Linkage emergency storage layout optimization method and system based on spatial analysis

Abstract

The invention discloses a linkage emergency storage layout optimization method and system based on spatial analysis, and relates to the technical field of storage. The method comprises the following steps: collecting disaster risk, population density, traffic network and resource configuration data, and determining a multi-disaster scene data set and an associated region group set by utilizing GIS space overlapping analysis; performing linkage emergency storage layout analysis based on the data, and determining a storage layout scheme set; performing evolution expansion in combination with the scene data to generate an evolution expansion group set; performing response fitness analysis and scheme optimization according to the evolution expansion group to form an optimization scheme set; and fusing the optimization schemes to determine a target scheme. The technical problem that a traditional emergency storage layout lacks dynamic adaptability and cross-regional linkage capability when facing a complex multi-disaster chain is solved, and the technical effects that dynamic optimization and multi-stage linkage of the storage layout are achieved through space analysis and scene evolution, and the emergency response capability and resource allocation efficiency of the storage layout are improved are achieved.

Description

Technical Field

[0001] This invention relates to the field of warehousing technology, and more specifically to a method and system for optimizing the layout of coordinated emergency warehousing based on spatial analysis. Background Technology

[0002] In the context of frequent natural disasters, public safety incidents, and major accidents, the construction of a regional emergency material support system is particularly important. Existing emergency storage layout methods are mostly designed based on single disaster scenarios or static environmental conditions, failing to fully consider the cumulative effects of multiple disasters and the need for coordinated response between regions. This leads to prominent problems such as unreasonable distribution of material reserves, low response efficiency, and limited transportation routes when actual disasters occur. Furthermore, traditional storage layout optimization is often based on empirical or linear models, lacking a systematic analysis of spatial elements, dynamic disaster evolution, and comprehensive factors such as population and transportation, making it difficult to achieve scientific and flexible emergency resource allocation. Summary of the Invention

[0003] This application provides a method and system for optimizing the layout of linked emergency warehouses based on spatial analysis, which solves the technical problem that traditional emergency warehouse layouts lack dynamic adaptability and cross-regional linkage capabilities when facing complex multi-hazard chains.

[0004] The first aspect of this application provides a method for optimizing the layout of coordinated emergency storage facilities based on spatial analysis, the method comprising: Data on disaster risk, population density and distribution, transportation network, and resource allocation in the target area are collected. Spatial overlap analysis is performed using GIS spatial analysis technology to determine a multi-hazard scenario data set and a corresponding set of associated regional groups. Based on the multi-hazard scenario data set and the set of associated regional groups, a multi-level linkage emergency warehousing layout analysis is conducted to determine a set of warehousing layout schemes. The scenario evolution is expanded by combining the multi-hazard scenario data set to obtain a set of multi-hazard scenario evolution expansion groups. Layout response adaptability analysis is performed on the set of warehousing layout schemes according to the scenario evolution expansion groups, and the schemes are optimized by combining the layout response adaptability groups to obtain a set of optimized warehousing layout schemes. The optimized warehousing layout schemes are then fused with linked scenarios to determine the target optimized warehousing layout scheme.

[0005] A second aspect of this application provides a spatial analysis-based coordinated emergency warehouse layout optimization system, the system comprising: Overlap Analysis Module: Collects disaster risk data, population density and distribution data, transportation network data, and resource allocation data of the target area. Utilizes GIS spatial analysis technology to perform spatial overlap analysis, determining the multi-hazard scenario data set and the corresponding associated regional group set. Layout Analysis Module: Based on the multi-hazard scenario data set and associated regional group set, performs multi-level linkage emergency warehouse layout analysis to determine the warehouse layout scheme set. Scenario Evolution Module: Combines the multi-hazard scenario data set to expand the scenarios, obtaining a multi-hazard scenario evolution expansion group set. Layout Optimization Module: Performs layout response fitness analysis on the warehouse layout scheme set according to the scenario evolution expansion group set, and optimizes the schemes based on the layout response fitness group set, obtaining a warehouse layout optimization scheme set. Scenario Fusion Module: Performs linkage scenario fusion on the warehouse layout optimization scheme set to determine the target warehouse layout optimization scheme.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages: First, data on disaster risk, population distribution, transportation networks, and resource allocation in the target area are collected and overlaid using spatial analysis techniques to identify multi-hazard scenarios and their associated impact areas. Then, based on this, a multi-level, interconnected warehouse layout analysis is conducted to generate preliminary layout plans. Next, by evolving and expanding the multi-hazard scenarios, more complex and dynamic disaster scenarios are constructed to evaluate the responsiveness of each layout plan under different scenarios. Then, based on the evaluation results, the plans are optimized and adjusted to form a set of optimized warehouse layout plans. Finally, scenario fusion analysis is performed on the optimized plans to determine the target emergency warehouse layout plan that performs optimally under multi-hazard environments, thereby achieving the scientific allocation and efficient linkage of emergency resources. Attached Figure Description

[0007] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0008] Figure 1 A schematic diagram of the process for optimizing the layout of a coordinated emergency warehouse based on spatial analysis, provided in an embodiment of this application.

[0009] Figure 2 A schematic diagram of the structure of the linkage emergency warehouse layout optimization system based on spatial analysis provided in the embodiments of this application.

[0010] Figure labeling: Overlap analysis module 11, layout analysis module 12, scene evolution module 13, layout optimization module 14, scene fusion module 15. Detailed Implementation

[0011] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided below.

[0012] Example 1, as Figure 1 As shown, this application provides a method for optimizing the layout of coordinated emergency warehouses based on spatial analysis. The method includes: Collect disaster risk data, population density and distribution data, transportation network data and resource allocation data of the target area, and use GIS spatial analysis technology to conduct spatial overlap analysis to determine the multi-hazard scenario data set and the corresponding associated regional group set.

[0013] In this embodiment, relevant data for the target area are first collected, including disaster risk data, population density and distribution data, transportation network data, and resource allocation data. These data form the basis for spatial analysis and cover information such as disaster types, frequency of occurrence, population distribution, traffic flow, and the allocation and distribution of existing resources within the area. Disaster risk data includes historical disaster records, disaster types, probability of occurrence, and scope of impact. Population density and distribution data covers the population size, population concentration, and spatial distribution characteristics within the area. Transportation network data includes road grades, road connectivity, traffic flow, and accessibility information. Resource allocation data includes the location of existing emergency storage facilities, the type and quantity of reserve materials, storage capacity, and dispatchability. Subsequently, by aggregating the collected disaster risk data of the same type, a multi-disaster scenario data set is determined. Then, using Geographic Information System (GIS) technology, spatial analysis is performed on other collected data based on this multi-disaster scenario data set to identify areas of overlapping disaster locations and areas of superimposed disaster impact. A set of associated regional groups corresponding to the multi-disaster scenario data set is determined. These associated regional groups provide basic data support for subsequent warehouse layout optimization, help to understand the impact of disasters on various factors in the region, and achieve a comprehensive understanding and preparedness for complex disaster scenarios.

[0014] Furthermore, disaster risk data, population density and distribution data, transportation network data, and resource allocation data for the target area are collected. Spatial overlap analysis is then performed using GIS spatial analysis techniques to determine multi-hazard scenario datasets and corresponding related regional sets, including: Based on the disaster risk data, similar types of aggregation are performed to obtain multiple aggregated disaster risk data sets; disaster scenarios within each of the multiple aggregated disaster risk data sets are identified to determine multi-disaster scenario data sets; using GIS spatial analysis technology, based on the multi-disaster scenario data sets, disaster spatial location overlap and disaster superposition impact areas are identified for the population density and distribution data, transportation network data, and resource allocation data, respectively, to determine the associated regional group set.

[0015] Preferably, disaster risk data for the target area, such as earthquakes, floods, and typhoons, are first classified according to disaster type. Then, the DBSCAN algorithm or K-means clustering is used to aggregate disasters of the same type according to geographical location, impact range, and risk level, forming multiple aggregated disaster risk datasets, such as earthquake aggregates and flood aggregates. Each aggregated disaster risk dataset represents the spatial distribution characteristics and potential impact areas of the same type of disaster. Subsequently, a disaster scene recognition model based on multilayer perceptron pre-training is used to analyze the mean of each aggregated disaster risk dataset to identify specific scenarios that may occur under the aggregated disaster. For example, floods may occur in certain low-lying areas, while earthquakes may affect geologically active areas. By summarizing the identified disaster scene data, a multi-disaster scene dataset is determined. These scenarios specifically describe the location, impact range, intensity, and duration of the disaster, providing basic data for subsequent layout optimization. Subsequently, using GIS spatial analysis technology and based on a multi-hazard scenario dataset, the impact of each hazard scenario on the target area was analyzed. This process involved identifying overlapping areas based on the multi-hazard scenario dataset, and also combining population density and distribution data, transportation network data, and resource allocation data to identify areas affected by overlapping hazard impacts. This helped determine which areas were affected by the hazard. For example, a region might not be directly located within a flood or earthquake disaster zone, but due to high population density, important transportation hubs, or key resource allocations such as emergency storage and medical facilities, these factors combined made the region a disaster-affected area. Finally, these identified disaster-affected areas were categorized into a set of associated regions based on their spatial location and the cumulative effect of the hazard impacts. These associated regions included not only areas directly overlapping with the disaster origin but also areas indirectly affected by factors such as population density, transportation networks, and resource allocation. For example, some high-density population areas might be far from the disaster source, but due to a lack of effective transportation connections or emergency resources, they were more likely to be more severely impacted when a disaster occurred. These areas were considered potential disaster-risk areas and therefore, as part of the associated region group, were included in the subsequent emergency storage layout analysis. In this way, disaster data is taken into account in conjunction with social, economic, and infrastructure factors within the region, providing precise regional data support for optimizing the layout of emergency storage facilities. This ensures that resources are rationally allocated to where they are most needed, thereby improving the efficiency and effectiveness of emergency response.

[0016] Furthermore, using GIS spatial analysis technology, based on the multi-disaster scenario data set, the population density and distribution data, transportation network data, and resource allocation data are respectively analyzed to identify the spatial overlap of disaster locations and the areas affected by overlapping disasters, thus determining a set of associated regional groups, including: First multi-hazard scenario data is extracted from the multi-hazard scenario data set; the disaster type and disaster source location of the first multi-hazard scenario data are extracted; based on the disaster source location, overlapping area identification is performed to obtain a first overlapping area group; based on the disaster type and the disaster source location, combined with the population density and distribution data, transportation network data and resource allocation data, the superimposed impact area is identified to obtain a first superimposed impact area group; regional fusion is performed based on the first overlapping area group and the first superimposed impact area group to obtain a first overlapping area group, and regional association data is extracted from the population density and distribution data, transportation network data and resource allocation data. The first overlapping area group is identified according to the extraction results, and the identified first overlapping area group is added to the associated area group set.

[0017] Optionally, firstly, a disaster scenario dataset is randomly extracted from the multi-hazard scenario dataset as the first multi-hazard scenario dataset. The corresponding disaster type and disaster source location are then extracted from this first multi-hazard scenario dataset. The disaster type can be earthquake, flood, typhoon, fire, etc., and the disaster source location is the origin or starting point of the disaster, such as the epicenter of an earthquake, the overflow point of a flood, or the center of a storm. Subsequently, based on the extracted disaster source location, it is mapped in a GIS spatial coordinate system, and spatial overlay analysis is used to identify areas that directly overlap with the disaster source location. These areas constitute the first location overlap area group, representing the geographical range directly affected by the disaster in this scenario. Next, disaster type, disaster source location, and other important socio-economic factors are comprehensively considered. By overlaying the disaster source with population density and distribution data, transportation network data, and resource allocation data, areas that may be indirectly affected during a disaster are identified. For example, some areas may not be directly located within the disaster source area, but due to dense populations or their role as transportation hubs, they may suffer greater impact during a disaster. Therefore, spatial analysis combining these factors identifies these potential disaster-affected areas as the first disaster overlay impact area group. Then, the obtained first location overlap area group and first disaster superimposed impact area group are merged to obtain a more comprehensive disaster-affected area, which serves as the first location overlap area group. This ensures that all potentially affected areas are considered. Based on the determined first location overlap area group, data corresponding to the affected areas are extracted from collected population density and distribution data, transportation network data, and resource allocation data to form regional correlation data. Finally, the extracted regional correlation data is identified and classified, and this information is integrated into the corresponding areas of the first location overlap area group. The identified first location overlap area group is then added to a pre-established set of correlation area groups. In this way, all areas affected during a disaster can be included in the scope of analysis and optimization, providing data support for subsequent emergency storage layout and resource allocation.

[0018] Based on the multi-disaster scenario data set and the associated regional group set, a multi-level linkage emergency warehouse layout analysis is conducted to determine a set of warehouse layout schemes.

[0019] In one embodiment, after obtaining a multi-hazard scenario data set and a set of associated regional groups, the system determines a multi-level linkage structure, generally including a central reserve warehouse, regional central warehouses, local branch warehouses, and forward reserve points. Each level undertakes emergency support functions of different scope and level. Then, the multi-hazard scenario data and the set of associated regional groups are input into a warehouse layout analyzer. The analyzer uses this data to combine and generate layout schemes for different warehouse levels, ensuring that warehouses at each level can form a collaborative response network under different disaster scenarios. This generates a set of warehouse layout schemes, each scheme specifying the geographical location, coverage area, storage capacity, and expected response capability of the warehouse facilities at each level. These schemes not only consider the material support capability under a single disaster scenario but also the linkage response capability under multiple disaster scenarios, providing a data foundation and decision-making basis for subsequent scenario evolution expansion and layout optimization, achieving scientific and executable emergency warehouse deployment planning.

[0020] Furthermore, based on the aforementioned multi-disaster scenario data set and associated regional group set, a multi-level coordinated emergency warehousing layout analysis is conducted to determine a set of warehousing layout schemes, including: The system employs a multi-level linkage structure consisting of a central reserve warehouse, regional central warehouses, local branch warehouses, and forward reserve points. A warehouse layout scheme analyzer is used to analyze the layout of the multi-hazard scenario data set and the associated regional group set, based on this multi-level linkage structure, to determine the set of warehouse layout schemes.

[0021] Preferably, when conducting multi-level coordinated emergency warehousing layout analysis, a multi-level coordinated structure is first constructed according to the hierarchy of central reserve warehouses, regional central warehouses, local branch warehouses, and forward reserve points. The central reserve warehouse is responsible for cross-regional material reserves, with the largest reserve volume and the widest allocation range. Regional central warehouses are responsible for the allocation and reserve of materials within their respective regions, serving multiple local branch warehouses. Local branch warehouses provide short-term emergency material supplies for specific cities or counties, typically on a smaller scale and in smaller quantities. Forward reserve points are located near high-risk areas or transportation hubs to enable rapid response in the early stages of a disaster. After establishing the multi-level coordinated structure, the system acquires a warehousing layout scheme analyzer. This analyzer is an intelligent analysis model built on a deep neural network, consisting of an input layer, multiple hidden layers, and an output layer. The input layer receives a multi-disaster scenario data set and a set of associated regional groups, including multi-dimensional feature data such as disaster type, disaster probability, impact range, population density, transportation network connectivity, and warehousing resource distribution. The hidden layer employs a multi-layer nonlinear mapping structure, learning the complex spatial relationship between disaster impact and warehouse layout through training samples, and extracting the coupling features between disaster response and resource allocation. During the analysis, the warehouse layout scheme analyzer performs feature fusion and pattern recognition on the input multi-disaster scenario data and regional correlation data. Using the trained weight parameters, it outputs the priority, coverage, and response efficiency indicators of each candidate region at different warehouse levels. Based on the output results, the system automatically combines warehouse node location schemes to generate multiple warehouse layout schemes. Finally, the warehouse layout scheme analyzer summarizes the calculated layout results by level, forming a set of warehouse layout schemes. Each scheme includes the geographical location, service radius, reserve scale, and linkage paths with other levels of warehouse facilities at different levels, thereby achieving multi-level warehouse matching and coordination, providing an intelligent foundation for subsequent layout optimization and emergency dispatch.

[0022] By combining the aforementioned multi-disaster scenario data set, scenario evolution expansion is performed to obtain a multi-disaster scenario evolution expansion group set.

[0023] In one embodiment, after completing the multi-level linkage emergency storage layout analysis, in order to enable the storage layout scheme to adapt to the dynamic changes and complex evolution of disasters, the system will expand the obtained multi-disaster scenario data set according to a preset expansion method. By setting the adjustment range within a certain range, multiple rounds of simulation changes are performed on variables such as disaster intensity, affected population density, traffic accessibility, and material consumption rate to form multiple possible initial multi-disaster scenario evolution expansion groups. Then, these expansion groups are processed by approximate mean within the set to retain representative evolution results, thereby forming a set of multi-disaster scenario evolution expansion groups. This set of multi-disaster scenario evolution expansion groups not only includes the typical impact patterns under the original disaster scenario, but also covers multiple combination scenarios under different disaster intensities, spatial diffusion trends, and environmental evolution conditions. It can simulate the emergency response needs under various real disaster scenarios, thereby improving the adaptability, robustness, and scientific nature of the layout scheme.

[0024] Furthermore, by combining the aforementioned multi-hazard scenario dataset with scenario evolution expansion, a multi-hazard scenario evolution expansion set is obtained, including: Based on the multi-hazard scenario data set, the scenario evolution is expanded according to a preset expansion method to obtain an initial multi-hazard scenario evolution expansion group set; the initial multi-hazard scenario evolution expansion group set is processed by approximate mean within the set to obtain a multi-hazard scenario evolution expansion group set; wherein, the preset expansion method is to randomly adjust the scenario impact degree and environmental parameters according to a preset adjustment range.

[0025] Preferably, when expanding the scenario evolution, the original disaster scenario is first dynamically generated and expanded based on the multi-hazard scenario dataset according to a preset expansion method. During this process, the system simulates random disturbances and changes in the scenario's impact and environmental parameters within a preset adjustment range, based on parameters such as disaster type, location, radius of influence, disaster intensity, duration, climate conditions, and terrain features from the multi-hazard scenario dataset. For example, a series of different but reasonable and representative disaster evolution samples can be generated by increasing or decreasing the disaster intensity by a certain percentage, randomly changing the boundary of the affected area, or adjusting the accessibility of the transportation network or resource availability. Through multiple iterative calculations, multiple expanded scenarios with differentiated characteristics can be obtained to construct an initial multi-hazard scenario evolution expansion set. Subsequently, to avoid excessive redundancy between samples and improve computational efficiency, the system performs approximate mean processing on the initial multi-hazard scenario evolution expansion set. That is, it performs similarity analysis on the key parameters of each expanded scenario, using Euclidean distance, cosine similarity, etc., to quantify the similarity between scenario samples. When multiple extended scenarios are found to have a similarity threshold greater than or equal to the similarity threshold in features such as disaster impact intensity, spatial distribution, affected population density, and traffic disruption degree, they are classified as samples of the same type. For these highly similar scenarios, instead of consuming system resources individually, they are merged through averaging. That is, the mean or median of the main parameters of similar scenarios is taken to form a representative sample to replace the sample set of that type. After approximate averaging within the set, the resulting multi-hazard scenario evolution extended set not only maintains the diversity and representativeness of the original scenarios but also significantly reduces sample redundancy and optimizes computational resource consumption. The final multi-hazard scenario evolution extended set can cover multiple disaster evolution trends at a more reasonable scale, providing a comprehensive, realistic, and efficient simulation foundation for subsequent layout response adaptability analysis and scheme optimization.

[0026] Based on the scenario evolution expansion set, the layout response fitness analysis is performed on the warehouse layout scheme set, and the scheme is optimized by combining the layout response fitness set to obtain the warehouse layout optimization scheme set.

[0027] In one embodiment, after obtaining the extended set of multi-hazard scenario evolution, the system performs fitness analysis on the response performance of each warehouse layout scheme in the set under different evolution scenarios based on preset layout response indicators, obtaining the response performance of each scheme in that scenario. After completing the simulation of all extended scenarios, the response fitness of each warehouse layout scheme under different scenarios is summarized to form a set of layout response fitness. Subsequently, based on this set of layout response fitness, the warehouse layout schemes are optimized by adjusting the warehouse node positions, warehouse capacity allocation, etc., to improve overall response efficiency and material support capabilities, generating the final set of optimized warehouse layout schemes. Each scheme in the set of optimized warehouse layout schemes not only meets the emergency needs under a single disaster scenario but also has strong robustness and collaborative response capabilities under multi-hazard evolution conditions, providing a scientific and executable data foundation and decision support for subsequent linkage scenario integration and the determination of the final target warehouse layout.

[0028] Furthermore, based on the scenario evolution expansion set, layout response fitness analysis is performed on the warehouse layout scheme set, and the schemes are optimized by combining the layout response fitness set to obtain a warehouse layout optimization scheme set, including: Obtain preset layout response indicators, including response time, material arrival rate, and warehouse capacity utilization; simulate the scenario response of the corresponding warehouse layout schemes in the warehouse layout scheme set according to the scenario evolution expansion group set, and evaluate the simulation results according to the preset layout response indicators to obtain a layout response fitness group set; optimize the warehouse layout scheme set based on the layout response fitness group set to obtain the warehouse layout optimization scheme set.

[0029] Preferably, a preset layout response index is first obtained to evaluate the emergency response capabilities of each warehousing layout scheme under different disaster scenarios. This preset layout response index includes response time, material arrival rate, and warehouse capacity utilization. Response time refers to the time required from the occurrence of a disaster to the arrival of materials in the affected area; material arrival rate refers to the proportion of materials that can be successfully delivered to the affected area within a specified time; and warehouse capacity utilization refers to the degree to which warehouse resources are rationally utilized during the response process. Subsequently, according to the multi-disaster scenario evolution expansion set, scenario response simulations are performed on each scheme in the simulation software. During the simulation, each expanded scenario is input into the simulation software. Combining the disaster impact range, affected population density, transportation network conditions, and the material reserves and transportation capacity of each warehousing node, the material delivery path, scheduling sequence, and warehouse capacity utilization are dynamically calculated to obtain the response performance data of each scheme under that scenario. After the simulation is completed, a quantitative evaluation is performed based on the simulated values ​​of the preset layout response index for each scheme. The layout response adaptability of each scheme under each scenario is obtained through a weighted average. Subsequently, these layout response fitness scores are aggregated to form a layout response fitness set. This set comprehensively reflects the performance and adaptability of each warehouse layout scheme under different disaster evolution scenarios. Finally, based on the layout response fitness set, the adaptive scale of the warehouse layout scheme set is adjusted to ensure that the layout schemes achieve optimal response performance and resource utilization efficiency in most evolution scenarios, resulting in the final set of optimized warehouse layout schemes. Each scheme in this set of optimized warehouse layout schemes demonstrates high response efficiency, material support capability, and warehouse resource utilization rate under multiple disaster scenarios, providing a scientific basis and data support for subsequent linkage scenario integration and target warehouse layout determination.

[0030] Furthermore, based on the set of layout response fitness groups, the set of warehouse layout schemes is optimized to obtain the set of optimized warehouse layout schemes, including: Calculate the mean of the set of layout response fitness groups to obtain the set of scheme layout response fitness; based on the magnitude of the scheme layout response fitness in the set of scheme layout response fitness, adjust the adaptive scale of the set of warehouse layout schemes to obtain the set of warehouse layout optimization schemes.

[0031] Optionally, after obtaining the set of layout response fitness groups, for each warehouse layout scheme in the set of warehouse layout schemes, the average value of its layout response fitness in all multi-hazard scenario evolution expansion groups is calculated, thereby obtaining the comprehensive response performance of each warehouse layout scheme and forming a scheme layout response fitness set. This scheme layout response fitness set can quantify the overall adaptability and order of merit of each warehouse layout scheme under different evolution scenarios, providing a unified evaluation standard for scheme optimization. Subsequently, based on the fitness of each scheme in the scheme layout response fitness set, the set of warehouse layout schemes is adjusted for adaptability. Specifically, for schemes with fitness greater than or equal to the excellent fitness threshold, their warehouse node location, capacity allocation, and scheduling strategies remain unchanged to maintain their efficient response capability. For schemes with fitness lower than the excellent fitness threshold, these warehouse layout schemes are iteratively calculated using heuristic algorithms, genetic algorithms, or neural networks based on the deviation ratio from the excellent fitness threshold, ensuring that the warehouse layout schemes have the best response capability and resource utilization efficiency under most disaster evolution scenarios. After the above mean calculation and adaptive scaling adjustment, the system finally generates a set of warehouse layout optimization schemes. Each warehouse layout optimization scheme in this set can achieve reasonable allocation of warehouse resources, rapid response material dispatch and efficient coverage of disaster areas under multi-disaster scenarios, thereby providing scientific basis and executable data support for subsequent linkage scenario integration and target warehouse layout determination.

[0032] The set of warehouse layout optimization schemes is linked and integrated to determine the target warehouse layout optimization scheme.

[0033] In one embodiment, after obtaining a set of warehouse layout optimization schemes, a scenario fusion analysis is performed on the performance of each scheme under multi-hazard evolution scenarios. During this process, the multi-level warehouse nodes, storage capacity, material scheduling strategies, and coverage areas corresponding to each scheme in the optimization scheme set are spatially and functionally mapped to form a scheme feature matrix. Subsequently, based on demand and response indicators under multi-hazard evolution scenarios, a weighted synthesis or neural network-based fusion model is used to optimize and adjust the geographical location, capacity configuration, hierarchical scheduling strategies, and material allocation paths of each warehouse node under different scenarios for each warehouse layout optimization scheme. This takes into account the advantages of each scheme under different evolution scenarios, maximizing resource utilization and optimizing response efficiency. Finally, the target warehouse layout optimization scheme obtained through scenario fusion includes a clear multi-level warehouse node layout, reasonable capacity allocation, and efficient logistics scheduling scheme. It can achieve rapid, coordinated, and stable emergency response under various disaster types and intensities, providing reliable decision-making basis and executable solutions for emergency material support.

[0034] In summary, the embodiments of this application have at least the following technical effects: First, disaster risk data, population density and distribution data, transportation network data, and resource allocation data for the target area are collected. Spatial overlap analysis is performed using GIS spatial analysis technology to determine a multi-hazard scenario data set and corresponding associated regional groups. Next, based on the multi-hazard scenario data set and associated regional groups, a multi-level linkage emergency warehousing layout analysis is conducted to determine a set of warehousing layout schemes. Then, the scenarios are expanded through evolution, resulting in a set of expanded multi-hazard scenario evolution groups. Next, layout response adaptability analysis is performed on each of the warehousing layout schemes according to the expanded scenario evolution groups, and scheme optimization is performed based on the layout response adaptability groups to obtain a set of optimized warehousing layout schemes. Finally, the optimized warehousing layout schemes are fused through linkage scenarios to determine the target optimized warehousing layout scheme. This approach solves the technical problem of traditional emergency warehousing layouts lacking dynamic adaptability and cross-regional linkage capabilities when facing complex multi-hazard chains. It achieves the technical effect of dynamically optimizing and multi-levelly linking warehousing layouts through spatial analysis and scenario evolution, thereby improving the emergency response capability and resource allocation efficiency of warehousing layouts.

[0035] Example 2, based on the same inventive concept as the spatial analysis-based collaborative emergency warehouse layout optimization method in the aforementioned examples, such as... Figure 2 As shown, this application provides a spatial analysis-based collaborative emergency warehouse layout optimization system, the system comprising: Overlap Analysis Module 11: Collects disaster risk data, population density and distribution data, transportation network data, and resource allocation data of the target area, and uses GIS spatial analysis technology to perform spatial overlap analysis to determine the multi-disaster scenario data set and the corresponding associated regional group set; Layout Analysis Module 12: Based on the multi-disaster scenario data set and associated regional group set, performs multi-level linkage emergency warehouse layout analysis to determine the warehouse layout scheme set; Scenario Evolution Module 13: Combines the multi-disaster scenario data set to perform scenario evolution expansion to obtain a multi-disaster scenario evolution expansion group set; Layout Optimization Module 14: Performs layout response fitness analysis on the warehouse layout scheme set according to the scenario evolution expansion group set, and optimizes the schemes based on the layout response fitness group set to obtain a warehouse layout optimization scheme set; Scenario Fusion Module 15: Performs linkage scenario fusion on the warehouse layout optimization scheme set to determine the target warehouse layout optimization scheme.

[0036] Furthermore, the overlap analysis module 11 is used to perform the following method: Based on the disaster risk data, similar types of aggregation are performed to obtain multiple aggregated disaster risk data sets; disaster scenarios within each of the multiple aggregated disaster risk data sets are identified to determine multi-disaster scenario data sets; using GIS spatial analysis technology, based on the multi-disaster scenario data sets, disaster spatial location overlap and disaster superposition impact areas are identified for the population density and distribution data, transportation network data, and resource allocation data, respectively, to determine the associated regional group set.

[0037] Furthermore, the overlap analysis module 11 is used to perform the following method: First multi-hazard scenario data is extracted from the multi-hazard scenario data set; the disaster type and disaster source location of the first multi-hazard scenario data are extracted; based on the disaster source location, overlapping area identification is performed to obtain a first overlapping area group; based on the disaster type and the disaster source location, combined with the population density and distribution data, transportation network data and resource allocation data, the superimposed impact area is identified to obtain a first superimposed impact area group; regional fusion is performed based on the first overlapping area group and the first superimposed impact area group to obtain a first overlapping area group, and regional association data is extracted from the population density and distribution data, transportation network data and resource allocation data. The first overlapping area group is identified according to the extraction results, and the identified first overlapping area group is added to the associated area group set.

[0038] Furthermore, the layout analysis module 12 is used to perform the following methods: The system employs a multi-level linkage structure consisting of a central reserve warehouse, regional central warehouses, local branch warehouses, and forward reserve points. A warehouse layout scheme analyzer is used to analyze the layout of the multi-hazard scenario data set and the associated regional group set, based on this multi-level linkage structure, to determine the set of warehouse layout schemes.

[0039] Furthermore, the scene evolution module 13 is used to execute the following methods: Based on the multi-hazard scenario data set, the scenario evolution is expanded according to a preset expansion method to obtain an initial multi-hazard scenario evolution expansion group set; the initial multi-hazard scenario evolution expansion group set is processed by approximate mean within the set to obtain a multi-hazard scenario evolution expansion group set; wherein, the preset expansion method is to randomly adjust the scenario impact degree and environmental parameters according to a preset adjustment range.

[0040] Furthermore, the layout optimization module 14 is used to perform the following method: Obtain preset layout response indicators, including response time, material arrival rate, and warehouse capacity utilization; simulate the scenario response of the corresponding warehouse layout schemes in the warehouse layout scheme set according to the scenario evolution expansion group set, and evaluate the simulation results according to the preset layout response indicators to obtain a layout response fitness group set; optimize the warehouse layout scheme set based on the layout response fitness group set to obtain the warehouse layout optimization scheme set.

[0041] Furthermore, the layout optimization module 14 is used to perform the following method: Calculate the mean of the set of layout response fitness groups to obtain the set of scheme layout response fitness; based on the magnitude of the scheme layout response fitness in the set of scheme layout response fitness, adjust the adaptive scale of the set of warehouse layout schemes to obtain the set of warehouse layout optimization schemes.

[0042] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any modifications, equivalent changes, and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A method for optimizing the layout of coordinated emergency storage facilities based on spatial analysis, characterized in that, The method includes: Collect disaster risk data, population density and distribution data, transportation network data and resource allocation data of the target area, and use GIS spatial analysis technology to conduct spatial overlap analysis to determine the multi-hazard scenario data set and the corresponding associated regional group set; Based on the multi-disaster scenario data set and the associated regional group set, a multi-level linkage emergency storage layout analysis is conducted to determine a set of storage layout schemes. By combining the aforementioned multi-hazard scenario data set, scenario evolution expansion is performed to obtain a multi-hazard scenario evolution expansion group set; Based on the scenario evolution expansion group set, the layout response fitness analysis is performed on the warehouse layout scheme set, and the scheme is optimized by combining the layout response fitness group set to obtain the warehouse layout optimization scheme set. The set of warehouse layout optimization schemes is linked and integrated to determine the target warehouse layout optimization scheme.

2. The method for optimizing the layout of coordinated emergency storage based on spatial analysis as described in claim 1, characterized in that, Collect disaster risk data, population density and distribution data, transportation network data, and resource allocation data for the target area. Utilize GIS spatial analysis technology to conduct spatial overlap analysis, determine the multi-hazard scenario dataset and the corresponding set of associated regional groups, including: Based on the disaster risk data, perform similar aggregation to obtain multiple aggregated disaster risk data sets; Disaster scenarios within each of the multiple aggregated disaster risk datasets are identified to determine the multi-disaster scenario dataset. Using GIS spatial analysis technology, based on the multi-disaster scenario data set, the spatial location overlap of disasters and the areas affected by disaster superposition are identified for the population density and distribution data, transportation network data and resource allocation data, respectively, and the associated regional group set is determined.

3. The method for optimizing the layout of coordinated emergency storage based on spatial analysis as described in claim 2, characterized in that, Using GIS spatial analysis technology, based on the multi-hazard scenario data set, the spatial overlap of disaster locations and the areas of overlapping disaster impacts are identified for the population density and distribution data, transportation network data, and resource allocation data, respectively, to determine a set of associated regional groups, including: Extract the first multi-hazard scenario data from the multi-hazard scenario dataset; Extract the disaster type and disaster source location from the first multi-disaster scenario data; Based on the location of the disaster source, the location overlap area is identified to obtain the first location overlap area group; Based on the disaster type and the location of the disaster source, and combined with the population density and distribution data, transportation network data and resource allocation data, the disaster superimposed impact area is identified to obtain the first disaster superimposed impact area group; Based on the first location overlap area group and the first disaster superimposed impact area group, regional fusion is performed to obtain the first location overlap area group. Regional correlation data is extracted from the population density and distribution data, transportation network data and resource allocation data. The first location overlap area group is identified according to the extraction results and added to the associated area group set.

4. The method for optimizing the layout of coordinated emergency storage based on spatial analysis as described in claim 1, characterized in that, Based on the aforementioned multi-disaster scenario data set and associated regional group set, a multi-level coordinated emergency warehousing layout analysis is conducted to determine a set of warehousing layout schemes, including: The system is structured as a multi-level linkage, consisting of central reserve warehouses, regional central warehouses, local branch warehouses, and forward reserve points. The warehouse layout scheme analyzer is used to analyze the layout of the multi-disaster scenario data set and the associated area group set in conjunction with the multi-level linkage structure, and to determine the warehouse layout scheme set.

5. The method for optimizing the layout of coordinated emergency storage based on spatial analysis as described in claim 1, characterized in that, By combining the aforementioned multi-hazard scenario dataset with scenario evolution expansion, a multi-hazard scenario evolution expansion set is obtained, including: Based on the multi-hazard scenario data set, the scenarios are expanded according to a preset expansion method to obtain an initial multi-hazard scenario evolution expansion group set; The initial multi-hazard scenario evolution expansion set is subjected to an approximate mean within the set to obtain the multi-hazard scenario evolution expansion set; The preset expansion method involves randomly adjusting the scene's impact level and environmental parameters according to a preset adjustment range.

6. The method for optimizing the layout of coordinated emergency storage based on spatial analysis as described in claim 1, characterized in that, Based on the scenario evolution expansion set, layout response fitness analysis is performed on the warehouse layout scheme set, and the schemes are optimized by combining the layout response fitness set to obtain a warehouse layout optimization scheme set, including: Obtain preset layout response indicators, wherein the preset layout response indicators include response time, material arrival rate and warehouse capacity utilization. According to the scenario evolution expansion group set, the corresponding warehouse layout schemes in the warehouse layout scheme set are simulated for scenario response, and the simulation results are evaluated according to the preset layout response index to obtain the layout response fitness group set. Based on the set of layout response fitness groups, the set of warehouse layout schemes is optimized to obtain the set of optimized warehouse layout schemes.

7. The method for optimizing the layout of coordinated emergency storage based on spatial analysis as described in claim 6, characterized in that, Based on the set of layout response fitness groups, the set of warehouse layout schemes is optimized to obtain the set of optimized warehouse layout schemes, including: Calculate the mean of the set of layout response fitness groups to obtain the set of layout response fitness groups for the proposed solutions; Based on the magnitude of the response fitness of the proposed layout in the proposed layout fitness set, the fitness scale of the proposed warehouse layout is adjusted to obtain the proposed warehouse layout optimization set.

8. A coordinated emergency warehouse layout optimization system based on spatial analysis, characterized in that, The system is used to implement the spatial analysis-based coordinated emergency warehouse layout optimization method according to any one of claims 1-7, the system comprising: Overlap Analysis Module: Collects disaster risk data, population density and distribution data, transportation network data and resource allocation data of the target area, uses GIS spatial analysis technology to perform spatial overlap analysis, and determines the data set of multiple disaster scenarios and the corresponding set of related regional groups; Layout Analysis Module: Based on the multi-disaster scenario data set and the associated regional group set, perform multi-level linkage emergency warehouse layout analysis to determine a set of warehouse layout schemes; Scene evolution module: Combines the multi-hazard scene data set to perform scene evolution expansion, and obtains a multi-hazard scene evolution expansion group set; Layout optimization module: Based on the scenario evolution expansion group set, perform layout response fitness analysis on the warehouse layout scheme set, and optimize the schemes by combining the layout response fitness group set to obtain a warehouse layout optimization scheme set; Scene fusion module: Performs scene fusion on the set of warehouse layout optimization schemes to determine the target warehouse layout optimization scheme.

Images