Methods, devices, equipment and media for assessing economic losses caused by earthquake damage to buildings

Abstract

The present invention provides an evaluation method, device, equipment and medium for economic losses of earthquake damage to buildings, the evaluation method for economic losses of earthquake damage to buildings comprising: obtaining remote sensing image data of a disaster-damaged area; inputting the remote sensing image data into a preliminary disaster-damage evaluation model to obtain disaster-damage result data in the disaster-damaged area; obtaining economic value distribution data in the disaster-damaged area based on the remote sensing image data, wherein the economic value distribution data is based on multiple influencing factors with contribution weights to the location value of the building, and the multiple influencing factors are comprehensively calculated to obtain the estimated value of the building located in the disaster-damaged area; the disaster-damage result data and the economic value distribution data are processed to generate an evaluation result of economic losses of earthquake damage to buildings. The present invention can effectively improve the problem of low accuracy of evaluation results of economic losses of earthquake damage to buildings.

Description

Technical Field

[0001] The present invention relates to the field of earthquake disaster assessment, and in particular to an assessment method, device, equipment and medium for economic loss of earthquake damage to buildings. Background Art

[0002] After a typical natural disaster such as an earthquake, rapid detection and assessment of building disaster losses is crucial to effective disaster emergency management. Detection and assessment of the extent of disaster losses helps us make decisions on the priority of dispatching emergency teams and materials, and achieving rapid and effective estimation of the extent of building disaster losses is also a necessary step in post-disaster recovery and reconstruction.

[0003] With the software and hardware support of the current 3S space technology of geographic information system (GIS), remote sensing (RS) and global positioning system (GPS), how to accurately assess the economic losses caused by the reduction or loss of the value of buildings after earthquake disasters, and achieve reasonable and refined assessment of the economic losses of buildings, can quickly and effectively judge the amount of property losses and loss distribution of people in the disaster-stricken areas, which is of great significance for disaster management and emergency response. It can also provide a basis for emergency decision-making when people face earthquake disasters in the future, so as to take appropriate emergency rescue measures and material distribution for the severely affected areas with serious building losses, so as to effectively minimize the casualties and economic losses caused by earthquake disasters.

[0004] At present, conventional methods for the refined economic loss assessment of major disaster-sustaining objects such as buildings mainly rely on manual on-site inspections or field surveys. The investigation cycle is long and consumes a lot of manpower and material resources. In addition, manual investigation methods cannot meet the timeliness and effectiveness requirements of post-earthquake rescue and assessment work. Summary of the invention

[0005] In view of the above-mentioned shortcomings of the prior art, the present invention provides a method, device, equipment and medium for assessing economic losses caused by earthquake damage to buildings, so as to solve the problem of low accuracy of assessment results of economic losses caused by earthquake damage to buildings in the prior art.

[0006] To achieve the above-mentioned and other related purposes, the present invention provides a method for assessing economic losses caused by earthquake damage to buildings, which comprises:

[0007] Obtain remote sensing image data of the disaster-damaged area;

[0008] Inputting the remote sensing image data into a preliminary disaster damage assessment model to obtain disaster damage result data in the disaster damage area;

[0009] According to the remote sensing image data, the economic value distribution data in the disaster-damaged area is obtained, wherein the economic value distribution data is based on a plurality of influencing factors having contribution weights to the location value of the building, and the plurality of influencing factors are comprehensively calculated to obtain the estimated value of the building located in the disaster-damaged area;

[0010] The disaster damage result data and the economic value distribution data are processed to generate an assessment result of the economic loss of the building caused by the earthquake.

[0011] The present invention also provides a device for assessing economic losses caused by earthquake damage to buildings, comprising:

[0012] A data acquisition module is used to obtain remote sensing image data of the disaster-damaged area;

[0013] A disaster damage result data generation module is used to input the remote sensing image data into a preliminary disaster damage assessment model to obtain disaster damage result data in the disaster damage area;

[0014] An economic value distribution data generation module is configured to obtain economic value distribution data in the disaster-damaged area based on the remote sensing image data, wherein the economic value distribution data is based on a plurality of influencing factors having contribution weights to the location value of the building, and the plurality of influencing factors are comprehensively calculated to obtain an estimated value of the building located in the disaster-damaged area;

[0015] The evaluation module is used to analyze the disaster damage result data and the economic value distribution data to generate an evaluation result of the economic loss of the building caused by the earthquake.

[0016] The present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned method for assessing economic losses caused by earthquake damage to buildings are implemented.

[0017] The present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the above-mentioned method for assessing economic losses caused by earthquake damage to buildings are implemented.

[0018] As described above, the present invention provides a method, device, equipment and medium for assessing the economic losses of earthquake damage to buildings. Combined with remote sensing image data of the disaster-damaged area, the method analyzes and obtains the location traffic accessibility data, the location value contribution value data based on road density analysis, and the disaster damage result data related to the location value contribution value data based on administrative divisions, and calculates the economic value of buildings in different locations based on spatial overlay analysis. By constructing a building disaster economic loss model to calculate the economic loss assessment results, an effective assessment of the economic losses of earthquake damage to buildings in the disaster-damaged area is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 A schematic diagram of an application environment of a method for assessing economic losses caused by earthquake damage to buildings in one embodiment of the present invention;

[0021] Figure 2 It is a flow chart of a method for assessing economic losses caused by earthquake damage to buildings in one embodiment of the present invention;

[0022] Figure 3 Schematic diagram of the flow of step S20 in the method for assessing economic losses caused by earthquake damage to buildings in one embodiment of the present invention;

[0023] Figure 4 It is a schematic diagram of spatial superposition analysis in a method for assessing economic losses caused by earthquake damage to buildings in one embodiment of the present invention;

[0024] Figure 5 It is a schematic diagram of modules in a device for assessing economic losses caused by earthquake damage to buildings in one embodiment of the present invention;

[0025] Figure 6 FIG. 1 is a schematic diagram of a computer device according to an embodiment of the present invention.

[0026] Component number description

[0027] 100. Apparatus for assessing economic losses caused by earthquake damage to buildings; 101. Electronic equipment; 102. Memory; 103. Processor;

[0028] 200. Data acquisition module;

[0029] 300. disaster damage result data generation module; 301. disaster damage result data;

[0030] 400. Economic value distribution data generation module;

[0031] 401. Economic value distribution data;

[0032] 410. Regional transportation accessibility data;

[0033] 420. Location value contribution data based on road density analysis;

[0034] 430. Location value contribution data based on administrative divisions;

[0035] 500. Evaluation module; 501. Evaluation result. DETAILED DESCRIPTION

[0036] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0037] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0038] See also Figure 1 As shown, the method for assessing the economic losses of earthquake damage to buildings provided in this embodiment, its execution subject includes but is not limited to at least one of the electronic devices such as the server and the terminal that can be configured to execute the method provided in the embodiment of the present application. In other words, the method for assessing the economic losses of earthquake damage to buildings can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be 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, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0039] See also Figure 2 In one embodiment, a method for assessing economic losses caused by earthquake damage to buildings is provided. Figure 1 The server in the example is used as an example to illustrate the following steps:

[0040] S10. Acquire remote sensing image data of the disaster-damaged area.

[0041] It is understandable that the disaster-damaged area can be a large area, such as part of a city; or the disaster-damaged area can be a small area, such as a community in a county. Specifically, the buildings that need to be assessed for earthquake economic losses are located in the disaster-damaged area. Therefore, in the process of assessing the earthquake economic losses of buildings in the disaster-damaged area, it is first allowed to obtain remote sensing image data of the disaster-damaged area.

[0042] In one embodiment, in the process of acquiring remote sensing image data of the disaster-damaged area, satellite remote sensing image data acquired with the support of software and hardware based on the current geographic information system (GIS), remote sensing (RS), global positioning system (GPS) and 3S space technology can be allowed. Or it can be based on the satellite remote sensing image data disclosed by the relevant disaster-damaged departments after the earthquake. In one embodiment, high-resolution satellite remote sensing image data in the disaster-damaged area after matching is acquired from the relevant disaster-damaged departments, and the high-resolution satellite remote sensing image data is analyzed and processed to obtain remote sensing image data of the disaster-damaged area before and after the earthquake. Specifically, it is allowed to select control points with the same name such as road intersections and building edges through ENVI remote sensing digital image processing software, and use the ENVI geometric polynomial registration tool to accurately register the images before and after the earthquake to generate registered remote sensing image data before and after the earthquake.

[0043] In one embodiment, in the process of acquiring remote sensing image data of the disaster-damaged area, it is allowed to automatically acquire a number of initial satellite remote sensing data of different resolutions and different periods of the disaster-damaged area according to a preset time. The initial satellite remote sensing data can be unprocessed satellite images and unprocessed spectral remote sensing information. The initial satellite remote sensing data before the disaster, before the disaster, during the disaster, and after the disaster can be collected to obtain remote sensing image data of the disaster-damaged area. The initial satellite remote sensing data represents unprocessed satellite remote sensing data.

[0044] Specifically, after obtaining the remote sensing image data of the disaster-damaged area, it is allowed to make a preliminary location division of the disaster-damaged area through the remote sensing image data. For example, it is allowed to divide the disaster-damaged area according to the administrative area where the building where the earthquake economic loss assessment is required is located, and the disaster-damaged area may include urban areas, rural areas, industrial areas, and non-aggregated areas. Or it is allowed to divide the building where the earthquake economic loss assessment is required is located according to the distance from the earthquake source. For example, the disaster-damaged area may include a 1-2 km area, a 2-4 km area, a 4-6 km area, and a 6-10 km area. And it is allowed to divide the disaster-damaged area according to the geographical location where the building where the earthquake economic loss assessment is required is located, and the disaster-damaged area may include a river area, a mountain area, and a plain area. However, it is not limited to this, and the location division of the disaster-damaged area can be determined according to actual needs.

[0045] S20, obtaining disaster damage result data in the disaster damage area according to the remote sensing image data, wherein the disaster damage result data may include the damaged area of ​​buildings in the disaster damage area, the number of building types in the disaster damage area, the number of damage levels, and the number of disaster area location divisions.

[0046] See also Figure 3 As shown, the step of obtaining the disaster damage result data in the disaster damage area according to the remote sensing image data includes:

[0047] S201. Extract the vector outlines of the buildings in the disaster-damaged area according to the remote sensing image data. In the process of extracting the vector outlines of the buildings, any automatic extraction algorithm in the prior art can be relied upon. However, it is not limited thereto, and those skilled in the art can make a selection according to the specific application scenario. It should be noted that in the process of extracting the vector outlines of the buildings in the disaster-damaged area, the buildings can be all the buildings in the disaster-damaged area or a specific building in the disaster-damaged area.

[0048] S202. Calculate corresponding preset feature parameters according to the vector outline of the building to form a target feature parameter set. For different buildings, the extracted feature parameters may also be different. At the same time, for the same building, the extracted feature parameters may also be different. Of course, the same category of feature parameters can also be extracted for all buildings. Those skilled in the art can select the feature parameters to be extracted according to actual needs, and this application does not impose any restrictions on this. In order to reflect the degree of damage to the building before and after the earthquake, more feature parameters that can characterize the changes in appearance can be extracted, such as calculating the difference in area characteristics before and after the earthquake.

[0049] Specifically, in one embodiment, in the process of extracting characteristic parameters of a building, it is allowed to automatically extract according to the characteristic calculation formula in the prior art, and the extracted characteristic parameters of the building to be evaluated before and after the earthquake constitute the target parameter set. Among them, if there is only one characteristic parameter, it is also allowed to be input into the preliminary disaster damage assessment model, and the output result of the preliminary disaster damage assessment model is obtained.

[0050] S203, input the target parameter set into the preliminary disaster damage assessment model to obtain the disaster damage result data. The preliminary disaster damage assessment model may be obtained by training a feature parameter set using a machine learning algorithm, and the feature parameter set is composed of preset feature parameters of each building sample selected from a sample training set containing multiple building samples with different degrees of damage using a feature selection algorithm. For example, the feature parameters used to train the preliminary disaster damage assessment model may be selected using an optimal first search algorithm, and then the selected feature parameters may be imported into an SVM machine learning classifier for training.

[0051] The output result is obtained by inputting the target parameter set into the preliminary disaster damage assessment model. The output result may include the number of building types, the number of damage levels and the number of disaster area location divisions located in the disaster area. It can be understood that the number of types of buildings located in the disaster area may include residential buildings, public buildings, industrial buildings and agricultural buildings, etc., the number of damage levels may include multiple levels such as collapse, serious damage, general damage and intact, and the number of disaster area location divisions may include multiple levels such as primary location, secondary location and tertiary location. Therefore, in a certain disaster area, its buildings may be allowed to correspond to multiple labels such as the number of building types, the number of damage levels and the number of disaster area location divisions.

[0052] S30: Obtaining economic value distribution data in the disaster-damaged area based on the remote sensing image data.

[0053] It can be understood that the economic value distribution data is based on multiple influencing factors with contribution weights to the location value of the building, and the multiple influencing factors are comprehensively calculated to obtain the estimated value of the building located in the disaster-damaged area.

[0054] In one embodiment, the corresponding influencing factors can be directly obtained according to the remote sensing image data. The influencing factors may include: basic geographic data such as provincial (municipal) administrative boundaries, district and county administrative boundaries, township administrative boundaries, provincial capital name, city name, district and county name, township name, village name, highway, railway, river, lake, reservoir, railway station, bus station, airport, port, tourist attractions, important targets, etc. The acquisition of the influencing factors may be directly obtained through existing professional databases. At the same time, after obtaining the remote sensing image data, a road intersection data layer may be generated according to the road intersection data.

[0055] In one embodiment, the economic value distribution data includes location traffic accessibility data and location value contribution data. Among them, the location traffic accessibility data represents the influence scores of the main roads and / or secondary roads located within the disaster-damaged area on the buildings, and the location value contribution data represents the contribution values of relevant influencing factors within different locations to the location value of the buildings. Specifically, the location traffic accessibility data is calculated based on buffer analysis. Among them, buffer analysis is an important means of measuring spatial features and is also a commonly used method in spatial analysis of geographic information systems. Buffer analysis mainly studies an analysis method for realizing horizontal information expansion of spatial data by automatically establishing buffer polygon entities with a specific width range around the point, line, and surface entities in the database. From the perspective of spatial transformation, the buffer analysis model is to transform the distribution of point, line, and surface features into the extended distance distribution of features, so that the value of each point on the map represents the distance from this point to the nearest certain feature. In engineering planning and design, the buffer is actually an image range of a specific feature target in spatial analysis. It should be noted that the buffer is a scale representation of the influence range and service range of a geographic space target and is also a dependent variable that changes with the form of the research element. Therefore, in one embodiment, it is allowed to define object A, and the buffer of object A can be defined as: P = {x / d(x,A) < r}, where r is the neighborhood radius or the condition for establishing this buffer, and d generally refers to the Euclidean distance or other distances.

[0056] In one embodiment, when performing buffer analysis, it is allowed to implement the variation law of the influence degree of the analysis subject on the surrounding space according to different analysis models.

[0057] As an example, in one analysis model, when the influence degree F of the core subject on the surrounding space i decays linearly with the increase of distance, the model form can include: F i = f0(1 - r i ), r i = d i / d x , 0 ≤ r i ≤ 1. Or, in one analysis model, when the influence degree F of the core subject on the surrounding space i decays quadratically with the increase of distance, the model form can include: F i = f0(1 - r i ) 2 , r i = d i / d x , 0 ≤ r i ≤ 1. And, in one analysis model, when the influence degree F of the core subject on the surrounding space iWhen the decay is exponential with increasing distance, the model form may include: Among them, in the above analysis model, F i Represents the actual influence of the core subject on the analyzed object; F0 represents the comprehensive scale index of the core subject itself; d i Characterizes the actual distance of the object to be analyzed from the subject; d x Characterizes the maximum influence distance of the main object on the object to be analyzed; r i Characterizes the ratio between the actual distance and the maximum distance.

[0058] It should be noted that in the analysis model of buffer generation, the influence changes continuously with distance, that is, for each distance d i They all have a different influence F i In actual application, it is allowed to i According to the actual situation, it is divided into several typical levels, and then according to F i Determine i The continuously changing buffer is converted into a phased buffer, that is, an average impact F is taken at each level. i As the influence score of the factor at this level. Finally, the buffer maps at all levels are superimposed to obtain the influence factor map of the subject on the neighboring objects.

[0059] In one embodiment, since the accessibility of the main road decreases rapidly in an exponential manner from the road centerline, the analysis model that can be used is: Specifically, according to the size of the disaster damage area to be assessed, the maximum impact distances of the main roads and secondary roads within the disaster damage area can be set to 500m and 300m respectively, but it is not limited to this and can be determined according to actual needs. i It is divided into multiple impact levels, for example, the impact level F i It can include 5 levels, and the 5 levels include 1, 25, 50, 75 and 100 respectively. It should be noted that F i The larger the value, the higher the impact, and 0≤F i ≤F0, where F0 represents the highest weight of the main road and the secondary road, and the value of F0 is 100. Then, for d i The calculation of numerical values ​​can be performed through the following model:

[0060] as well as

[0061] Among them, d i1 represents the actual distance between the main road and the building to be evaluated, and d i2Represents the actual distance between the secondary road and the building to be evaluated.

[0062] In one embodiment, the weights of road accessibility at each level F i ,d i1 and i2 The correspondence between them can be allowed by F i -d i1 -d i2 For example, for the impact level F i There are five levels, which are respectively i1 and i2 The corresponding relationships are: 1-500-300, 25-151-91, 50-75-45, 75-31-19 and 100-0-0. Therefore, it is allowed to make multiple buffer zones of 31m, 75m, 151m and 500m for the main roads, and assign the impact score Fi to the corresponding buffer zone to obtain the impact factor map of the main roads. Similarly, it is allowed to make multiple buffer zones of 19m, 45m, 91m and 300m for the secondary roads, and assign the impact score Fi to the corresponding buffer zone to obtain the impact factor map of the secondary roads.

[0063] In one embodiment, the influence factor graph of the main road and the influence factor graph of the secondary road are superimposed to obtain a comprehensive influence graph of roads at all levels, namely, a road accessibility factor graph. Specifically, for the road accessibility factor graph, the location traffic accessibility value of each unit in the graph is set as: F i =max(F i1 , F i2 ) to obtain the road accessibility factor weight map, where F i is the value of the location traffic accessibility, F i1 is the impact score of the main road, F i2 is the impact score of the secondary road. Therefore, for the location traffic accessibility data, it is allowed to express it through the road accessibility factor weight map.

[0064] In one embodiment, the location value contribution data may include location value contribution data based on road density analysis and location value contribution data based on administrative divisions. The location value contribution data based on road density analysis may include a weighted contribution layer of road intersections to the economic location of buildings and a weighted contribution layer of road line data to the economic location of buildings. The location value contribution data based on administrative divisions may include a weighted contribution layer of administrative divisions to the economic location of buildings.

[0065] In one embodiment, density analysis can be used to calculate the aggregation of spatial point / line data within a specified search radius, and quantify the spatial data in the form of points / lines to produce a continuous density surface. Density analysis includes three forms: kernel density, line density and point density, among which line density and point density belong to simple density. In the process of kernel density analysis, the elements in the search area have different weights, and the elements close to the center of the search area have larger weights. As the distance from the search center increases, the weight of the elements decreases. In the process of simple density analysis, the elements in the search area have the same weight, regardless of the distance from the search center. Therefore, it is allowed to perform kernel density analysis on the obtained road intersection data layer, and obtain the weight contribution layer of the road intersection to the economic location of the building. In the process of obtaining the location value contribution value data based on road density analysis, it is allowed to perform kernel density analysis on the branch intersection point data and kernel density analysis on the road line data to obtain the location value contribution value data based on road density analysis.

[0066] In one embodiment, since the value contribution of administrative divisions to buildings is obvious, the location value contribution data based on administrative divisions may include a weight contribution layer of administrative divisions to the economic location of buildings. Based on the relevant data of administrative divisions, it is allowed to determine the weight of the influence of different administrative divisions on the economic location of buildings according to factors such as the political and commercial prosperity of different administrative regions, and obtain the location value contribution data of administrative divisions.

[0067] See also Figure 4As shown, in one embodiment, after obtaining the location traffic accessibility data 410, the location value contribution data 420 based on road density analysis, and the location value contribution data 430 based on administrative division, it is allowed to perform overlay analysis on the location traffic accessibility data 410, the location value contribution data 420 based on road density analysis, and the location value contribution data 430 based on administrative division. Specifically, the overlay analysis is to overlay the data layers composed of thematic layers related to the location value of the building to form a new data layer. The new data layer encompasses the element attributes of two or more original layers. While generating new spatial relationships, the overlay analysis constructs the connection between the attributes of multiple input data layers, forming a new attribute relationship about the location value of the building in the study area. Among them, the element layers input by the overlay analysis are data with the same reference plane and the same coordinate system in the same region. While comparing spatial relationships, the overlay analysis also takes into account the comparison of attribute relationships, so it is the most effective analysis method in the geographic information system. For example, by overlaying the location traffic accessibility data 410, the location value contribution data 420 based on road density analysis, and the location value contribution data 430 based on administrative divisions, a new data layer containing the location characteristics of buildings is obtained, and the location value of buildings in the corresponding area can be analyzed accordingly.

[0068] In one embodiment, during the overlay analysis, it is allowed to comprehensively consider various factors affecting the economic location of buildings by using raster data overlay analysis as the main method and vector data overlay analysis as the auxiliary method. Among them, raster data is the most classic spatial data organization form, and the attribute information implied in its spatial information is relatively clear. The overlay analysis of raster data can be understood as an operation on the attribute values ​​of corresponding pixels at different levels. The following formula is the mathematical expression of this operation:

[0069] E=f(x1,x2,…,x n ), where x1, x2, …, x n is the attribute value of the corresponding pixel on the 1st to the nth layer, the f function is the relationship between the user demand and the pixel attributes on each layer, and E is the attribute value of the corresponding pixel on the result data layer. The output of the overlay analysis may be in the form of: ① the logical operation result of the pixel attributes of each layer; ② the arithmetic operation result of the pixel attributes of each layer; ③ the statistical characteristic value of the pixel attributes of each layer; ④ other model operation results.

[0070] Therefore, the overlay analysis is used to compound the multi-layer information that affects the economic location of the building in the above steps, and the economic location distribution adopts the weighted arithmetic operation results of each layer of attribute data. By assigning different weights to each layer of influencing factor data layer, the comprehensive consideration of influencing factors includes location traffic accessibility data, location value contribution value data based on road density analysis, and location value contribution value data based on administrative divisions.

[0071] S40, overlay and analyze the disaster damage result data 301 and the economic value distribution data 401 to generate the building earthquake economic loss assessment result 501. In the process of generating the building earthquake economic loss assessment result, it is allowed to construct a building disaster economic loss model to calculate the economic loss assessment result.

[0072] The method for calculating the economic loss assessment result includes:

[0073] Among them, L represents the economic loss assessment result, N i Represents the number of building types, N j Characterizes the number of damage levels, N k represents the number of disaster area location divisions, A(i,j,k) represents the number of buildings with damage level j in area k, B(i,j,k) represents the average area of ​​buildings with damage level j in area k, and C(i,k) represents the average price of buildings with damage level j in area k.

[0074] It can be seen that in the above scheme, the location traffic accessibility data 410, the location value contribution value data 420 based on the road density analysis, and the location value contribution value data 430 based on the administrative division are obtained in combination with the image analysis results, and the economic value of buildings in different locations is calculated based on the spatial overlay analysis. By constructing a building disaster economic loss model to calculate the economic loss assessment results, an effective assessment of the economic losses of earthquake damage to buildings in the disaster-damaged area is achieved.

[0075] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0076] In one embodiment, an evaluation device 100 for economic losses caused by earthquake damage to buildings is provided. The evaluation device 100 for economic losses caused by earthquake damage to buildings corresponds one-to-one to the evaluation method for economic losses caused by earthquake damage to buildings in the above-mentioned embodiment.

[0077] See also Figure 6As shown, the building earthquake economic loss assessment device 100 includes a data acquisition module 200, a disaster loss result data generation module 300, an economic value distribution data generation module 400, and an assessment module 500. The module referred to in the present invention refers to a series of computer program segments that can be executed by a processor and can complete fixed functions, which are stored in a memory.

[0078] In one embodiment, the data acquisition module 200 acquires remote sensing image data of the disaster-damaged area. In the process of evaluating the economic losses of buildings in the disaster-damaged area due to earthquake damage, it is first allowed to acquire remote sensing image data of the disaster-damaged area. Among them, in the process of acquiring remote sensing image data of the disaster-damaged area, satellite remote sensing image data acquired with the support of software and hardware based on the current geographic information system (GIS), remote sensing (RS), global positioning system (GPS) and 3S space technology can be allowed. Or it is based on the satellite remote sensing image data disclosed by the relevant disaster-damaged department after the earthquake. In one embodiment, high-resolution satellite remote sensing image data in the disaster-damaged area after matching is acquired from the relevant disaster-damaged department, and the high-resolution satellite remote sensing image data is analyzed and processed to acquire remote sensing image data of the disaster-damaged area before and after the earthquake. Specifically, it is allowed to select control points with the same name such as road intersections and building edges through ENVI remote sensing digital image processing software, and use ENVI geometric polynomial registration tool to accurately register the images before and after the earthquake, and generate registered remote sensing image data before and after the earthquake.

[0079] Specifically, after obtaining the remote sensing image data of the disaster-damaged area, it is allowed to make a preliminary location division of the disaster-damaged area through the remote sensing image data. For example, it is allowed to divide the disaster-damaged area according to the administrative area where the building where the earthquake economic loss assessment is required is located, and the disaster-damaged area may include urban areas, rural areas, industrial areas, and non-aggregated areas. Or it is allowed to divide the building where the earthquake economic loss assessment is required is located according to the distance from the earthquake source. For example, the disaster-damaged area may include a 1-2 km area, a 2-4 km area, a 4-6 km area, and a 6-10 km area. And it is allowed to divide the disaster-damaged area according to the geographical location where the building where the earthquake economic loss assessment is required is located, and the disaster-damaged area may include a river area, a mountain area, and a plain area. However, it is not limited to this, and the location division of the disaster-damaged area can be determined according to actual needs.

[0080] In one embodiment, the disaster damage result data generation module 300 is used to obtain the disaster damage result data in the disaster damage area according to the remote sensing image data. The disaster damage result data may include the damaged area of ​​buildings in the disaster damage area, the number of building types in the disaster damage area, the number of damage levels, and the number of disaster area location divisions. Specifically, in the step of obtaining the disaster damage result data in the disaster damage area according to the remote sensing image data, it includes:

[0081] S201. Extract the vector outlines of the buildings in the disaster-damaged area according to the remote sensing image data. In the process of extracting the vector outlines of the buildings, any automatic extraction algorithm in the prior art can be relied upon. However, it is not limited thereto, and those skilled in the art can make a selection according to the specific application scenario. It should be noted that in the process of extracting the vector outlines of the buildings in the disaster-damaged area, the buildings can be all the buildings in the disaster-damaged area or a specific building in the disaster-damaged area.

[0082] S202. According to the vector outline of the building, the corresponding preset feature parameters are calculated to form a target feature parameter set. For different buildings, the extracted feature parameters may also be different. At the same time, for the same building, the extracted feature parameters may also be different. Of course, the same category of feature parameters can also be extracted for all buildings. Those skilled in the art can select the feature parameters to be extracted according to actual needs, and the present application does not impose any restrictions on this. In order to reflect the degree of damage to the building before and after the earthquake, more feature parameters that can characterize the changes in appearance can be extracted, such as calculating the difference in area characteristics before and after the earthquake. Among them, in the process of extracting the feature parameters of the building, it is allowed to automatically extract according to the feature calculation formula in the prior art, and the extracted feature parameters of the building to be evaluated before and after the earthquake constitute the target parameter set. Among them, if there is only one feature parameter, it is also allowed to be input into the preliminary disaster damage assessment model, and the output result of the preliminary disaster damage assessment model is obtained.

[0083] S203, input the target parameter set into the preliminary disaster damage assessment model to obtain the disaster damage result data. The output result may include the number of building types located in the disaster damage area, the number of damage levels, and the number of disaster area location divisions. It can be understood that the number of types of buildings located in the disaster damage area may include residential buildings, public buildings, industrial buildings, and agricultural buildings, etc. The number of damage levels may include multiple levels such as collapse, serious damage, general damage, and intact, and the number of disaster area location divisions may include multiple levels such as primary location, secondary location, and tertiary location. Therefore, in a certain disaster damage area, its buildings may be allowed to correspond to multiple labels such as the number of building types, the number of damage levels, and the number of disaster area location divisions.

[0084] In one embodiment, the economic value distribution data generation module 400 is configured to obtain the economic value distribution data within the disaster loss area based on the remote sensing image data. It can be understood that the economic value distribution data is obtained by comprehensively calculating multiple thematic layers based on the economic location distribution data and geographical location distribution data within the disaster loss area and having contribution weights to the building location value, so as to obtain the location value distribution of the buildings within the disaster loss area. Among them, the geographical location distribution data can be based on spatial analysis technologies such as buffer analysis and density analysis in the geographical distribution information system, including multiple influencing factors such as the accessibility of roads and administrative division differences.

[0085] In one embodiment, the economic value distribution data includes location traffic accessibility data and location value contribution data. Among them, the location traffic accessibility data represents the influence scores of the main roads and / or secondary roads within the disaster loss area on the buildings, and the location value contribution data represents the contribution values of the relevant influencing factors within different locations to the building location value. Buffer analysis is an important means of measuring spatial features and is also a commonly used method in spatial analysis in geographical information systems. Therefore, it is allowed to define object A, and the buffer of object A can be defined as: P = {x / d(x,A)<r}, where r is the neighborhood radius or the condition for establishing this buffer, and d generally refers to the Euclidean distance or other distances. When performing buffer analysis, it is allowed to implement based on different analysis models according to the variation law of the influence degree of the analysis subject on the surrounding space.

[0086] In one embodiment, due to the characteristic that the accessibility of the main roads decreases rapidly in an exponential form with the distance from the road center line, the analysis model that can be adopted is: Among them, F i represents the actual influence degree of the core subject on the object to be analyzed; F0 represents the comprehensive scale index of the core subject itself; d i represents the actual distance of the object to be analyzed from the subject; d x represents the maximum influence distance of the subject object on the object to be analyzed; r i represents the ratio between the actual distance and the maximum distance.

[0087] It should be noted that in the analysis model for buffer generation, the change of the influence degree with the distance is continuous, that is, for each distance d i it has a different influence degree F i value. In the actual application process, it is allowed to divide F i into several typical levels according to the actual situation, and then determine the value of d i according to F i . Convert the continuously changing buffer into a buffer with stage - wise changes, that is, take an average influence degree F iAs the influence score of the factor at this level. Finally, the buffer maps at all levels are superimposed to obtain the influence factor map of the subject on the neighboring objects.

[0088] As an example, according to the size of the disaster damage area to be evaluated, the maximum impact distance of the main road and the secondary road in the disaster damage area can be set to 500m and 300m respectively, but it is not limited to this and can be determined according to actual needs. i It is divided into multiple impact levels, for example, the impact level F i It can include 5 levels, and the 5 levels include 1, 25, 50, 75 and 100 respectively. It should be noted that F i The larger the value, the higher the impact, and 0≤F i ≤F0, where F0 represents the highest weight of the main road and the secondary road, and the value of F0 is 100. Then, for d i The calculation of numerical values ​​can be performed through the following model:

[0089] as well as

[0090] Among them, d i1 represents the actual distance between the main road and the building to be evaluated, and d i2 Represents the actual distance between the secondary road and the building to be evaluated.

[0091] In one embodiment, the weights of road accessibility at each level F i ,d i1 and i2 The correspondence between them can be allowed by F i -d i1 -d i2 For example, for the impact level F i There are five levels, which are respectively i1 and i2 The corresponding relationships are: 1-500-300, 25-151-91, 50-75-45, 75-31-19 and 100-0-0. Therefore, it is allowed to make multiple buffer zones of 31m, 75m, 151m and 500m for the main roads, and assign the impact score Fi to the corresponding buffer zone to obtain the impact factor map of the main roads. Similarly, it is allowed to make multiple buffer zones of 19m, 45m, 91m and 300m for the secondary roads, and assign the impact score Fi to the corresponding buffer zone to obtain the impact factor map of the secondary roads.

[0092] In one embodiment, the influence factor graph of the main road and the influence factor graph of the secondary road are superimposed to obtain a comprehensive influence graph of roads at all levels, namely, a road accessibility factor graph. Specifically, for the road accessibility factor graph, the location traffic accessibility value of each unit in the graph is set as: F i =max(F i1 , F i2 ) to obtain the road accessibility factor weight map, where F i is the value of the location traffic accessibility, F i1 is the impact score of the main road, F i2 is the impact score of the secondary road. Therefore, for the location traffic accessibility data, it is allowed to express it through the road accessibility factor weight map.

[0093] In one embodiment, the location value contribution data may include location value contribution data based on road density analysis and location value contribution data based on administrative divisions. Wherein, the location value contribution data based on road density analysis may include a weight contribution layer of road intersections to the economic location of buildings, and a weight contribution layer of road line data to the economic location of buildings. The location value contribution data based on administrative divisions may include a weight contribution layer of administrative divisions to the economic location of buildings. Wherein, density analysis can be used to calculate the agglomeration of spatial point / line data within a specified search radius, and quantify spatial data in the form of points / lines to generate a continuous density surface. Density analysis includes three forms: kernel density, line density and point density, where line density and point density belong to simple density. Wherein, in the process of kernel density analysis, the elements in the search area have different weights, and the elements close to the center of the search area have a larger weight. As the distance from the search center increases, the weight of the elements decreases, while in the process of simple density analysis, the elements in the search area have the same weight, regardless of the distance from the search center. Therefore, it is allowed to perform kernel density analysis on the obtained road intersection data layer, and obtain the weight contribution layer of the road intersection to the economic location of the building. In the process of obtaining the location value contribution value data based on road density analysis, it is allowed to perform kernel density analysis on the branch intersection data and the road line data to obtain the location value contribution value data based on road density analysis.

[0094] In one embodiment, since the value contribution of administrative divisions to buildings is obvious, the location value contribution data based on administrative divisions may include a weight contribution layer of administrative divisions to the economic location of buildings. Based on the relevant data of administrative divisions, it is allowed to determine the weight of the influence of different administrative divisions on the economic location of buildings according to factors such as the political and commercial prosperity of different administrative regions, and obtain the location value contribution data of administrative divisions.

[0095] In one embodiment, after obtaining the location traffic accessibility data, the location value contribution data based on road density analysis, and the location value contribution data based on administrative divisions, it is allowed to perform an overlay analysis on the location traffic accessibility data, the location value contribution data based on road density analysis, and the location value contribution data based on administrative divisions. Through overlay analysis, the multiple layers of information that affect the economic location of the building in the above steps are compounded, and the economic location distribution adopts the weighted arithmetic operation results of each layer of attribute data. By assigning different weights to each layer of influencing factor data layer, the comprehensively considered influencing factors include the location traffic accessibility data, the location value contribution data based on road density analysis, and the location value contribution data based on administrative divisions.

[0096] In one embodiment, the assessment module 500 is used to perform an overlay analysis on the disaster damage result data 301 and the economic value distribution data 401 to generate an assessment result 501 of the economic loss of earthquake damage to buildings. In the process of generating the assessment result of the economic loss of earthquake damage to buildings, it is allowed to construct a building disaster economic loss model to calculate the economic loss assessment result.

[0097] The method for calculating the economic loss assessment result includes:

[0098] Among them, L represents the economic loss assessment result, N i Represents the number of building types, N j Characterizes the number of damage levels, N k represents the number of disaster area location divisions, A(i,j,k) represents the number of buildings with damage level j in area k, B(i,j,k) represents the average area of ​​buildings with damage level j in area k, and C(i,k) represents the average price of buildings with damage level j in area k.

[0099] See also Figure 6As shown, the present invention also provides an electronic device, including one or more memories 102 and a processor 103, and may also include a computer program stored in the memory 102 and executable on the processor 103, such as a program for an assessment method for economic losses caused by earthquake damage to buildings. Among them, the electronic device 101 may be a computer, a laptop, a tablet computer, a workbench, and a personal digital assistant, etc. The components shown herein, their connections and relationships, and their functions are merely examples, and are not intended to limit the implementation of the present application described and / or required herein. In some embodiments, the processor 103 may be composed of an integrated circuit, for example, it may be composed of a single packaged integrated circuit, or it may be composed of a plurality of integrated circuits packaged with the same or different functions, including a combination of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 103 is the control core (Control Unit) of the electronic device 101. It uses various interfaces and lines to connect the various components of the entire electronic device 101, and executes various functions and processes data of the electronic device 101 by running or executing programs or modules stored in the memory 102, and calling data stored in the memory 102.

[0100] It should be noted that when the processor of the electronic device executes the computer program, it implements the steps in the above-mentioned method for assessing economic losses caused by earthquake damage to buildings. Therefore, the implementation methods based on the above-mentioned method for assessing economic losses caused by earthquake damage to buildings are all applicable to the electronic device and can achieve the same or similar beneficial effects.

[0101] The present invention also provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the steps in the above-mentioned method for assessing the economic losses of earthquake damage to buildings are implemented. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electric carrier signal, a telecommunication signal, and a software distribution medium.

[0102] In summary, the present invention provides a method, device, equipment and medium for assessing the economic losses of earthquake damage to buildings. Combined with remote sensing image data of the disaster-damaged area, the method analyzes and obtains disaster damage result data related to location traffic accessibility data, location value contribution value data based on road density analysis, and location value contribution value data based on administrative divisions, and simultaneously calculates the economic value of buildings in different locations based on spatial overlay analysis. By constructing a building disaster economic loss model to calculate the economic loss assessment results, an effective assessment of the economic losses of earthquake damage to buildings in the disaster-damaged area is achieved. Therefore, the present invention effectively overcomes the various shortcomings of the prior art and has a high industrial utilization value.

[0103] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. A method for assessing economic losses caused by earthquake damage to buildings, characterized in that: include: Obtain remote sensing image data of the disaster-damaged area; Input the remote sensing image data into the preliminary disaster damage assessment model to obtain the disaster damage result data in the disaster damage area; obtain the economic value distribution data in the disaster damage area based on the remote sensing image data, wherein the economic value distribution data is based on multiple influencing factors with contribution weights to the location value of the building, and the multiple influencing factors are comprehensively calculated to obtain the estimated value of the building located in the disaster damage area; the economic value distribution data includes: location traffic accessibility data, which characterizes the impact score of the main roads and / or secondary roads in the disaster damage area on the building, and location value contribution value data, which characterizes the contribution value of the relevant influencing factors in different locations to the location value of the building; The disaster damage result data and the economic value distribution data are processed to generate an assessment result of the economic loss of the building caused by the earthquake.

2. The method for assessing economic losses caused by earthquake damage to buildings according to claim 1, characterized in that: The step of inputting the remote sensing image data into a preliminary disaster damage assessment model to obtain disaster damage result data in the disaster damage area includes: Extracting vector outlines of buildings in the disaster-damaged area based on the remote sensing image data; According to the building vector outline, corresponding preset feature parameters are calculated to form a target feature parameter set; The target parameter set is input into a preliminary disaster damage assessment model to obtain the disaster damage result data.

3. The method for assessing economic losses caused by earthquake damage to buildings according to claim 2, characterized in that: The output results of the preliminary disaster damage assessment model include: the number of building types located in the disaster area, the number of damage levels and the number of disaster area location divisions.

4. The method for assessing economic losses caused by earthquake damage to buildings according to claim 3, characterized in that: The calculation method of the location traffic accessibility value based on buffer zone analysis includes: i =max(F i1 , F i2 ), where F i is the value of the location traffic accessibility, F i1 is the impact score of the main road, F i2 It is the impact score of the secondary road.

5. The method for assessing economic losses caused by earthquake damage to buildings according to claim 4, characterized in that: The location value contribution includes: Location value contribution data based on road density analysis, which includes a weighted contribution layer of road intersections to the economic location of buildings; and Location value contribution data based on administrative divisions, which includes a weighted contribution layer of administrative divisions to the economic location of buildings.

6. The method for assessing economic losses caused by earthquake damage to buildings according to claim 5, characterized in that: The process of processing the disaster damage result data and the economic value distribution data to generate an assessment result of the economic loss of the building caused by the earthquake includes: Construct a building disaster economic loss model and calculate the economic loss assessment results; The economic loss assessment result L is expressed as: Among them, N i Represents the number of building types, N j Characterizes the number of damage levels, N k represents the number of disaster area location divisions, A(i,j,k) represents the number of buildings with damage level j in area k, B(i,j,k) represents the average area of ​​buildings with damage level j in area k, and C(i,k) represents the average price of buildings with damage level j in area k.

7. A device for assessing economic losses caused by earthquake damage to buildings, characterized in that: include: A data acquisition module is used to obtain remote sensing image data of the disaster-damaged area; A disaster damage result data generation module is used to input the remote sensing image data into a preliminary disaster damage assessment model to obtain disaster damage result data in the disaster damage area; An economic value distribution data generation module is used to obtain economic value distribution data in the disaster-damaged area based on the remote sensing image data, wherein the economic value distribution data is based on multiple influencing factors with contribution weights to the location value of the building, and the multiple influencing factors are comprehensively calculated to obtain the estimated value of the building located in the disaster-damaged area; the economic value distribution data includes: location traffic accessibility data, which represents the impact score of the main roads and / or secondary roads in the disaster-damaged area on the building, and location value contribution value data, which represents the contribution value of the relevant influencing factors in different locations to the location value of the building; The evaluation module is used to analyze the disaster damage result data and the economic value distribution data to generate an evaluation result of the economic loss of the building caused by the earthquake.

8. A computer device comprising a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, characterized in that: When the processor executes the computer-readable instructions, the method for assessing economic losses caused by earthquake damage to buildings according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that: The invention comprises a program which, when being run on a computer, enables the computer to execute the method for assessing economic losses caused by earthquake damage to buildings as claimed in any one of claims 1 to 6.

Images