Business risk map construction method and device, computer device and storage medium

Abstract

The embodiment of the application belongs to the field of artificial intelligence and financial technology, is applied to the field of insurance risk map construction, and relates to a business risk map construction method and device, computer equipment and a storage medium, which comprises risk factor normalization processing; an area map to be subjected to risk map construction is acquired and subjected to rasterization processing; property type business data is subjected to normalization processing; the correlation between different risk factors and the property type business data is analyzed by using a typical correlation analysis method to obtain business weight coefficients of different risk factors; multiplication calculation is performed according to the business weight coefficients and the property type business data in each grid map block to obtain corresponding business data of different risk factors in each grid map block, and the business data is marked in the area map corresponding to a specific map area to complete business risk map construction. The application combines actual business data to perform risk map construction, thereby guaranteeing the scientificity of business risk map construction.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence and financial technology, and particularly relates to a business risk map construction method and device, computer equipment and a storage medium. BACKGROUND

[0002] The construction of a business risk map has a certain guiding significance for the completion of subsequent business and can help an enterprise to determine key areas and non-key areas of business.

[0003] Taking the insurance industry as an example, when constructing a natural disaster risk map, the insurance industry often needs to consider a plurality of different risk factors, and different weight coefficients are assigned to these factors to calculate the final risk map. Therefore, how to determine the weight coefficients of these factors is important. The current method for determining the weight coefficients is not scientific and transparent. A simple method based on experience or equal weight generally cannot obtain the optimal combination of these factors and cannot well serve actual insurance business applications. SUMMARY

[0004] The purpose of the embodiments of the present application is to propose a business risk map construction method, device, computer equipment and storage medium to realize risk map construction combined with actual business data and ensure the scientificity of business risk map construction.

[0005] To solve the above technical problems, the embodiments of the present application provide a business risk map construction method, which adopts the following technical solution:

[0006] A business risk map construction method comprises the following steps:

[0007] From a preset disaster risk early warning platform, obtain the early warning times corresponding to different risk factors published in a specific map area in a preset time period, normalize the early warning times corresponding to the different risk factors, and obtain a first normalization result;

[0008] From a target database, obtain property type business data related to the different risk factors occurring in the specific map area in the preset time period, wherein the property type business data comprises a total number of businesses and a business amount corresponding to each business;

[0009] According to the property type business data and the location identifier in the specific map area, obtain the location information of all property type targets corresponding to the property type business data and convert the location information into longitude and latitude coordinates;

[0010] Obtain a regional map corresponding to the specific map area, and perform rasterization processing on the regional map according to a preset unit distance to obtain each raster map block;

[0011] According to the property business data and the corresponding latitude and longitude coordinates of all property targets, the property business data in each grid map block is counted, and the property business data in all grid map blocks is normalized to obtain a second normalization result;

[0012] Using a canonical correlation analysis method, the correlation between the first normalization result and the second normalization result is analyzed to obtain business weight coefficients corresponding to different risk factors respectively;

[0013] According to the business weight coefficients corresponding to different risk factors respectively and the property business data in each grid map block, a multiplication calculation is performed to obtain business data corresponding to the different risk factors in each grid map block, and the business data is marked in the regional map corresponding to the specific map area, thereby completing the business risk map construction.

[0014] Further, the step of normalizing the warning times corresponding to the different risk factors to obtain the first normalization result specifically includes:

[0015] Based on the first algorithm formula: The warning times corresponding to each risk factor in the different risk factors are normalized respectively, wherein i is the number corresponding to the different risk factors, x i represents a set of warning times corresponding to different risk factors, max(x i ) represents the maximum value in the set of warning times corresponding to different risk factors, and min(x i ) represents the minimum value in the set of warning times corresponding to different risk factors.

[0016] Further, the step of normalizing the property business data in all grid map blocks to obtain the second normalization result specifically includes:

[0017] Based on the second algorithm formula: The total number of property businesses corresponding to all grid map blocks is normalized, wherein j represents the number of each grid map block, y j represents the total number of property businesses corresponding to the grid map block numbered j, max(y j ) represents the total number of businesses corresponding to the grid map block with the maximum total number of property businesses among all grid map blocks, and min(y j ) represents the total number of businesses corresponding to the grid map block with the minimum total number of property businesses among all grid map blocks.

[0018] Based on the third algorithm formula: The total transaction amount for all property-related transactions corresponding to all raster map tiles is normalized, where j represents the number of each raster map tile, z j This represents the total business amount corresponding to the raster map tile numbered j, max(z j ) represents the total transaction amount of the raster map tile with the largest total transaction amount for property-related transactions among all raster map tiles, min(z j This represents the total transaction amount corresponding to the raster map block with the smallest total transaction amount for property-related transactions among all raster map blocks.

[0019] Furthermore, the step of analyzing the correlation between the first normalized result and the second normalized result using canonical correlation analysis specifically includes:

[0020] Based on the first normalization result, construct the first canonical variable;

[0021] Based on the results of the second normalization process, construct the second canonical variable;

[0022] Canonical correlation analysis was used to analyze the correlation between the first canonical variable and the second canonical variable.

[0023] Furthermore, the step of constructing the first canonical variable based on the first normalization result specifically includes:

[0024] Using the result of the first normalization process: Constructing the first canonical variable r X ,in, In the formula, w Xi w is the normalized value corresponding to the i-th risk factor. X =(w X1 ,w X2 ,w X3 ,…,w Xn ), where n represents the different types of risk factors.

[0025] Furthermore, the second normalization result includes the normalization result corresponding to the total number of property-related transactions for all raster map blocks and the normalization result corresponding to the total transaction amount of property-related transactions for all raster map blocks. The second typical variable includes a typical variable for the number of transactions and a typical variable for the total transaction amount. The step of constructing the second typical variable based on the second normalization result specifically includes:

[0026] Using the normalized result corresponding to the total number of property-related business transactions across all raster map tiles: Construct a typical variable r for the number of business transactions Y ,in, In the formula, wYj w is a normalized value of the total number of the property-type business corresponding to the jth grid map block, w Y = (w Y1 ,w Y2 ,w Y3 ,…,w Ym ), and m is the total number of the grid map blocks;

[0027] The normalized processing result corresponding to the total business amount of the property-type business corresponding to all the grid map blocks is: The total business amount typical variable r Z is constructed, wherein, In the formula, w Zj is a normalized value of the total amount of the property-type business corresponding to the jth grid map block, w Z = (w Z1 ,w Z2 ,w Z3 ,…,w Zm ), and m is the total number of the grid map blocks.

[0028] Further, the step of analyzing the correlation between the first typical variable and the second typical variable using the canonical correlation analysis method specifically includes:

[0029] Based on a first correlation analysis formula: The maximum correlation coefficient between the different risk factors and the total number of the property-type business corresponding to each grid map block is obtained, wherein, XX w X represents the autocorrelation coefficient matrix of variable X, ∑ YY w Y is the autocorrelation coefficient matrix of variable Y, ∑ XY w Y is the cross-correlation coefficient matrix of variable X and variable Y.

[0030] Based on a second correlation analysis formula: The maximum correlation coefficient between the different risk factors and the total amount of the property-type business corresponding to each grid map block is obtained, wherein, XX w X represents the autocorrelation coefficient matrix of variable X, ∑ ZZ w Z is the autocorrelation coefficient matrix of variable Z, ∑ XZ w Z is the cross-correlation coefficient matrix of variable X and variable Z.

[0031] Further, the step of obtaining the business weight coefficient corresponding to each risk factor specifically includes:

[0032] Based on the preset first condition and the second condition, the first correlation analysis formula is converted to obtain a converted first correlation analysis formula: XX ∑ YY -1∑ YZ w X =ρ 2 ∑ XX w X , wherein the first condition is The second condition is

[0033] According to the converted first correlation analysis formula, the feature vector w corresponding to the maximum value of p is obtained X , that is, the weight coefficient of different risk factors in the total number of business of the property type business corresponding to each grid map block;

[0034] Based on the preset third condition and the fourth condition, the second correlation analysis formula is converted to obtain a converted second correlation analysis formula: XX ∑ ZZ -1∑ ZX w X =ρ 2 ∑ XX w X , wherein the third condition is The fourth condition is

[0035] According to the converted second correlation analysis formula, the feature vector w corresponding to the maximum value of p is obtained X , as the weight coefficient of different risk factors in the total amount of business of the property type business corresponding to each grid map block.

[0036] To solve the above technical problems, the embodiments of the present application also provide a business risk map construction device, which adopts the following technical solutions:

[0037] A business risk map construction device comprises:

[0038] A first normalization processing module is configured to obtain, from a preset disaster risk early warning platform, the number of early warnings corresponding to different risk factors published in a specific map area within a preset time period, normalize the number of early warnings corresponding to the different risk factors, and obtain a first normalization processing result.

[0039] A risk business data acquisition module is configured to acquire, from a target database, property type business data related to the different risk factors occurring in the specific map area within the preset time period, wherein the property type business data comprises the total number of businesses and the business amount corresponding to each business.

[0040] The business occurrence location determination module is configured to obtain location information of all property-related targets corresponding to the property-related business data according to the property-related business data and location identifiers in the specific map region, and convert the location information into longitude and latitude coordinates.

[0041] The regional map rasterization module is configured to obtain a regional map corresponding to the specific map region, and perform rasterization processing on the regional map according to a preset unit distance to obtain each raster map block.

[0042] The second normalization processing module is configured to count the property-related business data in each raster map block according to the property-related business data and the longitude and latitude coordinates corresponding to all the property-related targets, and perform normalization processing on the property-related business data in all the raster map blocks to obtain a second normalization processing result.

[0043] The weight coefficient obtaining module is configured to use a canonical correlation analysis method to analyze the correlation between the first normalization processing result and the second normalization processing result, and obtain business weight coefficients corresponding to different risk factors respectively.

[0044] The risk map annotation construction module is configured to perform multiplication calculation according to the business weight coefficients corresponding to different risk factors respectively and the property-related business data in each raster map block, obtain business data corresponding to the different risk factors in each raster map block, and annotate the business data in the regional map corresponding to the specific map region to complete construction of a business risk map.

[0045] To solve the above technical problems, the embodiments of the present application further provide a computer device, which adopts the technical scheme as follows:

[0046] A computer device includes a memory and a processor, the memory stores computer readable instructions, and the processor executes the computer readable instructions to realize the steps of the business risk map construction method.

[0047] To solve the above technical problems, the embodiments of the present application further provide a computer readable storage medium, which adopts the technical scheme as follows:

[0048] A computer readable storage medium stores computer readable instructions, and the computer readable instructions are executed by a processor to realize the steps of the business risk map construction method.

[0049] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0050] The business risk map construction method provided in the embodiments of the present application comprises the following steps: performing normalization processing on the early warning times corresponding to different risk factors; acquiring a regional map to be used for risk map construction and performing rasterization processing; counting property type business data in each raster map block and performing normalization processing; using a canonical correlation analysis method to analyze the correlation between the normalization processing results of different risk factors and the normalization processing results of the property type business data, and obtaining business weight coefficients corresponding to different risk factors respectively; performing multiplication calculation on the business weight coefficients corresponding to different risk factors respectively and the property type business data in each raster map block, obtaining business data corresponding to different risk factors in each raster map block, and marking the business data in the regional map corresponding to the specific map region, thereby completing the construction of the business risk map. The present application can ensure the scientific nature of the construction of the business risk map by combining actual business data for the construction of the risk map. BRIEF DESCRIPTION OF DRAWINGS

[0051] In order to more clearly illustrate the schemes in the present application, the drawings used in the embodiments of the present application will be briefly introduced as follows. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without any creative effort.

[0052] Figure 1 is an exemplary system architecture diagram to which the present application can be applied;

[0053] Figure 2 a flowchart of an embodiment of the business risk map construction method according to the present application;

[0054] Figure 3 a structural schematic diagram of an embodiment of the business risk map construction device according to the present application;

[0055] Figure 4 a structural schematic diagram of an embodiment of the computer device according to the present application. DETAILED DESCRIPTION

[0056] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs; the terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "include" and "have" and any variations thereof in the specification of the present application and the claims and the above description of drawings are intended to cover non-exclusive inclusion. The terms "first", "second" and the like in the specification and claims of the present application and the above description of drawings are used to distinguish different objects, not to describe a specific order.

[0057] Reference to“an embodiment” or“the embodiment” means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase“in one embodiment” or“in at least one embodiment” in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily all referring to a particular embodiment which is separate from other embodiments. It is explicitly contemplated that embodiments described herein can be combined with each other in their individual aspects.

[0058] In order to make the person skilled in the art better understand the scheme of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings.

[0059] As shown in Figure 1 The system architecture 100 can include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is a medium for providing a communication link between the terminal devices 101, 102, 103 and the server 105. The network 104 can include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.

[0060] A user can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications can be installed on the terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0061] The terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 (Moving Picture Experts Group Audio Layer III) players, MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop portable computers, desktop computers, etc.

[0062] The server 105 can be a server providing various services, such as a background server supporting the pages displayed on the terminal devices 101, 102, 103.

[0063] It should be noted that the business risk map construction method provided by the embodiments of the present application is generally executed by a server / terminal device, and accordingly, the business risk map construction apparatus is generally arranged in a server / terminal device.

[0064] It should be understood that Figure 1The number of terminal devices, networks and servers in the system is only illustrative. Any number of terminal devices, networks and servers can be provided according to implementation needs.

[0065] With reference to the accompanying drawings still, Figure 2 , a flowchart of one embodiment of a business risk map construction method according to the present application is shown. The business risk map construction method includes the following steps:

[0066] Step 201, from a preset disaster risk early warning platform, obtain the number of early warnings corresponding to different risk factors published in a specific map area within a preset time period, normalize the number of early warnings corresponding to the different risk factors, and obtain a first normalization result.

[0067] In this embodiment, the preset disaster risk early warning platform can be a national authoritative disaster risk early warning platform.

[0068] In this embodiment, the specific time period can be the previous year, and the different risk factors include extreme weather, the new crown epidemic, earthquake factors, typhoon factors, and volcano factors.

[0069] In this embodiment, the step of normalizing the number of early warnings corresponding to the different risk factors to obtain the first normalization result specifically includes:

[0070] Based on the first algorithm formula: The number of early warnings corresponding to each of the different risk factors is normalized, where i is the number corresponding to the different risk factors, x i represents a set of the number of early warnings corresponding to different risk factors, max(x i ) represents the maximum value in the set of the number of early warnings corresponding to different risk factors, and min(x i ) represents the minimum value in the set of the number of early warnings corresponding to different risk factors.

[0071] Suppose that in 2022, Japan has a total of 1000 times of extreme weather, new crown epidemic, earthquake factors, typhoon factors, and volcano factors, and the number of times corresponding to the above different risk factors is obtained in sequence, and the different risk factors are numbered. The number of times corresponding to the different risk factors is added to the set in the order of numbering, and the first algorithm formula is used to obtain the proportion of different risk factors in the total number of times, i.e., the first normalization result.

[0072] By using the normalization processing method, the proportion of different types of risks in natural disasters causing damage to property targets is obtained, which facilitates the construction of a risk map in combination with the impact of natural disasters on property target losses.

[0073] Step 202, from the target database, obtain the property-related business data related to the different risk factors occurring in the specific map area within the preset time period, wherein the property-related business data includes the total number of businesses and the business amount corresponding to each business.

[0074] In this embodiment, the target database refers to a self-built claim database within a company or a claim database in a national authority platform, and the property-related business data related to different risk factors includes the total number of car insurance, enterprise property insurance, and engineering insurance claims and the claim amount of each claim case due to extreme weather, COVID-19, earthquake factors, typhoon factors, and volcanic factors.

[0075] Continuing with the above example, assume that in 2022, Japan experienced a total of 1000 times of extreme weather, COVID-19, earthquake factors, typhoon factors, and volcanic factors, and that these risk factors resulted in a total of 2 million insurance claims. Through the claim database, the total number of insurance claims related to the above extreme weather, COVID-19, earthquake factors, typhoon factors, and volcanic factors and the claim amount of each claim case are obtained.

[0076] By obtaining the claim-related business data related to the risk factors from the claim database, it is convenient for later processing to combine actual claim data to construct a business risk map, providing data basis for risk map construction.

[0077] Step 203, according to the property-related business data and the location identifier in the specific map area, obtain all property-related target location information corresponding to the property-related business data and convert it into latitude and longitude coordinates.

[0078] Taking a certain real estate as an example in property insurance, assume that the policyholder purchased insurance from an insurance company with his house as the target, agreeing that "between 2019 and 2022, if his house A is destroyed or causes loss due to natural disasters, the insurance company will make a claim." In 2022, the region experienced a record-breaking earthquake, causing his house A to be destroyed, but the policyholder was safe and sound, and the insurance company made a claim for the house.

[0079] By obtaining all property-related target location information corresponding to the property-related business data and converting it into latitude and longitude coordinates, it is convenient to count the property-related business data in different grid maps through latitude and longitude coordinates.

[0080] Step 204, obtain the regional map corresponding to the specific map area, and perform grid processing on the regional map according to a preset unit distance to obtain each grid map block.

[0081] In this embodiment, the gridding processing specifically refers to block division of the regional map according to a preset longitude and latitude interval, and numbering of the divided block map. The numbering result is denoted by j.

[0082] In step 205, according to the property-related business data and the corresponding longitude and latitude coordinates of the property-related targets, the property-related business data in each grid map block is counted, the property-related business data in all grid map blocks is normalized, and a second normalization result is obtained.

[0083] In this embodiment, the step of normalizing the property-related business data in all grid map blocks to obtain the second normalization result specifically includes:

[0084] Based on the second algorithm formula: The total number of property-related businesses corresponding to all grid map blocks is normalized, where j represents the number of each grid map block, y j represents the total number of property-related businesses corresponding to the grid map block numbered j, max(y j ) represents the total number of businesses corresponding to the grid map block with the maximum total number of property-related businesses among all grid map blocks, and min(y j ) represents the total number of businesses corresponding to the grid map block with the minimum total number of property-related businesses among all grid map blocks.

[0085] Based on the third algorithm formula: The total amount of businesses corresponding to all grid map blocks is normalized, where j represents the number of each grid map block, z j represents the total amount of businesses corresponding to the grid map block numbered j, max(z j ) represents the total amount of businesses corresponding to the grid map block with the maximum total amount of property-related businesses among all grid map blocks, and min(z j ) represents the total amount of businesses corresponding to the grid map block with the minimum total amount of property-related businesses among all grid map blocks.

[0086] By normalizing the property-related business data in all grid map blocks, a second normalization result is obtained, which facilitates the construction of typical variables for property-related business data using the normalized data.

[0087] In step 206, a typical correlation analysis method is used to analyze the correlation between the first normalization result and the second normalization result, and business weight coefficients corresponding to different risk factors are obtained.

[0088] Canonical correlation analysis (CCA) is a multivariate statistical analysis method that uses the correlation between pairs of composite variables to reflect the overall correlation between two groups of indicators. The basic principle of CCA is to extract representative composite variables from each group of variables to reflect the overall correlation between the two groups of indicators using the correlation between the two composite variables. In this application, the multiple risk variable data is used as a composite variable, and the number of different business data under multiple risks and the total amount of business data are used as another composite variable. The correlation between risk and business is analyzed using the CCA method, and a risk map is constructed based on the analysis results.

[0089] In this embodiment, the step of using the CCA method to analyze the correlation between the first normalized processing result and the second normalized processing result specifically includes: constructing a first canonical variable according to the first normalized processing result; constructing a second canonical variable according to the second normalized processing result; and using the CCA method to analyze the correlation between the first canonical variable and the second canonical variable.

[0090] In this embodiment, the step of constructing a first canonical variable according to the first normalized processing result specifically includes:

[0091] The step of constructing a first canonical variable according to the first normalized processing result specifically includes:

[0092] The first normalized processing result is used to: construct a first canonical variable r X wherein, In the formula, w Xi is the normalized value corresponding to the i-th risk factor, w X = (w X1 , w X2 , w X3 , …, w Xn ), and n is the number of different risk factors.

[0093] In this embodiment, the second normalized processing result includes the normalized processing result corresponding to the total number of property-type businesses corresponding to all grid map blocks and the normalized processing result corresponding to the total amount of property-type businesses corresponding to all grid map blocks, and the second canonical variable includes a business quantity canonical variable and a business total amount canonical variable. The step of constructing a second canonical variable according to the second normalized processing result specifically includes:

[0094] The normalized processing result corresponding to the total number of property-type businesses corresponding to all grid map blocks is used to: constructing a business quantity typical variable r Y wherein, wherein, w Yj is a normalized value of the total quantity of the property-related business corresponding to the jth grid map block, w Y = (w Y1 , w Y2 , w Y3 , …, w Ym ), and m is the total quantity of the grid map blocks;

[0095] using normalized processing results corresponding to the total amount of the property-related business corresponding to all the grid map blocks: constructing a business total amount typical variable r Z wherein, wherein, w Zj is a normalized value of the total amount of the property-related business corresponding to the jth grid map block, w Z = (w Z1 , w Z2 , w Z3 , …, w Zm ), and m is the total quantity of the grid map blocks.

[0096] In this embodiment, the step of analyzing the correlation between the first typical variable and the second typical variable using the canonical correlation analysis method specifically includes:

[0097] based on a first correlation analysis formula: obtaining the maximum correlation coefficient between the different risk factors and the total quantity of the property-related business corresponding to each grid map block, wherein, XX w X represents a self-correlation coefficient matrix of variable X, ∑ YY w Y is a self-correlation coefficient matrix of variable Y, ∑ XY w Y is a cross-correlation coefficient matrix of variable X and variable Y;

[0098] based on a second correlation analysis formula: obtaining the maximum correlation coefficient between the different risk factors and the total amount of the property-related business corresponding to each grid map block, wherein, XX w X represents a self-correlation coefficient matrix of variable X, ∑ ZZ w Z is a self-correlation coefficient matrix of variable Z, ∑ XZ w Z is a cross-correlation coefficient matrix of variable X and variable Z.

[0099] The correlation between different risk factors and property type claim data is compared by constructing canonical variables according to the normalized results corresponding to different risk factors, and constructing canonical variables according to the normalized results corresponding to property type business data, using canonical correlation analysis method, and constructing a business risk map according to the correlation, which is more scientific.

[0100] In the embodiment, the step of obtaining the business weight coefficient corresponding to each risk factor comprises:

[0101] The first correlation analysis formula is converted based on the preset first condition and the second condition, and a converted first correlation analysis formula is obtained: ∑ XX ∑ YY -1∑ YZ w X =ρ 2 ∑ XX w X , wherein the first condition is The second condition is

[0102] According to the converted first correlation analysis formula, the feature vector w corresponding to the maximum value of ρ is obtained X , that is, the weight coefficient of different risk factors in the total number of property type business corresponding to each grid map block, wherein ρ is the correlation coefficient between different risk factors and the total number of property type business corresponding to each grid map block;

[0103] The second correlation analysis formula is converted based on the preset third condition and the fourth condition, and a converted second correlation analysis formula is obtained: ∑ XX ∑ ZZ -1∑ ZX w X =ρ 2 ∑ XX w X , wherein the third condition is The fourth condition is

[0104] According to the converted second correlation analysis formula, the feature vector w corresponding to the maximum value of ρ is obtained X , as the weight coefficient of different risk factors in the total amount of property type business corresponding to each grid map block, wherein ρ is the correlation coefficient between different risk factors and the total amount of property type business corresponding to each grid map block.

[0105] By obtaining the weight coefficient of the total number of business and the weight coefficient of the total amount of business corresponding to each risk factor in each grid map block, the business risk map construction personnel can perform data labeling on each grid map block.

[0106] In step 207, multiplication calculation is performed according to the business weight coefficient corresponding to each risk factor and the property business data in each grid map block, to obtain the business data corresponding to each risk factor in each grid map block, and the business data is marked in the regional map corresponding to the specific map area, to complete the business risk map construction.

[0107] In the embodiment, before the business data is marked in the regional map corresponding to the specific map area to complete the business risk map construction, the method further includes: judging whether the target resolution of the business risk map to be constructed is consistent with the resolution of each grid map block, if yes, no processing is needed, and if not, the interpolation method is used to process the grid map block.

[0108] Through the interpolation processing, the grid map block and the resolution are consistent with the resolution of the business risk map to be constructed.

[0109] Through the multiplication calculation, the number of claim cases and the claim amount corresponding to each risk factor in each grid map block are obtained, so as to facilitate data marking by using the calculated data when the business risk map is constructed.

[0110] The application normalizes the early warning times corresponding to different risk factors, acquires a regional map to be constructed, performs rasterization processing, counts and normalizes the property business data in each grid map block, uses the canonical correlation analysis method to analyze the correlation between the normalized processing results of different risk factors and the normalized processing results of the property business data, obtains the business weight coefficient corresponding to each risk factor, performs multiplication calculation according to the business weight coefficient corresponding to each risk factor and the property business data in each grid map block, obtains the business data corresponding to each risk factor in each grid map block, marks the business data in the regional map corresponding to the specific map area, and completes the business risk map construction. The application combines the actual business data to construct the risk map, and ensures the scientificity of the business risk map construction.

[0111] The embodiment of the application can acquire and process related data based on artificial intelligence technology. Artificial intelligence (AI) is a theory, method, technology and application system for simulating, extending and expanding human intelligence by using a digital computer or a machine controlled by a digital computer, perceiving an environment, acquiring knowledge and using the knowledge to obtain the best results.

[0112] The artificial intelligence basic technology generally includes technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction system, mechatronics, etc. The artificial intelligence software technology mainly includes computer vision technology, robot technology, biometric identification technology, speech processing technology, natural language processing technology, and machine learning / deep learning, etc.

[0113] In the embodiments of the present application, the big data processing technology can be used to obtain early warning data of different risk factors from a national authoritative platform, and the big data processing technology can also be used to obtain and process claim data. When constructing a business risk map, data labeling can be performed in an automated manner.

[0114] Further referring to Figure 3 , as an implementation of the method shown in Figure 2 , the present application provides an embodiment of a business risk map construction device. The device embodiment corresponds to the method embodiment shown in Figure 2 . The device can be applied to various electronic devices.

[0115] As shown in Figure 3 , the business risk map construction device 300 described in the embodiments includes a first normalization processing module 301, a risk business data acquisition module 302, a business occurrence location determination module 303, a regional map rasterization module 304, a second normalization processing module 305, a weight coefficient acquisition module 306, and a risk map labeling construction module 307. Among them:

[0116] The first normalization processing module 301 is configured to obtain, from a national authoritative disaster risk early warning platform, the number of early warnings of different risk factors corresponding to a specific map area within a preset time period, and perform normalization processing on the number of early warnings of different risk factors to obtain a first normalization processing result.

[0117] The risk business data acquisition module 302 is configured to acquire, from a target database, property-type business data related to the different risk factors occurring in the specific map area within the preset time period, wherein the property-type business data includes the total number of businesses and the business amount corresponding to each business.

[0118] The business occurrence location determination module 303 is configured to obtain the location information of all property-type targets corresponding to the property-type business data according to the property-type business data and the location identifiers in the specific map area, and convert the location information into latitude and longitude coordinates.

[0119] The area map rasterization module 304 is configured to acquire an area map corresponding to the specific map area, and rasterize the area map according to a preset unit distance to obtain each grid map block.

[0120] The second normalization processing module 305 is configured to count the property-related business data in each grid map block according to the longitude and latitude coordinates corresponding to the property-related business data and the property-related targets, and normalize the property-related business data in all grid map blocks to obtain a second normalization processing result.

[0121] The weight coefficient acquisition module 306 is configured to analyze the correlation between the first normalization processing result and the second normalization processing result by using a canonical correlation analysis method to obtain the business weight coefficients corresponding to different risk factors respectively.

[0122] The risk map labeling construction module 307 is configured to multiply the business weight coefficients corresponding to different risk factors respectively and the property-related business data in each grid map block to obtain the business data corresponding to the different risk factors in each grid map block, and label the business data in the area map corresponding to the specific map area to complete the construction of the business risk map.

[0123] The application normalizes the warning times corresponding to different risk factors, acquires an area map to be constructed into a risk map, performs rasterization processing, counts and normalizes the property-related business data in each grid map block, analyzes the correlation between the normalization processing results of different risk factors and the normalization processing results of the property-related business data by using a canonical correlation analysis method to obtain the business weight coefficients corresponding to different risk factors respectively, multiplies the business weight coefficients corresponding to different risk factors respectively and the property-related business data in each grid map block to obtain the business data corresponding to the different risk factors in each grid map block, and labels the business data in the area map corresponding to the specific map area to complete the construction of the business risk map. The application combines actual business data to construct a risk map, and ensures the scientificity of the construction of the business risk map.

[0124] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing related hardware through computer-readable instructions. These computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the methods described above. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, optical disk, or read-only memory (ROM), or random access memory (RAM).

[0125] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0126] To address the aforementioned technical problems, embodiments of this application also provide a computer device. Please refer to [link / reference needed]. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0127] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected via a system bus. It should be noted that only the computer device 4 with components 41-43 is shown in the figure; however, it should be understood that it is not required to implement all the shown components, and more or fewer components can be implemented alternatively. Those skilled in the art will understand that the computer device described here is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0128] The computer device can be a desktop computer, a notebook computer, a palm computer, a cloud server, or the like. The computer device can interact with a user through a keyboard, a mouse, a remote controller, a touchpad, a voice control device, or the like.

[0129] The memory 41 can include at least one type of readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., an SD or DX memory, or the like), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, or the like. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or a memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, or the like. Of course, the memory 41 can include both an internal storage unit and an external storage device of the computer device 4. In this embodiment, the memory 41 is generally used to store an operating system and various application software installed in the computer device 4, such as computer readable instructions of the business risk map construction method, or the like. In addition, the memory 41 can also be used to temporarily store various data that have been output or will be output.

[0130] The processor 42 can be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run computer readable instructions or process data stored in the memory 41, such as computer readable instructions of the business risk map construction method.

[0131] The network interface 43 can include a wireless network interface or a wired network interface, and is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0132] The computer device provided in the embodiment belongs to the technical field of financial technology. The application performs normalization processing on the early warning times corresponding to different risk factors; acquires a regional map to be used for risk map construction and performs rasterization processing; statistics the property type business data in each raster map block and performs normalization processing; uses a canonical correlation analysis method to analyze the correlation between the normalization processing results of different risk factors and the normalization processing results of the property type business data, and obtains the business weight coefficients corresponding to different risk factors respectively; performs multiplication calculation according to the business weight coefficients corresponding to different risk factors respectively and the property type business data in each raster map block, obtains the business data corresponding to different risk factors in each raster map block, and labels the business data in the regional map corresponding to the specific map area, thereby completing the business risk map construction. The application combines actual business data to construct a risk map, thereby ensuring the scientificity of the business risk map construction.

[0133] The application further provides another implementation, namely providing a computer readable storage medium storing computer readable instructions, which can be executed by a processor to enable the processor to execute the steps of the business risk map construction method as described above.

[0134] The computer readable storage medium provided in the embodiment belongs to the technical field of financial technology. The application performs normalization processing on the early warning times corresponding to different risk factors; acquires a regional map to be used for risk map construction and performs rasterization processing; statistics the property type business data in each raster map block and performs normalization processing; uses a canonical correlation analysis method to analyze the correlation between the normalization processing results of different risk factors and the normalization processing results of the property type business data, and obtains the business weight coefficients corresponding to different risk factors respectively; performs multiplication calculation according to the business weight coefficients corresponding to different risk factors respectively and the property type business data in each raster map block, obtains the business data corresponding to different risk factors in each raster map block, and labels the business data in the regional map corresponding to the specific map area, thereby completing the business risk map construction. The application combines actual business data to construct a risk map, thereby ensuring the scientificity of the business risk map construction.

[0135] Those skilled in the art can clearly understand the above-mentioned embodiment method can be realized by means of software and the necessary general hardware platform, of course, it can also be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes a plurality of instructions for making a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) execute the method described in each embodiment of the present application.

[0136] Obviously, the above-described embodiments are only some of the embodiments of the present application, not all the embodiments, and the drawings show the preferred embodiments of the present application, but do not limit the patent scope of the present application. The present application can be implemented in many different forms, and conversely, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions recorded in the foregoing specific embodiments, or make equivalent replacements to some of the technical features. Any equivalent structure made by using the content of the specification and drawings, directly or indirectly applied to other related technical fields, is also within the scope of the patent protection of the present application.

Claims

1. A business risk map construction method characterized by, The method comprises the following steps: obtaining, from a preset disaster risk early warning platform, a number of early warnings of different risk factors corresponding to a specific map area within a preset time period, normalizing the number of early warnings of the different risk factors to obtain a first normalization result; obtaining, from a target database, property-related business data related to the different risk factors occurring in the specific map area within the preset time period, wherein the property-related business data comprises a total number of businesses and a business amount corresponding to each business; obtaining all property-related target location information corresponding to the property-related business data according to the property-related business data and location identifiers in the specific map area, and converting the all property-related target location information into latitude and longitude coordinates; obtaining a regional map corresponding to the specific map area, and rasterizing the regional map according to a preset unit distance to obtain each raster map block; statistically analyzing the property-related business data in each raster map block according to the property-related business data and the latitude and longitude coordinates corresponding to the all property-related targets, normalizing the property-related business data in all raster map blocks to obtain a second normalization result; using a canonical correlation analysis method to analyze the correlation between the first normalization result and the second normalization result to obtain business weight coefficients corresponding to the different risk factors respectively; performing multiplication calculation according to the business weight coefficients corresponding to the different risk factors respectively and the property-related business data in each raster map block to obtain business data corresponding to the different risk factors in each raster map block, and marking the business data in the regional map corresponding to the specific map area to complete business risk map construction.

2. The business risk map construction method according to claim 1, characterized by, The step of normalizing the number of early warnings of the different risk factors to obtain the first normalization result specifically comprises: Based on the first algorithm formula: , respectively, the number of early warning corresponding to each risk factor in the different risk factors is normalized, wherein, is the number corresponding to different risk factors, represents a set of early warning numbers corresponding to different risk factors, represents the maximum value in the set of early warning numbers corresponding to different risk factors, represents the minimum value in the set of early warning numbers corresponding to different risk factors.

3. The business risk map construction method of claim 2, wherein, The step of normalizing the property-related business data in all raster map blocks to obtain the second normalization result specifically comprises: Based on the second algorithm formula: , wherein the total number of property-related businesses corresponding to all grid map blocks is normalized, represents the number of each grid map block, represents the total number of property-related businesses corresponding to the grid map block numbered represents the total number of businesses corresponding to the grid map block with the largest total number of property-related businesses among all grid map blocks, represents the total number of businesses corresponding to the grid map block with the smallest total number of property-related businesses among all grid map blocks.​ Based on the third algorithm formula: , the total amount of business of the property type business corresponding to all grid map blocks is normalized, wherein, represents the number of each grid map block, represents the total amount of business corresponding to the grid map block numbered represents the total amount of business corresponding to the grid map block with the maximum total amount of business of the property type business in all grid map blocks, represents the total amount of business corresponding to the grid map block with the minimum total amount of business of the property type business in all grid map blocks.​ 4. The business risk map building method of claim 1, wherein, The step of using a canonical correlation analysis method to analyze the correlation between the first normalization result and the second normalization result specifically comprises: constructing a first canonical variable according to the first normalization result; constructing a second canonical variable according to the second normalization result; using a canonical correlation analysis method to analyze the correlation between the first canonical variable and the second canonical variable.

5. The business risk map construction method according to claim 4, characterized by, The step of constructing the first canonical variable according to the first normalization result specifically comprises: Using the first normalization processing result: , a first typical variable is constructed , wherein, , the formula, , is the type of different risk factors.

6. The business risk map construction method of claim 5, wherein, The second normalization result comprises a normalization result corresponding to the total number of property-related businesses of all raster map blocks and a normalization result corresponding to the total business amount of property-related businesses of all raster map blocks, the second canonical variable comprises a business quantity canonical variable and a business total amount canonical variable, and the step of constructing the second canonical variable according to the second normalization result specifically comprises: The total number of property-related businesses corresponding to all the grid map blocks is normalized to obtain a normalized result: , and a business quantity typical variable is constructed , wherein , in the formula, , is the total number of grid map blocks. The normalized processing result corresponding to the total amount of business of the property type business of all the grid map blocks is used to construct the total amount of business typical variable , wherein, , , in the formula, , is the total number of grid map blocks.

7. The business risk map construction method of claim 6, wherein, The step of using a canonical correlation analysis method to analyze the correlation between the first canonical variable and the second canonical variable specifically comprises: Based on a first correlation analysis formula: , a maximum correlation coefficient between the different risk factors and the total number of the property-related businesses corresponding to each grid map block is obtained, wherein, represents a self-correlation coefficient matrix of a variable X, is a self-correlation coefficient matrix of a variable Y, is a cross-correlation coefficient matrix of the variable X and the variable Y; Based on a second correlation analysis formula: , a maximum correlation coefficient between the different risk factors and the total amount of the property-related business corresponding to each grid map block is obtained, wherein, represents a self-correlation coefficient matrix of variable X, is a self-correlation coefficient matrix of variable Z, is a cross-correlation coefficient matrix of variable X and variable Z.

8. The business risk map construction method of claim 7, wherein, The step of obtaining the business weight coefficients respectively corresponding to the different risk factors specifically comprises: The first correlation analysis formula is converted based on preset first and second conditions to obtain a converted first correlation analysis formula: wherein the first condition is and the second condition is ; According to the converted first correlation analysis formula, obtain The characteristic vector corresponding to the maximum value That is, the weight coefficient of different risk factors in the total number of business of the property type business corresponding to each grid map block; The second correlation analysis formula is converted based on a preset third condition and a fourth condition to obtain a converted second correlation analysis formula: , wherein the third condition is , and the fourth condition is ; According to the converted second correlation analysis formula, the following is obtained The characteristic vector corresponding to the maximum value is taken as the weight coefficient of the total business amount of the property-type business corresponding to each grid map block of different risk factors.

9. A business risk map construction apparatus characterized by comprising: The method comprises: The first normalization processing module is configured to obtain, from a preset disaster risk early warning platform, early warning times of different risk factors corresponding to a specific map region in a preset time period, normalize the early warning times of the different risk factors, and obtain a first normalization processing result; The risk business data acquisition module is configured to obtain, from a target database, property class business data related to the different risk factors occurring in the specific map region in the preset time period, wherein the property class business data comprises a total number of businesses and a business amount corresponding to each business; The business occurrence location determination module is configured to obtain location information of all property class targets corresponding to the property class business data according to the property class business data and location identifiers in the specific map region, and convert the location information into longitude and latitude coordinates; The region map rasterization module is configured to obtain a region map corresponding to the specific map region, and perform rasterization processing on the region map according to a preset unit distance to obtain each grid map block; The second normalization processing module is configured to count the property class business data in each grid map block according to the property class business data and the longitude and latitude coordinates corresponding to all the property class targets, normalize the property class business data in all the grid map blocks, and obtain a second normalization processing result; The weight coefficient acquisition module is configured to analyze the correlation between the first normalization processing result and the second normalization processing result using a canonical correlation analysis method, and obtain business weight coefficients respectively corresponding to the different risk factors; The risk map labeling construction module is configured to perform multiplication calculation on the business weight coefficients respectively corresponding to the different risk factors and the property class business data in each grid map block to obtain business data corresponding to the different risk factors in each grid map block, label the business data in the region map corresponding to the specific map region, and complete construction of a business risk map. 10.A computer device comprising a memory and a processor, wherein the memory stores computer readable instructions, and the processor executes the computer readable instructions to implement steps of the business risk map construction method according to any one of claims 1 to 8.

11. A computer readable storage medium, characterized in that, The computer readable storage medium stores computer readable instructions, and the computer readable instructions are executed by a processor to implement steps of the business risk map construction method according to any one of claims 1 to 8.

Images