Multi-agent-based disaster prevention and risk avoiding greenbelt system layout optimization method and system

Abstract

The invention discloses a multi-agent-based disaster prevention and risk avoiding greenbelt system layout optimization method and system, and relates to the technical field of urban planning. The method comprises the steps that original geographic data in a to-be-optimized area are received, the original geographic data are preprocessed to form effective geographic data, and the original geographic data comprise original residential area data, original road network data and original disaster prevention and risk avoiding greenbelt data; according to the invention, a multi-agent evacuation simulation model is introduced into the planning design of the disaster prevention and risk avoidance greenbelt, and multiple targets such as road congestion, greenbelt overload and the like are optimized during simulation, so that the real-time escape condition can be accurately simulated, and the real-time disaster risk of the road, the congestion risk of escape crowds and the capacity overload risk of the disaster prevention and risk avoidance greenbelt during disaster can be avoided; and an optimal escape scheme is formulated, the evacuation path and strategy can be dynamically adjusted according to different emergency requirements, and the optimal scheme under the multi-target condition is formulated.

Description

Technical Field

[0001] The present invention relates to the technical field of urban planning, and in particular to a multi-agent-based green space system layout optimization method and system. Background Art

[0002] With the acceleration of urbanization, urban population density continues to increase, and the risk of urban disasters also increases. When sudden disasters such as earthquakes, fires, and floods occur, how to efficiently organize people to evacuate to safe shelters, such as disaster prevention and evacuation green spaces, has become an important issue in urban emergency management.

[0003] The existing evacuation simulation methods have the following main problems: during the evacuation process, road congestion will affect the travel speed and path selection of people in real time. Traditional methods mostly use macro models that fail to provide real-time feedback and adjustments. At the same time, there is an imbalance in the utilization of some disaster prevention and evacuation green spaces in actual evacuations. The utilization efficiency of disaster prevention and evacuation green space resources is extremely high in some areas, while the utilization efficiency is extremely low in some areas. For this reason, we propose a multi-agent-based green space system layout optimization method and system. Summary of the invention

[0004] The purpose of the present invention is to provide a multi-agent based disaster prevention and evacuation green space system layout optimization method and system, by introducing multi-agent simulation, path planning and dynamic adjustment mechanism, combined with multi-objective optimization layout method, to provide more scientific and accurate planning decision support for urban disaster management.

[0005] To achieve the above object, the present invention provides the following technical solution: a multi-agent-based disaster prevention and risk avoidance green space system layout optimization method, comprising the following steps:

[0006] Receiving original geographic data in the area to be optimized, and preprocessing the original geographic data to form effective geographic data, wherein the original geographic data includes original residential area data, original road network data, and original disaster prevention and evacuation green space data;

[0007] Set the evacuation target, select the specified evacuation target and the multi-agent evacuation model for simulation, and the multi-agent evacuation model outputs the optimal evacuation plan;

[0008] Among them, the multi-agent evacuation model uses effective geographic data as the data source to simulate and record the real-time evacuation status, which includes the number of people entering each disaster prevention and refuge green space and the utilization efficiency, the evacuation path of each community, and the number of road users and congestion of each section of the road network in each time step;

[0009] The optimal evacuation plan is compared with the original road network data and the original disaster prevention and hazard avoidance green space data to optimize the layout of roads and disaster prevention and hazard avoidance green spaces in the area to be optimized.

[0010] Furthermore, the geographic data in the area to be optimized is obtained based on the Internet map open platform and the planning plan, as follows:

[0011] Residential area data include boundary SHP data and population of each residential area;

[0012] Road network data includes geographical location information and grade attributes of roads, and road width data;

[0013] The disaster prevention and evacuation green space data includes the green space geographical location data and the green space maximum capacity data, where the green space maximum capacity data = the total effective evacuation area of ​​the disaster prevention and evacuation green space / the effective evacuation area per capita;

[0014] The specific preprocessing of the original geographic data is as follows:

[0015] Based on GIS software, the above geographic data are integrated and processed, the geographic coordinate system is unified, and missing values ​​and outliers are processed.

[0016] Furthermore, the pre-built multi-agent evacuation model includes an agent module, an environment module and a communication module, wherein:

[0017] The agent module includes residential area agent, evacuation agent and green space agent;

[0018] The environment module includes GIS basic environment data and global real-time information, including road network data, residential area boundary data, green space location and maximum capacity data, and dynamically updated road weight and green space status data;

[0019] The communication module is used to support information exchange and resource sharing among residential intelligent agents, evacuation intelligent agents and green space intelligent agents, ensuring collaboration and synchronization among residential intelligent agents, evacuation intelligent agents and environmental modules.

[0020] Furthermore, taking the evacuation target as the goal, the optimal evacuation plan after simulation is output, which specifically includes: evacuation route planning, disaster prevention and evacuation green space capacity update, road congestion feedback update, iterative control and evacuation simulation result output, modifying the weight ratio according to the realization of different evacuation targets and generating the optimal evacuation plan.

[0021] Furthermore, the evacuation route planning is specifically as follows:

[0022] Based on the Mesa framework, we define the residential area agent, evacuation agent, green space agent and their attributes, and simulate the dynamic decision-making process of individual residents in different evacuation scenarios.

[0023] Among them, the residential area agent is used to manage the residential area data, road network data and disaster prevention and evacuation green space data in the GIS basic data information database; the evacuation agent is used to store the initial geographic data of all residential areas, roads and green spaces, and record the real-time evacuation status of each residential area during the simulation process; the green space agent is used to comprehensively evaluate the weights of roads and green spaces, sort by distance, and take the first 10 nearest disaster prevention and evacuation green spaces as the target destination candidate green space list, calculate the optimal evacuation path through the A* algorithm, and track and record the evacuation situation at different time steps in real time.

[0024] Furthermore, the capacity of the disaster prevention and evacuation green space is updated as follows:

[0025] According to the number of intelligent agents entering the disaster prevention and evacuation green space, the remaining capacity of the green space is updated. When the green space capacity is insufficient, the intelligent agent module re-evaluates the shelter selection strategy, selects other disaster prevention and evacuation green spaces that are closest and have available capacity based on the surrounding real-time environmental data, and regenerates the list for evacuation.

[0026] Furthermore, the road congestion feedback update comprises the following specific steps:

[0027] (71) The processed road network data is converted into graph structure data, where nodes represent road intersections, edges represent road segments, and the initial weights of the edges are set as follows:

[0028] The selection weight of each road is R n According to its risk factor D n and escape distance L n The specific calculation formula is:

[0029] R n =D n ×L n

[0030] Escape distance L n is the path length calculated based on the A* optimal path algorithm, and the risk factor D n The road safety influencing factors are calculated and normalized by the objective entropy weight method;

[0031] (72) The agent module has planned and generated the simulated evacuation path, calculated the road congestion degree of each road section at different time steps, and updated the weight of each road edge, as follows:

[0032] The calculation formula of congestion degree C is:

[0033]

[0034] Where N is the number of people escaping on the road section, N maxis the maximum number of people that the road segment can carry;

[0035] The weight of the road segment is adjusted according to the congestion degree C. The new weight is:

[0036] R n '=D n *L n *C

[0037] In the formula, R n ' is the new weight, D n is the risk factor, L n is the escape distance;

[0038] (73) The intelligent agent module performs the next iteration based on the updated road weights and recalculates the optimal evacuation path.

[0039] Furthermore, the iterative control and evacuation simulation result output are specifically performed in the following steps:

[0040] Set the evacuation target or the maximum number of iterations as the preset condition, determine whether the preset condition is met after each simulation, decide whether to continue iteration, and then perform multiple calculations and road congestion calculations, and perform an iterative simulation process until the preset condition is met and the evacuation simulation result is output;

[0041] The evacuation simulation results include the evacuation time distribution of the intelligent agent module, the congestion data of each road section, the remaining capacity data of the disaster prevention and evacuation green space, and the spatial distribution of the simulated evacuation path;

[0042] Modify the weight ratio according to the realization of different evacuation goals and generate the optimal evacuation plan, as follows:

[0043] The specific evacuation goals include: the closest green space distance goal, which aims to achieve the shortest straight-line distance to the target green space; the total evacuation time goal, which aims to achieve the shortest total time; the disaster prevention and evacuation green space utilization rate goal, which aims to achieve the highest comprehensive utilization rate of each disaster prevention and evacuation green space;

[0044] The various evacuation simulation schemes specifically include: the shortest green space distance scheme, which uses the straight-line distance to the residential area as the basis for sorting the target destination green space list, and uses the sum of the congestion coefficient and the danger coefficient as the road selection weight; the shortest evacuation time scheme, which uses the actual distance to the residential area as the basis for sorting the target destination green space list, and uses the sum of the road distance, danger coefficient and congestion coefficient as the road selection weight; the balanced distribution of personnel in disaster prevention and evacuation green spaces scheme, which uses the utilization efficiency of each green space as the basis for sorting the target destination green space list, gives priority to the green space with the lowest utilization efficiency, and uses the sum of the danger coefficient and the congestion coefficient as the road selection weight.

[0045] Furthermore, the optimal evacuation plan is compared with the original road network data and the original disaster prevention and evacuation green space data to optimize the layout of roads and disaster prevention and evacuation green spaces in the area to be optimized, specifically including three aspects:

[0046] Optimization of site selection for new disaster prevention and evacuation green spaces: Based on areas with high residential density but insufficient coverage of existing green space services, an optimization plan for site selection for new green spaces is proposed, and plots with convenient transportation and low risks are selected as candidate green spaces;

[0047] Expansion and optimization of existing disaster prevention and evacuation green spaces: For existing green spaces with overloaded services, expand the green space area or add evacuation facilities;

[0048] Optimization of disaster prevention and escape routes: Combined with the evacuation routes of the optimal evacuation plan, the main roads leading to the green space are renovated or widened, and the road network structure is adjusted to optimize path connectivity.

[0049] According to a second aspect of the present invention, the present invention provides a multi-agent-based disaster prevention and risk avoidance green space system layout optimization system, which is used to implement the multi-agent-based disaster prevention and risk avoidance green space system layout optimization method, comprising:

[0050] A data processing module is used to receive the original geographic data in the area to be optimized, and pre-process the original geographic data to form effective geographic data, wherein the original geographic data includes original residential area data, original road network data and original disaster prevention and risk avoidance green space data;

[0051] The plan output module is used to set the evacuation target, select the specified evacuation target and simulate the multi-agent evacuation model, and the multi-agent evacuation model outputs the optimal evacuation plan;

[0052] Among them, the multi-agent evacuation model uses effective geographic data as the data source to simulate and record the real-time evacuation status, which includes the number of people entering each disaster prevention and refuge green space and the utilization efficiency, the evacuation path of each community, and the number of road users and congestion of each section of the road network in each time step;

[0053] The layout optimization scheme generation module is used to compare the optimal evacuation scheme with the original road network data and the original disaster prevention and evacuation green space data, and optimize the layout of roads and disaster prevention and evacuation green spaces in the area to be optimized.

[0054] Among them, the solution output module includes:

[0055] An agent model building unit, used to build a multi-agent evacuation model, wherein the multi-agent evacuation model includes an agent module, an environment module and a communication module, wherein the agent module includes a residential area agent, an evacuation agent and a green space agent;

[0056] The path planning unit is used to define residential area agents, evacuation agents and green space agents and their attributes based on the Mesa framework, and simulate the dynamic decision-making process of individual residents in different evacuation scenarios. The residential area agent is used to manage residential area data, road network data and disaster prevention and risk avoidance green space data in the GIS basic data information database; the evacuation agent is used to store the initial geographic data of all residential areas, roads and green spaces, and record the real-time evacuation status of each residential area during the simulation process; the green space agent is used to dynamically calculate the optimal evacuation path by comprehensively evaluating the weights of roads and green spaces, and track and record the evacuation situation at different time steps in real time;

[0057] The disaster prevention and evacuation green space capacity update unit is used to dynamically adjust the remaining capacity of the green space according to the real-time recorded evacuation situation. When the green space is overloaded, the intelligent agent module is triggered to select other disaster prevention and evacuation green spaces that are closest and have available capacity, and re-plan the simulated evacuation route;

[0058] The road congestion feedback update unit is used to convert the processed road network data into graph structure data, where nodes represent road intersections and edges represent road segments, and set the initial weights of the edges. Then, according to the simulated evacuation path planned and generated by the agent module, the road congestion of each road segment at different time steps is calculated, and the weights of the edges of each road segment are updated. Then, the agent module performs the next iteration according to the updated road weights and recalculates the optimal evacuation path.

[0059] An iterative control unit, used to set an evacuation target or a maximum number of iterations as a preset condition, control the iterative process of the evacuation simulation of the intelligent agent module, and output the evacuation simulation result after the preset condition is met;

[0060] The evacuation simulation scheme generation unit is used to set multiple evacuation targets. According to the weight ratio of achieving different evacuation targets, the intelligent agent module is controlled to generate multiple evacuation simulation schemes. Each evacuation simulation scheme is an optimization result under different weight ratios, and the evacuation simulation scheme is used to achieve a comprehensive goal or a single goal.

[0061] The present invention has at least the following beneficial effects:

[0062] The present invention introduces a multi-agent evacuation simulation model in the planning and design of disaster prevention and risk avoidance green space and optimizes multiple objectives such as road congestion and green space overload during simulation. It can not only accurately simulate real-time escape situations, avoid real-time road disaster risks, congestion risks of escaping crowds and overload risks of disaster prevention and risk avoidance green space capacity during disasters, and help formulate optimal escape plans, but also dynamically adjust evacuation routes and strategies according to different emergency needs, formulate optimal plans under multiple objectives, and provide more scientific and accurate planning and decision-making support for future urban pre-disaster emergency plan formulation and post-disaster plan response.

[0063] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 It is a schematic diagram of the process of the optimization method of the present invention;

[0065] Figure 2 It is a structural schematic diagram of the optimization system of the present invention;

[0066] Figure 3 This is a schematic diagram of the evacuation simulation results of a green space in a certain area with a distance of 30 minutes from the nearest solution in an embodiment of the present invention;

[0067] Figure 4 This is a schematic diagram of evacuation simulation results of a certain area with the shortest evacuation time of 30 minutes in an embodiment of the present invention;

[0068] Figure 5 It is a schematic diagram of the evacuation simulation results of a 30-minute equilibrating plan for personnel distribution in a disaster prevention and evacuation green space in a certain area in an embodiment of the present invention; DETAILED DESCRIPTION

[0069] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0070] Embodiment 1:

[0071] See also Figure 1 and Figure 2 The present invention provides a technical solution: a multi-agent-based disaster prevention and risk avoidance green space system layout optimization method, comprising the following steps:

[0072] S1. Data reception and processing: Receive geographic data in the area to be optimized, including residential area data, road network data and disaster prevention and green space data, integrate and process the above geographic data based on GIS software, unify the geographic coordinate system, process missing values ​​and outliers, and build a complete GIS basic data information database;

[0073] Geographic data are obtained based on the Internet map open platform and planning plan. The residential area data include the boundary shp data of each residential area and the population. The population is calculated by substituting the street population data of the study area in the seventh census data into the ratio of the residential area building area to the street building area, and then calculating the proportion.

[0074] Road network data includes extracting road data in the target area, including geographical location information and grade attributes of the roads, and road width data;

[0075] The disaster prevention and evacuation green space data includes the geographical location data of the green space. The maximum capacity data of the green space is obtained by converting the effective evacuation area of ​​the disaster prevention and evacuation green space in the "Guidelines for the Design of Urban Green Spaces for Disaster Prevention and Evacuation" to the per capita area. Specifically, the maximum capacity data of the green space = the total effective evacuation area of ​​the disaster prevention and evacuation green space / the per capita effective evacuation area;

[0076] S2. Road network construction: Convert the processed road network data into graph structure data, where nodes represent road intersections, edges represent road segments, and set the initial weights of the edges, as follows:

[0077] The selection weight of each road is R n According to its risk factor D n and escape distance L n The specific calculation formula is:

[0078] R n =D n ×L n

[0079] Escape distance L n is the path length calculated based on the A* optimal path algorithm, and the risk factor D n The road safety influencing factors are calculated and normalized by the objective entropy weight method. The specific influencing factors may include the medical facility POI points, police station POI points, gas station POI points, the number of industrial areas, the risk of building collapse and the number of hospitals within 500m of each road buffer zone;

[0080] It should be noted that when performing geographic information system (GIS) analysis, it is often necessary to convert map data into a graph structure in order to perform operations such as path planning and network analysis. For the technical solution of this embodiment, Python is used to convert map data into a graph structure;

[0081] S3. Construction of agent evacuation model: construct a multi-agent evacuation model, which includes an agent module, an environment module and a communication module, wherein the agent module includes a residential agent, an evacuation agent and a green space agent;

[0082] The multi-agent system can achieve comprehensive consideration of multi-objective optimization problems by defining communication protocols and interaction rules between agents and simulating complex interaction processes. Specifically, it can simultaneously optimize multiple dimensions such as evacuation time, path selection, and balanced utilization of shelters, ensuring that in an emergency, it can not only effectively shorten the overall evacuation time and reduce casualties, but also intelligently allocate shelter resources to avoid overcrowding in some shelters while idle resources in other places.

[0083] In the Jupyter notebook environment, Python language is used to model and simulate the agent-based multi-agent evacuation model. Jupyter Notebook provides a write-and-run development method, which is convenient for quickly adjusting code logic and parameters. Python's visualization library can quickly and dynamically display the evacuation process and results in the subsequent scheme selection process. At the same time, Python's open source libraries (such as mesa, networkx, and geopandas) are used to build the agent behavior logic and simulation process, and quickly build a multi-agent simulation framework.

[0084] The multi-agent evacuation model consists of three main parts: the agent, the environment module, and the communication module. The model environment module includes GIS basic environment data and global real-time information, specifically the road network, residential area boundaries, green space location and capacity, and dynamically updated road weights and green space status data;

[0085] The communication module is a module that supports information exchange and resource sharing between agents, ensuring effective collaboration and synchronization between residential agents, evacuation agents, and environmental data, thereby achieving efficient operation and dynamic adjustment of the entire evacuation simulation process;

[0086] S4. Evacuation route planning: Based on the Mesa framework, we define the residential area agent, evacuation agent, green space agent and their attributes, and simulate the dynamic decision-making process of individual residents in different evacuation scenarios:

[0087] The residential area agent is used to manage the residential area data, road network data and disaster prevention and evacuation green space data in the GIS basic data information database, specifically the geographical boundary information, population size, basic capacity information of disaster prevention and evacuation green space and basic road network data of each residential area;

[0088] The evacuation agent is used to store the initial geographic data of all residential areas, roads and green spaces, and record the real-time evacuation status of each residential area during the simulation. During the simulation, the residential area agent records the core information of the evacuation, including the number of residents evacuated, the number of residents arriving at each green space, and the evacuation path information of different green spaces;

[0089] The green space agent is used to comprehensively evaluate the weights of roads and green spaces, sort the distances and select the top 10 nearest disaster prevention and evacuation green spaces as the target destination candidate green space list, calculate the optimal evacuation path through the A* algorithm, and track and record the evacuation situation at different time steps in real time;

[0090] It should be noted that in the process of simulating evacuation by the agent module, each disaster prevention and evacuation green space is prioritized by distance to form a list of green spaces to be evacuated. Each agent uses the A* optimal path algorithm based on the road network weight and the capacity of the current disaster prevention and evacuation green space list, and uses the road hazard coefficient as the weight to calculate the optimal route, simulating the process of the agent moving along the path;

[0091] Among them, the A* algorithm is a heuristic search algorithm that combines the actual cost (the path cost from the starting point to the current point) and the estimated cost (the estimated cost from the current point to the target point) to minimize the total cost to find the shortest path from the starting point to the target. Compared with Dijkstra and other methods, the A* algorithm can ensure the calculation of the optimal path solution, and at the same time improve the search efficiency and reduce the amount of calculation through the heuristic function. At the same time, the A* algorithm is more flexible and can adjust the heuristic function according to different environmental characteristics and requirements. Therefore, it is suitable for large-scale, dynamic or complex path planning tasks;

[0092] S5. Update of disaster prevention green space capacity: According to the real-time recorded evacuation situation, the remaining capacity of the green space is dynamically adjusted. When the green space is overloaded, the intelligent agent module is triggered to select other disaster prevention green spaces with the nearest distance and available capacity, and re-plan the simulated evacuation route;

[0093] Specifically, the remaining capacity of the green space is updated based on the number of agents entering the disaster prevention and evacuation green space. When the green space capacity is insufficient, the agent re-evaluates the shelter selection strategy, selects other disaster prevention and evacuation green spaces that are closest and have available capacity based on the surrounding real-time environmental data, and regenerates the list for evacuation.

[0094] S6. Road congestion feedback update: The evacuation process is simulated multiple times. Each time the simulated agent module plans a simulated evacuation path. According to the planned simulated evacuation path, the road congestion of each road section at different time steps is calculated, and the weight of each road edge is updated, as follows:

[0095] The calculation formula of congestion degree C is:

[0096]

[0097] Where N is the number of people escaping on the road section, N max is the maximum number of people that the road segment can carry;

[0098] The weight of the road segment is adjusted according to the congestion degree C. The new weight is:

[0099] R n '=D n *L n *C

[0100] In the formula, R n ' is the new weight, D n is the risk factor, L n is the escape distance;

[0101] Then the agent module performs the next iteration based on the updated road weights and recalculates the optimal evacuation path;

[0102] S7. Iterative control and evacuation simulation result output: Set the evacuation target as the preset condition, control the iterative process of the evacuation simulation of the intelligent agent module, and output the evacuation simulation result after the preset condition is met;

[0103] Specifically, for the evacuation plan, set the evacuation efficiency target (such as total evacuation time, arrival rate), perform multiple evacuation simulation calculations and road congestion calculations preset in the model, and perform an iterative simulation process until the number of iterations reaches the preset upper limit. Finally, the evacuation simulation results are output, which may include: the evacuation time distribution of the agent, the congestion situation of each road section, the use of disaster prevention and evacuation green space, and the spatial distribution of evacuation paths;

[0104] S8. Optimal evacuation simulation scheme screening: set multiple evacuation targets, modify the weight ratio according to the realization of different evacuation targets, control the intelligent agent module to generate multiple evacuation simulation schemes, each evacuation simulation scheme is the optimization result under different weight ratios;

[0105] Specifically, in order to compare the advantages and disadvantages of different evacuation simulation schemes, the following evacuation indicators can be used for quantitative evaluation:

[0106] The green space is closest to the target, and the dynamics of the escape green space are closest;

[0107] The total evacuation time goal is to achieve the shortest straight-line distance to the target green space;

[0108] The utilization rate of disaster prevention and evacuation green spaces is targeted to achieve the highest comprehensive utilization rate of disaster prevention and evacuation green spaces;

[0109] The various evacuation simulation schemes specifically include: the shortest distance to green space scheme, which uses the straight-line distance to the residential area as the basis for sorting the target destination green space list, and uses the congestion coefficient and the risk coefficient as the road selection weight; the shortest evacuation time scheme, which uses the actual distance to the residential area as the basis for sorting the target destination green space list, and uses the road distance plus the risk coefficient and the congestion coefficient as the road selection weight; the balanced distribution of personnel in disaster prevention and evacuation green spaces scheme, which uses the efficiency of each green space as the basis for sorting the target destination green space list, gives priority to the green space with the lowest efficiency, and uses the risk coefficient and the congestion coefficient as the road selection weight;

[0110] The constraints for achieving these goals include: each residential area has at least one disaster prevention and refuge green space, the number of users of each disaster prevention and refuge green space must not exceed the capacity, and disaster prevention and refuge green spaces with full populations cannot be candidates, and roads with the highest congestion level cannot be candidates;

[0111] Through these indicators and constraints, the advantages and disadvantages of each generated plan are compared, and finally the evacuation plan that best suits the current emergency needs is selected, such as the shortest evacuation time plan, the minimum congestion plan, and the plan for balanced distribution of personnel in disaster prevention and evacuation green spaces;

[0112] It should be noted that after each plan is generated, Python's matplotlib is used to draw dynamic evacuation route maps, road congestion heat maps, etc., and the distribution maps of green spaces and residential areas are superimposed on the GIS platform to intuitively present the layout results. Comprehensive display and comparison are carried out through different visualization methods to help decision makers make quick judgments in emergency situations;

[0113] S9. Generate layout optimization plan: Compare the optimal evacuation plan for comprehensive objectives or single objectives with the current status of disaster prevention and evacuation green space, and come up with a specific optimization plan, which may include the following four suggested directions:

[0114] Recommendations for the location of new green spaces for disaster prevention and evacuation: Based on areas with high residential density but insufficient coverage of existing green space services, recommendations for the location of new green spaces are proposed, with priority given to sites with convenient transportation and low risks as candidate green spaces;

[0115] Existing disaster prevention and evacuation green space expansion strategy: For some existing green space service overload situations, it is recommended to improve service capacity by expanding the green space area or adding evacuation function facilities;

[0116] Optimization of disaster prevention and escape routes: Based on the optimal evacuation route plan selected, the main roads leading to the green space are renovated or widened to reduce road obstructions and improve road capacity. At the same time, by adjusting the road network structure, the path connectivity is optimized and the detour time is reduced.

[0117] Next, the technical solution of the present invention is described in detail with reference to the embodiments:

[0118] like Figures 3 to 5 As shown, the embodiment takes the main urban area of ​​a certain city as the research object. The main urban area of ​​a certain city is a typical high-density urban area with densely populated residential areas. At the same time, the green space types are rich and complex, and the distribution is mainly scattered and fragmented. The efficiency of active escape and evacuation cannot be guaranteed. Therefore, a reasonable and effective pre-disaster evacuation plan is urgently needed to ensure the orderly escape of disaster personnel and maximize the personal safety of residents.

[0119] Figure 3-5 The simulation results of the disaster prevention and evacuation green space model in the main urban area of ​​a city under three types of objectives are shown, among which: Figure 3 , 5 The blue line segments are the escape routes of each residential area; the red blocks represent residential areas, darker colors represent unsuccessful escapes, and lighter colors represent successful escapes; the green blocks represent green areas, darker colors represent overloaded capacity, and lighter colors represent unoverloaded capacity; Figure 4 The green color of the middle road indicates that it is not overloaded (unblocked), and the red color indicates that it is overloaded (congested).

[0120] It can be seen from the figure that, in the comparison of the results of the three models, Model 3 (balanced distribution of personnel in disaster prevention and evacuation green space) has the best overall performance. Figure 5 As shown in the figure, the simulation can complete the emergency evacuation of most communities within 30 minutes. At the same time, the green space for disaster prevention and risk avoidance is less full, and the crowd distribution is more reasonable and balanced. This shows that the green space selection strategy with balanced personnel distribution can not only improve the overall evacuation efficiency, but also effectively prevent congestion and resource depletion of individual green spaces due to excessive population flow, thereby improving the overall disaster prevention and risk avoidance capabilities.

[0121] like Figure 4 As shown in the figure, the simulation results of Model 2 show that the main roads in the central area of ​​the main urban area continued to be severely congested within 30 minutes. This phenomenon reflects that the traffic bottleneck problem in the central area during peak evacuation periods is particularly prominent, which seriously affects the evacuation efficiency. Therefore, in the future, the main roads and some branches in the central, western and southwestern parts of the main urban area need to be widened to increase traffic flow and passenger flow to ensure that the evacuation traffic can maintain efficient operation and actual evacuation efficiency when a disaster occurs.

[0122] like Figure 3 As shown in the figure, Model 1 has a fixed target green space and lacks dynamic adjustment capabilities. When faced with complex and changeable road congestion conditions, the evacuation results are not ideal and other green space resources may not be fully utilized, resulting in overload of some green space capacity or waste of resources. However, Model 1 still shows a relatively reasonable evacuation path and green space utilization. As a basic evacuation model based on straight-line distance, decision makers and urban planners can more easily understand and apply its results, which can provide a baseline reference for other more complex models for formulating and adjusting disaster prevention and risk avoidance policies.

[0123] By summarizing the simulation results of the three types of target models at each time step, we can also draw in-depth evaluations and suggestions on the congestion levels of other relevant escape routes in the main urban area of ​​a city, as well as effective suggestions and planning guidance for future escape routes.

[0124] To sum up, the present invention introduces a multi-agent evacuation simulation model in the planning and design process of disaster prevention and risk avoidance green space and optimizes multiple objectives such as road congestion and green space overload during simulation. It can not only accurately simulate real-time escape situations, avoid real-time road disaster risks, congestion risks of escaping crowds, and overload risks of disaster prevention and risk avoidance green space capacity during disasters, and help formulate optimal escape plans, but also dynamically adjust evacuation routes and strategies according to different emergency needs, and formulate optimal plans under multiple objectives, providing more scientific and accurate planning and decision-making support for future urban pre-disaster emergency plan formulation and post-disaster plan response.

[0125] Embodiment 2:

[0126] like Figure 2 As shown, this embodiment provides a multi-agent-based disaster prevention and risk avoidance green space system layout optimization system, which is used to implement the multi-agent-based disaster prevention and risk avoidance green space system layout optimization method described in Embodiment 1, including:

[0127] The data processing module is used to receive the geographic data in the area to be optimized, wherein the geographic data includes residential area data, road network data and disaster prevention and risk avoidance green space data, integrate and process the above-mentioned geographic data based on GIS software, unify the geographic coordinate system, process missing values ​​and abnormal values, and construct a complete GIS basic data information database; the data processing module is used to receive the original geographic data in the area to be optimized, pre-process the original geographic data to form effective geographic data, wherein the original geographic data includes original residential area data, original road network data and original disaster prevention and risk avoidance green space data;

[0128] The plan output module is used to set the evacuation target, select the specified evacuation target and simulate the multi-agent evacuation model, and the multi-agent evacuation model outputs the optimal evacuation plan;

[0129] Among them, the multi-agent evacuation model uses effective geographic data as a data source to simulate and record the real-time evacuation status, which includes the number of people entering each disaster prevention and evacuation green space and its usage efficiency, the evacuation routes of each community, the number of road users and the congestion degree of each section of the road network in each time step; outputs the optimal evacuation plan after simulation; the real-time evacuation status includes the real-time green space overload status and the real-time road congestion status of each section of the evacuation route;

[0130] The layout optimization scheme generation module is used to compare the optimal evacuation scheme with the original road network data and the original disaster prevention and evacuation green space data, and optimize the layout of roads and disaster prevention and evacuation green spaces in the area to be optimized.

[0131] Among them, the solution output module includes:

[0132] An agent model building unit, used to build a multi-agent evacuation model, wherein the multi-agent evacuation model includes an agent module, an environment module and a communication module, wherein the agent module includes a residential area agent, an evacuation agent and a green space agent;

[0133] The path planning unit is used to define residential area agents, evacuation agents and green space agents and their attributes based on the Mesa framework, and simulate the dynamic decision-making process of individual residents in different evacuation scenarios. The residential area agent is used to manage residential area data, road network data and disaster prevention and risk avoidance green space data in the GIS basic data information database; the evacuation agent is used to store the initial geographic data of all residential areas, roads and green spaces, and record the real-time evacuation status of each residential area during the simulation process; the green space agent is used to dynamically calculate the optimal evacuation path by comprehensively evaluating the weights of roads and green spaces, and track and record the evacuation situation at different time steps in real time;

[0134] The disaster prevention and evacuation green space capacity update unit is used to dynamically adjust the remaining capacity of the green space according to the real-time recorded evacuation situation. When the green space is overloaded, the intelligent agent module is triggered to select other disaster prevention and evacuation green spaces that are closest and have available capacity, and re-plan the simulated evacuation route;

[0135] The road congestion feedback update unit is used to convert the processed road network data into graph structure data, where nodes represent road intersections and edges represent road segments, and set the initial weights of the edges. Then, according to the simulated evacuation path planned and generated by the agent module, the road congestion of each road segment at different time steps is calculated, and the weights of the edges of each road segment are updated. Then, the agent module performs the next iteration according to the updated road weights and recalculates the optimal evacuation path.

[0136] An iterative control unit, used to set an evacuation target or a maximum number of iterations as a preset condition, control the iterative process of the evacuation simulation of the intelligent agent module, and output the evacuation simulation result after the preset condition is met;

[0137] The evacuation simulation scheme generation unit is used to set multiple evacuation targets. According to the weight ratio of achieving different evacuation targets, the intelligent agent module is controlled to generate multiple evacuation simulation schemes. Each evacuation simulation scheme is an optimization result under different weight ratios, and the evacuation simulation scheme is used to achieve a comprehensive goal or a single goal.

[0138] Specifically, the above-mentioned data processing module, solution output module and layout optimization solution generation module can be embedded in a computer processing system. The computer calls the above-mentioned modules to complete the task of optimizing the planning of the disaster prevention and risk avoidance green space system according to the above-mentioned multi-agent-based disaster prevention and risk avoidance green space system layout optimization method; the above-mentioned data processing module, solution output module and layout optimization solution generation module can perform operations according to the specific steps given in the multi-agent-based disaster prevention and risk avoidance green space system layout optimization method.

[0139] It should be noted that it should be understood that the division of the various modules of the above system is only the division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated, and these modules can all be implemented in the form of software calling through processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software calling through processing elements, and some modules can be implemented in the form of hardware. For example, the data processing module can be a separately established processing element, or it can be integrated in a chip of the above-mentioned device. In addition, it can also be stored in the memory of the above-mentioned device in the form of program code, and called and executed by a processing element of the above-mentioned device. The functions of the above signal processing module, and the implementation of other modules is similar. In addition, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element described here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by the hardware integrated logic circuit in the processor element or the instructions in the form of software.

[0140] For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASIC), or one or more digital singnal processors (DSP), or one or more field programmable gate arrays (FPGA). For another example, when a module is implemented in the form of a processing element scheduling program code, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processors that can call program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0141] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0142] For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances. When an element is referred to as being "assembled on", "installed on", "fixed on" or "set on" another element, it can be directly on the other element or there can also be a centered element. When an element is considered to be "connected" to another element, it can be directly connected to the other element or there may be a centered element at the same time. The terms "vertical", "horizontal", "up", "down", "left", "right" and similar expressions used herein are only for illustrative purposes and are not intended to be the only implementation method.

[0143] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

[0144] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

Claims

1. A multi-agent-based green space system layout optimization method for disaster prevention and risk avoidance, characterized in that: The following steps are involved: Receiving original geographic data in the area to be optimized, and preprocessing the original geographic data to form effective geographic data, wherein the original geographic data includes original residential area data, original road network data, and original disaster prevention and evacuation green space data; Set the evacuation target, select the specified evacuation target and the multi-agent evacuation model for simulation, and the multi-agent evacuation model outputs the optimal evacuation plan; Among them, the multi-agent evacuation model uses effective geographic data as the data source to simulate and record the real-time evacuation status, which includes the number of people entering each disaster prevention and refuge green space and the utilization efficiency, the evacuation path of each community, and the number of road users and congestion of each section of the road network in each time step; The optimal evacuation plan is compared with the original road network data and the original disaster prevention and hazard avoidance green space data to optimize the layout of roads and disaster prevention and hazard avoidance green spaces in the area to be optimized.

2. The multi-agent-based green space system layout optimization method for disaster prevention and risk avoidance according to claim 1 is characterized by: The geographic data in the area to be optimized is obtained based on the Internet map open platform and the planning plan, as follows: Residential area data include boundary SHP data and population of each residential area; Road network data includes geographical location information and grade attributes of roads, and road width data; The disaster prevention and evacuation green space data includes the green space geographical location data and the green space maximum capacity data, where the green space maximum capacity data = the total effective evacuation area of ​​the disaster prevention and evacuation green space / the effective evacuation area per capita; The specific preprocessing of the original geographic data is as follows: Based on GIS software, the above geographic data are integrated and processed, the geographic coordinate system is unified, and missing values ​​and outliers are processed.

3. The multi-agent-based green space system layout optimization method for disaster prevention and risk avoidance according to claim 2 is characterized in that: The pre-built multi-agent evacuation model includes an agent module, an environment module, and a communication module, among which: The agent module includes residential agent, evacuation agent and green space agent; The environment module includes GIS basic environment data and global real-time information, including road network data, residential area boundary data, green space location and maximum capacity data, and dynamically updated road weight and green space status data; The communication module is used to support information exchange and resource sharing among residential intelligent agents, evacuation intelligent agents and green space intelligent agents, ensuring collaboration and synchronization among residential intelligent agents, evacuation intelligent agents and environmental modules.

4. The multi-agent-based green space system layout optimization method for disaster prevention and risk avoidance according to claim 3 is characterized in that: The multi-agent evacuation model uses effective geographic data as the data source, simulates and records the real-time evacuation status, takes the evacuation target as the goal, and outputs the optimal evacuation plan after simulation, including: evacuation route planning, disaster prevention and risk avoidance green space capacity update, road congestion feedback update, iterative control and evacuation simulation result output, and modifies the weight ratio according to the realization of different evacuation goals to generate the optimal evacuation plan.

5. The multi-agent-based green space system layout optimization method for disaster prevention and risk avoidance according to claim 4 is characterized in that: The evacuation route planning is specifically as follows: Based on the Mesa framework, we define the residential area agent, evacuation agent, green space agent and their attributes, and simulate the dynamic decision-making process of individual residents in different evacuation scenarios. Among them, the residential area agent is used to manage the residential area data, road network data and disaster prevention and evacuation green space data in the GIS basic data information database; the evacuation agent is used to store the initial geographic data of all residential areas, roads and green spaces, and record the real-time evacuation status of each residential area during the simulation process; the green space agent is used to comprehensively evaluate the weights of roads and green spaces, sort by distance, and take the first 10 nearest disaster prevention and evacuation green spaces as the target destination candidate green space list, use the A* algorithm to calculate the optimal evacuation path, and track and record the evacuation situation at different time steps in real time.

6. The multi-agent-based green space system layout optimization method for disaster prevention and risk avoidance according to claim 5 is characterized in that: The capacity of the disaster prevention and evacuation green space is updated as follows: According to the number of intelligent agents entering the disaster prevention and evacuation green space, the remaining capacity of the green space is updated. When the green space capacity is insufficient, the intelligent agent module re-evaluates the shelter selection strategy, selects other disaster prevention and evacuation green spaces that are closest and have available capacity based on the surrounding real-time environmental data, and regenerates the list for evacuation.

7. The multi-agent-based green space system layout optimization method for disaster prevention and risk avoidance according to claim 5, characterized in that: The specific steps of updating the road congestion feedback are as follows: (71) The processed road network data is converted into graph structure data, where nodes represent road intersections, edges represent road segments, and the initial weights of the edges are set as follows: The selection weight of each road is R n According to its risk factor D n and escape distance L n The specific calculation formula is: R n =D n ×L n Escape distance L n is the path length calculated based on the A* optimal path algorithm, and the risk factor D n The road safety influencing factors are calculated and normalized by the objective entropy weight method; (72) The agent module has planned and generated the simulated evacuation path, calculated the road congestion degree of each road section at different time steps, and updated the weight of each road edge, as follows: The calculation formula of congestion degree C is: Where N is the number of people escaping on the road section, N max is the maximum number of people that the road segment can carry; The weight of the road segment is adjusted according to the congestion degree C. The new weight is: R n '=D n *L n *C In the formula, R n ' is the new weight, D n is the risk factor, L n is the escape distance; (73) The intelligent agent module performs the next iteration based on the updated road weights and recalculates the optimal evacuation path.

8. The multi-agent-based green space system layout optimization method for disaster prevention and risk avoidance according to claim 7, characterized in that: The specific steps of iterative control and evacuation simulation result output are as follows: Set the evacuation target or the maximum number of iterations as the preset condition, determine whether the preset condition is met after each simulation, decide whether to continue iteration, and then perform multiple calculations and road congestion calculations, and perform an iterative simulation process until the preset condition is met and the evacuation simulation result is output; The evacuation simulation results include the evacuation time distribution of the intelligent agent module, the congestion data of each road section, the remaining capacity data of the disaster prevention and evacuation green space, and the spatial distribution of the simulated evacuation path; Modify the weight ratio according to the realization of different evacuation goals and generate the optimal evacuation plan, as follows: The specific evacuation goals include: the closest green space distance goal, which aims to achieve the shortest straight-line distance to the target green space; the total evacuation time goal, which aims to achieve the shortest total time; the disaster prevention and evacuation green space utilization rate goal, which aims to achieve the highest comprehensive utilization rate of each disaster prevention and evacuation green space; The various evacuation simulation schemes specifically include: the shortest green space distance scheme, which uses the straight-line distance to the residential area as the basis for sorting the target destination green space list, and uses the sum of the congestion coefficient and the danger coefficient as the road selection weight; the shortest evacuation time scheme, which uses the actual distance to the residential area as the basis for sorting the target destination green space list, and uses the sum of the road distance, danger coefficient and congestion coefficient as the road selection weight; the balanced distribution of personnel in disaster prevention and evacuation green spaces scheme, which uses the utilization efficiency of each green space as the basis for sorting the target destination green space list, gives priority to the green space with the lowest utilization efficiency, and uses the sum of the danger coefficient and the congestion coefficient as the road selection weight.

9. The multi-agent-based green space system layout optimization method for disaster prevention and risk avoidance according to claim 8, characterized in that: The optimal evacuation plan is compared with the original road network data and the original disaster prevention and evacuation green space data to optimize the layout of roads and disaster prevention and evacuation green spaces in the area to be optimized, which specifically includes three aspects: Optimization of site selection for new disaster prevention and evacuation green spaces: Based on areas with high residential density but insufficient existing green space services, an optimization plan for site selection for new green spaces is proposed, and plots with convenient transportation and low risks are selected as candidate green spaces; Expansion and optimization of existing disaster prevention and evacuation green spaces: For existing green spaces with overloaded services, expand the green space area or add evacuation facilities; Optimization of disaster prevention and escape routes: Combined with the evacuation routes of the optimal evacuation plan, the main roads leading to the green space are renovated or widened, and the road network structure is adjusted to optimize path connectivity.

10. A multi-agent-based green space system layout optimization system for disaster prevention and risk avoidance, used to implement the multi-agent-based green space system layout optimization method for disaster prevention and risk avoidance according to any one of claims 1 to 9, characterized in that: include: A data processing module is used to receive the original geographic data in the area to be optimized, and pre-process the original geographic data to form effective geographic data, wherein the original geographic data includes original residential area data, original road network data and original disaster prevention and evacuation green space data; The plan output module is used to set the evacuation target, select the specified evacuation target and simulate the multi-agent evacuation model, and the multi-agent evacuation model outputs the optimal evacuation plan; Among them, the multi-agent evacuation model uses effective geographic data as the data source to simulate and record the real-time evacuation status, which includes the number of people entering each disaster prevention and refuge green space and the utilization efficiency, the evacuation path of each community, and the number of road users and congestion of each section of the road network in each time step; The layout optimization scheme generation module is used to compare the optimal evacuation scheme with the original road network data and the original disaster prevention and evacuation green space data, and optimize the layout of roads and disaster prevention and evacuation green spaces in the area to be optimized. The scheme output module includes: An agent model building unit, used to build a multi-agent evacuation model, wherein the multi-agent evacuation model includes an agent module, an environment module and a communication module, wherein the agent module includes a residential area agent, an evacuation agent and a green space agent; The path planning unit is used to define residential area agents, evacuation agents and green space agents and their attributes based on the Mesa framework, and simulate the dynamic decision-making process of individual residents in different evacuation scenarios. The residential area agent is used to manage residential area data, road network data and disaster prevention and risk avoidance green space data in the GIS basic data information database; the evacuation agent is used to store the initial geographic data of all residential areas, roads and green spaces, and record the real-time evacuation status of each residential area during the simulation process; the green space agent is used to dynamically calculate the optimal evacuation path by comprehensively evaluating the weights of roads and green spaces, and track and record the evacuation situation at different time steps in real time; The disaster prevention and evacuation green space capacity update unit is used to dynamically adjust the remaining capacity of the green space according to the real-time recorded evacuation situation. When the green space is overloaded, the intelligent agent module is triggered to select other disaster prevention and evacuation green spaces that are closest and have available capacity, and re-plan the simulated evacuation route; The road congestion feedback update unit is used to convert the processed road network data into graph structure data, where nodes represent road intersections and edges represent road segments, and set the initial weights of the edges. Then, according to the simulated evacuation path planned and generated by the agent module, the road congestion of each road segment at different time steps is calculated, and the weights of the edges of each road segment are updated. Then, the agent module performs the next iteration according to the updated road weights and recalculates the optimal evacuation path. An iterative control unit, used to set an evacuation target or a maximum number of iterations as a preset condition, control the iterative process of the evacuation simulation of the intelligent agent module, and output the evacuation simulation result after the preset condition is met; The evacuation simulation scheme generation unit is used to set multiple evacuation targets. According to the weight ratio of achieving different evacuation targets, the intelligent agent module is controlled to generate multiple evacuation simulation schemes. Each evacuation simulation scheme is an optimization result under different weight ratios, and the evacuation simulation scheme is used to achieve a comprehensive goal or a single goal.

Images