present application;

[0021] Figure 2 The study area susceptibility prediction map and statistical information map in the embodiments of the present application;

[0022] Figure 3 LGNN path optimization result diagram in five cases in the embodiment of the present application;

[0023] Figure 4 It is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to have a clearer understanding of the technical features, purposes and effects of this application, the specific implementation methods of this application are now described in detail with reference to the accompanying drawings.

[0025] The embodiments of the present application provide a post-earthquake rescue route optimization method that couples safety and efficiency.

[0026] Please refer to Figure 1 , Figure 1 This is a step diagram of a post-earthquake rescue path optimization method that couples safety and efficiency in an embodiment of the present application, including:

[0027] S1: Acquire multi-source data; use the multi-source data in combination with the CGBoost algorithm to predict the susceptibility of co-seismic landslides, obtain susceptibility results, and verify them; the multi-source data include: topographic data, geological data, human engineering activity data, environmental data, rainfall data, and earthquake data;

[0028] Specifically, CGBoost landslide susceptibility prediction with a small number of landslide samples. Currently, co-seismic landslide susceptibility evaluation usually uses all co-seismic landslide training models and evaluates landslide susceptibility. However, there are a large number of co-seismic landslides and they are distributed over a wide area. A complete and accurate interpretation of these landslides usually takes weeks to months, making it difficult to support the 72-hour golden rescue, and its practicality is limited. The present invention uses 10% of the co-seismic landslide cataloging data to simulate a small amount of landslide data obtained shortly after the earthquake for susceptibility modeling. Since the CGBoost algorithm has good susceptibility modeling capabilities with a small number of samples, the CGBoost co-seismic landslide susceptibility prediction using a small number of landslides can well support emergency rescue.

[0029] Specifically, a Crossing Graph Attention Network (Crossgat) and Extreme Gradient Boosting Trees (XGBoost) ensemble method, called the CGBoost algorithm, is used. This algorithm is derived from Chinese patent CN116894523A - A CGBoost algorithm, device, and storage device for predicting coseismic landslide susceptibility.

[0030] S2: Construct a road map using multi-source data and susceptibility results;

[0031] S3: Determine rescue centers and disaster-affected areas based on emergency rescue reports from multi-source data;

[0032] Specifically, the emergency rescue report determines the help center and disaster site. Based on the disaster situation and rescue force distribution reported in the emergency rescue response bulletin, the disaster site with severe casualties is designated as the waiting point for rescue (end point t), and the main rescue force deployed in the rescue report is designated as the rescue center (starting point s).

[0033] S4: Building a lightweight graph neural network;

[0034] Specifically, mathematical modeling and analysis are performed on the emergency rescue path optimization problem. The problem of optimizing rescue vehicle routes in a complex road network across a large area is abstracted into a mathematical problem. The edge weights of the road graph are used to aggregate neighbor node features. Minimum aggregation is used to aggregate neighbor node features to construct a lightweight graph neural network (LGNN). Minimum aggregation with edge weights enables node features to converge, while the parallel representation of nodes in minimum neighbor aggregation allows node features to converge quickly to a minimum, thereby improving the speed of path optimization.

[0035] S5: Input the road map, rescue centers, and disaster-affected areas into the lightweight graph neural network;

[0036] The cumulative weight of each node from the rescue center to the road graph is used as the node feature to perform node feature characterization;

[0037] Through the lightweight graph neural network iterative node feature representation, the minimum value of the cumulative weight of the disaster-stricken point is obtained. By backtracing the cumulative weight of the disaster-stricken point, the optimal rescue path from the rescue center to the disaster-stricken point is obtained.

[0038] Step S1 includes:

[0039] S11: Terrain data includes seamless digital elevation model data; geological data includes geological maps, pre-earthquake fault data, and world digital soil maps; human engineering activity data includes land use data and pre-earthquake road network data; environmental data includes water network data; earthquake data includes shake maps, post-earthquake 3D Google images, co-seismic landslide catalog data, and real-world resettlement site data for earthquake emergency response.

[0040] Specifically, terrain factors are established through seamless digital elevation model data; engineering rock groups are constructed through geological maps; distances to faults are constructed through pre-earthquake fault data; soil type factors are constructed through the world digital soil map; types and characteristics of human engineering activities are obtained through land use data; distances of environmental factors to water systems are established through water network data; annual average rainfall, monthly average rainfall, monthly average rainfall change rate, and monthly average rainfall change acceleration factors are constructed through rainfall data; peak ground acceleration, peak seismic velocity, Mercalli earthquake intensity, and distance from the epicenter factors are extracted through vibration maps; and road accessibility is determined through pre-earthquake road networks and post-earthquake 3D Google images.

[0041] Specifically, the Digital Soil Map of the World. Rainfall data includes monthly rainfall from 1960 to 2018. ShakeMap is used to extract Peak Ground Acceleration (PGA), Peak Ground Velocity (PGV), Modified Mercalli Intensity (MMI), and distance from the epicenter factor.

[0042] S12: Construct disaster-pregnancy and disaster-causing factors using topographic data, geological data, human engineering activity data, environmental data, rainfall data, and vibration maps; these factors are used to predict 20 landslide susceptibility indicators;

[0043] S13: Based on 10% of the coseismic landslide catalog data and the disaster-pregnancy and disaster-causing factors, the CGBoost algorithm is used to predict the susceptibility of coseismic landslides and obtain the susceptibility results;

[0044] S14: Validate the predicted susceptibility results using all coseismic landslide inventory data.

[0045] Specifically, the rationality of the path optimization results is verified through the real resettlement point data of earthquake emergency response.

[0046] Step S2 includes:

[0047] S21: Extract road grade and road length from pre-earthquake road network data in human engineering activity data;

[0048] S22: Calculate the road travel time according to the road grade and road length;

[0049] Specifically, for road travel time, refer to traffic speed limit regulations: the maximum speed on expressways is 100km / h, the maximum speed on intercity roads and main roads is 80km / h, the maximum speed on secondary roads and urban roads is 50km / h, and the maximum speed in residential areas is 30km / h. The maximum speed V of the road g is quantified according to the road grade and road type. g As shown in Table 1. Calculate the road travel time T g , where l g Indicates the length of the road g.

[0050] S23: quantifying the susceptibility results to determine a landslide susceptibility level; the landslide susceptibility level includes: very low susceptibility, low susceptibility, medium susceptibility, high susceptibility, and very high susceptibility;

[0051] S24: Select the maximum landslide susceptibility level in the road buffer zone as the landslide susceptibility level P of road g g , g∈{1,2,…,NS}, NS represents the number of roads in the road network;

[0052] Specifically, the susceptibility of landslides within 50 m on both sides of the road can well reflect the susceptibility of landslides on the road. Therefore, the maximum value of the landslide susceptibility level within the 50 m buffer zone of the road is selected as the landslide susceptibility level P of road g. g .

[0053] S25: Determine road accessibility: Based on pre-earthquake road network data and post-earthquake 3D Google imagery, interpret impassable roads and obtain interpretation results. Impassable roads include those blocked by landslides and roads blocked by debris from collapsed buildings.

[0054] S26: Based on the interpretation results, remove impassable roads; construct a road map with the intersections of traversable roads as nodes, roads as edges, and road travel time and landslide susceptibility level of roads as edge weights.

[0055] Step S4 includes:

[0056] The problem of optimal route selection for rescue vehicles in a large-scale complex road network is abstracted into a mathematical problem and mathematical modeling is performed;

[0057] Define the node where the rescue center is located as the vehicle's starting point s, and the disaster site with serious casualties as the vehicle's end point t, where s and t are both nodes in the graph data; assume that the number of vehicles at the starting point s is 1 and that the vehicle is only capable of rescuing one disaster site;

[0058] The intersections of accessible roads are taken as nodes, roads as edges, and the road travel time and landslide susceptibility level of the roads are taken as edge weights. The graph data is constructed as G(V,W), where N represents the number of road intersection nodes in the road network, and V = {0, 1, 2, ..., N-1} represents the node set. The adjacency matrix representing the edges of the graph data, is the weight matrix of the edge of the graph data;

[0059] For a road g with nodes i and j, its corresponding edges are (i, j) and (j, i); (i, j) represents the road g from node i to node j; (j, i) represents the road g from node j to node i, so A i,j =A j,i =1, if road g is an impassable road, then A i,j =A j,i =0;

[0060] Specifically, the purpose of emergency rescue vehicle route optimization is to find a route that takes into account both safety and timeliness on the accessible road map. The path safety is the sum of the landslide susceptibility levels of all roads in the path. The landslide susceptibility level P of road g is g The lower it is, the safer it is for rescue vehicles to pass through the road. The path travel time is the accumulation of the road travel time in the path. The road travel time T g The smaller the number of g, the faster search and rescue vehicles can pass through the road, which is more efficient and beneficial for personnel search and rescue. The landslide susceptibility level and road travel time are equally important for rescue.

[0061] Landslide susceptibility level P of road g g and road travel time T g are equally important for emergency rescue operations. If there is a road g, then the weight W of the edge (i, j) is i,j =P g +T g , W i,j =W j,i ; If there is no road g, then W i,j =W j,i =∞;

[0062] Define node s as the starting point, node t as the end point, a′, c′, d′, u′, as nodes different from s and t; s, a′, c′, d′, u′, t∈V;

[0063] Define the matrix P and matrix C to represent the path matrix and cumulative weight matrix respectively.

[0064]

[0065] definition The element in the sth row and tth column of the matrix P represents the path from node s to node t;

[0066] definition represents the element in row s and column t in C, which represents the cumulative weight from node s to node t;

[0067] If there are edges (s,a′),(a′,c′),(c′,d′),…,(u′,t), their corresponding paths are g1,g2,g3,…,g l , then the path from s to t is The corresponding cumulative weight from s to t is g1,g2,g3,…,g l ∈{1,2,…,NS};

[0068] Based on the above definition, the path from the starting point s to the end point t on the graph data G(V,W) that considers security and timeliness is preferably described as a minimization problem on G(V,W), as follows:

[0069]

[0070] Where min′ represents the function of finding the minimum value of the variable;

[0071] definition The minimum value of represents the minimum cumulative weight from s to t; The corresponding path from s to t is The minimum value of is the shortest path;

[0072] Through the triangle inequality property of the shortest path, we get the following proposition and inference:

[0073] Proposition 1: For represents the set of neighbor nodes of t and

[0074] Known W u,t , W u,t Represents the weight of the edge (u, t), u represents a neighbor node of t; if given but min(·) represents a function that finds the minimum value in a set, and the mark The corresponding u is u′, then

[0075] Corollary 1: Definition achieve When , the corresponding neighbor node of t is u′, then among the neighbor nodes u of node t, only u=u′ satisfies That is, the predecessor node of t on the shortest path from s to t And at this time achieve For any other u=u e ,regardless Whether it is achieved have u e represents the set of neighbor nodes of node t that does not include u′;

[0076] Specifically, to speed up The calculation will The calculation is converted into a parallel representation of the GNN nodes of the graph neural network, and the speed of path optimization for large graphs is further improved with the help of the parallelism of the GNN node representation.

[0077] Will The solution is defined as of Minimize the problem, i∈V, and pass Solution

[0078] The cumulative weight from node s to node i is used as the feature of node i, and Modeled as the representation process of node i;

[0079] The node features of each node i are represented in parallel using the node topology relationship and the message passing and feature aggregation mechanism of the graph neural network GNN

[0080] initial Due to the minimum feature aggregation mechanism, after iterative characterization Gradually converge to For i = s, we have exist After convergence, we iterate back to the predecessor node through Corollary 1 and get

[0081] Step S4 further includes:

[0082] Using minimum aggregation, the edge weights are involved in the aggregation of neighbor node features. The initial node representation of the lightweight graph neural network is as follows:

[0083]

[0084] in represents the kth iteration represents the cumulative weight from node s to node i; represents the k-1th iteration represents the cumulative weight from node s to node j;

[0085] For k=0,i=s, we have

[0086] For i = other∈V-{s}, we have

[0087] For node t, h t express That is, the cumulative weight from node s to node t; when h t When k drops from k = 0 to k = k', and no longer changes from k = k' to k = k' + τ, that is, Reach the minimum value and find satisfaction through inference 1 The predecessor node u′ of t is obtained by iterative backtracking τ represents the maximum number of iterations in which the node features on the graph remain unchanged after not being ∞;

[0088] Specifically, the LGNN (Light Graph Neural Network) bidirectional path optimization algorithm can further improve the speed of rescue path optimization.

[0089] In the weighted undirected graph G(V,W), s is the starting point and t is the end point. The bidirectional algorithm calculates the value of each node i from the starting point s and the end point t respectively. and If the node v and Both reach the minimum value. Since G(V,W) is an undirected graph, Corresponding Reversed(·) represents the reversal function;

[0090] In the LGNN bidirectional path optimization algorithm, and Represented as node features, let Therefore, for each node i, LGNN represents the node features from s to i in parallel and node features from t to s D i ;

[0091] The bidirectional node characterization process of the LGNN bidirectional path optimization algorithm is as follows:

[0092]

[0093] in, Represents the characteristics of node i at the kth iteration and When i = s hour When i = t When i=other

[0094] For any node i, Therefore If there exists a node v such that When the node v corresponds to First converge to hour, has converged, and at other nodes i e ∈V-{v} corresponds to During the convergence process, has ceased to change, so when It can be judged when it drops to no longer change Convergence, without having to wait until any node i corresponds to No longer changes.

[0095] Step S4 further includes:

[0096] In the LGNN bidirectional path optimization algorithm, C s,k ,C t,k =D k [:,0],D k [:,1],

[0097] C s,k Denotes the cumulative weight vector C from node s to all nodes represented by the kth iteration s ;

[0098] C t,k Represents the cumulative weight vector C from node t to all nodes represented by the kth iteration t ;

[0099] make When it decreases until it no longer changes from k = k' to k = k' + τ, it is determined that has converged;

[0100] Mark min(C s,k +C t,k ) corresponds to node v, then node v is the intersection node of bidirectional optimization, that is, the node on the shortest path;

[0101] By the formula get and Based on the node v as the starting point and The optimal rescue path obtained by backtracking.

[0102] Table 1. Quantitative rules for maximum traffic speed

[0103]

[0104] The present invention adopts 10% random co-seismic landslides after the earthquake to simulate the small amount of co-seismic landslide data that can be obtained after the earthquake, and uses the CGBoost algorithm to achieve a more accurate prediction of the susceptibility of co-seismic landslides in a wide area of ​​strong earthquakes, so as to better support emergency rescue; Based on the 10% randomly obtained co-seismic landslides, CGBoost is used to predict the susceptibility of M w The landslide susceptibility prediction for the 6.9 Lombok earthquake was conducted. The overall accuracy, precision, recall, F1 index, and Kappa coefficient of the susceptibility prediction were 0.9233, 0.9387, 0.9079, 0.9231, and 0.8467, respectively. Figure 2 Displays a susceptibility map and statistical information for the study area. NPLHVH represents the percentage of landslides falling within high and very high susceptibility zones. Practicality refers to the practicality of the susceptibility prediction, expressed as the percentage of area within high and very high susceptibility zones. The map shows that 92.25% of landslides in the study area fall within high and very high susceptibility zones, while high and very high susceptibility zones account for 15.73% of the total area. Identifying broad areas of low and very low susceptibility strongly supports effective and efficient emergency response.

[0105] Figure 3 The figure shows the path optimization results of LGNN in five cases. s1-s5 and t1-t5 represent the rescue center and the disaster site. Figure 3 (a)-(e) represent the path optimization results of Situation 1-5 with and without considering susceptibility, respectively. ORE represents the optimal path obtained by considering only traffic efficiency, and ORSE represents the optimal path obtained by considering both traffic efficiency and road safety. Figure 3 (f) Statistics of the preferred paths for Situations 1-5. In Situations 2-5, the paths without considering susceptibility pass through more sections with high and extremely high landslide susceptibility. Figure 3 (f) It can be seen that the sum of the landslide susceptibility grades of the paths selected based on susceptibility in Situations 1-5 is smaller than the sum of the landslide susceptibility grades of the paths selected without considering susceptibility. This indicates that the paths selected after considering susceptibility have lower landslide susceptibility and are safer to a certain extent.

[0106] Table 2 shows the quantitative evaluation results of various path optimization methods, where CW represents the cumulative weight of the optimal path, ET represents the algorithm runtime, and SIT represents the algorithm iteration time. The table shows that compared with mainstream path optimization algorithms such as Dijkstra, A*, RPA, Jaya, and RSA, LGNN achieves the best path optimization performance. It not only finds the optimal path (with the lowest CW value), but also achieves the highest path optimization efficiency (with the lowest ET value), effectively supporting safe, effective, and efficient post-earthquake emergency rescue efforts.

[0107] Table 2. Quantitative evaluation results of various method paths

[0108]

[0109] This application also discloses an electronic device. Figure 4 , Figure 4 Schematic diagram of the structure of an electronic device disclosed in an embodiment of the present application. The electronic device 500 may include: at least one processor 501, at least one network interface 504, a user interface 503, a memory 505, and at least one communication bus 502.

[0110] The communication bus 502 is used to implement the connection and communication between these components.

[0111] The user interface 503 may include a display screen, and the optional user interface 503 may also include a standard wired interface or a wireless interface.

[0112] The network interface 504 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0113] The present application also discloses a computer-readable storage medium storing a plurality of instructions suitable for loading by a processor to execute the above-mentioned post-earthquake rescue path optimization method that couples safety and efficiency.

[0114] The above are merely exemplary embodiments of the present disclosure and are not intended to limit the scope of the present disclosure. In other words, any equivalent variations and modifications made in accordance with the teachings of the present disclosure are still within the scope of the present disclosure. Those skilled in the art will readily conceive of other embodiments of the present disclosure after considering the disclosure and the practical implications thereof.

[0115] This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not described herein. The description and examples are to be considered as exemplary only, and the scope and spirit of the present disclosure are to be defined by the claims.

Claims

1. A post-earthquake rescue route optimization method that couples safety and efficiency, characterized by: include: S1: Acquire multi-source data; Using multi-source data, including topographic data, geological data, human engineering data, environmental data, rainfall data, and earthquake data, combined with the CGBoost algorithm, the susceptibility of coseismic landslides is predicted, and the susceptibility results are obtained and verified. S2: Construct a road map using multi-source data and susceptibility results; S3: Determine rescue centers and disaster-affected areas based on emergency rescue reports from multi-source data; S4: Build a lightweight graph neural network (LGNN); Step S4 includes: The problem of optimizing rescue vehicle routes in a large-scale complex road network is abstracted into a mathematical problem and mathematical modeling is performed; Define the node where the rescue center is located as the vehicle's starting point s, and the disaster site with serious casualties as the vehicle's end point t, where s and t are both nodes in the graph data; assume that the number of vehicles at the starting point s is 1 and that the vehicle is only capable of rescuing one disaster site; The intersections of accessible roads are taken as nodes, roads as edges, and the road travel time and landslide susceptibility level of the roads are taken as edge weights. The graph data is constructed as G(V,W), where N represents the number of road intersection nodes in the road network, and V = {0, 1, 2, ..., N-1} represents the node set. The adjacency matrix representing the edges of the graph data, is the weight matrix of the edge of the graph data; For a road g with nodes i and j, its corresponding edges are (i, j) and (j, i); (i, j) represents the road g from node i to node j; (j, i) represents the road g from node j to node i, so A i,j =A j,i =1, if road g is an impassable road, then A i,j =A j,i =0; Landslide susceptibility level P of road g g and road travel time T g are equally important for emergency rescue operations. If there is a road g, then the weight W of the edge (i, j) is i,j =P g +T g , W i,j =W j,i ; If there is no road g, then W i,j =W j,i =∞; Define node s as the starting point, node t as the end point, a′, c′, d′, u′ as nodes different from s and t; s, a′, c′, d′, u′, t∈V; Define the matrix P and matrix C to represent the path matrix and cumulative weight matrix respectively. definition The element in the sth row and tth column of the matrix P represents the path from node s to node t; definition represents the element in row s and column t in C, which represents the cumulative weight from node s to node t; If there are edges (s,a′),(a′,c′),(c′,d′),…,(u′,t), their corresponding paths are g1,g2,g3,…,g l , then the path from s to t is The corresponding cumulative weight from s to t is g1,g2,g3,…,g l ∈{1,2,…,NS}; NS represents the number of roads in the road network; Based on the above definition, the path from the starting point s to the end point t on the graph data G(V,W) that considers security and timeliness is preferably described as a minimization problem on G(V,W), as follows: Where min′ represents the function of finding the minimum value of the variable; definition The minimum value of represents the minimum cumulative weight from s to t; The corresponding path from s to t is The minimum value of is the shortest path; The node features of each node i are represented in parallel using the node topology relationship and the message passing and feature aggregation mechanism of the graph neural network GNN initial Due to the minimum feature aggregation mechanism, after iterative characterization Gradually converge to For i = s, we have exist After convergence, we iterate back to the predecessor node through Corollary 1 and get S5: Input the road map, rescue centers, and disaster-affected areas into the lightweight graph neural network; The cumulative weight of each node from the rescue center to the road graph is used as the node feature to perform node feature characterization; Through the lightweight graph neural network iterative node feature representation, the minimum value of the cumulative weight of the disaster-stricken point is obtained. By backtracing the cumulative weight of the disaster-stricken point, the optimal rescue path from the rescue center to the disaster-stricken point is obtained.

2. A post-earthquake rescue route optimization method that couples safety and efficiency as claimed in claim 1, characterized in that: Step S1 includes: S11: Terrain data includes seamless digital elevation model data; geological data includes geological maps, pre-earthquake fault data, and world digital soil maps; human engineering activity data includes land use data and pre-earthquake road network data; environmental data includes water network data; earthquake data includes shake maps, post-earthquake 3D Google images, co-seismic landslide catalog data, and real-world resettlement site data for earthquake emergency response. S12: Construct disaster-pregnancy and disaster-causing factors using topographic data, geological data, human engineering activity data, environmental data, rainfall data, and vibration maps; these factors are used to predict 20 landslide susceptibility indicators; S13: Based on 10% of the coseismic landslide catalog data and the disaster-pregnancy and disaster-causing factors, the CGBoost algorithm is used to predict the susceptibility of coseismic landslides and obtain the susceptibility results; S14: Validate the predicted susceptibility results using all coseismic landslide inventory data.

3. A post-earthquake rescue route optimization method that couples safety and efficiency as claimed in claim 1, characterized in that: Step S2 includes: S21: Extract road grade and road length from pre-earthquake road network data in human engineering activity data; S22: Calculate the road travel time according to the road grade and road length; S23: quantifying the susceptibility results to determine a landslide susceptibility level; the landslide susceptibility level includes: very low susceptibility, low susceptibility, medium susceptibility, high susceptibility, and very high susceptibility; S24: Select the maximum landslide susceptibility level in the road buffer zone as the landslide susceptibility level P of road g g , g∈{1,2,…,NS}, NS represents the number of roads in the road network; S25: Determine road accessibility: Based on pre-earthquake road network data and post-earthquake 3D Google imagery, interpret impassable roads and obtain interpretation results. Impassable roads include those blocked by landslides and roads blocked by debris from collapsed buildings. S26: Based on the interpretation results, remove impassable roads; construct a road map with the intersections of traversable roads as nodes, roads as edges, and road travel time and landslide susceptibility level of roads as edge weights.

4. A post-earthquake rescue route optimization method that couples safety and efficiency as claimed in claim 3, characterized in that: Step S4 includes: Through the triangle inequality property of the shortest path, we get the following proposition and inference: Proposition 1: For t≠s, represents the set of neighbor nodes of t and Known W u,t , W u,t Represents the weight of the edge (u, t), u represents a neighbor node of t; if given but min(·) represents a function that finds the minimum value in a set, and the mark The corresponding u is u′, then Corollary 1: Definition achieve When , the corresponding neighbor node of t is u′, then among the neighbor nodes u of node t, only u=u′ satisfies That is, the predecessor node of t on the shortest path from s to t And at this time achieve For any other u=u e ,regardless Whether it is achieved have u e represents the set of neighbor nodes of node t that does not include u′; Will The solution is defined as of Minimize the problem, i∈V, and pass Solution The cumulative weight from node s to node i is used as the feature of node i, and Modeled as the representation process of node i.

5. A post-earthquake rescue route optimization method that couples safety and efficiency as claimed in claim 4, characterized in that: Step S4 further includes: Using minimum aggregation, the edge weights are involved in the aggregation of neighbor node features. The initial node representation of the lightweight graph neural network is as follows: in represents the kth iteration represents the cumulative weight from node s to node i; represents the k-1th iteration represents the cumulative weight from node s to node j; For k=0,i=s, we have For i = other∈V-{s}, we have For node t, h t express That is, the cumulative weight from node s to node t; when h t When k drops from k = 0 to k = k', and no longer changes from k = k' to k = k' + τ, that is, Reach the minimum value and find satisfaction through inference 1 The predecessor node u′ of t is obtained by iterative backtracking τ represents the maximum number of iterations in which the node features on the graph remain unchanged after not being ∞; In the weighted undirected graph G(V,W), s is the starting point and t is the end point. The bidirectional algorithm calculates the value of each node i from the starting point s and the end point t respectively. and If the node v and Both reach the minimum value. Since G(V,W) is an undirected graph, Corresponding Reversed(·) represents the reversal function; In the LGNN bidirectional path optimization algorithm, and Represented as node features, let Therefore, for each node i, LGNN represents the node features from s to i in parallel and node features from t to s D i ; The bidirectional node characterization process of the LGNN bidirectional path optimization algorithm is as follows: in, Represents the characteristics of node i at the kth iteration and When i = s When i=other When i = t When i=other For any node i, Therefore If there exists a node v such that When the node v corresponds to First converge to hour, has converged, and at other nodes i e ∈V-{v} corresponds to During the convergence process, has ceased to change, so when It can be judged when it drops to no longer change Convergence, without having to wait until any node i corresponds to No longer changes.

6. A post-earthquake rescue route optimization method that couples safety and efficiency as claimed in claim 5, characterized in that: Step S4 further includes: In the LGNN bidirectional path optimization algorithm, C s,k ,C t,k =D k [:,0],D k [:,1], C s,k Denotes the cumulative weight vector C from node s to all nodes represented by the kth iteration s ; C t,k Denotes the cumulative weight vector C from node t to all nodes represented by the kth iteration t ; make When it decreases until it no longer changes from k = k' to k = k' + τ, it is determined that has converged; Mark min(C s,k +C t,k ) The corresponding node is node v, then node v is the intersection node of bidirectional optimization, that is, the node on the shortest path; By the formula get and Based on the node v as the starting point and The optimal rescue path obtained by backtracking.

7. An electronic device, characterized in that: The invention comprises a processor (501), a memory (505), a user interface (503) and a network interface (504), wherein the memory (505) is used to store instructions, the user interface (503) and the network interface (504) are used to communicate with other devices, and the processor (501) is used to execute the instructions stored in the memory (505) so that the electronic device executes the post-earthquake rescue path optimization method according to any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions, and when the instructions are executed by a computer, the post-earthquake rescue path optimization method according to any one of claims 1 to 6 is executed.

Images