Resource Allocation Method and Device Based on Cross-Regional Disaster Risk Assessment

Abstract

An embodiment of the present application provides a resource allocation method and device based on cross-regional disaster risk assessment, belonging to the field of disaster response resource allocation. The method includes: First, obtain the target data of at least two target regions, and perform disaster risk assessment on each sub-region to be evaluated according to the target data to obtain the preliminary risk assessment data of each sub-region to be evaluated. Then, mine the risk characteristics of each target region according to the preliminary risk assessment data to obtain the target risk characteristics of each target region, and perform similarity assessment between target regions on all the target risk characteristics of at least two target regions to obtain the similarity measurement data between target regions. Finally, perform resource allocation on each target region according to the similarity measurement data between target regions. The embodiment of the present application can improve the accuracy of risk assessment for cross-regional and cross-scale disasters, so as to improve the rationality of resource allocation, thereby improving the utilization efficiency of disaster response resources.

Description

Technical Field

[0001] This application relates to the field of disaster response resource allocation, and particularly to a resource allocation method and device based on cross-regional disaster risk assessment. Background Art

[0002] Currently, resource allocation strategies in disaster risk management are usually based on the assessment of disaster risks in each region. However, existing disaster risk assessment methods are limited to dividing risk regions based on administrative divisions. This single scale of risk region division fails to fully consider the internal connections of risk characteristics between regions at different spatial scales, making it difficult for existing risk assessment methods to effectively assess risks in the face of natural disasters across regions and scales. Inaccurate risk assessment further leads to mistakes in resource allocation strategies, making it impossible to reasonably allocate disaster response resources to the areas in greatest need.

[0003] Therefore, how to improve the accuracy of risk assessment methods in dealing with cross-regional and cross-scale disasters to improve the efficiency of disaster response resource allocation has become a technical problem to be solved urgently. Summary of the Invention

[0004] The main purpose of the embodiments of this application is to propose a resource allocation method and device based on cross-regional disaster risk assessment, aiming to improve the accuracy of risk assessment methods in dealing with cross-regional and cross-scale disasters to improve the efficiency of disaster response resource allocation.

[0005] To achieve the above object, a first aspect of the embodiments of this application proposes a resource allocation method based on cross-regional disaster risk assessment, and the method includes:

[0006] Obtain target data of at least two target regions; wherein, the target data is data related to disasters in the target regions, and each target region includes at least two sub-regions to be evaluated;

[0007] Perform disaster risk assessment on each sub-region to be evaluated according to each target data to obtain preliminary risk assessment data of each sub-region to be evaluated;

[0008] Mine risk characteristics of each target region according to the preliminary risk assessment data to obtain target risk characteristics of each target region;

[0009] Perform similarity assessment between target regions on the target risk characteristics of at least two target regions to obtain similarity measurement data between target regions; wherein, each similarity measurement data between target regions represents the inter-regional risk similarity between any two target regions;

[0010] Allocate resources to each target region according to the similarity measurement data between target regions.

[0011] In some embodiments, mining risk characteristics for each of the target regions based on the preliminary risk assessment data to obtain the target risk characteristics of each of the target regions includes:

[0012] Obtaining the location information of each of the sub-regions to be evaluated to obtain sub-region location information;

[0013] Constructing graph network nodes according to the sub-region location information corresponding to each of the sub-regions to be evaluated and the preliminary risk assessment data; wherein each graph network node is used to describe the risk of a sub-region to be evaluated suffering from a disaster;

[0014] Constructing a target graph network according to the graph network nodes, the sub-region location information, and the preliminary risk assessment data; wherein the graph network edges of the target graph network represent the spatial adjacency relationship between the sub-regions to be evaluated, and the edge weight data of the target graph network represents the difference in the preliminary risk assessment data between the sub-regions to be evaluated;

[0015] Performing a first-level region division process according to the graph network edges, the edge weight data, and the sub-regions to be evaluated to obtain target first-level regions;

[0016] Mining the regional risk characteristics of each of the target first-level regions according to the target first-level regions, the preliminary risk assessment data, and the sub-region location information to obtain the target risk characteristics of each of the target regions.

[0017] In some embodiments, constructing a target graph network according to the graph network nodes, the sub-region location information, and the preliminary risk assessment data includes:

[0018] Selecting a first target node and at least one first adjacent node from the graph network nodes according to the sub-region location information; wherein the first adjacent node and the first target node are adjacent in terms of spatial relationship;

[0019] Obtaining the preliminary risk assessment data corresponding to the first target node to obtain target risk assessment data;

[0020] Obtaining the preliminary risk assessment data corresponding to the first adjacent node to obtain adjacent risk assessment data;

[0021] Performing a sub-region risk relevance measurement on each of the sub-regions to be evaluated according to the target risk assessment data and the adjacent risk assessment data to obtain the edge weight data;

[0022] Constructing the graph network edges according to the first target node, the first adjacent node, and the edge weight data;

[0023] Construct a target graph network based on the graph network nodes and the graph network edges.

[0024] In some embodiments, the first-level region division process is performed according to the graph network edges, the edge weight data, and the sub-region to be evaluated, and a target first-level region is obtained, including:

[0025] Select a second target node and at least one second adjacent node from the graph network nodes; wherein, the second adjacent node and the second target node are adjacent in spatial relationship;

[0026] Perform an initial region division on the graph network nodes according to a preset first-level region division rule to obtain at least one initial first-level region;

[0027] Obtain the initial first-level region where each second adjacent node is located to obtain an adjacent first-level region;

[0028] Perform a first-level region re-division process according to the second target node, each adjacent first-level region, the graph network edges, and the edge weight data to obtain an updated first-level region;

[0029] Update the initial first-level region according to the updated first-level region to obtain the target first-level region.

[0030] In some embodiments, the region risk feature mining is performed on each target first-level region according to the target first-level region, the preliminary risk assessment data, and the sub-region location information to obtain the target risk feature of each target region, including:

[0031] Obtain the graph network nodes of each target first-level region to obtain candidate graph network nodes;

[0032] Obtain the preliminary risk assessment data according to the candidate graph network nodes to obtain the first-level region risk to be evaluated data of each target first-level region;

[0033] Perform a first-level region risk assessment according to the first-level region risk to be evaluated data of each target first-level region to obtain first-level region risk assessment data; wherein, the first-level region risk assessment data characterizes the risk of the target first-level region suffering from disasters;

[0034] Determine the location information of the target first-level region according to the target first-level region and the sub-region location information to obtain the first-level region location information;

[0035] Perform risk correlation degree measurement based on the target first-level region, the first-level region location information, and the first-level region risk assessment data to obtain first-level region risk correlation degree data; wherein, each piece of the first-level region risk correlation degree data corresponds to one of the target first-level regions, and the first-level region risk correlation degree data characterizes the risk difference between the target first-level region and its surrounding first-level regions.

[0036] Perform regional risk feature mining based on the first-level region risk assessment data and the first-level region risk correlation degree data corresponding to each target first-level region to obtain the target risk features of each target region.

[0037] In some embodiments, the performing target region similarity evaluation on the target risk features of at least two target regions to obtain target region similarity measurement data includes:

[0038] Select a first region and a second region from at least two target regions; wherein, the first region and the second region are different.

[0039] Select at least one selected region from the target first-level regions of the first region.

[0040] Select at least one candidate region from the target first-level regions of the second region.

[0041] Perform feature similarity evaluation based on each selected region and the candidate region to obtain target feature similarity evaluation data.

[0042] Perform target region similarity measurement based on the target feature similarity evaluation data of the selected regions to obtain target region similarity measurement data.

[0043] In some embodiments, the performing feature similarity evaluation based on each selected region and the candidate region to obtain target feature similarity evaluation data includes:

[0044] Obtain the target risk features corresponding to each selected region to obtain first feature similarity to-be-evaluated features.

[0045] Obtain the target risk features corresponding to each candidate region to obtain second feature similarity to-be-evaluated features.

[0046] Perform risk feature distance measurement based on the first feature similarity to-be-evaluated features and each of the second feature similarity to-be-evaluated features to obtain risk feature distance measurement data.

[0047] Perform risk feature similarity evaluation based on the distance measurement data to obtain initial feature similarity evaluation data.

[0048] Select the target feature similarity evaluation data from at least one of the initial feature similarity evaluation data corresponding to the selected region; wherein, the risk feature similarity degree between the selected region corresponding to the target feature similarity evaluation data and the second region is the largest.

[0049] In some embodiments, the target data includes: historical disaster data, geographical environment data, social loss data, economic loss data, social development level evaluation data, social and economic exposure data, ecological environment exposure data, and infrastructure exposure data. Conduct disaster risk assessment on each sub-region to be evaluated according to each target data, and obtain the preliminary risk assessment data of each sub-region to be evaluated, including:

[0050] Extract risk vulnerability assessment features according to the historical disaster data and the geographical environment data;

[0051] Conduct risk occurrence probability assessment according to the risk vulnerability assessment features to obtain risk occurrence probability assessment data; wherein, the risk occurrence probability assessment data represents the possibility of a disaster occurring in the target area;

[0052] Extract socio-economic vulnerability assessment features according to the social loss data, the economic loss data, and the social development level evaluation data;

[0053] Conduct disaster resistance assessment according to the socio-economic vulnerability assessment features to obtain target socio-economic vulnerability assessment data; wherein, the target socio-economic vulnerability assessment data represents the disaster resistance ability of the target area;

[0054] Extract disaster exposure assessment features according to the social and economic exposure data, the ecological environment exposure data, and the infrastructure exposure data;

[0055] Conduct disaster impact range assessment according to the disaster exposure assessment features to obtain target disaster exposure data; wherein, the target disaster exposure data represents the impact range of the disaster on the target area;

[0056] Conduct comprehensive disaster risk assessment according to the risk occurrence probability assessment data, the target socio-economic vulnerability assessment data, and the target disaster exposure data to obtain the preliminary risk assessment data of each sub-region to be evaluated.

[0057] In some embodiments, the resource allocation for each target area according to the similarity metric data between the target areas includes:

[0058] Conduct resource allocation similarity assessment on at least two target areas according to the similarity metric data between the target areas to obtain target area resource allocation similarity data;

[0059] Perform target area risk assessment on the target risk characteristics corresponding to each of the said target areas to obtain target area risk assessment data;

[0060] Allocate resources to the target areas according to the target area risk assessment data and the target area resource allocation similarity data.

[0061] To achieve the above object, a second aspect of the embodiments of the present application proposes a resource allocation device based on cross - regional disaster risk assessment, and the device includes:

[0062] A data acquisition module, configured to acquire target data of at least two target areas; wherein, the target data is data related to disasters in the target areas, and each of the target areas includes at least two sub - areas to be evaluated;

[0063] A preliminary risk assessment module, configured to perform disaster risk assessment on each of the sub - areas to be evaluated according to the target data to obtain preliminary risk assessment data of each sub - area to be evaluated;

[0064] A risk characteristic mining module, configured to perform risk characteristic mining on each of the target areas according to the preliminary risk assessment data to obtain the target risk characteristics of each of the target areas;

[0065] A similarity measurement module between target areas, configured to perform similarity assessment between target areas on the target risk characteristics of at least two of the target areas to obtain similarity measurement data between target areas; wherein, each of the similarity measurement data between target areas represents the inter - area risk similarity between any two of the target areas;

[0066] A resource allocation module, configured to allocate resources to each of the target areas according to the similarity measurement data between target areas.

[0067] The resource allocation method and device based on cross - regional disaster risk assessment proposed in this application obtain the target data of at least two target regions, and conduct disaster risk assessment on each sub - region to be evaluated according to the target data, obtaining the preliminary risk assessment data of each sub - region to be evaluated. Then, according to the preliminary risk assessment data, risk feature mining is carried out on each target region to obtain the target risk features of each target region, and similarity assessment between target regions is conducted on the target risk features of at least two target regions to obtain the similarity measurement data between target regions. Finally, resource allocation is carried out on each target region according to the similarity measurement data between target regions. Therefore, the resource allocation method and device based on cross - regional disaster risk assessment proposed in this application measure risk similarity between target regions according to the spatial scale, and conduct resource allocation for each target region based on the inter - regional risk similarity measurement data, improving the accuracy of the risk assessment method for natural disaster risk assessment of cross - regional and cross - scale disasters. Moreover, by using the measurement data of inter - regional risk similarity to guide resource allocation, the rationality and accuracy of disaster - response resource allocation can be improved, enabling disaster - response resources to be utilized more efficiently. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 is a flowchart of the resource allocation method based on cross - regional disaster risk assessment provided by an embodiment of this application;

[0069] Figure 2 is Figure 1 the flowchart of step S102 in

[0070] Figure 3 is Figure 1 the flowchart of step S103 in

[0071] Figure 4 is Figure 3 the flowchart of step S303 in

[0072] Figure 5 is Figure 3 the flowchart of step S304 in

[0073] Figure 6 is Figure 3 the flowchart of step S305 in

[0074] Figure 7 is Figure 1 the flowchart of step S104 in

[0075] Figure 8 is Figure 7 the flowchart of step S704 in

[0076] Figure 9 is Figure 1The flowchart of step S105 in

[0077] Figure 10 is a schematic structural diagram of a resource allocation device based on cross - regional disaster risk assessment provided by an embodiment of the present application;

[0078] Figure 11 is a schematic hardware structure diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0079] In order to make the objectives, technical solutions and advantages of the present application more clear and understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0080] It should be noted that although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order from the module division in the device or the order in the flowchart. Terms such as "first" and "second" in the description, claims and the above - mentioned drawings are used to distinguish similar objects and do not necessarily need to describe a specific order or sequence.

[0081] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application and are not intended to limit the present application.

[0082] First, several terms involved in the present application are analyzed:

[0083] Artificial intelligence (AI): It is a new technical science that studies, develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence; artificial intelligence is a branch of computer science. Artificial intelligence attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a way similar to human intelligence. The research in this field includes robots, speech recognition, image recognition, natural language processing and expert systems, etc. Artificial intelligence can simulate the information process of human consciousness and thinking.

[0084] In today's complex and ever-changing disaster environment, the core of disaster risk management lies in how to reasonably allocate limited resources to cope with potential disaster threats. The effectiveness of resource allocation strategies depends to a large extent on the accuracy of disaster risk assessment. However, existing assessment methods are usually limited by traditional administrative divisions, which often overlook the distribution characteristics of disaster risks at different geographical and spatial scales. Due to the complexity and uncertainty of natural disasters, they often do not follow artificially defined boundaries, making it difficult for single-scale risk assessment to comprehensively capture the full picture of disasters. For example, the flood risk in a river basin may involve multiple administrative regions in the upper, middle, and lower reaches, and existing assessment methods may not be able to fully consider the risk connections across the entire basin. Similarly, the impacts of disasters such as earthquakes and typhoons often span multiple regions and need to be evaluated at a broader spatial scale to allocate disaster response resources reasonably.

[0085] Based on this, the embodiments of this application provide a resource allocation method and device based on cross-regional disaster risk assessment, aiming to improve the accuracy of risk assessment methods in dealing with cross-regional and cross-scale disasters, so as to improve the efficiency of disaster response resource allocation.

[0086] The resource allocation method and device based on cross-regional disaster risk assessment provided by the embodiments of this application are specifically described through the following embodiments. First, the resource allocation method based on cross-regional disaster risk assessment in the embodiments of this application is described.

[0087] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain the best results.

[0088] Artificial intelligence basic technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, and mechatronics. Artificial intelligence software technologies mainly include several major directions such as computer vision technology, robotics, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0089] The resource allocation method based on cross - regional disaster risk assessment provided by the embodiments of the present application relates to the field of disaster response resource allocation. The resource allocation method based on cross - regional disaster risk assessment provided by the embodiments of the present application can be applied to a terminal, or to a server - side, or can also be software running on a terminal or a server - side. In some embodiments, the terminal can be a smart phone, a tablet computer, a notebook computer, a desktop computer, etc.; the server - side can be configured as an independent physical server, or can be configured as a server cluster or a distributed system composed of multiple physical servers, or can also be configured as a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application implementing the resource allocation method based on cross - regional disaster risk assessment, etc., but is not limited to the above forms.

[0090] The present application can be used in many general - purpose or special - purpose computer system environments or configurations. For example: personal computers, server computers, hand - held or portable devices, tablet - type devices, multi - processor systems, micro - processor - based systems, set - top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and so on. The present application can be described in the general context of computer - executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0091] Figure 1 is an optional flowchart of the resource allocation method based on cross - regional disaster risk assessment provided by the embodiments of the present application, Figure 1 The method in can include but is not limited to steps S101 to S105.

[0092] Step S101, obtain target data of at least two target regions; wherein, the target data is data related to disasters in the target regions, and each target region includes at least two sub - regions to be evaluated;

[0093] Step S102, perform disaster risk assessment on each sub - region to be evaluated according to each target data, and obtain preliminary risk assessment data of each sub - region to be evaluated;

[0094] Step S103: Mine the risk characteristics for each target area based on the preliminary risk assessment data to obtain the target risk characteristics of each target area.

[0095] Step S104: Evaluate the similarity between the target risk characteristics of at least two target areas to obtain the similarity measurement data between target areas; wherein, each similarity measurement data between target areas represents the inter-regional risk similarity between any two target areas.

[0096] Step S105: Allocate resources to each target area according to the similarity measurement data between target areas.

[0097] Steps S101 to S105 illustrated in the embodiments of the present application obtain the target data of at least two target areas, and perform disaster risk assessment on each sub-area to be evaluated according to the target data to obtain the preliminary risk assessment data of each sub-area to be evaluated. Then, mine the risk characteristics for each target area based on the preliminary risk assessment data to obtain the target risk characteristics of each target area, evaluate the similarity between the target risk characteristics of at least two target areas to obtain the similarity measurement data between target areas, and finally allocate resources to each target area according to the similarity measurement data between target areas. Therefore, the resource allocation method based on cross-regional disaster risk assessment proposed in the present application measures the risk similarity between target areas according to the spatial scale, and allocates resources to each target area based on the inter-regional risk similarity measurement data, improving the accuracy of the risk assessment method for natural disaster risk assessment of cross-regional and cross-scale disasters. Moreover, by using the measurement data of the inter-regional risk similarity to guide resource allocation, the rationality and accuracy of disaster response resource allocation can be improved, enabling more efficient utilization of disaster response resources.

[0098] Please refer to Figure 2 , in some embodiments, the target data includes but is not limited to historical disaster data, geographical environment data, social loss data, economic loss data, social development level assessment data, social and economic exposure data, ecological environment exposure data, and infrastructure exposure data. Step S102 may include but is not limited to steps S201 to S207:

[0099] Step S201: Extract risk vulnerability assessment features according to the historical disaster data and geographical environment data.

[0100] Step S202: Evaluate the risk occurrence probability according to the risk vulnerability assessment features to obtain the risk occurrence probability assessment data; wherein, the risk occurrence probability assessment data represents the possibility of a disaster occurring in the target area.

[0101] Step S203: Extract the socio-economic vulnerability assessment features based on the social loss data, economic loss data, and social development level assessment data;

[0102] Step S204: Conduct a disaster resistance assessment based on the socio-economic vulnerability assessment features to obtain the target socio-economic vulnerability assessment data; wherein, the target socio-economic vulnerability assessment data characterizes the disaster resistance ability of the target area;

[0103] Step S205: Extract the disaster exposure assessment features based on the socio-economic exposure data, ecological environment exposure data, and infrastructure exposure data;

[0104] Step S206: Conduct a disaster impact range assessment based on the disaster exposure assessment features to obtain the target disaster exposure data; wherein, the target disaster exposure data characterizes the impact range of the disaster on the target area;

[0105] Step S207: Conduct a comprehensive disaster risk assessment based on the risk occurrence probability assessment data, target socio-economic vulnerability assessment data, and target disaster exposure data to obtain the preliminary risk assessment data for each sub-area to be evaluated.

[0106] In step S201 of some embodiments, the historical disaster data is used to describe the natural disaster situations that occurred in the target area in history. The historical disaster data includes, but is not limited to, at least one of the following data: historical disaster type data, historical disaster duration data, and historical disaster intensity data. Other data can also be selected according to the needs of those skilled in the art, as long as it can meet the needs of analyzing historical disaster situations. The geographical environment data can include, but is not limited to, at least one of the following: geo-geological data, hydro-meteorological data, population distribution data, land use type data, and urban built environment data. On this basis, a machine learning model can be used to extract the risk susceptibility assessment features. Specifically, first, preprocess various types of data to eliminate outliers and missing values, and then extract the features that have the most influence on susceptibility prediction through feature engineering methods to obtain the risk susceptibility assessment features. The feature engineering method can be the Random Forest (RF) algorithm, or other feature extraction methods that can be obtained by those skilled in the art.

[0107] In step S202 of some embodiments, the risk occurrence probability assessment data is used to describe the probability of a specific disaster occurring at a specific time and specific location. The risk vulnerability assessment features include, but are not limited to, the following features: hydrological vulnerability assessment features, rocky vulnerability assessment features, biological vulnerability assessment features, meteorological vulnerability assessment features, and topographical vulnerability assessment features. Among them, the hydrological vulnerability assessment features include, but are not limited to: surface runoff characteristics, drainage density characteristics, terrain moisture index characteristics, and water flow intensity index characteristics. The rocky vulnerability assessment features include, but are not limited to: soil texture characteristics and soil moisture characteristics. The biological vulnerability assessment features include, but are not limited to: land use type characteristics and normalized vegetation characteristics. The meteorological vulnerability assessment features include, but are not limited to: temperature characteristics, precipitation characteristics, and wind speed characteristics. The topographical vulnerability assessment features include, but are not limited to: elevation characteristics, slope characteristics, aspect characteristics, plane curvature characteristics, and profile curvature characteristics. The process of risk occurrence probability assessment can be implemented by the LightGBM model of gradient boosting trees or other machine learning models.

[0108] In some embodiments, steps S201 to S202 can also be implemented by a multi-dimensional disaster vulnerability prediction model. First, historical disaster data and geographical environment data are input into the multi-dimensional disaster vulnerability prediction model, and then the risk vulnerability assessment feature extraction module in the multi-dimensional disaster vulnerability prediction model extracts the risk vulnerability assessment features, and then the risk occurrence probability assessment module of the multi-dimensional disaster vulnerability prediction model performs a risk occurrence probability assessment on the risk vulnerability assessment features to obtain the risk occurrence probability assessment data.

[0109] In step S203 of some embodiments, the social loss data and economic loss data are used to describe the number of people affected by disasters and property losses in history, and the social development level data is used to describe the social and economic recovery ability after the disaster. Specifically, the social loss data includes, but is not limited to: dead population data and affected population data. The dead population data is used to describe the number of dead and missing people. The affected population data is used to describe the number of injured people, disturbed people, and homeless people. The economic loss data is used to describe the economic losses directly or indirectly related to the disaster.

[0110] In step S204 of some embodiments, the disaster resistance evaluation can be carried out by the fuzzy comprehensive evaluation method. Specifically, the fuzzy comprehensive evaluation method first constructs a fuzzy relation matrix according to the social and economic vulnerability evaluation characteristics, then performs fuzzy operations on the fuzzy relation matrix to automatically determine the weights of each social and economic vulnerability evaluation characteristic, and finally evaluates the social and economic vulnerability scores based on the social and economic vulnerability evaluation characteristics and the corresponding weights of the social and economic vulnerability evaluation characteristics to obtain the target social and economic vulnerability evaluation data. Among them, the social and economic vulnerability evaluation characteristics include but are not limited to: the characteristics of the deceased population, the characteristics of the affected population, and the characteristics of economic losses. By using the fuzzy comprehensive evaluation method for disaster resistance evaluation, the fuzziness in the evaluation process can be effectively handled, and the qualitative evaluation can be transformed into a quantitative score, so as to more accurately reflect the disaster resistance ability of the region.

[0111] In some embodiments of the present application, the weight of the deceased population characteristic is 0.443, the weight of the affected population characteristic is 0.335, and the weight of the economic loss characteristic is 0.222.

[0112] In some embodiments of the present application, the specific process of evaluating the social and economic vulnerability scores based on the social and economic vulnerability evaluation characteristics and the corresponding weights of the social and economic vulnerability evaluation characteristics to obtain the target social and economic vulnerability evaluation data can be expressed as:

[0113] ;

[0114] Among them, represents the target social and economic vulnerability evaluation data, represents the weight corresponding to the i-th social and economic vulnerability evaluation characteristic, represents the standardized characteristic value of the i-th social and economic vulnerability evaluation characteristic, represents the total number of social and economic vulnerability evaluation characteristics.

[0115] In step S205 of some embodiments, the disaster exposure evaluation characteristics can be extracted from the social and economic exposure data, the ecological environment exposure data, and the infrastructure exposure data, or can be extracted from other data according to the actual needs of those skilled in the art. In some embodiments of the present application, the disaster exposure evaluation characteristics include but are not limited to: the social and economic exposure characteristics, the ecological environment exposure characteristics, and the infrastructure exposure characteristics. The social and economic exposure characteristics include but are not limited to: the population distribution characteristics, the ecological environment exposure characteristics include but are not limited to: the climate exposure level characteristics, the sea level rise characteristics, the ecological reserve area characteristics, and the floodplain area characteristics, and the infrastructure exposure characteristics include but are not limited to: the building volume characteristics and the road network density characteristics.

[0116] In step S206 of some embodiments, the target disaster exposure data characterizes the impact range of the disaster on the target area. On this basis, the process of evaluating the disaster impact range can be realized through a multi-dimensional disaster exposure evaluation model. Specifically, first, a multi-dimensional disaster exposure evaluation model is constructed according to three dimensions: social economy, ecological environment, and infrastructure. Then, the disaster exposure evaluation characteristics are evaluated for disaster exposure through the multi-dimensional disaster exposure evaluation model to obtain the target disaster exposure data. It should be noted that for different regions or different disaster types, the contribution degrees of various disaster exposure evaluation characteristics to the evaluation of the disaster impact range are dynamically changing. Therefore, to provide a more flexible analysis framework, the present invention does not limit the specific weights when performing exposure evaluation. The specific implementation process of evaluating the disaster impact range based on the disaster exposure evaluation characteristics to obtain the target disaster exposure data can be expressed as follows:

[0117] ;

[0118] Among them, represents the target disaster exposure data, represents the standardized characteristic value of the i-th disaster exposure evaluation characteristic, represents the total number of disaster exposure evaluation characteristics.

[0119] In step S207 of some embodiments of the present application, the specific process of performing a comprehensive disaster risk assessment based on the risk occurrence probability assessment data, the target social economy vulnerability assessment data, and the target disaster exposure data to obtain the preliminary risk assessment data for each sub-region to be evaluated can be expressed as follows:

[0120] ;

[0121] Where represents the preliminary risk assessment data, represents the risk occurrence probability assessment data, represents the target social economy vulnerability assessment data, represents the target disaster exposure data. In some embodiments of the present application, the preliminary risk assessment data, the risk occurrence probability assessment data, the target social economy vulnerability assessment data, and the target disaster exposure data can be represented in the form of a matrix.

[0122] Steps S201 to S207 illustrated in the embodiments of the present application first obtain risk occurrence probability assessment data by evaluating the risk occurrence probability of target data, obtain target socio-economic vulnerability assessment data by conducting disaster resistance assessment, and obtain target disaster exposure data by conducting disaster impact scope assessment. Then, comprehensive disaster risk assessment is carried out according to the risk occurrence probability assessment data, target socio-economic vulnerability assessment data, and target disaster exposure data to obtain preliminary risk assessment data for each sub-region to be evaluated. Therefore, the resource allocation method based on cross-regional disaster risk assessment proposed in the present application can conduct comprehensive disaster risk assessment on the sub-regions to be evaluated in the target region in terms of the risk proneness degree, disaster resistance ability, and disaster impact scope, obtain more comprehensive disaster risk assessment data, and make the allocation of corresponding disaster resources more accurate.

[0123] Please refer to Figure 3 , in some embodiments, step S103 may include but is not limited to steps S301 to S305:

[0124] Step S301, obtain the location information of each sub-region to be evaluated to obtain sub-region location information;

[0125] Step S302, construct graph network nodes according to the sub-region location information corresponding to each sub-region to be evaluated and the preliminary risk assessment data; wherein, each graph network node is used to describe the risk of a sub-region to be evaluated suffering from a disaster.

[0126] Step S303, conduct graph network construction according to the graph network nodes, sub-region location information, and preliminary risk assessment data to obtain a target graph network; wherein, the graph network edges of the target graph network represent the spatial adjacency relationship between the sub-regions to be evaluated, and the edge weight data of the target graph network represents the difference in preliminary risk assessment data between the sub-regions to be evaluated.

[0127] Step S304, conduct first-level regional division processing according to the graph network edges, edge weight data, and sub-regions to be evaluated to obtain target first-level regions;

[0128] Step S305, conduct regional risk feature mining on each target first-level region according to the target first-level regions, preliminary risk assessment data, and sub-region location information to obtain the target risk features of each target region.

[0129] In step S303 of some embodiments, the graph network edges of the target graph network are used to connect two graph network nodes that are spatially adjacent, so it can represent the spatial adjacency relationship between the sub-regions to be evaluated. The edge weight data of the target graph network represents the difference in the preliminary risk assessment data between the sub-regions to be evaluated. Specifically, the larger the edge weight data, the more similar the likelihood and disaster-affected situations of the two sub-regions to be evaluated suffering from the same disaster; the smaller the edge weight data, the greater the difference in the likelihood and disaster-affected situations of the two sub-regions to be evaluated suffering from the same disaster.

[0130] In step S304 of some embodiments, the process of performing the first-level regional division processing according to the graph network edges, edge weight data, and sub-regions to be evaluated can be implemented by the Louvain algorithm.

[0131] Steps S301 to S305 illustrated in the embodiments of the present application obtain the sub-region position information by acquiring the position information of each sub-region to be evaluated, construct graph network nodes according to the sub-region position information corresponding to each sub-region to be evaluated and the preliminary risk assessment data, perform graph network construction according to the graph network nodes, sub-region position information, and preliminary risk assessment data to obtain the target graph network; wherein, the graph network edges of the target graph network represent the spatial adjacency relationship between the sub-regions to be evaluated, and the edge weight data of the target graph network represents the difference in the preliminary risk assessment data between the sub-regions to be evaluated. Finally, perform the first-level regional division processing according to the graph network edges, edge weight data, and sub-regions to be evaluated to obtain the target first-level region, and perform regional risk feature mining on each target first-level region according to the target first-level region, preliminary risk assessment data, and sub-region position information to obtain the target risk features of each target region. Therefore, the resource allocation method based on cross-regional disaster risk assessment proposed in the present application performs the first-level regional division processing on the sub-regions to be evaluated according to the risk differences between the sub-regions to be evaluated, identifies and divides the groups of sub-regions to be evaluated with similar risk characteristics, and performs risk analysis according to the groups of sub-regions to be evaluated after regional division, overcoming the dependence on static risk regional division in previous studies, providing a more dynamic and flexible regional division method, enabling the risk assessment data to more accurately reflect the actual disaster risk situation, and providing a more targeted allocation plan for disaster response resources.

[0132] Please refer to Figure 4 , in some embodiments, step S303 may include but is not limited to steps S401 to S406:

[0133] Step S401, select a first target node and at least one first adjacent node from the graph network nodes according to the sub-region position information; wherein, the first adjacent node and the first target node are adjacent in terms of spatial relationship;

[0134] Step S402: Obtain the preliminary risk assessment data corresponding to the first target node to obtain the target risk assessment data;

[0135] Step S403: Obtain the preliminary risk assessment data corresponding to the first adjacent node to obtain the adjacent risk assessment data;

[0136] Step S404: According to the target risk assessment data and the adjacent risk assessment data, perform sub-region risk relevance measurement on each sub-region to be evaluated to obtain edge weight data;

[0137] Step S405: Construct a graph network edge according to the first target node, the first adjacent node and the edge weight data;

[0138] Step S406: Construct a target graph network according to the graph network nodes and the graph network edges.

[0139] In step S404 of some embodiments, the specific process of performing sub-region risk relevance measurement on each sub-region to be evaluated according to the target risk assessment data and the adjacent risk assessment data to obtain edge weight data can be expressed as follows:

[0140] ;

[0141] Among them, represents the edge weight data between the i-th first target node and the j-th first adjacent node, represents the target risk assessment data of the i-th first target node, represents the adjacent risk assessment data of the j-th first adjacent node, The value of is 0.001, which is used to avoid the denominator being zero, can also be other constants.

[0142] Steps S401 to S406 illustrated in the embodiments of the present application first perform risk relevance measurement on adjacent sub-regions to be evaluated to obtain edge weight data, and then integrate all graph network nodes and graph network edges according to the sub-region position information and the edge weight data to construct a complete target graph network, which integrates the spatial information and risk assessment data of the sub-regions to be evaluated in the form of a target graph network, and can comprehensively reflect the risk relationship between the sub-regions to be evaluated.

[0143] Please refer to Figure 5 , in some embodiments, step S304 may include but is not limited to steps S501 to S505:

[0144] Step S501: Select a second target node and at least one second adjacent node from the graph network nodes; among them, the second adjacent node and the second target node are adjacent in spatial relationship;

[0145] Step S502: Perform initial area division on the graph network nodes according to a preset first-level area division rule to obtain at least one initial first-level area;

[0146] Step S503: Obtain the initial first-level area where each second adjacent node is located to obtain adjacent first-level areas;

[0147] Step S504: Perform first-level area re-division processing according to the second target node, each adjacent first-level area, the graph network edges, and the edge weight data to obtain updated first-level areas;

[0148] Step S505: Update the initial first-level areas according to the updated first-level areas to obtain target first-level areas.

[0149] In step S502 of some embodiments, the preset first-level area division rule may be: regarding each graph network node as an initial first-level area. The preset first-level area division rule can also be selected according to the actual needs of those skilled in the art.

[0150] In step S504 of some embodiments, by performing first-level area re-division processing according to the second target node, each adjacent first-level area, the graph network edges, and the edge weight data, updated first-level areas can be obtained. Specifically, first, calculate the modularity gain according to the second target node, each adjacent first-level area, the second adjacent nodes within each adjacent first-level area, the graph network edges, and the edge weight data to obtain candidate modularity gain data; among them, the candidate modularity gain data characterizes the connection tightness between the second target node and each adjacent first-level area when the second target node moves into each adjacent first-level area. Then, compare multiple candidate modularity gain data to obtain modularity gain comparison data, and select target modularity gain data from the candidate modularity gain data according to the modularity gain comparison data; among them, the connection degree between the second target node corresponding to the target modularity gain data and the adjacent first-level area corresponding to the target modularity gain data is the tightest. Finally, select the adjacent first-level area corresponding to the target modularity gain data as the target adjacent first-level area, and move the second target node into the target adjacent first-level area to obtain updated first-level areas. Among them, the specific process of calculating the candidate modularity gain data according to the second target node, each adjacent first-level area, the second adjacent nodes within each adjacent first-level area, the graph network edges, and the edge weight data can be expressed as:

[0151] ;

[0152] Among them, represents the candidate modularity gain data, represents the sum of the edge weight data of the graph network edges inside the adjacent first-level area, It represents the sum of the edge weight data between the second target node i and the second adjacent nodes in the adjacent first-level region. It represents the sum of the edge weight data of all the graph network edges in the graph network. It represents the sum of the degrees of all the graph network nodes in the adjacent first-level region. It represents the degree of the second target node i.

[0153] In step S504 of some embodiments, the process of updating the initial first-level region according to the updated first-level region is an iterative update process. Each time the initial first-level region is updated, it is necessary to re-select the adjacent first-level region from the updated first-level region according to the second target node, and calculate the candidate modularity gain data between each second target node and the selected adjacent first-level region from the updated first-level region to obtain the updated modularity gain data, and then update the updated first-level region again according to the updated modularity gain data. It should be noted that after each iterative update, it is necessary to calculate the modularity data of the graph network. When the modularity data of the graph network no longer increases, the iterative update of the updated first-level region is stopped, and the updated first-level region obtained by the last update is used as the target first-level region.

[0154] Steps S501 to S505 illustrated in the embodiments of the present application first select a second target node and at least one second adjacent node from the graph network nodes, and obtain the adjacent first-level region according to the initial first-level region where each second adjacent node is located. Then, based on the second target node, each adjacent first-level region, the graph network edges, and the edge weight data, the first-level region is re-divided to obtain the updated first-level region, and the initial first-level region is iteratively updated according to the updated first-level region to obtain the target first-level region. Therefore, the resource allocation method based on cross-regional disaster risk assessment proposed in the present application can, by utilizing the risk differences between the sub-regions to be evaluated, perform the first-level region division processing on the sub-regions to be evaluated, and dynamically adjust and optimize the region division in an iterative manner, taking into account both the geographical proximity and the similarity of risk characteristics of the sub-regions to be evaluated, so as to accurately reflect the actual risk situation of the target first-level region and improve the accuracy of risk assessment.

[0155] Please refer to Figure 6 , in some embodiments, step S305 may include but is not limited to steps S601 to S606:

[0156] Step S601: Obtain the graph network nodes of each target first-level region to obtain candidate graph network nodes;

[0157] Step S602: Obtain the preliminary risk assessment data according to the candidate graph network nodes to obtain the first-level region risk data to be evaluated for each target first-level region;

[0158] Step S603: Perform first-level area risk assessment based on the first-level area risk data to be evaluated for each target first-level area, and obtain first-level area risk assessment data; wherein, the first-level area risk assessment data characterizes the risk of the target first-level area suffering from disasters.

[0159] Step S604: Determine the location information of the target first-level area based on the target first-level area and sub-area location information, and obtain first-level area location information.

[0160] Step S605: Perform risk correlation measurement based on the target first-level area, first-level area location information, and first-level area risk assessment data, and obtain first-level area risk correlation data; wherein, each first-level area risk correlation data corresponds to a target first-level area, and the first-level area risk correlation data characterizes the risk difference between the target first-level area and its surrounding first-level areas.

[0161] Step S606: Perform regional risk feature mining based on the first-level area risk assessment data and first-level area risk correlation data corresponding to each target first-level area, and obtain the target risk features of each target area.

[0162] In step S602 of some embodiments, for each target first-level area, each first-level area risk data to be evaluated is the preliminary risk assessment data corresponding to a graph network node in the target first-level area.

[0163] In step S603 of some embodiments, first-level area risk assessment can be performed based on multiple first-level area risk data to be evaluated to obtain first-level area risk assessment data. Specifically, for each first-level area, the average value of the preliminary risk assessment data corresponding to the graph network nodes in the target first-level area is taken to obtain the first-level area risk assessment data.

[0164] In step S605 of some embodiments, first-level area risk correlation measurement can be performed based on the target first-level area, first-level area location information, and first-level area risk assessment data to obtain first-level area risk correlation data. The first-level area risk correlation data can be represented by the Local Geary’s C. Specifically, the process of performing first-level area risk correlation measurement based on the target first-level area, first-level area location information, and first-level area risk assessment data to obtain first-level area risk correlation data can be expressed as follows:

[0165] ;

[0166] Wherein, represents the first-level area risk correlation data of the i-th target first-level area, represents the weight of the spatial adjacency relationship matrix calculated from the first-level area location information, The first-level regional risk assessment data representing the i-th target first-level region The first-level regional risk assessment data representing the j-th target first-level region.

[0167] For steps S601 to S606 illustrated in the embodiments of the present application, first, the first-level regional risk assessment data and the first-level regional risk correlation data of each first-level regional risk to-be-assessed data are calculated, and then, based on the first-level regional risk assessment data and the first-level regional risk correlation data corresponding to each target first-level region, regional risk feature mining is performed to obtain the target risk features of each target region, which can understand the disaster risks of the first-level regions from both the risk level within the target first-level regions and the risk correlation and differences between the target first-level regions, so as to more comprehensively evaluate the disaster risk level of the target first-level regions and improve the accuracy of risk assessment.

[0168] Please refer to Figure 7 , in some embodiments, step S104 may include but is not limited to steps S701 to S705:

[0169] Step S701, select a first region and a second region from at least two target regions; wherein, the first region and the second region are different;

[0170] Step S702, select at least one selected region from the target first-level regions of the first region;

[0171] Step S703, select at least one candidate region from the target first-level regions of the second region;

[0172] Step S704, perform feature similarity evaluation according to each selected region and candidate region to obtain target feature similarity evaluation data;

[0173] Step S705, perform similarity measurement between target regions according to the target feature similarity evaluation data of the selected regions to obtain similarity measurement data between target regions.

[0174] In step S701 of some embodiments, the target regions may be regions at the same spatial scale or regions at different spatial scales. The spatial scale may include but is not limited to at least one of the following: urban scale, regional scale, national scale, and global scale. For at least two target regions, the first region may be selected in sequence between all target regions, and a target region different from the first region may be selected as the second region, and then similarity measurement between target regions is performed between the first region and the second region to obtain similarity measurement data between target regions for any two target regions.

[0175] In step S705 of some embodiments, the similarity metric between target regions can be obtained according to the target feature similarity evaluation data corresponding to the selected region. Specifically, for each first region, the target feature similarity evaluation data corresponding to all the target first-level regions in the first region is obtained, and the average value of all the target feature similarity evaluation data is taken to obtain the similarity metric data between the first region and the second region.

[0176] Steps S701 to S705 illustrated in the embodiments of the present application select a first region and a second region from at least two target regions at multiple spatial scales, select at least one selected region from the target first-level regions of the first region, and select at least one candidate region from the target first-level regions of the second region. Then, the feature similarity of each selected region and each candidate region is evaluated to obtain the target feature similarity evaluation data. Finally, the similarity metric between the target regions is obtained according to the target feature similarity evaluation data, which can take into account the risk characteristics of regions at different geographical and administrative levels in the face of disasters, realize cross-regional and cross-scale risk assessment, help to build a more comprehensive disaster response strategy when disasters occur in multiple regions, and thus realize a more effective allocation of disaster response resources.

[0177] Please refer to Figure 8 , in some embodiments, step S704 may include but is not limited to steps S801 to S805:

[0178] Step S801, obtain the target risk characteristics corresponding to each selected region to obtain the first feature similarity to-be-evaluated features;

[0179] Step S802, obtain the target risk characteristics corresponding to each candidate region to obtain the second feature similarity to-be-evaluated features;

[0180] Step S803, perform a risk feature distance metric according to the first feature similarity to-be-evaluated features and each second feature similarity to-be-evaluated feature to obtain the risk feature distance metric data;

[0181] Step S804, perform a risk feature similarity evaluation according to the distance metric data to obtain the initial feature similarity evaluation data;

[0182] Step S805, select the target feature similarity evaluation data from at least one initial feature similarity evaluation data corresponding to the selected region; wherein, the risk feature similarity degree between the selected region corresponding to the target feature similarity evaluation data and the second region is the largest.

[0183] In step S803 of some embodiments, risk feature distance metrics can be obtained by performing risk feature distance measurement on the to-be-evaluated feature of the first feature similarity and each to-be-evaluated feature of the second feature similarity. Specifically, Mahalanobis Distance measurement method can be adopted for risk feature distance measurement, and the Mahalanobis distance measurement data can be used as the risk feature distance measurement data.

[0184] In step S804 of some embodiments, in the case of using Mahalanobis Distance measurement method for risk feature distance measurement, the specific process of performing risk feature similarity evaluation based on the distance measurement data to obtain the initial feature similarity evaluation data can be expressed as:

[0185] Initial feature similarity evaluation data = 1 / (1 + Mahalanobis distance measurement data).

[0186] Please refer to Figure 9 , in some embodiments, step S105 may include but is not limited to steps S901 to S903:

[0187] Step S901, perform resource allocation similarity evaluation on at least two target regions according to the target region similarity measurement data to obtain target region resource allocation similarity data;

[0188] Step S902, perform target region risk assessment on the target risk features corresponding to each target region to obtain target region risk assessment data;

[0189] Step S903, perform resource allocation for the target region according to the target region risk assessment data and the target region resource allocation similarity data.

[0190] Steps S901 to S903 illustrated in the embodiments of the present application, by performing resource allocation similarity evaluation on at least two target regions to obtain target region resource allocation similarity data, then performing target region risk assessment on the target risk features corresponding to each target region to obtain target region risk assessment data, and performing resource allocation for the target region according to the target region risk assessment data and the target region resource allocation similarity data. Therefore, the resource allocation method based on cross-region disaster risk assessment provided by the present application can identify regions that may have similarities in resource requirements, and allocate corresponding resources to regions with similar resource requirements according to the disaster risk status of the regions, taking into account both the risk status of the regions and the similarities between regions, thus realizing reasonable and efficient allocation of resources.

[0191] Please refer to Figure 10, an embodiment of the present application further provides a resource allocation device based on cross - regional disaster risk assessment, which can implement the above - mentioned resource allocation method based on cross - regional disaster risk assessment. The device includes:

[0192] A data acquisition module 1001, configured to acquire target data of at least two target regions; wherein, the target data is disaster - related data of the target regions, and each target region includes at least two sub - regions to be evaluated;

[0193] A preliminary risk assessment module 1002, configured to perform disaster risk assessment on each sub - region to be evaluated according to the target data, and obtain preliminary risk assessment data of each sub - region to be evaluated;

[0194] A risk feature mining module 1003, configured to perform risk feature mining on each target region according to the preliminary risk assessment data, and obtain target risk features of each target region;

[0195] A similarity measurement module 1004 between target regions, configured to perform similarity assessment between target regions on the target risk features of at least two target regions, and obtain similarity measurement data between target regions; wherein, each similarity measurement data between target regions represents the inter - regional risk similarity between any two target regions;

[0196] A resource allocation module 1005, configured to perform resource allocation on each target region according to the similarity measurement data between target regions.

[0197] The specific implementation manner of the resource allocation device based on cross - regional disaster risk assessment is basically the same as the specific embodiment of the above - mentioned resource allocation method based on cross - regional disaster risk assessment, and will not be elaborated here.

[0198] An embodiment of the present application further provides an electronic device. The electronic device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the above - mentioned resource allocation method based on cross - regional disaster risk assessment. The electronic device can be any intelligent terminal including a tablet computer, an in - vehicle computer, etc.

[0199] Please refer to Figure 11 , Figure 11 schematically shows the hardware structure of an electronic device in another embodiment. The electronic device includes:

[0200] A processor 1101, which can be implemented in ways such as a general - purpose CPU (Central Processing Unit, central processor), a microprocessor, an application - specific integrated circuit (ASIC), or one or more integrated circuits, and is configured to execute relevant programs to implement the technical solutions provided by the embodiments of the present application;

[0201] The memory 1102 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM), etc. The memory 1102 can store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 1102 and are called by the processor 1101 to execute the resource allocation method based on cross-regional disaster risk assessment in the embodiments of this application;

[0202] The input / output interface 1103 is used to implement information input and output;

[0203] The communication interface 1104 is used to implement communication interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or through wireless means (such as mobile network, WIFI, Bluetooth, etc.);

[0204] The bus 1105 transmits information between the various components of the device (such as the processor 1101, the memory 1102, the input / output interface 1103, and the communication interface 1104);

[0205] Among them, the processor 1101, the memory 1102, the input / output interface 1103, and the communication interface 1104 achieve communication connections with each other inside the device through the bus 1105.

[0206] The embodiments of this application also provide a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the above-mentioned resource allocation method based on cross-regional disaster risk assessment.

[0207] As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs and non-transitory computer-executable programs. In addition, the memory can include high-speed random access memory, and can also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory optionally includes a memory remotely set relative to the processor, and these remote memories can be connected to the processor through a network. Examples of the above-mentioned network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0208] The resource allocation method and device based on cross - regional disaster risk assessment provided by the embodiments of the present application obtain the target data of at least two target regions, and conduct disaster risk assessment on each sub - region to be evaluated according to the target data to obtain the preliminary risk assessment data of each sub - region to be evaluated. Then, based on the preliminary risk assessment data, risk feature mining is carried out on each target region to obtain the target risk features of each target region, and similarity assessment between target regions is conducted on the target risk features of at least two target regions to obtain the similarity metric data between target regions. Finally, resource allocation is carried out on each target region according to the similarity metric data between target regions. Therefore, the resource allocation method and device based on cross - regional disaster risk assessment proposed in the present application measure the risk similarity between target regions according to the spatial scale, and allocate resources to each target region based on the inter - regional risk similarity metric data, improving the accuracy of the risk assessment method for natural disaster risk assessment of cross - regional and cross - scale disasters. Moreover, by using the metric data of inter - regional risk similarity to guide resource allocation, the rationality and accuracy of disaster response resource allocation can be improved, enabling disaster response resources to be utilized more efficiently.

[0209] The embodiments described in the embodiments of the present application are for more clearly explaining the technical solutions of the embodiments of the present application, and do not constitute a limitation to the technical solutions provided by the embodiments of the present application. Those skilled in the art know that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems.

[0210] Those skilled in the art can understand that the technical solutions shown in the figures do not constitute a limitation to the embodiments of the present application, and may include more or fewer steps than those shown, or combine some steps, or different steps.

[0211] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0212] Those of ordinary skill in the art can understand that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices can be implemented as software, firmware, hardware and their appropriate combinations.

[0213] In the description of the present application and the above-mentioned drawings, terms such as "first" and "second" are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0214] It should be understood that in the present application, "at least one (item)" means one or more, and "a plurality" means two or more. "At least one (one) of the following" or a similar expression means any combination of these items, including any combination of single items (ones) or plural items (ones). For example, at least one (one) of a, b or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0215] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the above-mentioned division of units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0216] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present application. The aforementioned storage medium includes: various media that can store programs such as USB flash drives, mobile hard disks, read-only memory (ROM for short), random access memory (RAM for short), magnetic disks or optical discs.

[0217] The preferred embodiments of the embodiments of the present application have been described above with reference to the accompanying drawings, which does not limit the scope of the rights of the embodiments of the present application. Any modifications, equivalent replacements, and improvements made by those skilled in the art without departing from the scope and essence of the embodiments of the present application shall fall within the scope of the rights of the embodiments of the present application.

Claims

1. A resource allocation method based on cross - regional disaster risk assessment, characterized in that, The method includes: Obtaining target data of at least two target regions; wherein, the target data is disaster-related data of the target regions, and each target region includes at least two sub-regions to be evaluated; Performing disaster risk assessment on each sub-region to be evaluated according to each target data, to obtain preliminary risk assessment data of each sub-region to be evaluated; Mining risk characteristics of each target region according to the preliminary risk assessment data, to obtain target risk characteristics of each target region; Performing similarity assessment between target regions on the target risk characteristics of at least two target regions, to obtain similarity measurement data between target regions; wherein, each similarity measurement data between target regions represents the inter-regional risk similarity between any two target regions; Performing resource allocation on each target region according to the similarity measurement data between target regions; The mining risk characteristics of each target region according to the preliminary risk assessment data to obtain target risk characteristics of each target region includes: Obtaining position information of each sub-region to be evaluated, to obtain sub-region position information; Constructing graph network nodes according to the sub-region position information corresponding to each sub-region to be evaluated and the preliminary risk assessment data; wherein, each graph network node is used to describe the risk of a sub-region to be evaluated suffering from a disaster; Constructing a target graph network according to the graph network nodes, the sub-region position information and the preliminary risk assessment data; wherein, the graph network edges of the target graph network represent the spatial adjacency relationship between the sub-regions to be evaluated, and the edge weight data of the target graph network represents the difference in preliminary risk assessment data between the sub-regions to be evaluated; Performing first-level region division processing according to the graph network edges, the edge weight data and the sub-regions to be evaluated, to obtain target first-level regions; Mining regional risk characteristics of each target first-level region according to the target first-level regions, the preliminary risk assessment data and the sub-region position information, to obtain target risk characteristics of each target region; The performing first-level region division processing according to the graph network edges, the edge weight data and the sub-regions to be evaluated to obtain target first-level regions includes: Selecting a second target node and at least one second adjacent node from the graph network nodes; wherein, the second adjacent node and the second target node are adjacent in spatial relationship; Performing initial region division on the graph network nodes according to a preset first-level region division rule, to obtain at least one initial first-level region; Obtaining the initial first-level region where each second adjacent node is located, to obtain adjacent first-level regions; Performing first-level region re-division processing according to the second target node, each adjacent first-level region, the graph network edges and the edge weight data, to obtain updated first-level regions; Updating the initial first-level regions according to the updated first-level regions, to obtain the target first-level regions.

2. The method according to claim 1, wherein Constructing a graph network based on the graph network nodes, the sub-region location information, and the preliminary risk assessment data to obtain a target graph network, including: Selecting a first target node and at least one first adjacent node from the graph network nodes according to the sub-region location information; wherein, the first adjacent node and the first target node are adjacent in spatial relationship; Obtaining the preliminary risk assessment data corresponding to the first target node to obtain target risk assessment data; Obtaining the preliminary risk assessment data corresponding to the first adjacent node to obtain adjacent risk assessment data; Performing sub-region risk correlation measurement on each to-be-evaluated sub-region according to the target risk assessment data and the adjacent risk assessment data to obtain the edge weight data; Constructing the graph network edge according to the first target node, the first adjacent node, and the edge weight data; Constructing a target graph network according to the graph network nodes and the graph network edge.

3. The method according to claim 1, wherein Mining the regional risk characteristics of each target first-level region according to the target first-level region, the preliminary risk assessment data, and the sub-region location information to obtain the target risk characteristics of each target region, including: Obtaining the graph network nodes of each target first-level region to obtain candidate graph network nodes; Obtaining the preliminary risk assessment data according to the candidate graph network nodes to obtain the first-level region risk to-be-evaluated data of each target first-level region; Performing first-level region risk assessment according to the first-level region risk to-be-evaluated data of each target first-level region to obtain first-level region risk assessment data; wherein, the first-level region risk assessment data characterizes the risk of the target first-level region suffering from disasters; Determining the location information of the target first-level region according to the target first-level region and the sub-region location information to obtain first-level region location information; Performing risk correlation measurement according to the target first-level region, the first-level region location information, and the first-level region risk assessment data to obtain first-level region risk correlation data; wherein, each first-level region risk correlation data corresponds to a target first-level region, and the first-level region risk correlation data characterizes the risk difference between the target first-level region and its surrounding first-level regions; Mining the regional risk characteristics according to the first-level region risk assessment data and the first-level region risk correlation data corresponding to each target first-level region to obtain the target risk characteristics of each target region.

4. The method according to claim 1, wherein Performing similarity assessment between target regions on the target risk characteristics of at least two target regions to obtain similarity measurement data between target regions, including: Selecting a first region and a second region from at least two target regions; wherein, the first region and the second region are different; Selecting at least one selected region from the target first-level regions of the first region; Selecting at least one candidate region from the target first-level regions of the second region; Performing feature similarity assessment according to each selected region and the candidate region to obtain target feature similarity assessment data; Perform similarity measurement between target regions based on the target feature similarity evaluation data of the selected regions to obtain similarity measurement data between target regions.

5. The method according to claim 4, characterized in that The obtaining of the target feature similarity evaluation data by performing feature similarity evaluation according to each of the selected regions and the candidate regions includes: Obtain the target risk features corresponding to each of the selected regions to obtain the first feature similarity to-be-evaluated features; Obtain the target risk features corresponding to each of the candidate regions to obtain the second feature similarity to-be-evaluated features; Perform risk feature distance measurement according to the first feature similarity to-be-evaluated features and each of the second feature similarity to-be-evaluated features to obtain risk feature distance measurement data; Perform risk feature similarity evaluation according to the distance measurement data to obtain initial feature similarity evaluation data; Select the target feature similarity evaluation data from at least one of the initial feature similarity evaluation data corresponding to the selected regions; wherein, the risk feature similarity degree between the selected region corresponding to the target feature similarity evaluation data and the second region is the largest.

6. The method according to claim 1, wherein The target data includes: historical disaster data, geographical environment data, social loss data, economic loss data, social development level evaluation data, social and economic exposure data, ecological environment exposure data, and infrastructure exposure data. The performing of disaster risk assessment on each of the sub-regions to be evaluated according to each of the target data includes: Extract risk vulnerability evaluation features according to the historical disaster data and the geographical environment data; Perform risk occurrence probability assessment according to the risk vulnerability evaluation features to obtain risk occurrence probability assessment data; wherein, the risk occurrence probability assessment data represents the possibility of a disaster occurring in the target region; Extract social and economic vulnerability evaluation features according to the social loss data, the economic loss data, and the social development level evaluation data; Perform disaster resistance evaluation according to the social and economic vulnerability evaluation features to obtain target social and economic vulnerability evaluation data; wherein, the target social and economic vulnerability evaluation data represents the disaster resistance ability of the target region; Extract disaster exposure evaluation features according to the social and economic exposure data, the ecological environment exposure data, and the infrastructure exposure data; Perform disaster impact range evaluation according to the disaster exposure evaluation features to obtain target disaster exposure data; wherein, the target disaster exposure data represents the impact range of the disaster on the target region; Perform comprehensive disaster risk assessment according to the risk occurrence probability assessment data, the target social and economic vulnerability evaluation data, and the target disaster exposure data to obtain the preliminary risk assessment data of each of the sub-regions to be evaluated.

7. The method according to claim 1, wherein The performing of resource allocation for each of the target regions according to the similarity measurement data between target regions includes: Perform resource allocation similarity evaluation on at least two target regions according to the similarity measurement data between target regions to obtain target region resource allocation similarity data; Perform target area risk assessment on the target risk characteristics corresponding to each of the said target areas to obtain target area risk assessment data; Allocate resources to the target areas according to the target area risk assessment data and the target area resource allocation similarity data.

8. A resource allocation device based on cross-regional disaster risk assessment, characterized in that The device includes: A data acquisition module, configured to acquire target data of at least two target areas; wherein, the target data is data related to disasters in the target areas, and each of the target areas includes at least two sub-areas to be evaluated; A preliminary risk assessment module, configured to perform disaster risk assessment on each of the sub-areas to be evaluated according to the target data to obtain preliminary risk assessment data of each sub-areas to be evaluated; A risk characteristic mining module, configured to perform risk characteristic mining on each of the target areas according to the preliminary risk assessment data to obtain the target risk characteristics of each of the target areas; The performing risk characteristic mining on each of the target areas according to the preliminary risk assessment data to obtain the target risk characteristics of each of the target areas includes: Obtain the location information of each of the sub-areas to be evaluated to obtain sub-area location information; Construct graph network nodes according to the sub-area location information corresponding to each of the sub-areas to be evaluated and the preliminary risk assessment data; wherein, each of the graph network nodes is used to describe the risk of a sub-area to be evaluated suffering from a disaster; Construct a target graph network according to the graph network nodes, the sub-area location information and the preliminary risk assessment data; wherein, the graph network edges of the target graph network represent the spatial adjacency relationship between the sub-areas to be evaluated, and the edge weight data of the target graph network represents the difference in preliminary risk assessment data between the sub-areas to be evaluated; Perform first-level area division processing according to the graph network edges, the edge weight data and the sub-areas to be evaluated to obtain target first-level areas; Perform area risk characteristic mining on each of the target first-level areas according to the target first-level areas, the preliminary risk assessment data and the sub-area location information to obtain the target risk characteristics of each of the target areas; The performing first-level area division processing according to the graph network edges, the edge weight data and the sub-areas to be evaluated to obtain target first-level areas includes: Select a second target node and at least one second adjacent node from the graph network nodes; wherein, the second adjacent node and the second target node are adjacent in spatial relationship; Perform initial area division on the graph network nodes according to a preset first-level area division rule to obtain at least one initial first-level area; Obtain the initial first-level area where each of the second adjacent nodes is located to obtain adjacent first-level areas; Perform first-level area re-division processing according to the second target node, each of the adjacent first-level areas, the graph network edges and the edge weight data to obtain updated first-level areas; Update the initial first-level areas according to the updated first-level areas to obtain the target first-level areas; The target region similarity measurement module is used to perform target region similarity evaluation on the target risk features of at least two of the target regions to obtain target region similarity measurement data; wherein, each of the target region similarity measurement data represents the inter-region risk similarity between any two of the target regions. The resource allocation module is used to perform resource allocation on each of the target regions according to the target region similarity measurement data.

Images