Resource allocation method and device based on cross-regional disaster risk assessment

Abstract

The embodiment of the invention provides a resource allocation method and device based on cross-regional disaster risk assessment, and belongs to the field of disaster response resource allocation. The method comprises the following steps: firstly, acquiring target data of at least two target areas, and performing disaster risk assessment on each to-be-assessed sub-area according to the target data to obtain preliminary risk assessment data of each to-be-assessed sub-area; then, risk feature mining is carried out on each target area according to the preliminary risk assessment data, target risk features of each target area are obtained, similarity assessment between the target areas is carried out on all the target risk features of the at least two target areas, and similarity measurement data between the target areas are obtained; and finally, carrying out resource allocation on each target region according to the similarity measurement data between the target regions. According to the embodiment of the invention, the risk assessment accuracy of cross-regional and cross-scale disasters can be improved, so that the rationality of resource allocation is improved, and the utilization efficiency of disaster-responding resources is improved.

Description

Technical Field

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

[0002] At present, resource allocation strategies in disaster risk management are usually based on the assessment of disaster risks in various regions. However, existing disaster risk assessment methods are limited to dividing risk areas based on administrative divisions. This single risk area division scale fails to fully consider the inherent connection between risk characteristics between regions at different spatial scales, making it difficult for existing risk assessment methods to conduct effective risk assessment when facing cross-regional and cross-scale natural disasters. Inaccurate risk assessments further lead to errors in resource allocation strategies, making it impossible for disaster response resources to be reasonably allocated to the areas that need them most.

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

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

[0005] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present application proposes a resource allocation method based on cross-regional disaster risk assessment, the method comprising: Acquire target data of at least two target areas; wherein the target data is disaster-related data of the target areas, and each of the target areas includes at least two sub-areas to be evaluated; Conduct disaster risk assessment on each of the sub-regions to be assessed according to each of the target data to obtain preliminary risk assessment data for each of the sub-regions to be assessed; Perform risk feature mining on each of the target areas according to the preliminary risk assessment data to obtain target risk features of each of the target areas; Performing inter-target region similarity evaluation on the target risk characteristics of at least two of the target regions to obtain inter-target region similarity measurement data; wherein each of the inter-target region similarity measurement data represents the inter-region risk similarity between any two of the target regions; Resources are allocated to each of the target areas according to the similarity measurement data between the target areas.

[0006] In some embodiments, the step of mining risk characteristics of each target area according to the preliminary risk assessment data to obtain target risk characteristics of each target area includes: Acquire the location information of each sub-region to be evaluated to obtain the sub-region location information; Constructing a graph network node according to the sub-region location information corresponding to each sub-region to be assessed and the preliminary risk assessment data; wherein each graph network node is used to describe the risk of a sub-region to be assessed suffering from a disaster; A graph network is constructed according to the graph network nodes, the sub-region location information and the 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 assessed, and the edge weight data of the target graph network represent the difference in preliminary risk assessment data between the sub-regions to be assessed; Performing a first-level region division process according to the graph network edge, the edge weight data and the sub-region to be evaluated to obtain a target first-level region; Regional risk characteristics of each of the target first-level regions are mined according to the target first-level regions, the preliminary risk assessment data and the sub-region location information to obtain target risk characteristics of each of the target regions.

[0007] In some embodiments, constructing a graph network according to the graph network nodes, the sub-region location information and the preliminary risk assessment data to obtain a target graph network includes: Selecting 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 spatial relationship; Acquire the preliminary risk assessment data corresponding to the first target node to obtain target risk assessment data; Acquire the preliminary risk assessment data corresponding to the first adjacent node to obtain adjacent risk assessment data; According to the target risk assessment data and the adjacent risk assessment data, a sub-region risk correlation measurement is performed on each of the sub-regions to be assessed 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; A target graph network is constructed according to the graph network nodes and the graph network edges.

[0008] In some embodiments, performing a primary region division process according to the graph network edge, the edge weight data, and the sub-region to be evaluated to obtain a target primary region 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; Acquire an initial primary region where each of the second adjacent nodes is located, to obtain an adjacent primary region; Re-dividing the first-level region according to the second target node, each of the adjacent first-level regions, the graph network edge and the edge weight data to obtain an updated first-level region; The initial first-level region is updated according to the updated first-level region to obtain the target first-level region.

[0009] In some embodiments, the performing regional risk feature mining on each of the target primary regions according to the target primary region, the preliminary risk assessment data and the sub-region location information to obtain the target risk feature of each of the target regions includes: Obtain the graph network node of each target primary area to obtain a candidate graph network node; Acquire the preliminary risk assessment data according to the candidate graph network nodes to obtain the first-level regional risk data to be assessed for each of the target first-level regions; Performing a first-level regional risk assessment based on the first-level regional risk to be assessed data of each of the target first-level regions to obtain first-level regional risk assessment data; wherein the first-level regional risk assessment data represents the risk of the target first-level region suffering from disasters; Determine the location information of the target first-level area according to the target first-level area and the sub-area location information to obtain the first-level area location information; A risk correlation degree measurement is performed according to the target first-level region, the location information of the first-level region and the risk assessment data of the first-level region to obtain first-level region risk correlation degree data; wherein each first-level region risk correlation degree data corresponds to one target first-level region, and the first-level region risk correlation degree data represents the risk difference between the target first-level region and its surrounding first-level regions; Regional risk feature mining is performed based on the first-level regional risk assessment data and the first-level regional risk association data corresponding to each of the target first-level regions to obtain target risk features of each target region.

[0010] In some embodiments, the performing target area similarity evaluation on the target risk characteristics of at least two target areas to obtain target area similarity measurement data includes: Selecting a first area and a second area from at least two of the target areas; wherein the first area and the second area are different; Selecting at least one selected area from the target primary area of ​​the first area; Selecting at least one candidate area from the target primary area of ​​the second area; Perform feature similarity evaluation on each of the selected regions and the candidate regions to obtain target feature similarity evaluation data; The target region similarity measurement is performed based on the target feature similarity evaluation data of the selected region to obtain the target region similarity measurement data.

[0011] In some embodiments, performing feature similarity evaluation on each of the selected regions and the candidate regions to obtain target feature similarity evaluation data includes: Obtain the target risk feature corresponding to each of the selected areas to obtain a first feature similarity to be evaluated; Obtaining the target risk feature corresponding to each candidate area to obtain a second feature similarity to be evaluated; Perform risk feature distance measurement based on the first feature similarity to be evaluated feature and each of the second feature similarity to be evaluated features to obtain risk feature distance measurement data; Perform risk feature similarity assessment based on the distance measurement data to obtain initial feature similarity assessment data; The target feature similarity evaluation data is selected from at least one of the initial feature similarity evaluation data corresponding to the selected area; wherein the risk feature similarity between the selected area and the second area corresponding to the target feature similarity evaluation data is the greatest.

[0012] In some embodiments, the target data includes: historical disaster data, geographical environment data, social loss data, economic loss data, social development level assessment data, socio-economic exposure data, ecological environment exposure data and infrastructure exposure data. The disaster risk assessment is performed on each sub-region to be assessed according to each target data to obtain preliminary risk assessment data for each sub-region to be assessed, including: Extracting risk susceptibility assessment features based on the historical disaster data and the geographic environment data; Performing a risk occurrence probability assessment based on the risk susceptibility assessment characteristics to obtain risk occurrence probability assessment data; wherein the risk occurrence probability assessment data represents the possibility of a disaster occurring in a target area; Extracting socioeconomic vulnerability assessment features based on the social loss data, the economic loss data and the social development level assessment data; Conducting a disaster resilience assessment based on the socioeconomic vulnerability assessment characteristics to obtain target socioeconomic vulnerability assessment data; wherein the target socioeconomic vulnerability assessment data represents the resilience of the target area to disasters; Extracting disaster exposure assessment features according to the socioeconomic exposure data, the ecological environment exposure data, and the infrastructure exposure data; Perform disaster impact range assessment according to the disaster exposure assessment characteristics to obtain target disaster exposure data; wherein the target disaster exposure data represents the impact range of the disaster on the target area; A comprehensive disaster risk assessment is performed based on the risk occurrence probability assessment data, the target socioeconomic vulnerability assessment data and the target disaster exposure data to obtain the preliminary risk assessment data for each sub-area to be assessed.

[0013] In some embodiments, allocating resources to each of the target areas according to the similarity measurement data between the target areas includes: Performing resource allocation similarity evaluation on at least two target areas according to the similarity measurement data between the target areas to obtain target area resource allocation similarity data; Performing target area risk assessment on the target risk characteristics corresponding to each target area to obtain target area risk assessment data; Resources are allocated to the target area according to the target area risk assessment data and the target area resource allocation similarity data.

[0014] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application proposes a resource allocation device based on cross-regional disaster risk assessment, the device comprising: A data acquisition module, used to acquire target data of at least two target areas; wherein the target data is disaster-related data of the target areas, and each of the target areas includes at least two sub-areas to be evaluated; A preliminary risk assessment module, used to perform disaster risk assessment on each of the sub-regions to be assessed according to the target data, and obtain preliminary risk assessment data for each sub-region to be assessed; A risk feature mining module, used to perform risk feature mining on each of the target areas according to the preliminary risk assessment data to obtain target risk features of each of the target areas; The target region similarity measurement module is used to perform target region similarity evaluation on the target risk characteristics of at least two target regions to obtain target region similarity measurement data; wherein each target region similarity measurement data represents the inter-region risk similarity between any two target regions; The resource allocation module is used to allocate resources to each of the target areas according to the similarity measurement data between the target areas.

[0015] The resource allocation method and device based on cross-regional disaster risk assessment proposed in the present application obtain target data of at least two target areas, and perform disaster risk assessment on each sub-area to be assessed according to the target data, so as to obtain preliminary risk assessment data of each sub-area to be assessed. Then, risk feature mining is performed on each target area according to the preliminary risk assessment data to obtain target risk features of each target area, and target risk features of at least two target areas are evaluated for similarity between target areas to obtain similarity measurement data between target areas, and finally resources are allocated to each target area according to the similarity measurement data between target areas. Therefore, the resource allocation method and device based on cross-regional disaster risk assessment proposed in the present application measures risk similarity between target areas according to spatial scale, and allocates resources to each target area based on risk similarity measurement data between regions, thereby improving the accuracy of risk assessment method for natural disaster risk assessment of cross-regional and cross-scale disasters, and guiding resource allocation by using measurement data of risk similarity between regions, which can improve the rationality and accuracy of disaster response resource allocation, so that disaster response resources can be used more efficiently. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a flow chart of a resource allocation method based on cross-regional disaster risk assessment provided in an embodiment of the present application; Figure 2 yes Figure 1 Flow chart of step S102 in FIG. Figure 3 yes Figure 1 Flow chart of step S103 in FIG. Figure 4 yes Figure 3 Flow chart of step S303 in FIG. Figure 5 yes Figure 3 Flow chart of step S304 in FIG. Figure 6 yes Figure 3 Flow chart of step S305 in FIG. Figure 7 yes Figure 1 Flow chart of step S104 in FIG. Figure 8 yes Figure 7 Flow chart of step S704 in FIG. Fig. 9 yes Figure 1 Flow chart of step S105 in FIG. Fig.10is a structural schematic diagram of a resource allocation device based on cross-regional disaster risk assessment provided in an embodiment of the present application; Fig.11 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with 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.

[0018] 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 may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0020] First, some nouns involved in this application are analyzed: Artificial intelligence (AI) is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. AI is a branch of computer science that attempts to understand the essence of intelligence and produce a new type of intelligent machine that can respond in a similar way to human intelligence. Research in this field includes robotics, language recognition, image recognition, natural language processing and expert systems. AI can simulate the information process of human consciousness and thinking.

[0021] In today's complex and ever-changing disaster environment, the core of disaster risk management lies in how to reasonably allocate limited resources to respond to potential disaster threats. The effectiveness of resource allocation strategies depends largely on the accuracy of disaster risk assessment. However, existing assessment methods are usually limited to traditional administrative divisions, which often ignore 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, which makes it difficult for risk assessments at a single scale to fully capture the full picture of the disaster. For example, the flood risk of a river basin may involve multiple administrative regions in the upstream, midstream and downstream, and existing assessment methods may not fully consider the risk connection of the entire river basin. Similarly, the impact of disasters such as earthquakes and typhoons often spans multiple regions, and needs to be assessed at a wider spatial scale to reasonably allocate disaster response resources to the affected areas.

[0022] Based on this, the embodiments of the present application provide a resource allocation method and device based on cross-regional disaster risk assessment, aiming to improve the accuracy of the risk assessment method when dealing with cross-regional and cross-scale disasters, so as to improve the efficiency of disaster response resource allocation.

[0023] The resource allocation method and device based on cross-regional disaster risk assessment provided in the embodiments of the present application are specifically illustrated through the following embodiments. First, the resource allocation method based on cross-regional disaster risk assessment in the embodiments of the present application is described.

[0024] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. 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.

[0025] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0026] The resource allocation method based on cross-regional disaster risk assessment provided in the embodiment 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 in the embodiment of the present application can be applied to a terminal, can also be applied to a server side, and can also be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop 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, and can also be configured as a cloud server that provides 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 that implements a resource allocation method based on cross-regional disaster risk assessment, etc., but is not limited to the above forms.

[0027] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. 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, in which 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.

[0028] Figure 1 is an optional flow chart of a resource allocation method based on cross-regional disaster risk assessment provided in an embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S105.

[0029] Step S101, obtaining target data of at least two target areas; wherein the target data is disaster-related data of the target area, and each target area includes at least two sub-areas to be evaluated; Step S102, performing disaster risk assessment on each sub-region to be assessed according to each target data, and obtaining preliminary risk assessment data for each sub-region to be assessed; Step S103, mining the risk characteristics of each target area according to the preliminary risk assessment data to obtain the target risk characteristics of each target area; Step S104, performing inter-target region similarity evaluation on target risk characteristics of at least two target regions to obtain inter-target region similarity measurement data; wherein each inter-target region similarity measurement data represents the inter-region risk similarity between any two target regions; Step S105: Allocate resources to each target area according to the similarity measurement data between target areas.

[0030] Steps S101 to S105 shown in the embodiment of the present application are obtained by acquiring target data of at least two target areas, and performing disaster risk assessment on each sub-area to be assessed according to the target data, so as to obtain preliminary risk assessment data of each sub-area to be assessed. Then, risk feature mining is performed on each target area according to the preliminary risk assessment data to obtain the target risk feature of each target area, and similarity assessment is performed between target areas on the target risk features of at least two target areas to obtain similarity measurement data between target areas, and finally, resources are allocated 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 risk similarity between target areas according to spatial scale, and allocates resources to each target area based on risk similarity measurement data between regions, thereby improving the accuracy of the risk assessment method for natural disaster risk assessment of cross-regional and cross-scale disasters, and guiding resource allocation by using the measurement data of risk similarity between regions, which can improve the rationality and accuracy of disaster response resource allocation, so that disaster response resources can be used more efficiently.

[0031] See also 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 economic exposure data, ecological environment exposure data and infrastructure exposure data. Step S102 may include but is not limited to steps S201 to S207: Step S201, extracting risk susceptibility assessment features based on historical disaster data and geographic environment data; Step S202, performing risk occurrence probability assessment according to the risk susceptibility assessment characteristics to obtain risk occurrence probability assessment data; wherein the risk occurrence probability assessment data represents the possibility of disasters occurring in the target area; Step S203, extracting socio-economic vulnerability assessment features based on social loss data, economic loss data and social development level assessment data; Step S204, performing disaster resilience assessment according to the socio-economic vulnerability assessment characteristics to obtain target socio-economic vulnerability assessment data; wherein the target socio-economic vulnerability assessment data represents the resilience of the target area to disasters; Step S205, extracting disaster exposure assessment features based on the socio-economic exposure data, the ecological environment exposure data, and the infrastructure exposure data; Step S206, evaluating the disaster impact range according to the disaster exposure assessment characteristics to obtain target disaster exposure data; wherein the target disaster exposure data represents the impact range of the disaster on the target area; Step S207, performing a comprehensive disaster risk assessment based on the risk occurrence probability assessment data, the target socioeconomic vulnerability assessment data and the target disaster exposure data, to obtain preliminary risk assessment data for each sub-region to be assessed.

[0032] In step S201 of some embodiments, historical disaster data is used to describe the natural disasters that have 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 technical personnel in this field, as long as the needs of analyzing historical disaster situations can be met. Geographical environment data may include but is not limited to at least one of the following: geographical geological data, hydrological and 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 risk susceptibility assessment features. Specifically, various types of data are first preprocessed to eliminate outliers and missing values, and then the most influential features for susceptibility prediction are extracted through feature engineering methods to obtain risk susceptibility assessment features. The feature engineering method can be a random forest (RF) algorithm, or it can be other feature extraction methods that can be obtained by technical personnel in this field.

[0033] 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 a specific location. The risk susceptibility assessment features include, but are not limited to, the following features: hydrological susceptibility assessment features, rock susceptibility assessment features, biological susceptibility assessment features, meteorological susceptibility assessment features, and terrain susceptibility assessment features. Among them, the hydrological susceptibility assessment features include, but are not limited to, surface runoff features, drainage density features, terrain moisture index features, and water flow intensity index features. The rock susceptibility assessment features include, but are not limited to, soil texture features and soil moisture features. The biological susceptibility assessment features include, but are not limited to, land use type features and normalized vegetation features. The meteorological susceptibility assessment features include, but are not limited to, temperature features, precipitation features, and wind speed features. The terrain susceptibility assessment features include, but are not limited to, elevation features, slope features, aspect features, plane curvature features, and profile curvature features. The process of risk occurrence probability assessment can be implemented by a gradient boosting tree LightGBM model, or by other machine learning models.

[0034] In some embodiments, steps S201 to S202 may also be implemented by a multidimensional disaster susceptibility prediction model. First, historical disaster data and geographic environment data are input into the multidimensional disaster susceptibility prediction model, and then the risk susceptibility assessment features are extracted by the risk susceptibility assessment feature extraction module in the multidimensional disaster susceptibility prediction model, and then the risk occurrence probability assessment module of the multidimensional disaster susceptibility prediction model performs a risk occurrence probability assessment on the risk susceptibility assessment features to obtain risk occurrence probability assessment data.

[0035] In step S203 of some embodiments, social loss data and economic loss data are used to describe the number of people and property losses affected by disasters in history, and social development level data are used to describe the social and economic recovery capacity after the disaster. Specifically, social loss data include but are not limited to: death population data and disaster-affected population data. Death population data is used to describe the number of deaths and missing people. Disaster-affected population data is used to describe the number of injured people, disturbed people and homeless people. Economic loss data is used to describe the economic losses directly or indirectly related to the disaster.

[0036] In step S204 of some embodiments, a disaster resilience assessment can be performed using a fuzzy comprehensive evaluation method. Specifically, the fuzzy comprehensive evaluation method first constructs a fuzzy relationship matrix based on the socioeconomic vulnerability assessment characteristics, then performs fuzzy operations on the fuzzy relationship matrix to automatically determine the weights of each socioeconomic vulnerability assessment feature, and finally performs a socioeconomic vulnerability score assessment based on the socioeconomic vulnerability assessment features and the weights corresponding to the socioeconomic vulnerability assessment features to obtain target socioeconomic vulnerability assessment data. Among them, the socioeconomic vulnerability assessment features include, but are not limited to, characteristics of the death population, characteristics of the affected population, and characteristics of economic losses. Using the fuzzy comprehensive evaluation method to conduct a disaster resilience assessment can effectively deal with the ambiguity in the evaluation process and convert qualitative evaluations into quantitative scores, thereby more accurately reflecting the region's disaster resilience.

[0037] In some embodiments of the present application, the weight of the death population characteristic is 0.443, the weight of the disaster-affected population characteristic is 0.335, and the weight of the economic loss characteristic is 0.222.

[0038] In some embodiments of the present application, the specific process of performing socioeconomic vulnerability score assessment according to the socioeconomic vulnerability assessment characteristics and the weights corresponding to the socioeconomic vulnerability assessment characteristics to obtain the target socioeconomic vulnerability assessment data can be expressed as follows: ; in, represents the target socioeconomic vulnerability assessment data, represents the weight corresponding to the i-th socioeconomic vulnerability assessment feature, represents the standardized characteristic value of the ith socioeconomic vulnerability assessment characteristic, Represents the total number of socioeconomic vulnerability assessment characteristics.

[0039] In step S205 of some embodiments, disaster exposure assessment features can be extracted from socio-economic exposure data, ecological environmental exposure data, and 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, disaster exposure assessment features include, but are not limited to, socio-economic exposure features, ecological environmental exposure features, and infrastructure exposure features. Socio-economic exposure features include, but are not limited to, population distribution features, ecological environmental exposure features include, but are not limited to, climate exposure level features, sea level rise features, ecological protection area features, and floodplain area features, and infrastructure exposure features include, but are not limited to, building volume features and road network density features.

[0040] In step S206 of some embodiments, the target disaster exposure data characterizes the scope of impact of the disaster on the target area. On this basis, the process of evaluating the scope of disaster impact can be implemented through a multidimensional disaster exposure assessment model. Specifically, a multidimensional disaster exposure assessment model is first constructed based on the three dimensions of social economy, ecological environment and infrastructure, and then the disaster exposure assessment features are evaluated through the multidimensional disaster exposure assessment model to obtain target disaster exposure data. It should be noted that for different regions or different disaster types, the contribution of various disaster exposure assessment features to the assessment of the scope of disaster impact changes dynamically. Therefore, in order to provide a more flexible analysis framework, the present invention does not limit specific weights when performing exposure assessment. The specific implementation process of evaluating the scope of disaster impact based on the disaster exposure assessment features to obtain the target disaster exposure data can be expressed as follows: ; in, represents the target disaster exposure data, represents the standardized characteristic value of the ith disaster exposure assessment feature, Represents the total number of hazard exposure assessment features.

[0041] In step S207 of some embodiments of the present application, a comprehensive disaster risk assessment is performed based on the risk occurrence probability assessment data, the target socioeconomic vulnerability assessment data, and the target disaster exposure data to obtain the preliminary risk assessment data for each sub-region to be assessed. The specific process can be expressed as follows: ; in Indicates preliminary risk assessment data, Represents the risk probability assessment data, represents the target socioeconomic vulnerability assessment data, In some embodiments of the present application, the preliminary risk assessment data, the risk occurrence probability assessment data, the target socio-economic vulnerability assessment data and the target disaster exposure data may be represented in the form of a matrix.

[0042] In the steps S201 to S207 shown in the embodiment of the present application, firstly, the target data is subjected to a risk probability assessment to obtain risk probability assessment data, a disaster resistance assessment is performed to obtain target socio-economic vulnerability assessment data, and a disaster impact range assessment is performed to obtain target disaster exposure data, and then a comprehensive disaster risk assessment is performed based on the risk probability assessment data, the target socio-economic vulnerability assessment data, and the target disaster exposure data to obtain preliminary risk assessment data for each sub-region to be assessed. Therefore, the resource allocation method based on cross-regional disaster risk assessment proposed in the present application can conduct a comprehensive disaster risk assessment on the sub-region to be assessed in the target region in terms of risk susceptibility, disaster resistance, and disaster impact range, and obtain more comprehensive disaster risk assessment data, so that the allocation of corresponding disaster resources is more accurate.

[0043] See also Figure 3 In some embodiments, step S103 may include but is not limited to steps S301 to S305: Step S301, obtaining the location information of each sub-region to be evaluated, and obtaining the sub-region location information; Step S302, constructing a graph network node according to the sub-region location information and preliminary risk assessment data corresponding to each sub-region to be assessed; wherein each graph network node is used to describe the risk of a sub-region to be assessed suffering from a disaster; Step S303, constructing a graph network according to the graph network nodes, the sub-region location information and the 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 assessed, and the edge weight data of the target graph network represent the difference in preliminary risk assessment data between the sub-regions to be assessed; Step S304, performing a first-level region division process according to the graph network edges, edge weight data and the sub-region to be evaluated to obtain a target first-level region; Step S305, mining the regional risk characteristics of each target first-level region according to the target first-level region, preliminary risk assessment data and sub-region location information to obtain the target risk characteristics of each target region.

[0044] In step S303 of some embodiments, the graph network edge of the target graph network is used to connect two spatially adjacent graph network nodes, thereby being able to characterize the spatial adjacency relationship between the sub-regions to be evaluated. The edge weight data of the target graph network characterizes the difference in preliminary risk assessment data between the sub-regions to be evaluated. Specifically, the larger the edge weight data, the more similar the possibility and disaster situation 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 possibility and disaster situation of the two sub-regions to be evaluated suffering from the same disaster.

[0045] In step S304 of some embodiments, the process of performing the first-level region division processing according to the graph network edges, edge weight data and the sub-regions to be evaluated may be implemented by the Louvain algorithm.

[0046] Steps S301 to S305 shown in the embodiment of the present application are to obtain the sub-region location information by acquiring the location information of each sub-region to be evaluated, to obtain the sub-region location information, to construct a graph network node according to the sub-region location information and preliminary risk assessment data corresponding to each sub-region to be evaluated, to construct a graph network according to the graph network nodes, the sub-region location information and the 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 represent the difference in preliminary risk assessment data between the sub-regions to be evaluated. Finally, a first-level region division process is performed according to the graph network edges, the edge weight data and the sub-regions to be evaluated to obtain a target first-level region, and regional 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. Therefore, the resource allocation method based on cross-regional disaster risk assessment proposed in this application performs a first-level regional division of the sub-regions to be assessed according to the risk differences between the sub-regions to be assessed, identifies and divides the sub-region groups to be assessed with similar risk characteristics, and performs risk analysis on the sub-region groups to be assessed after regional division. It overcomes the reliance on static risk area division in previous studies and provides a more dynamic and flexible regional division method, so that the risk assessment data can more accurately reflect the actual disaster risk situation, so as to provide more targeted allocation plans for disaster response resources.

[0047] See also Figure 4 In some embodiments, step S303 may include but is not limited to steps S401 to S406: Step S401, selecting 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 spatial relationship; Step S402, obtaining preliminary risk assessment data corresponding to the first target node to obtain target risk assessment data; Step S403, obtaining preliminary risk assessment data corresponding to the first adjacent node to obtain adjacent risk assessment data; Step S404, performing sub-region risk correlation measurement on each sub-region to be evaluated according to the target risk assessment data and the adjacent risk assessment data, and obtaining edge weight data; Step S405, constructing a graph network edge according to the first target node, the first adjacent node and the edge weight data; Step S406, constructing a target graph network based on the graph network nodes and graph network edges.

[0048] In step S404 of some embodiments, the specific process of measuring the sub-region risk correlation for each sub-region to be evaluated based on the target risk assessment data and the adjacent risk assessment data, and obtaining the edge weight data can be expressed as follows: ; in, 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 jth first adjacent node, The value of is 0.001 to avoid the denominator being zero. It can also be other constants.

[0049] In steps S401 to S406 shown in the embodiment of the present application, risk correlation is first measured for adjacent sub-areas to be evaluated to obtain edge weight data, and then all graph network nodes and graph network edges are integrated according to the sub-area location information and edge weight data to construct a complete target graph network. The spatial information of the sub-areas to be evaluated and the risk assessment data are integrated in the form of a target graph network, which can comprehensively reflect the risk relationship between the sub-areas to be evaluated.

[0050] See also Figure 5 In some embodiments, step S304 may include but is not limited to steps S501 to S505: Step S501, 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; Step S502, 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; Step S503, obtaining the initial first-level region where each second adjacent node is located, and obtaining an adjacent first-level region; Step S504, re-dividing the first-level region according to the second target node, each adjacent first-level region, the graph network edge and the edge weight data to obtain an updated first-level region; Step S505, updating the initial first-level region according to the updated first-level region to obtain a target first-level region.

[0051] In step S502 of some embodiments, the preset first-level region division rule may be: taking each graph network node as an initial first-level region. The preset first-level region division rule may also be selected according to actual needs of those skilled in the art.

[0052] In step S504 of some embodiments, the first-level region is re-divided according to the second target node, each adjacent first-level region, the graph network edge and the edge weight data, and the updated first-level region can be obtained. Specifically, the modularity gain is first calculated according to the second target node, each adjacent first-level region, the second adjacent node in each adjacent first-level region, the graph network edge and the edge weight data to obtain the candidate modularity gain data; wherein, the candidate modularity gain data characterizes the degree of connection between the second target node and each adjacent first-level region when the second target node moves to each adjacent first-level region. Then, a plurality of candidate modularity gain data are compared to obtain modularity gain comparison data, and the target modularity gain data is selected from the candidate modularity gain data according to the modularity gain comparison data; wherein, the second target node corresponding to the target modularity gain data and the adjacent first-level region corresponding to the target modularity gain data are most closely connected. Finally, the adjacent first-level region corresponding to the target modularity gain data is selected as the target adjacent first-level region, and the second target node is moved to the target adjacent first-level region to obtain the updated first-level region. The specific process of calculating the modularity gain according to the second target node, each adjacent first-level region, the second adjacent node in each adjacent first-level region, the graph network edge and the edge weight data to obtain the candidate modularity gain data can be expressed as: ; in, represents the candidate modularity gain data, Represents the sum of the edge weight data of the internal graph network edges of adjacent first-level regions, represents the sum of the edge weight data between the second target node i and the second adjacent node in the adjacent first-level region, Represents the sum of the edge weight data of all graph network edges in the graph network, represents the sum of the degrees of all graph network nodes in adjacent first-level regions, represents the degree of the second target node i.

[0053] 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 reselect the adjacent first-level region from the updated first-level region after the last update according to the second target node, and calculate the candidate modularity gain data between each second target node and the adjacent first-level region selected from the updated first-level region to obtain the updated modularity gain data, and update the updated first-level region again according to the updated modularity gain data. It should be noted that after each iterative update, the modularity data of the graph network needs to be calculated. 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 from the last update is used as the target first-level region.

[0054] In the steps S501 to S505 shown in the embodiment of the present application, the second target node and at least one second adjacent node are first selected from the graph network nodes, and the adjacent first-level region is obtained based on the initial first-level region where each second adjacent node is located. Then, the first-level region is re-divided according to the second target node, each adjacent first-level region, the graph network edge and the edge weight data to obtain an 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 performs a first-level regional division process on the sub-region to be assessed by utilizing the risk differences between the sub-regions to be assessed, and dynamically adjusts and optimizes the regional division in an iterative manner, which can simultaneously take into account the geographical proximity of the sub-regions to be assessed and the similarity of risk characteristics, thereby accurately reflecting the actual risk status of the target first-level region and improving the accuracy of risk assessment.

[0055] See also Figure 6 In some embodiments, step S305 may include but is not limited to steps S601 to S606: Step S601, obtaining the graph network nodes of each target first-level area to obtain candidate graph network nodes; Step S602, obtaining preliminary risk assessment data according to the candidate graph network nodes, and obtaining the first-level regional risk data to be assessed for each target first-level region; Step S603, performing a first-level regional risk assessment based on the first-level regional risk to be assessed data of each target first-level region to obtain first-level regional risk assessment data; wherein the first-level regional risk assessment data represents the risk of the target first-level region suffering from disasters; Step S604, determining the location information of the target first-level region according to the location information of the target first-level region and the sub-region, and obtaining the first-level region location information; Step S605, 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 represents the risk difference between the target first-level region and its surrounding first-level regions; Step S606, performing regional risk feature mining based on the first-level regional risk assessment data and the first-level regional risk association data corresponding to each target first-level region, to obtain the target risk feature of each target region.

[0056] In step S602 of some embodiments, for each target first-level region, each first-level region risk assessment data is preliminary risk assessment data corresponding to a graph network node in the target first-level region.

[0057] In step S603 of some embodiments, a first-level regional risk assessment is performed based on multiple first-level regional risk assessment data to obtain first-level regional risk assessment data. Specifically, for each first-level region, the initial risk assessment data corresponding to the graph network nodes in the target first-level region are averaged to obtain the first-level regional risk assessment data.

[0058] In step S605 of some embodiments, the first-level region risk correlation degree measurement is performed according to the target first-level region, the first-level region location information and the first-level region risk assessment data, and the first-level region risk correlation degree data can be obtained. The first-level region risk correlation degree data can be represented by the local Geary's C. Specifically, the process of performing the first-level region risk correlation degree measurement according to the target first-level region, the first-level region location information and the first-level region risk assessment data to obtain the first-level region risk correlation degree data can be represented as follows: ; in, represents the first-level regional risk correlation data of the i-th target first-level region, represents the weight of the spatial adjacency matrix calculated from the first-level region location information, represents the first-level regional risk assessment data of the i-th target first-level region, Represents the first-level regional risk assessment data of the j-th target first-level area.

[0059] In steps S601 to S606 shown in the embodiment of the present application, the first-level regional risk assessment data and the first-level regional risk correlation data of each first-level regional risk data to be assessed are first calculated, and then regional risk feature mining is performed based on the first-level regional risk assessment data and the first-level regional risk correlation data corresponding to each target first-level region to obtain the target risk feature of each target region. The disaster risk of the first-level region can be understood from two aspects: the risk level within the target first-level region and the risk correlation and difference between the target first-level regions, so as to more comprehensively assess the disaster risk level of the target first-level region and improve the accuracy of risk assessment.

[0060] See also Figure 7 In some embodiments, step S104 may include but is not limited to steps S701 to S705: Step S701, selecting a first area and a second area from at least two target areas; wherein the first area and the second area are different; Step S702, selecting at least one selected area from the target primary area of ​​the first area; Step S703, selecting at least one candidate area from the target primary area of ​​the second area; Step S704, performing feature similarity evaluation on each selected region and candidate region to obtain target feature similarity evaluation data; Step S705 , performing similarity measurement between target regions according to the target feature similarity evaluation data of the selected region to obtain similarity measurement data between target regions.

[0061] In step S701 of some embodiments, the target area may be an area at the same spatial scale or an area at a different spatial scale. The spatial scale may include, but is not limited to, at least one of the following: a city scale, a regional scale, a national scale, and a global scale. For at least two target areas, a first area may be selected from all target areas in turn, and a target area different from the first area may be selected as a second area, and then an inter-target area similarity measurement may be performed between the first area and the second area to obtain inter-target area similarity measurement data between any two target areas.

[0062] In step S705 of some embodiments, target region similarity measurement is performed based on the target feature similarity evaluation data corresponding to the selected region, and target region similarity measurement data can be obtained. Specifically, for each first region, target feature similarity evaluation data corresponding to all target primary regions in the first region are obtained, and all target feature similarity evaluation data are averaged to obtain target region similarity measurement data between the first region and the second region.

[0063] Steps S701 to S705 shown in the embodiment of the present application select a first area and a second area from at least two target areas at multiple spatial scales, select at least one selected area from the target first-level area of ​​the first area, and select at least one candidate area from the target first-level area of ​​the second area, and then perform feature similarity evaluation on each selected area and each candidate area to obtain target feature similarity evaluation data, and finally perform similarity measurement between target areas based on the target feature similarity evaluation data to obtain similarity measurement data between target areas. This can take into account the risk characteristics of areas at different geographical and administrative levels when facing disasters, realize cross-regional and cross-scale risk assessment, and help to build a more comprehensive disaster response strategy when multi-regional disasters occur, thereby achieving more effective allocation of disaster response resources.

[0064] See also Figure 8 In some embodiments, step S704 may include but is not limited to steps S801 to S805: Step S801, obtaining the target risk feature corresponding to each selected area, and obtaining the first feature similarity to be evaluated; Step S802, obtaining the target risk feature corresponding to each candidate area, and obtaining the second feature similarity to be evaluated feature; Step S803, performing risk feature distance measurement according to the feature to be evaluated with the first feature similarity and each feature to be evaluated with the second feature similarity to obtain risk feature distance measurement data; Step S804, performing risk feature similarity assessment based on the distance measurement data to obtain initial feature similarity assessment data; Step S805, selecting target feature similarity evaluation data from at least one initial feature similarity evaluation data corresponding to the selected region; wherein the risk feature similarity between the selected region and the second region corresponding to the target feature similarity evaluation data is the greatest.

[0065] In step S803 of some embodiments, risk feature distance measurement is performed based on the first feature similarity to be evaluated feature and each second feature similarity to be evaluated feature, and risk feature distance measurement data can be obtained. Specifically, the risk feature distance measurement can adopt the Mahalanobis distance measurement method, and the Mahalanobis distance measurement data is used as the risk feature distance measurement data.

[0066] In step S804 of some embodiments, when the Mahalanobis distance measurement method is used to measure the risk feature distance, the risk feature similarity evaluation is performed according to the distance measurement data. The specific process of obtaining the initial feature similarity evaluation data can be expressed as: Initial feature similarity evaluation data = 1 / (1+Mahalanobis distance metric data).

[0067] See also Fig. 9 In some embodiments, step S105 may include but is not limited to steps S901 to S903: Step S901, performing resource allocation similarity evaluation on at least two target areas according to similarity measurement data between target areas, to obtain target area resource allocation similarity data; Step S902, performing target area risk assessment on the target risk characteristics corresponding to each target area to obtain target area risk assessment data; Step S903: Allocate resources to the target area according to the target area risk assessment data and the target area resource allocation similarity data.

[0068] In the steps S901 to S903 shown in the embodiment of the present application, by performing resource allocation similarity assessment on at least two target areas, target area resource allocation similarity data is obtained, and then target area risk assessment is performed on the target risk characteristics corresponding to each target area to obtain target area risk assessment data, and resources are allocated to the target area based on the target area risk assessment data and the target area resource allocation similarity data. Therefore, the resource allocation method based on cross-regional disaster risk assessment provided by the present application can identify areas that may have similarities in resource demand, and allocate corresponding resources to areas with similar resource demand based on the disaster risk status of the area, taking into account both the risk status of the area and the similarities between areas, thereby achieving reasonable and efficient allocation of resources.

[0069] See also Fig.10 The 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, and the device includes: The data acquisition module 1001 is used to acquire target data of at least two target areas; wherein the target data is disaster-related data of the target area, and each target area includes at least two sub-areas to be evaluated; A preliminary risk assessment module 1002 is used to perform disaster risk assessment on each sub-region to be assessed according to the target data, and obtain preliminary risk assessment data for each sub-region to be assessed; The risk feature mining module 1003 is used to mine the risk features of each target area according to the preliminary risk assessment data to obtain the target risk features of each target area; The target region similarity measurement module 1004 is used to perform target region similarity evaluation on target risk characteristics of at least two target regions to obtain target region similarity measurement data; wherein each target region similarity measurement data represents the inter-region risk similarity between any two target regions; The resource allocation module 1005 is used to allocate resources to each target area according to the similarity measurement data between target areas.

[0070] The specific implementation of the resource allocation device based on cross-regional disaster risk assessment is basically the same as the specific implementation of the resource allocation method based on cross-regional disaster risk assessment mentioned above, and will not be repeated here.

[0071] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the resource allocation method based on cross-regional disaster risk assessment when executing the computer program. The electronic device can be any smart terminal including a tablet computer, a car computer, etc.

[0072] See also Fig.11 , Fig.11 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes: The processor 1101 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application; The memory 1102 may 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). The memory 1102 may store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 1102, and the processor 1101 calls and executes the resource allocation method based on cross-regional disaster risk assessment in the embodiment of this application; Input / output interface 1103, used to implement information input and output; The communication interface 1104 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WIFI, Bluetooth, etc.); A bus 1105 that transmits information between various components of the device (e.g., the processor 1101, the memory 1102, the input / output interface 1103, and the communication interface 1104); The processor 1101 , the memory 1102 , the input / output interface 1103 and the communication interface 1104 are connected to each other in communication within the device via the bus 1105 .

[0073] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned resource allocation method based on cross-regional disaster risk assessment.

[0074] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0075] The resource allocation method and device based on cross-regional disaster risk assessment provided by the embodiment of the present application, by obtaining the target data of at least two target areas, and performing disaster risk assessment on each sub-area to be assessed according to the target data, obtains the preliminary risk assessment data of each sub-area to be assessed. Then, risk feature mining is performed on each target area according to the preliminary risk assessment data to obtain the target risk feature of each target area, and the target risk features of at least two target areas are evaluated for similarity between target areas to obtain similarity measurement data between target areas, and finally, resources are allocated to each target area according to the similarity measurement data between target areas. Therefore, the resource allocation method and device based on cross-regional disaster risk assessment proposed in the present application, the risk similarity measurement is performed between target areas according to the spatial scale, and resources are allocated to each target area based on the risk similarity measurement data between regions, which improves the accuracy of the risk assessment method for natural disaster risk assessment of cross-regional and cross-scale disasters, and by using the measurement data of risk similarity between regions to guide resource allocation, the rationality and accuracy of disaster response resource allocation can be improved, so that disaster response resources can be used more efficiently.

[0076] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0077] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0078] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0079] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0080] The terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0081] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "At least one of the following (items)" or similar expressions refers to any combination of these items, including any combination of single items (items) or plural items (items). For example, at least one of a, b or c can mean: 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.

[0082] In the several embodiments provided in this 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 schematic, for example, the division of the above units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0083] 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, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0084] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A resource allocation method based on cross-regional disaster risk assessment, characterized in that: The method comprises: Acquire target data of at least two target areas; wherein the target data is disaster-related data of the target areas, and each of the target areas includes at least two sub-areas to be evaluated; Conduct disaster risk assessment on each of the sub-regions to be assessed according to each of the target data to obtain preliminary risk assessment data for each of the sub-regions to be assessed; Perform risk feature mining on each of the target areas according to the preliminary risk assessment data to obtain target risk features of each of the target areas; Performing inter-target region similarity evaluation on the target risk characteristics of at least two of the target regions to obtain inter-target region similarity measurement data; wherein each of the inter-target region similarity measurement data represents the inter-region risk similarity between any two of the target regions; Resources are allocated to each of the target areas according to the similarity measurement data between the target areas.

2. The method according to claim 1, characterized in that The step of mining risk characteristics of each target area according to the preliminary risk assessment data to obtain target risk characteristics of each target area includes: Acquire the location information of each sub-region to be evaluated to obtain the sub-region location information; Constructing a graph network node according to the sub-region location information corresponding to each sub-region to be assessed and the preliminary risk assessment data; wherein each graph network node is used to describe the risk of a sub-region to be assessed suffering from a disaster; A graph network is constructed according to the graph network nodes, the sub-region location information and the 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 assessed, and the edge weight data of the target graph network represent the difference in preliminary risk assessment data between the sub-regions to be assessed; Performing a first-level region division process according to the graph network edge, the edge weight data and the sub-region to be evaluated to obtain a target first-level region; Regional risk characteristics of each of the target first-level regions are mined according to the target first-level regions, the preliminary risk assessment data and the sub-region location information to obtain target risk characteristics of each of the target regions.

3. The method according to claim 2, characterized in that The step of constructing a graph network according to the graph network nodes, the sub-region location information and the preliminary risk assessment data to obtain a target graph network includes: Selecting 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 spatial relationship; Acquire the preliminary risk assessment data corresponding to the first target node to obtain target risk assessment data; Acquire the preliminary risk assessment data corresponding to the first adjacent node to obtain adjacent risk assessment data; According to the target risk assessment data and the adjacent risk assessment data, a sub-region risk correlation measurement is performed on each of the sub-regions to be assessed 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; A target graph network is constructed according to the graph network nodes and the graph network edges.

4. The method according to claim 2, characterized in that: The first-level region division process is performed according to the graph network edge, the edge weight data and the sub-region to be evaluated to obtain the target first-level region, including: 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; Acquire an initial primary region where each of the second adjacent nodes is located, to obtain an adjacent primary region; Re-dividing the first-level region according to the second target node, each of the adjacent first-level regions, the graph network edge and the edge weight data to obtain an updated first-level region; The initial first-level region is updated according to the updated first-level region to obtain the target first-level region.

5. The method according to claim 2, characterized in that: The performing of regional risk feature mining on each of the target first-level regions 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 of the target regions includes: Obtain the graph network node of each target primary area to obtain a candidate graph network node; Acquire the preliminary risk assessment data according to the candidate graph network nodes to obtain the first-level regional risk data to be assessed for each of the target first-level regions; Performing a first-level regional risk assessment based on the first-level regional risk to be assessed data of each of the target first-level regions to obtain first-level regional risk assessment data; wherein the first-level regional risk assessment data represents the risk of the target first-level region suffering from disasters; Determine the location information of the target first-level area according to the target first-level area and the sub-area location information to obtain the first-level area location information; A risk correlation degree measurement is performed according to the target first-level region, the location information of the first-level region and the risk assessment data of the first-level region to obtain first-level region risk correlation degree data; wherein each first-level region risk correlation degree data corresponds to one target first-level region, and the first-level region risk correlation degree data represents the risk difference between the target first-level region and its surrounding first-level regions; Regional risk feature mining is performed based on the first-level regional risk assessment data and the first-level regional risk association data corresponding to each of the target first-level regions to obtain target risk features of each target region.

6. The method according to claim 2, characterized in that The performing target area similarity evaluation on the target risk characteristics of at least two target areas to obtain similarity measurement data between the target areas includes: Selecting a first area and a second area from at least two of the target areas; wherein the first area and the second area are different; Selecting at least one selected area from the target primary area of ​​the first area; Selecting at least one candidate area from the target primary area of ​​the second area; Perform feature similarity evaluation on each of the selected regions and the candidate regions to obtain target feature similarity evaluation data; The target region similarity measurement is performed based on the target feature similarity evaluation data of the selected region to obtain the target region similarity measurement data.

7. The method according to claim 6, characterized in that The step of performing feature similarity evaluation on each of the selected regions and the candidate regions to obtain target feature similarity evaluation data includes: Obtain the target risk feature corresponding to each of the selected areas to obtain a first feature similarity to be evaluated; Obtaining the target risk feature corresponding to each candidate area to obtain a second feature similarity to be evaluated; Perform risk feature distance measurement based on the first feature similarity to be evaluated feature and each of the second feature similarity to be evaluated features to obtain risk feature distance measurement data; Perform risk feature similarity assessment based on the distance measurement data to obtain initial feature similarity assessment data; The target feature similarity evaluation data is selected from at least one of the initial feature similarity evaluation data corresponding to the selected area; wherein the risk feature similarity between the selected area and the second area corresponding to the target feature similarity evaluation data is the greatest.

8. The method according to claim 1, characterized in that The target data include: historical disaster data, geographic environment data, social loss data, economic loss data, social development level assessment data, socio-economic exposure data, ecological environment exposure data and infrastructure exposure data. The disaster risk assessment is performed on each sub-region to be assessed based on each target data to obtain preliminary risk assessment data for each sub-region to be assessed, including: Extracting risk susceptibility assessment features based on the historical disaster data and the geographic environment data; Performing a risk occurrence probability assessment based on the risk susceptibility assessment characteristics to obtain risk occurrence probability assessment data; wherein the risk occurrence probability assessment data represents the possibility of a disaster occurring in a target area; Extracting socioeconomic vulnerability assessment features based on the social loss data, the economic loss data and the social development level assessment data; Conducting a disaster resilience assessment based on the socioeconomic vulnerability assessment characteristics to obtain target socioeconomic vulnerability assessment data; wherein the target socioeconomic vulnerability assessment data represents the resilience of the target area to disasters; Extracting disaster exposure assessment features according to the socioeconomic exposure data, the ecological environment exposure data, and the infrastructure exposure data; Perform disaster impact range assessment according to the disaster exposure assessment characteristics to obtain target disaster exposure data; wherein the target disaster exposure data represents the impact range of the disaster on the target area; A comprehensive disaster risk assessment is performed based on the risk occurrence probability assessment data, the target socioeconomic vulnerability assessment data and the target disaster exposure data to obtain the preliminary risk assessment data for each sub-area to be assessed.

9. The method according to claim 1, characterized in that: The allocating resources to each of the target areas according to the similarity measurement data between the target areas comprises: Performing resource allocation similarity evaluation on at least two target areas according to the similarity measurement data between the target areas to obtain target area resource allocation similarity data; Performing target area risk assessment on the target risk characteristics corresponding to each target area to obtain target area risk assessment data; Resources are allocated to the target area according to the target area risk assessment data and the target area resource allocation similarity data.

10. A resource allocation device based on cross-regional disaster risk assessment, characterized in that: The device comprises: A data acquisition module, used to acquire target data of at least two target areas; wherein the target data is disaster-related data of the target areas, and each of the target areas includes at least two sub-areas to be evaluated; A preliminary risk assessment module, used to perform disaster risk assessment on each of the sub-regions to be assessed according to the target data, and obtain preliminary risk assessment data for each sub-region to be assessed; A risk feature mining module, used to perform risk feature mining on each of the target areas according to the preliminary risk assessment data to obtain target risk features of each of the target areas; The target region similarity measurement module is used to perform target region similarity evaluation on the target risk characteristics of at least two target regions to obtain target region similarity measurement data; wherein each target region similarity measurement data represents the inter-region risk similarity between any two target regions; The resource allocation module is used to allocate resources to each of the target areas according to the similarity measurement data between the target areas.

Images