Typhoon disaster chain risk assessment method and device, terminal equipment and storage medium

Abstract

The invention discloses a typhoon disaster chain risk assessment method and device, terminal equipment and a storage medium, and the method comprises the steps: carrying out the weight analysis of risk assessment indexes corresponding to all data in an obtained typhoon disaster chain risk assessment data set, and obtaining the weight value of each risk assessment index; according to the weight value of each risk assessment index, the prior probability of the nodes in the pre-constructed Bayesian network is adjusted, and the adjusted Bayesian network is obtained; and finally, inputting the typhoon disaster chain risk assessment data set into the adjusted Bayesian network, so that the adjusted Bayesian network outputs and obtains the typhoon disaster chain risk level of the to-be-assessed region. Therefore, by implementing the typhoon disaster chain risk assessment method, the typhoon disaster chain risk levels of different areas can be effectively assessed, and the universality is high.

Description

Technical Field

[0001] The present invention relates to the field of typhoon risk assessment, and in particular to a typhoon disaster chain risk assessment method, device, terminal equipment and storage medium. Background Art

[0002] Under the influence of global climate change, extreme weather events are becoming more frequent, and typhoons are a typical example of an increasing trend in both intensity and frequency. The typhoon disaster chain consists of a series of disaster phenomena caused by typhoons, covering serial and concurrent disaster chains, such as the typhoon-rainstorm disaster chain and the cold wave disaster chain. The existence of such disaster chains greatly increases the complexity and far-reaching impact of typhoons.

[0003] In the field of typhoon risk assessment, the current assessment method is generally to first collect a large amount of historical typhoon data in a certain area, and then build a typhoon disaster network model based on these data. However, the typhoon disaster network model built based on a certain area may have good applicability in that area, but when it is extended to other areas, due to the differences in geographical environment, socio-economic conditions and typhoon disaster characteristics in different regions, the accuracy and reliability of the model may be affected, and its universality needs to be improved. Summary of the invention

[0004] The present invention provides a typhoon disaster chain risk assessment method, device, terminal equipment and storage medium. The method has strong universality and can effectively assess the risk level of typhoon disaster chains caused by typhoons in different regions, providing a scientific basis for disaster warning and response.

[0005] An embodiment of the present invention provides a typhoon disaster chain risk assessment method, comprising:

[0006] Acquire a typhoon disaster chain risk assessment dataset for the area to be assessed; wherein the typhoon disaster chain risk assessment dataset includes a historical typhoon disaster dataset, an infrastructure dataset, an economic development dataset, a population density data, and a typhoon defense plan set;

[0007] Performing weight analysis on the risk assessment indicators corresponding to each data in the typhoon disaster chain risk assessment data set to obtain a weight value of each risk assessment indicator;

[0008] According to the weight values ​​of the risk assessment indicators, the prior probabilities of the nodes in the pre-constructed Bayesian network are adjusted to obtain an adjusted Bayesian network; wherein the risk assessment indicators correspond one to one to the nodes in the Bayesian network;

[0009] The typhoon disaster chain risk assessment data set is input into the adjusted Bayesian network, so that the adjusted Bayesian network outputs the typhoon disaster chain risk level of the area to be assessed.

[0010] Furthermore, the weight analysis of the risk assessment indicators corresponding to each data in the typhoon disaster chain risk assessment data set to obtain the weight value of each risk assessment indicator includes:

[0011] Inputting the typhoon disaster chain risk assessment data set into a preset indicator weight analysis model, so that the indicator weight analysis model assigns weights to the risk assessment indicators corresponding to each data in the typhoon disaster chain risk assessment data set according to a built-in judgment matrix, and obtains a pre-selected weight value for each risk assessment indicator;

[0012] According to the typhoon disaster chain risk assessment data set and the pre-constructed Bayesian network, a secondary weight distribution is performed on the pre-selected weight values ​​of the risk assessment indicators to obtain the weight values ​​of the risk assessment indicators.

[0013] Furthermore, the construction process of the indicator weight analysis model includes:

[0014] Obtain target information, a sample set of typhoon disaster chain events, and a preset typhoon disaster chain risk assessment indicator system; wherein the target information points to the overall risk level assessment of the typhoon disaster chain; the sample set of typhoon disaster chain events includes the typhoon disaster chain risk scenarios and corresponding impact results generated when a typhoon occurs;

[0015] Constructing a hierarchical model; wherein the hierarchical model includes a target layer, a criterion layer and a solution layer;

[0016] Based on the target information, the assessment target of the target layer is set as the typhoon disaster chain risk level assessment, and the target layer is obtained after the target setting is completed;

[0017] Based on the typhoon disaster chain risk assessment indicator system, various risk assessment indicators are set in the criterion layer to obtain a criterion layer after the risk assessment indicators are set;

[0018] Based on the typhoon disaster chain event sample set, a typhoon disaster chain risk scenario is set in the solution layer to obtain a solution layer after the scenario setting is completed;

[0019] Constructing a judgment matrix based on the criterion layer after the risk assessment indicators are set;

[0020] The indicator weight analysis model is formed according to the target layer after the target setting is completed, the criterion layer after the risk assessment indicator setting is completed, the solution layer after the scenario setting is completed, and the judgment matrix.

[0021] Furthermore, the typhoon disaster chain risk assessment indicator system includes primary indicators, secondary indicators and tertiary indicators;

[0022] The first-level indicators include threat factors, vulnerability factors and defense capability factors;

[0023] The secondary indicators include typhoon behavior, population density, infrastructure, economic development and typhoon defense capabilities;

[0024] The three-level indicators include typhoon intensity, typhoon path, precipitation, wind speed, landing location, population distribution, regional area, population size, transportation facilities, energy facilities, water conservancy facilities, terrain conditions, regional industrial structure, economic output, rescue response capability, communication system response capability, evacuation capability and resource dispatch capability.

[0025] Furthermore, according to the typhoon disaster chain risk assessment data set and the pre-built Bayesian network, a secondary weight distribution is performed on the pre-selected weight values ​​of each risk assessment indicator to obtain the weight value of each risk assessment indicator, including:

[0026] Counting all the node objects in the Bayesian network for characterizing the typhoon disaster chain risk scenario;

[0027] Constructing a normalized matrix according to the data in the typhoon disaster chain risk assessment data set and the node object used to characterize the typhoon disaster chain risk scenario;

[0028] According to the normalized matrix, the entropy value corresponding to each data in the typhoon disaster chain risk assessment data set is calculated;

[0029] According to the entropy value corresponding to each data in the typhoon disaster chain risk assessment data set, the pre-selected weight value of the risk assessment indicator corresponding to each data is secondary weighted, so as to obtain the weight value of each risk assessment indicator.

[0030] Furthermore, the typhoon disaster chain risk assessment method further includes:

[0031] According to the typhoon disaster chain risk level of the area to be assessed, the emergency plan of the area to be assessed is screened in the preset comprehensive emergency plan system;

[0032] According to the emergency plan, preventive deployment is carried out in the area to be assessed.

[0033] An embodiment of the present invention further provides a typhoon disaster chain risk assessment device, comprising: a data set acquisition module, a weight value calculation module, a Bayesian network adjustment module, and a typhoon disaster chain risk level determination module;

[0034] The data set acquisition module is used to acquire a typhoon disaster chain risk assessment data set for the area to be assessed; wherein the typhoon disaster chain risk assessment data set includes a historical typhoon disaster data set, an infrastructure data set, an economic development data set, a population density data set, and a typhoon defense plan set;

[0035] The weight value calculation module is used to perform weight analysis on the risk assessment indicators corresponding to each data in the typhoon disaster chain risk assessment data set to obtain the weight value of each risk assessment indicator;

[0036] The Bayesian network adjustment module is used to adjust the prior probability of the nodes in the pre-constructed Bayesian network according to the weight value of each risk assessment indicator to obtain an adjusted Bayesian network; wherein the risk assessment indicators correspond one to one to the nodes in the Bayesian network;

[0037] The typhoon disaster chain risk level determination module is used to input the typhoon disaster chain risk assessment data set into the adjusted Bayesian network so that the adjusted Bayesian network outputs the typhoon disaster chain risk level of the area to be assessed.

[0038] Furthermore, the typhoon disaster chain risk assessment device further includes: an emergency plan determination module;

[0039] The emergency plan determination module is used to select the emergency plan for the area to be evaluated from a preset comprehensive emergency plan system according to the typhoon disaster chain risk level of the area to be evaluated; and to make preventive deployment for the area to be evaluated according to the emergency plan.

[0040] The present application also provides a terminal device, including:

[0041] one or more processors;

[0042] A memory, coupled to the processor, for storing one or more programs;

[0043] When the one or more programs are executed by the one or more processors, the one or more processors implement the typhoon disaster chain risk assessment method as described in the above-mentioned embodiment of the invention.

[0044] The present application also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the typhoon disaster chain risk assessment method as described in the above-mentioned embodiment of the invention is implemented.

[0045] The following beneficial effects are achieved by implementing the present invention:

[0046] The present invention provides a typhoon disaster chain risk assessment method, device, terminal equipment and storage medium. The method performs weight analysis on the risk assessment indicators corresponding to each data in the typhoon disaster chain risk assessment data set to obtain the weight value of each risk assessment indicator, and adjusts the prior probability of the nodes in the pre-constructed Bayesian network based on the weight value of each risk assessment indicator to obtain the adjusted Bayesian network. Finally, the typhoon disaster chain risk level of the area to be assessed is obtained by solving the adjusted Bayesian network.

[0047] Therefore, by performing weight analysis on the risk assessment indicators corresponding to each data in the typhoon disaster chain risk assessment dataset, and adjusting the prior probability of the nodes in the pre-constructed Bayesian network according to the weight value of each risk assessment indicator, the accuracy of the Bayesian network evaluation is improved, so that when facing different areas to be evaluated, the typhoon disaster chain risk assessment dataset of the corresponding area can be used to accurately assess the typhoon disaster chain risk level of different areas, thereby solving the problem of low applicability of the existing typhoon disaster chain risk assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solution of the present application, the drawings required for use in the implementation manner will be briefly introduced below. Obviously, the drawings described below are only some implementation manners of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0049] Figure 1 It is a flowchart of a typhoon disaster chain risk assessment method provided by a certain embodiment of the present application;

[0050] Figure 2 It is a structural schematic diagram of a typhoon disaster chain risk assessment device provided in a certain embodiment of the present application;

[0051] Figure 3 It is a structural schematic diagram of a typhoon disaster chain risk assessment device provided in a certain embodiment of the present application;

[0052] Figure 4 It is a structural diagram of a terminal device provided in a certain embodiment of the present application. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0054] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0055] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0056] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0057] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0058] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0059] In the description of the embodiments of the present application, unless otherwise clearly specified and limited, technical terms such as "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the internal connection of two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0060] See also Figure 1, is a flow chart of a typhoon disaster chain risk assessment method provided by an embodiment of the present invention, comprising:

[0061] S1. Obtain a typhoon disaster chain risk assessment dataset for the area to be assessed; wherein the typhoon disaster chain risk assessment dataset includes a historical typhoon disaster dataset, an infrastructure dataset, an economic development dataset, a population density data, and a typhoon defense plan set;

[0062] Indicatively, when determining the typhoon disaster chain risk level of a certain area to be evaluated, it is necessary to first obtain multidimensional data of the current area to be evaluated. In this application, these multidimensional data are divided into historical typhoon disaster data sets, infrastructure data sets, economic development data sets, population density data, and typhoon defense plan sets. These data sets together constitute the typhoon disaster chain risk assessment data set that needs to be input in the subsequent assessment;

[0063] Specifically, the typhoon disaster chain risk assessment data set contains a number of specific data, and the risk assessment indicators corresponding to these specific data include typhoon intensity, typhoon path, precipitation, wind speed, landing location, etc. These risk assessment indicators correspond to natural factors directly related to typhoon events;

[0064] Specifically, the risk assessment indicators corresponding to these specific data also include population distribution, regional area, population size, transportation facilities, energy facilities, water conservancy facilities, terrain conditions, regional industrial structure, economic volume, etc. These risk assessment indicators will affect the ability of the area to be assessed to resist typhoons;

[0065] Specifically, the risk assessment indicators corresponding to these specific data also include rescue response time, rescue equipment scale, rescue team composition, signal coverage range, available communication equipment and corresponding distribution (such as walkie-talkies, mobile base stations, etc.), information transmission rate, communication system performance, evacuation routes, evacuation transportation equipment, emergency material quantity, emergency material distribution information, dispatch decision time, etc. These risk assessment indicators will also affect the ability of the area to be assessed to resist typhoons.

[0066] S2. Performing weight analysis on the risk assessment indicators corresponding to each data in the typhoon disaster chain risk assessment data set to obtain a weight value of each risk assessment indicator;

[0067] Indicatively, after obtaining the typhoon disaster chain risk assessment data set of the area to be assessed, since the impact of each specific data in the typhoon disaster chain risk assessment data set on the typhoon disaster chain is not consistent, it is necessary to assign a weight to each specific data according to the actual situation to improve the accuracy of the assessment;

[0068] In order to better determine the weight values ​​of the risk assessment indicators corresponding to the specific data in the typhoon disaster chain risk assessment data set, it is necessary to first construct an indicator weight analysis model;

[0069] In a preferred embodiment, the process of constructing the indicator weight analysis model includes:

[0070] Obtain target information, a sample set of typhoon disaster chain events, and a preset typhoon disaster chain risk assessment indicator system; wherein the target information points to the overall risk level assessment of the typhoon disaster chain; the sample set of typhoon disaster chain events includes the typhoon disaster chain risk scenarios and corresponding impact results generated when a typhoon occurs;

[0071] Constructing a hierarchical model; wherein the hierarchical model includes a target layer, a criterion layer and a solution layer;

[0072] Based on the target information, the assessment target of the target layer is set as the typhoon disaster chain risk level assessment, and the target layer is obtained after the target setting is completed;

[0073] Based on the typhoon disaster chain risk assessment indicator system, various risk assessment indicators are set in the criterion layer to obtain a criterion layer after the risk assessment indicators are set;

[0074] Based on the typhoon disaster chain event sample set, a typhoon disaster chain risk scenario is set in the solution layer to obtain a solution layer after the scenario setting is completed;

[0075] Constructing a judgment matrix based on the criterion layer after the risk assessment indicators are set;

[0076] The indicator weight analysis model is formed according to the target layer after the target setting is completed, the criterion layer after the risk assessment indicator setting is completed, the solution layer after the scenario setting is completed, and the judgment matrix;

[0077] When it is necessary to explain, the present application constructs the hierarchical structure model by using the Analytic Hierarchy Process (AHP for short); the hierarchical structure model can be constructed by using a data analysis platform such as SPSSPRO;

[0078] Specifically, a hierarchical model is constructed in a preset data analysis platform, wherein the hierarchical model includes a target layer, a criterion layer, and a solution layer;

[0079] Then, considering that the purpose of this application is to evaluate the overall risk level of the typhoon disaster chain, it is necessary to configure the constructed hierarchical model based on this purpose;

[0080] Specifically, it is necessary to first obtain the target information, the target pointed to by the target information is the overall risk level of the typhoon disaster chain, and then use the target information as the target of the target layer in the hierarchical structure model to obtain the target layer after the target setting is completed.

[0081] Then, a sample set of typhoon disaster chain events is obtained, which covers various typhoon disaster chain risk scenarios and corresponding impact results generated when a typhoon occurs. Based on the sample set of typhoon disaster chain events, corresponding typhoon disaster chain risk scenarios are set in the solution layer, such as storm surge and flood disaster scenarios caused by strong typhoons landing in coastal cities, and mudslides and landslides caused by typhoons in mountainous areas. Thus, the construction of the solution layer in the hierarchical model is completed, and the solution layer after the scenario setting is completed is obtained;

[0082] Next, a typhoon disaster chain risk assessment index system is obtained. It should be noted that the typhoon disaster chain risk assessment index system is developed based on existing research results;

[0083] In a preferred embodiment, the typhoon disaster chain risk assessment index system includes primary indicators, secondary indicators and tertiary indicators;

[0084] The first-level indicators include threat factors, vulnerability factors and defense capability factors;

[0085] The secondary indicators include typhoon behavior, population density, infrastructure, economic development and typhoon defense capabilities;

[0086] The three-level indicators include typhoon intensity, typhoon path, precipitation, wind speed, landing location, population distribution, regional area, population size, transportation facilities, energy facilities, water conservancy facilities, terrain conditions, regional industrial structure, economic output, rescue response capabilities, communication system response capabilities, evacuation capabilities and resource dispatch capabilities;

[0087] Specifically, the indicators that need to be input into the criterion layer of the hierarchical model are divided into three levels of indicators, wherein the first-level indicators represent several major categories of risk that are generally summarized in the typhoon disaster chain risk assessment, namely, threat factors (reflecting the threat-related factors brought by the typhoon itself), vulnerability factors (reflecting the characteristics-related factors of the assessed entity that are susceptible to typhoons) and defense capability factors (related to the defense-related factors possessed when dealing with typhoons);

[0088] Specifically, the secondary indicators represent relatively more specific impact aspects that are further subdivided under the major categories of the primary indicators. For example, typhoon behavior belongs to the threat factor, reflecting the characteristics of typhoon activities; population density, infrastructure, and economic development belong to the vulnerability factor, reflecting the vulnerability of the region from the perspectives of population, facilities, and economy respectively; typhoon defense capability clearly belongs to the category of defense capability factor, focusing on reflecting different aspects related to defense;

[0089] Specifically, the third-level indicators represent more detailed, specific, measurable or descriptive indicator elements based on the second-level indicators, such as: typhoon intensity, typhoon path, precipitation, wind speed, landing location, which are more accurate descriptions of the typhoon's own characteristics under the typhoon behavior; population distribution, regional area, population size and other population-related conditions corresponding to population density are further refined; terrain conditions, transportation facilities, energy facilities, and water conservancy facilities are specific descriptions of different types of infrastructure facilities; regional industrial structure and economic aggregate are further subdivided elements for economic development; rescue response capabilities, communication system response capabilities, evacuation capabilities and resource scheduling capabilities are all more detailed manifestations of typhoon defense capabilities from different functional perspectives. They together constitute detailed indicator content that can be specifically input into the criterion layer in the hierarchical model, so as to more accurately conduct typhoon disaster chain risk assessment;

[0090] It should be noted that the various indicators included in the third-level indicators here correspond one-to-one to the risk assessment indicators corresponding to the specific data in the typhoon disaster chain risk assessment data set obtained in step S1 of this application.

[0091] Indicatively, a judgment matrix is ​​constructed based on the criterion layer after completing the risk assessment indicator setting;

[0092] Specifically, by conducting a pairwise comparative analysis of the risk assessment indicators in the criterion layer, their relative importance is determined and expressed in a judgment matrix in numerical form;

[0093] In addition, after obtaining the judgment matrix, it is necessary to perform a consistency test on the judgment matrix and the reverse consistency test. The consistency test is intended to verify whether the judgment matrix is ​​within a reasonable range (usually CR < 0.1 is used as the acceptance standard), so as to determine whether the constructed judgment matrix is ​​usable. The smaller the CR value, the higher the consistency of the result.

[0094]

[0095] In the formula, CI is the consistency index of the judgment matrix; CR is the average random one-time index; n is the number of rows and columns of the judgment matrix; λ max is the maximum eigenvalue of the judgment matrix.

[0096] Finally, the indicator weight analysis model is formed according to the target layer after the target setting is completed, the criterion layer after the risk assessment indicator setting is completed, the solution layer after the scenario setting is completed, and the judgment matrix.

[0097] In a preferred embodiment, the weight analysis of the risk assessment indicators corresponding to each data in the typhoon disaster chain risk assessment data set to obtain the weight value of each risk assessment indicator includes:

[0098] Inputting the typhoon disaster chain risk assessment data set into a preset indicator weight analysis model, so that the indicator weight analysis model assigns weights to the risk assessment indicators corresponding to each data in the typhoon disaster chain risk assessment data set according to a built-in judgment matrix, and obtains a pre-selected weight value for each risk assessment indicator;

[0099] According to the typhoon disaster chain risk assessment data set and the pre-built Bayesian network, a secondary weight distribution is performed on the pre-selected weight values ​​of each risk assessment indicator to obtain a weight value of each risk assessment indicator;

[0100] Specifically, after the indicator weight analysis model is constructed, the typhoon disaster chain risk assessment data set needs to be input into the preset indicator weight analysis model, so that the indicator weight analysis model can assign weights to the risk assessment indicators corresponding to each data in the typhoon disaster chain risk assessment data set according to the built-in judgment matrix, and obtain the pre-selected weight value w of each risk assessment indicator. j ;

[0101] Indicatively, after obtaining the pre-selected weight value w for each risk assessment indicator j After that, it is necessary to perform secondary weight distribution according to the pre-selected weight values ​​of each risk assessment indicator to obtain the weight value of each risk assessment indicator;

[0102] In a preferred embodiment, according to the typhoon disaster chain risk assessment data set and the pre-constructed Bayesian network, a secondary weight distribution is performed on the pre-selected weight values ​​of each risk assessment indicator to obtain the weight value of each risk assessment indicator, including:

[0103] Counting all the node objects in the Bayesian network for characterizing the typhoon disaster chain risk scenario;

[0104] Constructing a normalized matrix according to the data in the typhoon disaster chain risk assessment data set and the node object used to characterize the typhoon disaster chain risk scenario;

[0105] According to the normalized matrix, the entropy value corresponding to each data in the typhoon disaster chain risk assessment data set is calculated;

[0106] According to the entropy value corresponding to each data in the typhoon disaster chain risk assessment data set, a secondary weight distribution is performed on the pre-selected weight value of the risk assessment indicator corresponding to each data to obtain the weight value of each risk assessment indicator;

[0107] Specifically, first, it is necessary to count all the node objects in the Bayesian network that are used to characterize the typhoon disaster chain risk scenario;

[0108] It should be noted that the Bayesian network has been pre-constructed; when constructing it, it is necessary to set various indicators in the typhoon disaster chain risk assessment indicator system and various typhoon disaster chain risk scenarios in the typhoon disaster chain event sample set as various node objects in the Bayesian network to be constructed; then, based on the existing research results, the internal relationship between the nodes is deeply analyzed, and then a directed acyclic graph is constructed, and the node objects in the directed acyclic graph are assigned corresponding prior probabilities, thereby generating the pre-constructed Bayesian network described in this application;

[0109] It should be noted that this application uses the Entropy Weight Method (EWM) to pre-select the weight value w of the risk assessment indicator corresponding to each data j Perform secondary weight distribution;

[0110] Specifically, a normalized matrix p is constructed based on the n node objects obtained by statistics for characterizing the typhoon disaster chain risk scenario and the m data items in the typhoon disaster chain risk assessment data set. ij ;

[0111] Then according to the normalized matrix p ij , calculate the entropy value e corresponding to each data in the typhoon disaster chain risk assessment data set j , the specific calculation formula is as follows:

[0112]

[0113] In the formula,

[0114] Then, according to the entropy value e corresponding to each data in the typhoon disaster chain risk assessment data set j , the pre-selected weight value w of the risk assessment indicator corresponding to each data j Perform secondary weight distribution to obtain the weight value A of each risk assessment indicator j , the specific calculation formula is as follows:

[0115]

[0116] S3. According to the weight values ​​of the risk assessment indicators, the prior probabilities of the nodes in the pre-constructed Bayesian network are adjusted to obtain an adjusted Bayesian network; wherein the risk assessment indicators correspond one to one to the nodes in the Bayesian network;

[0117] Specifically, according to the weight value A of each risk assessment indicator j , determine the final evaluation weight vector W, and adjust the prior probabilities of the nodes in the pre-constructed Bayesian network according to the evaluation weight vector W to obtain an adjusted Bayesian network.

[0118] S4, inputting the typhoon disaster chain risk assessment data set into the adjusted Bayesian network, so that the adjusted Bayesian network outputs the typhoon disaster chain risk level of the area to be assessed;

[0119] Specifically, the typhoon disaster chain risk assessment data set is input into the adjusted Bayesian network, so that the adjusted Bayesian network outputs the typhoon disaster chain risk level R of the area to be assessed.

[0120] In a preferred embodiment, the typhoon disaster chain risk assessment method further includes: selecting an emergency plan for the area to be assessed from a preset comprehensive emergency plan system according to the typhoon disaster chain risk level of the area to be assessed;

[0121] According to the emergency plan, make preventive deployment for the area to be assessed;

[0122] Specifically, it is assumed that the area to be evaluated is a coastal city A. The typhoon disaster chain risk assessment method of the present application obtains that the typhoon disaster chain risk level of the area to be evaluated, City A, is level V (the level can be set to level I, level II, level III, level IV and level V according to actual needs, where level I is the lowest level and level V is the highest level).

[0123] Then, in the comprehensive emergency plan system that has been pre-edited, the emergency plans applicable to level V are screened out, so as to carry out preventive deployment for the area to be evaluated based on the screened emergency plans.

[0124] See also Figure 2 , is a typhoon disaster chain risk assessment device provided by an embodiment of the present invention, comprising: a data set acquisition module, a weight value calculation module, a Bayesian network adjustment module and a typhoon disaster chain risk level determination module;

[0125] The data set acquisition module is used to acquire a typhoon disaster chain risk assessment data set for the area to be assessed; wherein the typhoon disaster chain risk assessment data set includes a historical typhoon disaster data set, an infrastructure data set, an economic development data set, a population density data set, and a typhoon defense plan set;

[0126] The weight value calculation module is used to perform weight analysis on the risk assessment indicators corresponding to each data in the typhoon disaster chain risk assessment data set to obtain the weight value of each risk assessment indicator;

[0127] The Bayesian network adjustment module is used to adjust the prior probability of the nodes in the pre-constructed Bayesian network according to the weight value of each risk assessment indicator to obtain an adjusted Bayesian network; wherein the risk assessment indicators correspond one to one to the nodes in the Bayesian network;

[0128] The typhoon disaster chain risk level determination module is used to input the typhoon disaster chain risk assessment data set into the adjusted Bayesian network so that the adjusted Bayesian network outputs the typhoon disaster chain risk level of the area to be assessed.

[0129] See also Figure 3 ,In a preferred embodiment, the typhoon disaster chain risk assessment device further includes: an emergency plan determination module;

[0130] The emergency plan determination module is used to select the emergency plan for the area to be evaluated from a preset comprehensive emergency plan system according to the typhoon disaster chain risk level of the area to be evaluated; and to make preventive deployment for the area to be evaluated according to the emergency plan.

[0131] See also Figure 4 , a certain embodiment of the present application further provides a terminal device, including:

[0132] one or more processors;

[0133] A memory, coupled to the processor, for storing one or more programs;

[0134] When the one or more programs are executed by the one or more processors, the one or more processors implement the typhoon disaster chain risk assessment method as described above.

[0135] The processor is used to control the overall operation of the terminal device to complete all or part of the steps of the above-mentioned typhoon disaster chain risk assessment method. The memory is used to store various types of data to support the operation of the terminal device, and these data may include, for example, instructions for any application or method used to operate on the terminal device, and data related to the application. The memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, disk or optical disk.

[0136] In an exemplary embodiment, the terminal device can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the typhoon disaster chain risk assessment method as described in any of the above embodiments and achieve the same technical effect as the above method.

[0137] In another exemplary embodiment, a computer-readable storage medium including a computer program is also provided, and when the computer program is executed by a processor, the steps of the typhoon disaster chain risk assessment method as described in any of the above embodiments are implemented. For example, the computer-readable storage medium can be the above-mentioned memory including the computer program, and the above-mentioned computer program can be executed by the processor of the terminal device to complete the typhoon disaster chain risk assessment method as described in any of the above embodiments, and achieve the technical effect consistent with the above method.

[0138] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A typhoon disaster chain risk assessment method, characterized in that: include: Acquire a typhoon disaster chain risk assessment dataset for the area to be assessed; wherein the typhoon disaster chain risk assessment dataset includes a historical typhoon disaster dataset, an infrastructure dataset, an economic development dataset, a population density data, and a typhoon defense plan set; Performing weight analysis on the risk assessment indicators corresponding to each data in the typhoon disaster chain risk assessment data set to obtain a weight value of each risk assessment indicator; According to the weight values ​​of the risk assessment indicators, the prior probabilities of the nodes in the pre-constructed Bayesian network are adjusted to obtain an adjusted Bayesian network; wherein the risk assessment indicators correspond one to one to the nodes in the Bayesian network; The typhoon disaster chain risk assessment data set is input into the adjusted Bayesian network, so that the adjusted Bayesian network outputs the typhoon disaster chain risk level of the area to be assessed.

2. The typhoon disaster chain risk assessment method according to claim 1, characterized in that: The weight analysis of the risk assessment indicators corresponding to each data in the typhoon disaster chain risk assessment data set to obtain the weight value of each risk assessment indicator includes: Inputting the typhoon disaster chain risk assessment data set into a preset indicator weight analysis model, so that the indicator weight analysis model assigns weights to the risk assessment indicators corresponding to each data in the typhoon disaster chain risk assessment data set according to a built-in judgment matrix, and obtains a pre-selected weight value for each risk assessment indicator; According to the typhoon disaster chain risk assessment data set and the pre-constructed Bayesian network, a secondary weight distribution is performed on the pre-selected weight values ​​of the risk assessment indicators to obtain the weight values ​​of the risk assessment indicators.

3. The typhoon disaster chain risk assessment method according to claim 1, characterized in that: The construction process of the indicator weight analysis model includes: Obtain target information, a sample set of typhoon disaster chain events, and a preset typhoon disaster chain risk assessment indicator system; wherein the target information points to the overall risk level assessment of the typhoon disaster chain; the sample set of typhoon disaster chain events includes the typhoon disaster chain risk scenarios and corresponding impact results generated when a typhoon occurs; Constructing a hierarchical model; wherein the hierarchical model includes a target layer, a criterion layer and a solution layer; Based on the target information, the assessment target of the target layer is set as the typhoon disaster chain risk level assessment, and the target layer is obtained after the target setting is completed; Based on the typhoon disaster chain risk assessment indicator system, various risk assessment indicators are set in the criterion layer to obtain a criterion layer after the risk assessment indicators are set; Based on the typhoon disaster chain event sample set, a typhoon disaster chain risk scenario is set in the solution layer to obtain a solution layer after the scenario setting is completed; Constructing a judgment matrix based on the criterion layer after the risk assessment indicators are set; The indicator weight analysis model is formed according to the target layer after the target setting is completed, the criterion layer after the risk assessment indicator setting is completed, the solution layer after the scenario setting is completed, and the judgment matrix.

4. The typhoon disaster chain risk assessment method according to claim 3, characterized in that: The typhoon disaster chain risk assessment indicator system includes primary indicators, secondary indicators and tertiary indicators; The first-level indicators include threat factors, vulnerability factors and defense capability factors; The secondary indicators include typhoon behavior, population density, infrastructure, economic development and typhoon defense capabilities; The three-level indicators include typhoon intensity, typhoon path, precipitation, wind speed, landing location, population distribution, regional area, population size, transportation facilities, energy facilities, water conservancy facilities, terrain conditions, regional industrial structure, economic output, rescue response capability, communication system response capability, evacuation capability and resource dispatch capability.

5. The typhoon disaster chain risk assessment method according to claim 2, characterized in that: According to the typhoon disaster chain risk assessment data set and the pre-built Bayesian network, a secondary weight distribution is performed on the pre-selected weight values ​​of each risk assessment indicator to obtain the weight value of each risk assessment indicator, including: Counting all the node objects in the Bayesian network for characterizing the typhoon disaster chain risk scenario; Constructing a normalized matrix according to the data in the typhoon disaster chain risk assessment data set and the node object used to characterize the typhoon disaster chain risk scenario; According to the normalized matrix, the entropy value corresponding to each data in the typhoon disaster chain risk assessment data set is calculated; According to the entropy value corresponding to each data in the typhoon disaster chain risk assessment data set, the pre-selected weight value of the risk assessment indicator corresponding to each data is secondary weighted, so as to obtain the weight value of each risk assessment indicator.

6. The typhoon disaster chain risk assessment method according to claim 1, characterized in that: Also includes: According to the typhoon disaster chain risk level of the area to be assessed, the emergency plan of the area to be assessed is screened in the preset comprehensive emergency plan system; According to the emergency plan, preventive deployment is carried out in the area to be assessed.

7. A typhoon disaster chain risk assessment device, characterized in that: include: Data set acquisition module, weight value calculation module, Bayesian network adjustment module and typhoon disaster chain risk level determination module; The data set acquisition module is used to acquire a typhoon disaster chain risk assessment data set for the area to be assessed; wherein the typhoon disaster chain risk assessment data set includes a historical typhoon disaster data set, an infrastructure data set, an economic development data set, a population density data set, and a typhoon defense plan set; The weight value calculation module is used to perform weight analysis on the risk assessment indicators corresponding to each data in the typhoon disaster chain risk assessment data set to obtain the weight value of each risk assessment indicator; The Bayesian network adjustment module is used to adjust the prior probability of the nodes in the pre-constructed Bayesian network according to the weight value of each risk assessment indicator to obtain an adjusted Bayesian network; wherein the risk assessment indicators correspond one to one to the nodes in the Bayesian network; The typhoon disaster chain risk level determination module is used to input the typhoon disaster chain risk assessment data set into the adjusted Bayesian network so that the adjusted Bayesian network outputs the typhoon disaster chain risk level of the area to be assessed.

8. The typhoon disaster chain risk assessment device according to claim 7, characterized in that: Also includes: Emergency plan determination module; The emergency plan determination module is used to select the emergency plan for the area to be evaluated from a preset comprehensive emergency plan system according to the typhoon disaster chain risk level of the area to be evaluated; and to make preventive deployment for the area to be evaluated according to the emergency plan.

9. A terminal device, characterized in that: include: one or more processors; A memory, coupled to the processor, for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the typhoon disaster chain risk assessment method as described in any one of claims 1-6.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the typhoon disaster chain risk assessment method according to any one of claims 1 to 6 is implemented.

Images