Risk-avoiding path planning method and device, equipment, storage medium and program product

Abstract

The invention relates to the technical field of path planning, and provides a risk avoiding path planning method and device, equipment, a storage medium and a program product, and the method comprises the steps: obtaining the risk data of a flood disaster in a to-be-planned region; calculating a road risk index of a sub-path between any two road nodes based on the risk data in a road network topology structure of the to-be-planned area; and taking the road risk index as a weight value of the sub-path, traversing each road node by adopting a Dikstra algorithm based on a to-be-planned starting node and a to-be-planned ending node, and planning an optimal risk avoiding path from the starting node to the ending node. Quantitative assessment of road traffic capacity and risk based on combination of historical data and real-time monitoring data is realized through the road risk index, and a risk avoiding path with the lowest risk is planned by taking the road risk index as a path weight and adopting a Dikstra algorithm, so that the availability of the risk avoiding path is ensured, and the risk avoiding efficiency is improved. Therefore, the accuracy and effectiveness of the planned risk avoiding path are ensured.

Description

Technical Field

[0001] This application relates to the field of path planning technology, and in particular to a method, apparatus, equipment, storage medium, and program product for risk avoidance path planning. Background Technology

[0002] Route planning in disaster scenarios is a strategy optimization problem involving connecting the starting point to the destination. Road accessibility analysis in flood disasters typically employs GIS (Geographic Information System)-based assessments, statistical and probabilistic models, and multi-indicator comprehensive evaluations. Existing route planning for urban flooding scenarios largely focuses on in-depth analysis of historical data, aiming to learn from past events and provide a scientific basis for future disaster responses. This includes using historical rainfall data, employing complex mathematical models and statistical analysis to analyze the occurrence patterns, affected areas, and intensity changes of flood disasters, and constructing corresponding early warning systems and risk assessment models. Simultaneously, it focuses on how to utilize existing road network information, combined with GIS and traffic flow data, to analyze and optimize escape routes in flood disasters. By simulating road traffic conditions under different flood scenarios, potential traffic bottlenecks and danger zones can be identified to achieve safe and efficient evacuation guidance during flood disasters.

[0003] Currently, existing route planning methods in urban flood scenarios rely on highly complex algorithms such as machine learning or genetic algorithms to mine and analyze historical data. This makes it difficult to effectively and quantitatively assess road risks or the degree of impact of floods on roads when floods occur or are about to occur, thus affecting the accuracy and effectiveness of evacuation route planning. Summary of the Invention

[0004] This application provides a method, apparatus, equipment, storage medium, and program product for hazard avoidance route planning, which addresses the shortcomings of existing technologies that, through the analysis of historical data, are insufficient to effectively and quantitatively assess the degree of road risk or road damage during or in the event of floods, thus affecting the accuracy and effectiveness of hazard avoidance route planning.

[0005] This application provides a risk avoidance path planning method, including: Obtain risk data on flooding disasters in the area to be planned; the risk data includes historical risk data and real-time monitoring data. In the road network topology of the area to be planned, a road risk index is calculated for any two road nodes based on the risk data; the road risk index is used to characterize the traffic capacity of the sub-path. Using the road risk index as the weight value of the sub-path, and based on the starting node and ending node to be planned, the Dixtra algorithm is used to traverse each of the road nodes to plan the optimal risk avoidance path from the starting node to the ending node.

[0006] In one embodiment, the step of traversing each road node using the Dixtro algorithm based on the starting node and the ending node to be planned, and planning the optimal risk avoidance path from the starting node to the ending node, includes: Initialize the visited node list, the unvisited node list, and the risk weight array; add the starting node to the visited node list; and add all road nodes in the road network topology except the starting node to the unvisited node list. Based on the starting node and ending node to be planned, the Dixtra algorithm is used to traverse each road node in the list of unvisited nodes, starting from the starting node. During the traversal, a greedy algorithm is used to select the target node with the smallest path risk weight between the unvisited node list and the starting node, and the target node is added to the visited node list. Obtain each neighboring node of the target node, and calculate the minimum path risk weight between the starting node and each of the neighboring nodes; the elements in the risk weight array are used to characterize the minimum path risk weight between the starting node and each marked node in the visited node list; The optimal node is selected from the neighboring nodes according to the minimum path risk weight, and the optimal node is added to the list of unvisited nodes; wherein, the optimal node is a neighboring node whose target path risk weight is less than the minimum path risk weight; the target path risk weight is the sum of the minimum path risk weight corresponding to the target node in the risk weight array and the weight value of the target sub-path, and the target sub-path is the sub-path between the target node and the optimal node; The risk weight array is updated based on the target path risk weight of the optimal node. The steps of selecting the target node with the smallest path risk weight between the starting node and the unvisited node from the list of unvisited nodes using a greedy algorithm and adding the target node to the list of visited nodes are repeated until the target node is the termination node. The optimal risk avoidance path between the starting node and the termination node is determined according to the risk weight array.

[0007] In one embodiment, calculating the road risk index of a sub-path between any two road nodes based on the risk data in the road network topology of the area to be planned includes: In the road network topology of the area to be planned, the environmental adjustment coefficient of each road node is calculated based on the historical risk data in the risk data. Based on the real-time monitoring data in the risk data and the environmental adjustment coefficient, calculate the water accumulation risk index of the sub-path between any two road nodes within a future preset time period; Based on the historical risk data, calculate the risk probability index of the sub-path between any two road nodes; the risk probability index is used to measure the probability of a flood risk event occurring within a unit length of the sub-path. Based on the water accumulation risk index and the risk probability index of each sub-path, the road risk index of the sub-path is predicted within a preset time period in the future.

[0008] In one embodiment, calculating the water accumulation risk index of any two road nodes within a preset time period based on real-time monitoring data from the risk data and the environmental adjustment coefficient includes: Based on the real-time monitoring data in the risk data, a road resilience index is calculated for each road node; the road resilience index is used to characterize the ability of the road node to recover from a flooded environment to provide basic road traffic services; the real-time monitoring data includes the actual flood depth and the future rainfall per unit time. Based on the road resilience index and the environmental adjustment coefficient, the blockage coefficient of each road node is calculated within a preset time period in the future; the blockage coefficient is used to characterize the blockage situation of the road node affected by the depth of water accumulation; Obtain the low-lying nodes in the sub-path between any two road nodes, and calculate the average value of the blockage coefficient of each low-lying node to obtain the water accumulation risk index of the sub-path in the future preset time period.

[0009] In one embodiment, calculating the risk probability index of the sub-path between any two road nodes based on the historical risk data includes: Based on the historical risk data, determine the road risk parameters of the sub-path between any two road nodes; the road risk parameters include road length, number of low-lying nodes, and target distance between any two low-lying nodes. Based on the road risk parameters of each sub-path, determine the risk probability index of the sub-path; Wherein, if there are no low-lying nodes in the sub-path, the risk probability index of the sub-path is a first preset value; if there are low-lying nodes in the sub-path, and the target distance between any two low-lying nodes is greater than a preset maximum impassable distance, the risk probability index of the sub-path is calculated based on the road length, the number of low-lying nodes, and the target distance according to a first preset algorithm; if there are low-lying nodes in the sub-path, and the target distance between any two low-lying nodes is less than or equal to a preset maximum impassable distance, the risk probability index of the sub-path is a second preset value.

[0010] In one embodiment, calculating the environmental adjustment coefficient for each road node based on historical risk data from the risk data includes: Based on the historical risk data in the aforementioned risk data, the historical water accumulation depth and historical road resilience index of each road node are determined. Based on the correlation between the blockage coefficient and the water depth, the environmental adjustment coefficient of the road node is calculated using the undetermined coefficient method, based on the historical water depth and the historical road resilience index. The blocking coefficient is calculated based on the water depth, road resilience index, and environmental adjustment coefficient according to the second preset algorithm. In the correlation, the blocking coefficient is the target value when the water depth of the road node reaches the preset maximum passable depth.

[0011] This application also provides a risk avoidance path planning device, including the following modules: The data acquisition module is used to acquire risk data on flooding disasters in the area to be planned; the risk data includes historical risk data and real-time monitoring data. The risk assessment module is used to calculate the road risk index of a sub-path between any two road nodes based on the risk data in the road network topology of the area to be planned; the road risk index is used to characterize the traffic capacity of the sub-path. The path planning module is used to use the road risk index as the weight value of the sub-path, and based on the starting node and ending node to be planned, it uses the Dixtra algorithm to traverse each of the road nodes to plan the optimal risk avoidance path from the starting node to the ending node.

[0012] This application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the above-described risk avoidance path planning methods.

[0013] This application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the risk avoidance path planning method as described above.

[0014] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the risk avoidance path planning method as described above.

[0015] The evacuation path planning method, apparatus, equipment, storage medium, and program products provided in this application acquire historical risk data and real-time monitoring data of flood disasters in the area to be planned. Based on the acquired historical risk data and real-time monitoring data, they calculate the road risk index of sub-paths between any two road nodes within the road network topology of the area to be planned, thereby achieving a quantitative assessment of road capacity. Furthermore, using the road risk index as the weight value of the sub-path, the Dixtra algorithm is employed to traverse the road nodes between the starting and ending nodes, planning the optimal evacuation path with the minimum risk index between the starting and ending nodes. By using the road risk index to achieve a quantitative assessment of road capacity and risk by combining historical and real-time monitoring data, and using this as the path weight, the Dixtra algorithm is used to plan the optimal evacuation path with the lowest risk from the starting node to the ending node, ensuring the availability of the evacuation path and thus guaranteeing the accuracy and effectiveness of the planned evacuation path. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating the risk avoidance path planning method provided in the embodiments of this application.

[0018] Figure 2 This is a schematic diagram of the structure of the obstacle avoidance path planning device provided by the present invention.

[0019] Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0021] This application provides a method for planning evacuation routes, applicable to flood disaster scenarios, particularly urban flood disaster scenarios. It can quantitatively assess and analyze the disaster risk or the degree of impact of floods on roads when floods occur or are about to occur, thereby planning the lowest-risk travel routes to guide emergency evacuation, achieving safe and efficient evacuation in flood-affected scenarios, and effectively reducing traffic disruptions and safety risks caused by floods.

[0022] Specifically, Figure 1 This is a flowchart illustrating the risk avoidance path planning method provided in the embodiments of this application, as shown below. Figure 1 As shown, the method includes the following steps: Step 100: Obtain flood risk data for the area to be planned; the risk data includes historical risk data and real-time monitoring data; Step 200: In the road network topology of the area to be planned, calculate the road risk index of the sub-path between any two road nodes based on the risk data; the road risk index is used to characterize the traffic capacity of the sub-path. Step 300: Using the road risk index as the weight value of the sub-path, and based on the starting node and ending node to be planned, the Dixtra algorithm is used to traverse each of the road nodes to plan the optimal risk avoidance path from the starting node to the ending node.

[0023] Obtain risk data on flood disasters in the area to be planned. This risk data includes historical risk data and real-time monitoring data. The historical risk data is obtained by data mining and analysis based on historical flood disasters in the area to be planned, while the real-time monitoring data is obtained by real-time monitoring of the risk of flood disasters in the area to be planned.

[0024] In the road network topology of the area to be planned, the road risk index of the sub-path between any two road nodes is calculated based on risk data.

[0025] For the road network topology, roads are described in the form of a road network within the area to be planned. The regional road network consists of a finite number of "nodes" (V) and "edges" (E), and their relationship can be represented as G(V,E). Any road network can be represented by an adjacency matrix of the set of nodes V, as shown in Formula 1: , (1) in, This indicates the number of road nodes within the area to be planned. Used to characterize road nodes and Whether they are connected, that is, whether they are road nodes. and Does an "edge" exist between them? Represents road nodes and There are "edges" between them, meaning that two nodes are connected. Represents road nodes and There are no "edges" between them, and the two nodes are not connected.

[0026] When calculating the road risk index of a sub-path that is still under construction between any two road nodes, the process is based on the adjacency matrix corresponding to the road network topology. First, the connectivity between road nodes is assigned a value to characterize whether a sub-path exists between any two road nodes. Then, the road risk index of the sub-path is calculated based on this.

[0027] When assigning values ​​to road connectivity, the connectivity weights of the road network topology can also be represented using an adjacency matrix: , (2) In Formula 2, if any two road nodes and If the points are connected, then the weight of the subpath between them is... If two road nodes belong to the same node, their corresponding weight is 0; otherwise, if any two road nodes belong to the same node, their weight is 0. and The points are not connected and have an infinite weight, which indicates that there is no sub-path between them.

[0028] Optionally, a road risk index for a sub-path between any two road nodes is used to characterize the traffic capacity of that sub-path. This traffic capacity quantifies the degree of road risk and the impact of road disasters. In other words, the road risk index is an indicator used to characterize road traffic capacity and can be used to quantitatively assess the traffic risk and the degree of impact of flood disasters on roads in flood scenarios. The road risk index for a sub-path between any two road nodes is used to characterize the traffic capacity of that sub-path, enabling a quantitative assessment of road traffic risk and the degree of disaster.

[0029] When calculating the road risk index of sub-paths between any two road nodes based on acquired risk data, historical risk data can be used to identify risk nodes prone to waterlogging and flooding. Based on this, risk nodes, their adjacent nodes, and road nodes connected to risk nodes are weighted according to connectivity between road nodes. Furthermore, the actual disaster risk of each road node is analyzed based on real-time monitoring data. Therefore, based on historical risk nodes and the real-time disaster risk of each road node, a comprehensive assessment of the road risk index for each road node is obtained.

[0030] In one embodiment, the historical risk index of each road node is assessed based on historical risk data, and the real-time risk index of each road node is assessed based on real-time monitoring data. The road nodes are then weighted according to the historical and real-time risk indices to comprehensively assess the overall risk index of each road node. Based on this, and considering the connectivity between road nodes, the road risk index of the sub-path between any two road nodes is assessed based on the overall risk index of those two road nodes.

[0031] In another embodiment, the actual risk index of each road node is predicted or determined based on real-time monitoring data. Then, the historical risk index of each road node is evaluated based on historical risk data. The actual risk index is weighted based on the historical risk index to obtain the comprehensive risk index of each road node. On this basis, combined with the connectivity between road nodes, the road risk index of the sub-path between any two road nodes is determined according to the comprehensive risk index of any two road nodes.

[0032] The calculated road risk index is used as the weight value of the sub-path. The sub-path corresponds to an "edge" in the road network topology, and the road risk index of the sub-path is used as its weight value, that is, the road risk index is used as the "edge" weight. Based on the starting node and the ending node to be planned, the Dixtra algorithm is used to traverse all road nodes between the starting node and the ending node to plan the optimal risk avoidance path between the starting node and the ending node.

[0033] In this approach, given a clear starting and ending node for the planned hazard avoidance path, the road risk index is used as the weight value for each sub-path, thus constructing a directed weighted graph of the road network topology from the starting node to the ending node. Based on this directed weighted graph, the Dixtra algorithm is used to traverse all road nodes between the starting and ending nodes to plan the optimal hazard avoidance path.

[0034] Furthermore, Dixtra's algorithm is a graph theory algorithm used to solve the single-source shortest path problem in weighted graphs. Dixtra's algorithm is based on a greedy strategy, progressively expanding the shortest paths from the starting node (i.e., the source node) to all other nodes.

[0035] Based on this, when planning the optimal risk avoidance path from the starting node to the ending node, the road risk index is used as the path weight. The Dixtra algorithm is used to gradually expand the shortest path from the starting node to other nodes, that is, the path with the minimum risk, until it is expanded to the ending node, so as to obtain the optimal risk avoidance path with the minimum risk from the starting node to the ending node.

[0036] In flood emergency scenarios, especially when urban areas experience waterlogging, some roads may become functionally unusable due to water accumulation, leading to reduced road network service capacity and increased risks for vehicles and pedestrians. Related path planning methods often only consider distance as a weight to plan the shortest escape route to guide pedestrians to safe areas, but they cannot accurately measure road capacity under flood conditions, making it difficult to guarantee the availability of the planned escape routes. In this embodiment, a road risk index is used as an indicator to measure road risk. The quantitative calculation result of this index is used as the weight of the road network topology, thereby achieving a quantitative evaluation of road risk to guide the planning of escape routes and ensuring the availability of the planned escape routes.

[0037] In this embodiment, historical risk data and real-time monitoring data of flood disasters in the area to be planned are acquired. Based on the acquired historical risk data and real-time monitoring data, the road risk index of the sub-path between any two road nodes is calculated in the road network topology of the area to be planned, thereby achieving a quantitative assessment of road capacity. Furthermore, the road risk index is used as the weight value of the sub-path. Using the Dixtra algorithm, the road nodes between the starting and ending nodes are traversed to plan the optimal avoidance path with the minimum risk index between the starting and ending nodes. By using the road risk index to achieve a quantitative assessment of road capacity and risk by combining historical data and real-time monitoring data, and using this as the path weight, the optimal avoidance path with the lowest risk from the starting node to the ending node is planned using the Dixtra algorithm, ensuring the availability of the avoidance path and thus ensuring the accuracy and effectiveness of the planned avoidance path.

[0038] By combining historical and real-time data, the road risk index is assessed. In the risk assessment, not only can historical data be used as a reference, but real-time conditions can also be combined for assessment, so as to achieve a comprehensive and multi-level assessment of road disaster risk and improve the accuracy of the assessment results.

[0039] Furthermore, based on the road risk index, a quantitative assessment of road capacity and traffic risk is achieved, ensuring the effectiveness and accuracy of route planning and guaranteeing the usability of the planned avoidance routes. Specifically, when planning the optimal avoidance route, the Dixtra algorithm is used. Starting from the starting node, the algorithm progressively expands the shortest path from the starting node to all other nodes. Specifically, starting from the starting node, the node currently closest to the starting node is added to the visited set, and the shortest path length from its adjacent nodes to the starting node is updated. This process is repeated until all nodes have been visited or the route has been extended to the terminal node. The resulting shortest path is the optimal avoidance route. It should be noted that "closest" and "shortest" here specifically refer to the minimum sum of the weight values ​​of the sub-paths, where the weight value is the road risk index.

[0040] In step 300, based on the starting and ending nodes to be planned, the Dixtella algorithm is used to traverse each road node and plan the optimal risk avoidance path from the starting node to the ending node. This may also include: Step 310: Initialize the visited node list, the unvisited node list, and the risk weight array; add the starting node to the visited node list; and add all road nodes in the road network topology except the starting node to the unvisited node list. Step 320: Based on the starting node and ending node to be planned, the Dixtra algorithm is used to traverse each road node in the list of unvisited nodes, starting from the starting node. Step 330: During the traversal, a greedy algorithm is used to select the target node with the smallest path risk weight between the unvisited node list and the starting node, and the target node is added to the visited node list. Step 340: Obtain each neighboring node of the target node, and calculate the minimum path risk weight between the starting node and each of the neighboring nodes; the elements in the risk weight array are used to characterize the minimum path risk weight between the starting node and each marked node in the visited node list. Step 350: Select the optimal node from each of the neighboring nodes according to the minimum path risk weight, and add the optimal node to the unvisited node list; wherein, the optimal node is a neighboring node whose target path risk weight is less than the minimum path risk weight; the target path risk weight is the sum of the minimum path risk weight corresponding to the target node in the risk weight array and the weight value of the target sub-path, and the target sub-path is the sub-path between the target node and the optimal node; Step 360: Update the risk weight array based on the target path risk weight of the optimal node, return and execute the step of selecting the target node with the smallest path risk weight between the starting node and the unvisited node from the list of unvisited nodes using a greedy algorithm, and add the target node to the list of visited nodes, until the target node is the termination node, and determine the optimal risk avoidance path between the starting node and the termination node according to the risk weight array.

[0041] First, initialize the visited node list, the unvisited node list, and the risk weight array. The visited node list records the road nodes visited during the traversal, while the risk weight array records the currently known minimum path risk weight. The initialization of these arrays specifically includes adding the starting node to the visited list, adding all other road nodes in the road network topology (excluding the starting node) to the unvisited node list, and setting the minimum path risk weight corresponding to the starting node in the risk weight array to a first initial value (indicating no risk cost for the starting node), and setting the minimum path risk weights corresponding to other nodes to a second initial value (indicating the nodes are unvisited). For example, the first initial value is 0, and the second initial value is infinity. .

[0042] During the traversal, starting from the starting node, the shortest path from the starting node to all other nodes is gradually expanded. This shortest path corresponds to the path with the minimum path risk weight. In each node expansion process, a greedy algorithm is used to select the target node closest to the starting node from the list of unvisited nodes. The path closest to the starting node has the minimum path risk weight.

[0043] In one embodiment, the road nodes in the unvisited node list are sorted in priority order, which is determined by the path risk weight relative to the starting node. When selecting the target node with the lowest path risk weight relative to the starting node, it can be selected from the unvisited node list in priority order.

[0044] Furthermore, for the target node, its neighboring nodes are obtained, and the minimum path risk weight between the starting node and each neighboring node is calculated. The elements in the risk weight array are used to represent the minimum path risk weight between the starting node and each marked node in the visited node list. The minimum path risk weight corresponding to any marked node in the risk weight array is obtained by updating the known minimum path risk weight when traversing the marked node.

[0045] Based on the calculated minimum path risk weights between each adjacent node and the starting node, the optimal node is selected from the adjacent nodes and added to the unvisited node list. The priority order of each road node in the unvisited node list is then updated. The optimal node is an adjacent node whose target path risk weight is less than its minimum path risk weight. The target path risk weight is the sum of the minimum path risk weight of the target node in the risk weight array and the weight of the target sub-path. The target sub-path is the sub-path between the target node and the optimal node.

[0046] Update the risk weight array based on the target path risk weight, return and execute step 330, which uses a greedy algorithm to select the target node with the smallest path risk weight between the starting node and the unvisited node list, and add the target node to the visited node list. Then select the next unvisited node and gradually expand the road nodes until the selected target node is the termination node, that is, when it is expanded to the termination node, determine the optimal risk avoidance path from the starting node to the termination node based on the risk weight array.

[0047] In one embodiment, the visited node list, the unvisited node list, and the risk weight array are initialized. The process involves adding the starting node to the list of visited nodes and all other unvisited road nodes to the list of unvisited nodes, prioritizing them according to the path risk weight between them and the starting node. Further, in the risk weight array, the path risk weight from the starting node to itself is... If the risk weight is set to 0, the risk weight of other road nodes to the starting node is set to infinity, indicating that the minimum path risk weight has not yet been found.

[0048] The algorithm iterates through the unvisited node list in priority order. Specifically, a greedy algorithm is used to select the target node with the lowest path risk weight between itself and the starting node from the unvisited node list. This target node is then selected as the current node and added to the visited node list. Next, all adjacent nodes of the current node are traversed. If the path risk weight between an adjacent node and the starting node is less than the known minimum path risk weight, the risk weight array is updated, and the adjacent node is added to the unvisited node list, updating the priority order of the road nodes in the unvisited node list. This iterative process is repeated until all road nodes have been visited or the currently selected target node is the termination node. The path corresponding to the currently known minimum path risk weight recorded in the risk weight array is the planned optimal risk-avoidance path.

[0049] In one embodiment, during the traversal using Dixtella's algorithm, for each target node... neighboring nodes To determine whether there is a risk path with a smaller risk weight, i.e., to determine Whether it is valid, This is the risk value adjacency matrix of the road network topology obtained by using the road risk index as the weight value of the sub-paths. Represents the target node With neighboring nodes The weight values ​​of the sub-paths between them, i.e., the target node. With neighboring nodes The road risk index of the sub-paths between them. If true, then update. The process continues until the terminal node is reached. Then, the path with the minimum risk weight from the starting node to the terminal node is determined based on the risk weight array. The sum of the road risk indices of all sub-paths on this path is calculated, which is the minimum risk coefficient of the optimal risk avoidance path.

[0050] In urban flooding scenarios, the main risk to road traffic comes from traffic disruptions caused by water accumulation. The road risk index is determined by both the water accumulation risk index and the risk probability index. Optionally, the assessment of the road risk index is obtained by evaluating the disaster resistance risk index of roads in the planning area over a future period of time when flooding occurs or when an impending flood is detected.

[0051] Therefore, step 200 may also include: Step 210: In the road network topology of the area to be planned, calculate the environmental adjustment coefficient of each road node based on the historical risk data in the risk data; Step 220: Based on the real-time monitoring data in the risk data and the environmental adjustment coefficient, calculate the water accumulation risk index of the sub-path between any two road nodes within a future preset time period; Step 230: Based on the historical risk data, calculate the risk probability index of the sub-path between any two road nodes; the risk probability index is used to measure the probability of a flood risk event occurring within a unit length of the sub-path; Step 240: Based on the water accumulation risk index and the risk probability index of each sub-path, predict the road risk index of the sub-path within a preset time period in the future.

[0052] When calculating the road risk index of each sub-path, based on historical risk data in the road network topology of the area to be planned, the environmental adjustment coefficient of each road node is calculated. Then, based on real-time monitoring data and the calculated environmental adjustment coefficient, the water accumulation risk index of the sub-path between any two road nodes is calculated within a preset future time period. Further, based on historical risk data, the risk probability index of the sub-path between any two road nodes is calculated; this risk probability index measures the probability of a flood risk event occurring within a unit length of the sub-path. Based on the water accumulation risk index and risk probability index of each sub-path, the road risk index of the sub-path within a preset future time period is predicted. Specifically, based on the water accumulation risk index and risk probability index of any given sub-path, the road risk index of that sub-path within a preset future time period is predicted.

[0053] Optional, flood risk index water depth in low-lying areas and road resilience index The combined effects include, among them, the depth of water accumulation. Water level sensors pre-installed in low-lying areas of the road can be used to collect data in real time. If the water level sensors used have characteristics such as high accuracy, low power consumption, and real-time transmission, they can meet the requirements for accuracy and timeliness in measuring water depth. Road resilience index This refers to the inherent properties of roads, reflecting their ability to cope with floods in a natural, unmanaged environment. Specifically, the road resilience index... This refers to the road's ability to recover from flooding to a standard capable of providing basic road traffic services. Road resilience index. The road resilience index is positively correlated with road design and drainage capacity; the more reasonable the road design and the stronger the drainage capacity, the higher the road resilience index. The better.

[0054] Generally speaking, low-lying areas on roads are prone to water accumulation. For any low-lying area on a road, its road resilience index... Determined by the external physical environment, which is mainly related to road design, specifically including factors such as road lateral / longitudinal slope, catchment area, and inlet slope.

[0055] Based on this, step 200 may also include: Step 221: Based on the real-time monitoring data in the risk data, calculate the road resilience index for each road node; the road resilience index is used to characterize the ability of the road node to recover from a flooded environment to provide basic road traffic services; the real-time monitoring data includes the actual flood depth and the future rainfall per unit time. Step 222: Calculate the blockage coefficient of each road node within a preset time period based on the road resilience index and the environmental adjustment coefficient; the blockage coefficient is used to characterize the blockage situation of the road node affected by the depth of water accumulation. Step 223: Obtain the low-lying nodes in the sub-path between any two road nodes, and calculate the average value of the blockage coefficient of each low-lying node to obtain the water accumulation risk index of the sub-path in the future preset time period.

[0056] When calculating the flooding risk index, the road resilience index of each road node is first calculated based on real-time monitoring data from the risk data. Real-time monitoring data includes the current actual flooding depth of the road node and the expected rainfall per unit time. Then, based on the road resilience index and the environmental adjustment coefficient, the blockage coefficient of the road node is calculated for a predetermined time period in the future. This blockage coefficient characterizes the blockage situation of the road node due to flooding depth. Low-lying nodes in the sub-path between any two road nodes are obtained, and the average blockage coefficient of each low-lying node is calculated to obtain the flooding risk index of that sub-path for the predetermined time period in the future.

[0057] Optional, road resilience index of road nodes It can be calculated using the following formula 3: (3) in, This refers to the predicted rainfall within a preset time period, based on real-time monitoring data. The maximum water level depth after a certain period of water accumulation at a low-lying node within a pre-set timeframe can be predicted based on rainfall and actual water depth. This formula comprehensively considers the impact of rainfall and water depth on the road resilience index of low-lying nodes, thus obtaining a more accurate resilience value.

[0058] To more accurately describe the blockage situation of individual low-lying nodes in a road due to water depth, a blockage coefficient is introduced. ,in, for Low-lying road nodes Real-time water depth. Blockage coefficient. With water depth Strongly correlated and influenced by the environmental moderating coefficient of road nodes. and road resilience index The combined effects. Specifically, this can be expressed as: (4) For low-lying nodes, historical risk data can be used to identify them. Based on historical risk data, combined with design parameters such as road lateral / longitudinal slope, catchment area, and inlet slope, road nodes that are prone to water accumulation or are greatly affected by water accumulation can be identified as low-lying nodes.

[0059] Furthermore, the environmental adjustment coefficient is calculated using the undetermined coefficient method based on historical risk data. Specifically, step 210, calculating the environmental adjustment coefficient for each road node based on historical risk data, may further include: Step 211: Based on the historical risk data in the risk data, determine the historical water accumulation depth and historical road resilience index of each road node; Step 212: Based on the correlation between the blockage coefficient and the water depth, the environmental adjustment coefficient of the road node is calculated using the undetermined coefficient method, according to the historical water depth and the historical road resilience index. The blocking coefficient is calculated based on the water depth, road resilience index, and environmental adjustment coefficient according to the second preset algorithm. In the correlation, the blocking coefficient is the target value when the water depth of the road node reaches the preset maximum passable depth.

[0060] Based on historical risk data, the historical water accumulation depth and historical road resilience index of each road node are determined. Both the historical water accumulation depth and the historical road resilience index are actual values ​​recorded in historical monitoring. Based on the correlation between the blockage coefficient and water accumulation depth, the undetermined coefficient method is used to calculate the environmental adjustment coefficient of each road node based on the historical water accumulation depth and the historical road resilience index. Specifically, the environmental adjustment coefficient of any road node is calculated based on its historical water accumulation depth and the corresponding historical road resilience index at the same time. The environmental adjustment coefficients of different road nodes can be the same or different.

[0061] Furthermore, the blockage coefficient is calculated based on the water depth, road resilience index, and environmental adjustment coefficient according to the second preset algorithm, which characterizes the correlation between the blockage coefficient and the water depth.

[0062] Optionally, the second preset algorithm is as shown in Formula 4 above. In one embodiment, based on the correlation between the blocking coefficient and the water depth, the water depth of the road node reaches its preset maximum passable depth. At this point, the congestion coefficient is the target value, used to characterize the critical state of congestion at which the road is passable.

[0063] Taking a target value of 1 as an example, at this time, the following conditions are met: (5) Therefore, the environmental adjustment coefficient of the road node can be obtained. The method of undetermined coefficients is used, substituting the historical water depth and historical road resilience index of the road node into the formula for solving the environmental adjustment coefficient. Then, by using logarithmic tables and other methods, the environmental adjustment coefficient of the road node can be obtained. The value of .

[0064] Based on this, the water depth at road junctions exceeds the maximum passable depth. At this time, the road is impassable. Here, the congestion coefficient is also used to represent the congestion state as infinite, that is: (6) To assess the real-time flooding risk index of a single road Calculate the congestion coefficient of all low-lying nodes in the road. The average value is used as the flood risk index for that road. The value of is expressed as follows: (7) in, This refers to the number of low-lying nodes along a road that may experience water accumulation. and These are the low-lying road nodes. The real-time water depth and road resilience index can be determined based on real-time monitoring data. In practical applications, low-lying nodes can be identified as potential risk points in advance through the analysis of historical risk data, and water level sensors can be installed at corresponding key locations to monitor the actual water depth of low-lying nodes in real time.

[0065] Considering that floods are often accompanied by thunderstorms, a scheme is introduced to predict the road risk index over a future period based on weather factors. Based on predicted heavy rain warnings, heavy rain is categorized into multiple warning levels: blue, yellow, orange, and red. A corresponding rainfall estimate k (in mm) is assigned to each warning level per unit time. For example, blue warning (k=4), yellow warning (k=8), orange warning (k=16), and red warning (k=32), where k∈{4,8,16,32}. Optionally, the rainfall estimate k for each warning level can also correspond to a range of values, without specific limitations.

[0066] Based on the above settings, a blocking coefficient is introduced. The prediction function is used to predict the future duration. Congestion coefficient of a single low-lying node in the road The prediction function : (8) in, The maximum rainfall threshold (in mm) is set to be used to calculate the actual rainfall. Convert to relative rainfall for subsequent calculations.

[0067] According to Formula 8 above, based on the real-time monitoring data of each road node and the calculated environmental adjustment coefficient, the congestion coefficient of any road node, especially any low-lying node, can be calculated within a preset time period t. Therefore, for any sub-path between two road nodes, the water accumulation risk index of that sub-path within the preset time period t can be determined. This is the average of the blocking coefficients of all low-lying nodes on that sub-path, i.e.: (9) The road waterlogging risk index is calculated based on Formula 9, which can comprehensively consider the influence of multiple factors such as water depth, road resilience index and real-time weather factors, and comprehensively and quantitatively assess the road waterlogging risk index.

[0068] Furthermore, the risk probability index, which measures the probability of flooding occurring within a unit length of road, can be calculated based on historical risk data. Step 230 may also include: Step 231: Based on the historical risk data, determine the road risk parameters of the sub-path between any two road nodes; the road risk parameters include road length, number of low-lying nodes, and target distance between any two low-lying nodes. Step 232: Determine the risk probability index of each sub-path based on the road risk parameters of each sub-path; Wherein, if there are no low-lying nodes in the sub-path, the risk probability index of the sub-path is a first preset value; if there are low-lying nodes in the sub-path, and the target distance between any two low-lying nodes is greater than a preset maximum impassable distance, the risk probability index of the sub-path is calculated based on the road length, the number of low-lying nodes, and the target distance according to a first preset algorithm; if there are low-lying nodes in the sub-path, and the target distance between any two low-lying nodes is less than or equal to a preset maximum impassable distance, the risk probability index of the sub-path is a second preset value.

[0069] Based on historical risk data, road risk parameters for sub-paths between any two road nodes are determined. These parameters include road length, number of low-lying nodes, and target distance between any two low-lying nodes. Based on these road risk parameters, a risk probability index for each sub-path is determined.

[0070] Risk Probability Index It is an important indicator for measuring the probability of flooding risks occurring within a unit length of road, and its value range can be limited to... Between. The calculation of this index takes into account road length. Number of low-lying nodes in the road and the maximum impassable distance between two low-lying nodes. .

[0071] Specifically, if there are no low-lying nodes in the sub-path, the risk probability index of the sub-path is the first preset value; if there are low-lying nodes in the sub-path, and the target distance between any two low-lying nodes is greater than the preset maximum impassable distance. The risk probability index of the sub-path is calculated based on the road length, the number of low-lying nodes, and the target distance using the first preset algorithm; if there are low-lying nodes in the sub-path, and the target distance between any two low-lying nodes is less than or equal to the preset maximum impassable distance. Then the risk probability index of the sub-path is the second preset value.

[0072] For example, the first preset value is 0, the second preset value is 1, and the risk probability index is... The calculation method is as follows: when That is, when there are no low-lying nodes in the road. ; when and This occurs when there are low-lying nodes in the road, and the distance between any two low-lying nodes exceeds the maximum impassable distance. hour, ; when and When the distance between two low-lying nodes is less than or equal to the maximum impassable distance. At this time, the road is in a state of maximum impassability. = 1.

[0073] Right now: (10) Based on the water accumulation risk index and risk probability index of each sub-path, the road risk index of each sub-path is calculated. To comprehensively assess the overall risk level of the road network under flooding conditions, a risk index adjacency matrix of the road network topology is constructed based on the road risk indices of each sub-path. : (11) in, This indicates that at time t, from node To the node The road risk index, also known as the node With nodes Road risk index of sub-paths between: (12) Represents the node at time t With nodes The risk index of water accumulation on the sub-paths between them. Represents a node With nodes The risk probability index of the subpaths between nodes. If nodes With nodes There are directly connected sub-paths between them, that is ,but The corresponding road risk index; if node With nodes There are no directly connected roads between them, that is ,but Set to infinity ;when At that time, the risk index from the same node to itself is .

[0074] (13) In the matrix In this algorithm, the matrix elements represent the road risk index between each node in the road network topology, which is also the risk value of the road. This risk value is used as the weight value of the road to construct a weighted graph. After the starting node and ending node of the plan are determined, the Dixtra algorithm is used to find the optimal path with the lowest risk value based on the weighted graph, thereby planning the risk-avoidance path with the lowest risk.

[0075] In this embodiment, a precise risk quantification assessment model is established by integrating the water accumulation risk index and the risk probability index. This model can comprehensively and quantitatively assess the traffic risk of roads in flood disaster scenarios. The model considers not only direct risk factors such as water depth and duration, but also indirect risk factors such as the distribution of low-lying road nodes and drainage efficiency. Based on multiple factors, it transforms road risk and traffic capacity into quantifiable risk indices, achieving a comprehensive and multi-layered risk assessment of roads in flood disaster scenarios. This ensures the availability and accuracy of planned evacuation routes.

[0076] Furthermore, by combining historical risk data with real-time monitoring data, the road risk index can be predicted for a predetermined timeframe by integrating real-time flooding risk index and weather warning information. First, by analyzing historical data, a correlation is established between the flooding risk index and weather factors. When the latest weather warning information is obtained based on real-time monitoring data, the road risk index can be updated according to the correlation between the flooding risk index and weather factors, thus providing timely and accurate risk alerts to emergency management departments.

[0077] Furthermore, by integrating the risk indices of various roads in the road network, an intuitive and easy-to-use risk matrix is ​​constructed. Based on this matrix, the Dixtra algorithm is used to quickly and effectively plan the evacuation route with the lowest risk coefficient from one region to another. Based on the prediction of road risk indices over a preset time period, dynamic evacuation route planning can be achieved to cope with possible traffic congestion, road closures, and other emergencies, ensuring the safe and efficient evacuation of personnel in emergency scenarios.

[0078] The following describes the hazard avoidance path planning device provided in the embodiments of this application. The hazard avoidance path planning device described below can be referred to in correspondence with the hazard avoidance path planning method described above.

[0079] Reference Figure 2 The obstacle avoidance path planning device provided in this application includes: Data acquisition module 10 is used to acquire risk data of flood disasters in the area to be planned; the risk data includes historical risk data and real-time monitoring data; The risk assessment module 20 is used to calculate the road risk index of a sub-path between any two road nodes based on the risk data in the road network topology of the area to be planned; the road risk index is used to characterize the traffic capacity of the sub-path. The path planning module 30 is used to use the road risk index as the weight value of the sub-path, and based on the starting node and ending node to be planned, to traverse each of the road nodes using the Dixtra algorithm to plan the optimal risk avoidance path from the starting node to the ending node.

[0080] In one embodiment, the path planning module 30 is further configured to: Initialize the visited node list, the unvisited node list, and the risk weight array; add the starting node to the visited node list; and add all road nodes in the road network topology except the starting node to the unvisited node list. Based on the starting node and ending node to be planned, the Dixtra algorithm is used to traverse each road node in the list of unvisited nodes, starting from the starting node. During the traversal, a greedy algorithm is used to select the target node with the smallest path risk weight between the unvisited node list and the starting node, and the target node is added to the visited node list. Obtain each neighboring node of the target node, and calculate the minimum path risk weight between the starting node and each of the neighboring nodes; the elements in the risk weight array are used to characterize the minimum path risk weight between the starting node and each marked node in the visited node list; The optimal node is selected from the neighboring nodes according to the minimum path risk weight, and the optimal node is added to the list of unvisited nodes; wherein, the optimal node is a neighboring node whose target path risk weight is less than the minimum path risk weight; the target path risk weight is the sum of the minimum path risk weight corresponding to the target node in the risk weight array and the weight value of the target sub-path, and the target sub-path is the sub-path between the target node and the optimal node; The risk weight array is updated based on the target path risk weight of the optimal node. The steps of selecting the target node with the smallest path risk weight between the starting node and the unvisited node from the list of unvisited nodes using a greedy algorithm and adding the target node to the list of visited nodes are repeated until the target node is the termination node. The optimal risk avoidance path between the starting node and the termination node is determined according to the risk weight array.

[0081] In one embodiment, the risk assessment module 20 is further configured to: In the road network topology of the area to be planned, the environmental adjustment coefficient of each road node is calculated based on the historical risk data in the risk data. Based on the real-time monitoring data in the risk data and the environmental adjustment coefficient, calculate the water accumulation risk index of the sub-path between any two road nodes within a future preset time period; Based on the historical risk data, calculate the risk probability index of the sub-path between any two road nodes; the risk probability index is used to measure the probability of a flood risk event occurring within a unit length of the sub-path. Based on the water accumulation risk index and the risk probability index of each sub-path, the road risk index of the sub-path is predicted within a preset time period in the future.

[0082] In one embodiment, the risk assessment module 20 is further configured to: Based on the real-time monitoring data in the risk data, a road resilience index is calculated for each road node; the road resilience index is used to characterize the ability of the road node to recover from a flooded environment to provide basic road traffic services; the real-time monitoring data includes the actual flood depth and the future rainfall per unit time. Based on the road resilience index and the environmental adjustment coefficient, the blockage coefficient of each road node is calculated within a preset time period in the future; the blockage coefficient is used to characterize the blockage situation of the road node affected by the depth of water accumulation; Obtain the low-lying nodes in the sub-path between any two road nodes, and calculate the average value of the blockage coefficient of each low-lying node to obtain the water accumulation risk index of the sub-path in the future preset time period.

[0083] In one embodiment, the risk assessment module 20 is further configured to: Based on the historical risk data, determine the road risk parameters of the sub-path between any two road nodes; the road risk parameters include road length, number of low-lying nodes, and target distance between any two low-lying nodes. Based on the road risk parameters of each sub-path, determine the risk probability index of the sub-path; Wherein, if there are no low-lying nodes in the sub-path, the risk probability index of the sub-path is a first preset value; if there are low-lying nodes in the sub-path, and the target distance between any two low-lying nodes is greater than a preset maximum impassable distance, the risk probability index of the sub-path is calculated based on the road length, the number of low-lying nodes, and the target distance according to a first preset algorithm; if there are low-lying nodes in the sub-path, and the target distance between any two low-lying nodes is less than or equal to a preset maximum impassable distance, the risk probability index of the sub-path is a second preset value.

[0084] In one embodiment, the risk assessment module 20 is further configured to: Based on the historical risk data in the aforementioned risk data, the historical water accumulation depth and historical road resilience index of each road node are determined. Based on the correlation between the blockage coefficient and the water depth, the environmental adjustment coefficient of the road node is calculated using the undetermined coefficient method, based on the historical water depth and the historical road resilience index. The blocking coefficient is calculated based on the water depth, road resilience index, and environmental adjustment coefficient according to the second preset algorithm. In the correlation, the blocking coefficient is the target value when the water depth of the road node reaches the preset maximum passable depth.

[0085] Figure 3 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 3 As shown, the electronic device may include: a processor 310, a communications interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communications interface 320, and the memory 330 communicate with each other via the communication bus 340. The processor 310 can call logical instructions in the memory 330 to execute a risk avoidance path planning method, which includes: Obtain risk data on flooding disasters in the area to be planned; the risk data includes historical risk data and real-time monitoring data. In the road network topology of the area to be planned, a road risk index is calculated for any two road nodes based on the risk data; the road risk index is used to characterize the traffic capacity of the sub-path. Using the road risk index as the weight value of the sub-path, and based on the starting node and ending node to be planned, the Dixtra algorithm is used to traverse each of the road nodes to plan the optimal risk avoidance path from the starting node to the ending node.

[0086] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0087] On the other hand, embodiments of this application also provide a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the risk avoidance path planning method provided by the above methods, the method including: Obtain risk data on flooding disasters in the area to be planned; the risk data includes historical risk data and real-time monitoring data. In the road network topology of the area to be planned, a road risk index is calculated for any two road nodes based on the risk data; the road risk index is used to characterize the traffic capacity of the sub-path. Using the road risk index as the weight value of the sub-path, and based on the starting node and ending node to be planned, the Dixtra algorithm is used to traverse each of the road nodes to plan the optimal risk avoidance path from the starting node to the ending node.

[0088] In another aspect, embodiments of this application also provide a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the risk avoidance path planning method provided by the above-described methods, the method comprising: Obtain risk data on flooding disasters in the area to be planned; the risk data includes historical risk data and real-time monitoring data. In the road network topology of the area to be planned, a road risk index is calculated for any two road nodes based on the risk data; the road risk index is used to characterize the traffic capacity of the sub-path. Using the road risk index as the weight value of the sub-path, and based on the starting node and ending node to be planned, the Dixtra algorithm is used to traverse each of the road nodes to plan the optimal risk avoidance path from the starting node to the ending node.

[0089] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0090] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0091] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A risk avoidance path planning method, characterized in that, include: Obtain risk data on flooding in the area to be planned; The risk data includes historical risk data and real-time monitoring data; In the road network topology of the area to be planned, the road risk index of the sub-path between any two road nodes is calculated based on the risk data. The road risk index is used to characterize the traffic capacity of the sub-path; Using the road risk index as the weight value of the sub-path, and based on the starting node and ending node to be planned, the Dixtra algorithm is used to traverse each of the road nodes to plan the optimal risk avoidance path from the starting node to the ending node.

2. The risk avoidance path planning method according to claim 1, characterized in that, Based on the starting and ending nodes to be planned, the Dixtro algorithm is used to traverse each road node to plan the optimal risk avoidance path from the starting node to the ending node, including: Initialize the visited node list, the unvisited node list, and the risk weight array; add the starting node to the visited node list; and add all road nodes in the road network topology except the starting node to the unvisited node list. Based on the starting node and ending node to be planned, the Dixtra algorithm is used to traverse each road node in the list of unvisited nodes, starting from the starting node. During the traversal, a greedy algorithm is used to select the target node with the smallest path risk weight between the unvisited node list and the starting node, and the target node is added to the visited node list. Obtain each neighboring node of the target node, and calculate the minimum path risk weight between the starting node and each of the neighboring nodes; the elements in the risk weight array are used to characterize the minimum path risk weight between the starting node and each marked node in the visited node list; The optimal node is selected from the neighboring nodes according to the minimum path risk weight, and the optimal node is added to the list of unvisited nodes; wherein, the optimal node is a neighboring node whose target path risk weight is less than the minimum path risk weight; the target path risk weight is the sum of the minimum path risk weight corresponding to the target node in the risk weight array and the weight value of the target sub-path, and the target sub-path is the sub-path between the target node and the optimal node; The risk weight array is updated based on the target path risk weight of the optimal node. The steps of selecting the target node with the smallest path risk weight between the starting node and the unvisited node from the list of unvisited nodes using a greedy algorithm and adding the target node to the list of visited nodes are repeated until the target node is the termination node. The optimal risk avoidance path between the starting node and the termination node is determined according to the risk weight array.

3. The risk avoidance path planning method according to claim 1, characterized in that, In the road network topology of the area to be planned, the road risk index of any two road nodes is calculated based on the risk data, including: In the road network topology of the area to be planned, the environmental adjustment coefficient of each road node is calculated based on the historical risk data in the risk data. Based on the real-time monitoring data in the risk data and the environmental adjustment coefficient, calculate the water accumulation risk index of the sub-path between any two road nodes within a future preset time period; Based on the historical risk data, calculate the risk probability index of the sub-path between any two road nodes; the risk probability index is used to measure the probability of a flood risk event occurring within a unit length of the sub-path. Based on the water accumulation risk index and the risk probability index of each sub-path, the road risk index of the sub-path is predicted within a preset time period in the future.

4. The risk avoidance path planning method according to claim 3, characterized in that, The calculation of the water accumulation risk index of any two road nodes within a preset time period based on real-time monitoring data from the risk data and the environmental adjustment coefficient includes: Based on the real-time monitoring data in the risk data, a road resilience index is calculated for each road node; the road resilience index is used to characterize the ability of the road node to recover from a flooded environment to provide basic road traffic services; the real-time monitoring data includes the actual flood depth and the future rainfall per unit time. Based on the road resilience index and the environmental adjustment coefficient, the blockage coefficient of each road node is calculated within a preset time period in the future; the blockage coefficient is used to characterize the blockage situation of the road node affected by the depth of water accumulation; Obtain the low-lying nodes in the sub-path between any two road nodes, and calculate the average value of the blockage coefficient of each low-lying node to obtain the water accumulation risk index of the sub-path in the future preset time period.

5. The risk avoidance path planning method according to claim 3, characterized in that, The step of calculating the risk probability index of the sub-path between any two road nodes based on the historical risk data includes: Based on the historical risk data, determine the road risk parameters of the sub-path between any two road nodes; the road risk parameters include road length, number of low-lying nodes, and target distance between any two low-lying nodes. Based on the road risk parameters of each sub-path, determine the risk probability index of the sub-path; Wherein, if there are no low-lying nodes in the sub-path, the risk probability index of the sub-path is a first preset value; if there are low-lying nodes in the sub-path, and the target distance between any two low-lying nodes is greater than a preset maximum impassable distance, the risk probability index of the sub-path is calculated based on the road length, the number of low-lying nodes, and the target distance according to a first preset algorithm; if there are low-lying nodes in the sub-path, and the target distance between any two low-lying nodes is less than or equal to a preset maximum impassable distance, the risk probability index of the sub-path is a second preset value.

6. The risk avoidance path planning method according to claim 3, characterized in that, The calculation of the environmental adjustment coefficient for each road node based on the historical risk data in the risk data includes: Based on the historical risk data in the aforementioned risk data, the historical water accumulation depth and historical road resilience index of each road node are determined. Based on the correlation between the blockage coefficient and the water depth, the environmental adjustment coefficient of the road node is calculated using the undetermined coefficient method, based on the historical water depth and the historical road resilience index. The blocking coefficient is calculated based on the water depth, road resilience index, and environmental adjustment coefficient according to the second preset algorithm. In the correlation, the blocking coefficient is the target value when the water depth of the road node reaches the preset maximum passable depth.

7. A risk avoidance path planning device, characterized in that, include: The data acquisition module is used to obtain risk data on flooding in the area to be planned. The risk data includes historical risk data and real-time monitoring data; The risk assessment module is used to calculate the road risk index of the sub-path between any two road nodes based on the risk data in the road network topology of the area to be planned. The road risk index is used to characterize the traffic capacity of the sub-path; The path planning module is used to use the road risk index as the weight value of the sub-path, and based on the starting node and ending node to be planned, it uses the Dixtra algorithm to traverse each of the road nodes to plan the optimal risk avoidance path from the starting node to the ending node.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the risk avoidance path planning method as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the risk avoidance path planning method as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the risk avoidance path planning method as described in any one of claims 1 to 6.

Images