Risk map generation method, device, and equipment, and storage medium

Abstract

The present application relates to data processing, and provides a risk map generation method, device, equipment and storage medium. The method collects initial station rainfall data and pre-processes to obtain target station rainfall data, collects grid rainfall data and rainfall claim information, calculates index information of each preset rainfall index based on the grid rainfall data, selects a target index based on the index information and the rainfall claim information and extracts target information, corrects the target information based on the target station rainfall data to obtain correction data including intensity data and frequency data, updates the intensity data based on the frequency data to obtain a risk value, and identifies a preset map based on the risk value, thereby improving the accuracy and comprehensiveness of the rainfall risk map. In addition, the present application also relates to blockchain technology, and the rainfall risk map can be stored in the blockchain.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to a risk map generation method, device, equipment and storage medium. BACKGROUND

[0002] At present, in the risk map generation scheme, the risk is usually identified directly through satellite observation grid point data or directly using sensor collection station data, however, due to the low accuracy of grid point data, and the station data cannot be popularized to every position, resulting in that the risk map cannot be accurately and comprehensively generated. SUMMARY

[0003] In view of the above, it is necessary to provide a risk map generation method, device, equipment and storage medium, which can solve the technical problem that the risk map cannot be accurately and comprehensively generated.

[0004] In one aspect, the present application provides a risk map generation method, which comprises:

[0005] Collecting initial station rainfall data of a plurality of stations in a preset time period;

[0006] Pretreating the initial station rainfall data to obtain target station rainfall data;

[0007] Collecting grid rainfall data of a plurality of grids based on the preset time period, and collecting rainfall claim information corresponding to each grid and the preset time period at the same time;

[0008] Calculating index information corresponding to each preset rainfall index of the plurality of grids based on the grid rainfall data;

[0009] Selecting a target index from a plurality of preset rainfall indexes based on the index information and the rainfall claim information, and extracting target information from the index information based on the target index;

[0010] Correcting the target information based on the target station rainfall data to obtain correction data corresponding to the target index, the correction data comprising intensity data and frequency data;

[0011] Updating the intensity data based on the frequency data to obtain risk values of the plurality of grids;

[0012] Identifying a preset map based on the risk values to obtain a rainfall risk map.

[0013] According to the present application, the pretreatment of the initial station rainfall data to obtain target station rainfall data comprises:

[0014] Standardize the initial station rainfall data to obtain standard data;

[0015] Generate a data identifier of the standard data based on the collection station and collection timestamp of the initial station rainfall data;

[0016] De-duplicate the standard data based on the data identifier to obtain intermediate station rainfall data;

[0017] Count the data amount of data greater than a preset rainfall value in the intermediate station rainfall data;

[0018] If the data amount is greater than a configured amount, identify abnormal data of the intermediate station rainfall data;

[0019] Eliminate the abnormal data from the intermediate station rainfall data to obtain target station rainfall data.

[0020] According to the preferred embodiment of the present application, the index information corresponding to each preset rainfall index calculated based on the grid rainfall data comprises:

[0021] Obtain a calculation function of each preset rainfall index;

[0022] Construct an execution thread based on the index number of multiple preset rainfall indexes, and create a thread task of each execution thread based on the grid of multiple grids and each calculation function;

[0023] Control multiple execution threads to process multiple thread tasks in parallel to obtain the index information.

[0024] According to the preferred embodiment of the present application, the target index selected from multiple preset rainfall indexes based on the index information and the rainfall claim information comprises:

[0025] Identify a claim index corresponding to the rainfall claim information;

[0026] Calculate a covariance value of each preset rainfall index and the claim index based on the index information and the rainfall claim information;

[0027] Calculate a rainfall variance value of each preset rainfall index based on the index information, and calculate a claim variance value of the claim index based on the rainfall claim information;

[0028] Calculate an index correlation degree of each preset rainfall index and the claim index based on the covariance value, the rainfall variance value, and the claim variance value;

[0029] Determine n preset rainfall indexes with the largest absolute value of the index correlation degree as the target index, n being a positive integer.

[0030] According to the preferred embodiment of the present application, the correction processing of the target information based on the target site rainfall data to obtain the correction data corresponding to the target index comprises:

[0031] The site index data of each site in the target index is calculated based on the target site rainfall data;

[0032] The area information corresponding to each site is identified based on the multiple sites and a preset radius, and the site index data is associated with the area information;

[0033] The target information of each grid is compared with the site index data of the corresponding area information;

[0034] If the target information is less than the corresponding site index data, the corresponding site index data is determined as the correction data of the grid corresponding to the target information; or

[0035] If the target information is greater than or equal to the corresponding site index data, the target information is determined as the correction data of the grid corresponding to the target information.

[0036] According to the preferred embodiment of the present application, the updating of the intensity data based on the frequency data to obtain the risk value of the multiple grids comprises:

[0037] The intensity data is preprocessed to obtain target intensity, and the frequency data is preprocessed to obtain initial frequency;

[0038] The data greater than a preset frequency is extracted from the initial frequency as target frequency;

[0039] The target frequency is compared with the corresponding target intensity;

[0040] If the target frequency is greater than the corresponding target intensity, the target frequency is determined as the risk value; or

[0041] If the target frequency is less than or equal to the corresponding target intensity, the corresponding target intensity is determined as the risk value.

[0042] According to the preferred embodiment of the present application, the risk map generation further comprises:

[0043] The target grid is identified from the multiple grids based on the preset map;

[0044] Whether the target grid is null is detected based on the grid rainfall data;

[0045] If the target grid is empty, an adjacent grid adjacent to the target grid is obtained from the plurality of grids, and data corresponding to the adjacent grid in the grid rainfall data is obtained as the grid rainfall data of the target grid.

[0046] In another aspect, the present application also provides a risk map generation device, which comprises:

[0047] An acquisition unit is configured to acquire initial site rainfall data of a plurality of sites in a preset time period;

[0048] A preprocessing unit is configured to preprocess the initial site rainfall data to obtain target site rainfall data;

[0049] The acquisition unit is further configured to acquire grid rainfall data of a plurality of grids based on the preset time period, and acquire rainfall claim information corresponding to each grid and the preset time period simultaneously;

[0050] A calculation unit is configured to calculate index information corresponding to each preset rainfall index of the plurality of grids based on the grid rainfall data;

[0051] A selection unit is configured to select a target index from the plurality of preset rainfall indexes based on the index information and the rainfall claim information, and extract target information from the index information based on the target index;

[0052] A correction unit is configured to correct the target information based on the target site rainfall data to obtain correction data corresponding to the target index, wherein the correction data comprises intensity data and frequency data;

[0053] An update unit is configured to update the intensity data based on the frequency data to obtain risk values of the plurality of grids;

[0054] An identification unit is configured to identify a preset map based on the risk values to obtain a rainfall risk map.

[0055] In another aspect, the present application also provides an electronic device, which comprises:

[0056] A memory configured to store computer readable instructions; and

[0057] A processor configured to execute the computer readable instructions stored in the memory to implement the risk map generation method.

[0058] In another aspect, the present application also provides a computer readable storage medium, which stores computer readable instructions, and the computer readable instructions are executed by a processor in an electronic device to implement the risk map generation method.

[0059] From the above technical solutions can be seen, the application can avoid the problems of data repetition or different data of the same station caused by repeated collection of the same station by preprocessing the initial station rainfall data, thereby improving the data quality of the target station rainfall data, and by selecting a target index from a plurality of preset rainfall indexes, the influence of indexes with less influence on insurance claim on risk value identification can be avoided, thereby improving the generation accuracy of the rainfall risk map generation, and since the data quality of the target station rainfall data is higher than that of the grid rainfall data, the accuracy of the corrected data can be improved by correcting the target information by using the target station rainfall data, and the influence of local areas on the risk value due to the particularity of the local areas can be avoided by updating the intensity data by using the frequency data, thereby further improving the generation accuracy of the rainfall risk map generation. In addition, since the data range of the grid rainfall data is wide, the comprehensiveness of the rainfall risk map can be improved.

[0060] The application can generate the rainfall risk map by combining the rainfall claim information and other insurance information related to the insurance business scenario, and the rainfall claim information can be converted into a risk value and marked in the rainfall risk map, thereby assisting relevant insurance companies in reasonably allocating the number of employees at the geographical location in the rainfall risk map, and assisting relevant insurance companies in reasonably pricing insurance at the geographical location in the rainfall risk map, etc.

[0061] In addition, the application can also send early warning information to the associated device corresponding to the risk position in the rainfall risk map according to the rainfall risk map, so as to realize early warning of the risk, which is beneficial to relevant personnel to take certain measures to reduce the disaster caused by the risk, and reminds the relevant departments to reserve a certain number of support teams to assist in disaster repair matters, etc., wherein the risk position refers to the position of the upcoming risk in the rainfall risk map.

[0062] Meanwhile, the application can also screen out key areas according to the rainfall risk map, so as to realize the reconstruction of facilities and buildings in key areas, avoid secondary damage caused by the recurrence of disasters, and thereby promote the development of smart cities, wherein the key area can be a position with a risk value greater than a preset value. BRIEF DESCRIPTION OF DRAWINGS

[0063] Figure 1 is a flowchart of a preferred embodiment of the risk map generation method of the application.

[0064] Figure 2 is a functional module diagram of a preferred embodiment of the risk map generation device of the application.

[0065] Figure 3is a structural schematic diagram of an electronic device for implementing a preferred embodiment of the risk map generation method of the present application. DETAILED DESCRIPTION

[0066] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be described in detail below in combination with the drawings and specific embodiments.

[0067] As shown in Figure 1 is a flow chart of a preferred embodiment of the risk map generation method of the present application. The order of steps in the flow chart can be changed according to different requirements, and some steps can be omitted.

[0068] The risk map generation method can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) is the theory, method, technology and application system for using digital computers or computer-controlled machines to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0069] The basic technology of artificial intelligence generally includes technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. The software technology of artificial intelligence mainly includes computer vision technology, robot technology, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning, etc.

[0070] The risk map generation method is applied to one or more electronic devices, which is a device capable of automatically performing numerical calculation and / or information processing according to pre-set or stored computer readable instructions. 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.

[0071] The electronic device can be any kind of electronic product that can interact with the user, such as personal computers, tablet computers, smart phones, personal digital assistants (PDAs), game consoles, interactive Internet Protocol Televisions (IPTVs), smart wearable devices, etc.

[0072] The electronic device can include a network device and / or a user device. The network device includes, but is not limited to, a single network electronic device, a group of electronic devices composed of multiple network electronic devices, or a cloud composed of a large number of hosts or network electronic devices based on cloud computing.

[0073] The network in which the electronic device is located includes, but is not limited to, the Internet, a wide area network, a metropolitan area network, a local area network, a virtual private network (VPN), etc.

[0074] 101, collect initial site rainfall data of a plurality of sites in a preset period.

[0075] In at least one embodiment of the present application, the plurality of sites refers to a place where a test sensor is stored in advance, wherein the test sensor can detect the initial site rainfall data.

[0076] The preset period can be set according to actual needs, for example, the preset period is 2018-2019.

[0077] The initial site rainfall data includes rainfall of the plurality of sites, etc.

[0078] In at least one embodiment of the present application, the electronic device collects detection data of the plurality of sites in the preset period from the test sensor as the initial site rainfall data.

[0079] 102, pre-process the initial site rainfall data to obtain target site rainfall data.

[0080] In at least one embodiment of the present application, the target site rainfall data refers to data obtained after deduplication processing and abnormal data processing.

[0081] In at least one embodiment of the present application, the electronic device pre-processes the initial site rainfall data to obtain target site rainfall data, which includes:

[0082] Standardizing the initial site rainfall data to obtain standard data;

[0083] Generating a data identifier of the standard data based on a collection site and a collection timestamp of the initial site rainfall data;

[0084] Based on the data identifier, the standard data is deduplicated to obtain intermediate site rainfall data;

[0085] Statistical data of the intermediate site rainfall data greater than a preset rainfall value;

[0086] If the data amount is greater than the configuration amount, it is identified that the intermediate station rainfall data has abnormal data;

[0087] The abnormal data is removed from the intermediate station rainfall data to obtain the target station rainfall data.

[0088] The standard data refers to data with a unit, for example, the standard data is all data with a unit of millimeters.

[0089] The collection station refers to a station corresponding to the initial station rainfall data obtained by the test sensor, the collection timestamp refers to a time point corresponding to the initial station rainfall data obtained by the test sensor, and the data identifier refers to an identifier generated after splicing the collection station and the collection timestamp.

[0090] The preset rainfall value and the configuration amount can be set according to actual needs, for example, the preset rainfall value can be 1000 millimeters. The configuration amount can be 1% of the total amount of the intermediate station rainfall data. That is, the total amount of data is 1000, and the configuration amount is 10.

[0091] By standardizing the initial station rainfall data, the initial station rainfall data can be avoided to be removed by mistake, and by de-duplicating the standard data through the data identifier, the problem that the same station has multiple data values at the same time in the intermediate station rainfall data can be avoided, and further, when the data amount is greater than the configuration amount, by identifying the abnormal data, the influence of a large amount of abnormal data on the rainfall risk map can be avoided.

[0092] Specifically, the electronic device de-duplicates the standard data based on the data identifier to obtain intermediate station rainfall data, including:

[0093] Identifying data corresponding to the same data identifier from the standard data as duplicate data;

[0094] Identifying a plurality of collection sensors of the duplicate data;

[0095] Determining the duplicate data corresponding to the collection sensor with the largest weight as the intermediate station rainfall data.

[0096] The plurality of collection sensors refers to test sensors that collect the duplicate data, and the weight of the test sensor is positively correlated with the accuracy and the number of data collected by the test sensor itself.

[0097] By identifying the intermediate station rainfall data through the weight, the accuracy of the intermediate station rainfall data can be improved.

[0098] Specifically, the electronic device pulls the LIDAR criterion to identify the abnormal data of the intermediate station rainfall data.

[0099] In other embodiments, if the data amount is less than or equal to the configuration amount, data greater than the preset rainfall value in the intermediate station rainfall data is removed to obtain the intermediate station rainfall data.

[0100] 103, based on the preset period, a plurality of grid rainfall data of a plurality of grids is collected, and rainfall claim information corresponding to each grid and the preset period is collected.

[0101] In at least one embodiment of the present application, the plurality of grids refers to a region obtained by grid processing based on a preset region.

[0102] The rainfall claim information includes claim amount, claim amount, etc.

[0103] In at least one embodiment of the present application, the grid rainfall data and the rainfall claim information can be collected from different preset websites.

[0104] In at least one embodiment of the present application, the risk map generation further comprises:

[0105] Based on a preset map, a target grid is identified from the plurality of grids;

[0106] Based on the grid rainfall data, it is detected whether the target grid is null;

[0107] If the target grid is null, a neighboring grid adjacent to the target grid is obtained from the plurality of grids, and data corresponding to the neighboring grid in the grid rainfall data is obtained as the grid rainfall data of the target grid.

[0108] Among them, the target grid can be a grid corresponding to a sea-land junction area.

[0109] Through the above implementation, the collection comprehensiveness of the grid rainfall data can be improved.

[0110] 104, based on the grid rainfall data, the index information corresponding to each preset rainfall index of the plurality of grids is calculated.

[0111] In at least one embodiment of the present application, a plurality of preset rainfall indexes can include, but are not limited to: maximum continuous rainfall amount, maximum continuous rainfall days, cumulative continuous rainfall amount, cumulative continuous rainfall days, maximum continuous heavy rain amount, maximum continuous heavy rain days, total rainfall days, total heavy rain days, total rainfall amount, total heavy rain amount, maximum rainfall amount, maximum heavy rain amount, etc.

[0112] In at least one embodiment of the present application, the electronic device calculates the index information corresponding to each preset rainfall index of the plurality of grids based on the grid rainfall data, which includes:

[0113] obtaining a calculation function of each preset rainfall index;

[0114] constructing an execution thread based on the number of indices of the plurality of preset rainfall indices, and creating a thread task of each execution thread based on the grid of the plurality of grids and each calculation function;

[0115] controlling a plurality of execution threads to process a plurality of thread tasks in parallel, thereby obtaining the index information.

[0116] The execution thread is constructed by the number of indices, and the thread task is constructed by the number of grids, so that the index information can be generated in parallel, thereby improving the generation efficiency of the index information.

[0117] 105, selecting a target index from the plurality of preset rainfall indices based on the index information and the rainfall claim information, and extracting target information from the index information based on the target index.

[0118] In at least one embodiment of the present application, the target index refers to a preset rainfall index with a higher correlation degree with the claim index corresponding to the rainfall claim information. The target information refers to the index information corresponding to the target index.

[0119] In at least one embodiment of the present application, the electronic device selects a target index from the plurality of preset rainfall indices based on the index information and the rainfall claim information, which includes:

[0120] identifying a claim index corresponding to the rainfall claim information;

[0121] calculating a covariance value of each preset rainfall index and the claim index based on the index information and the rainfall claim information;

[0122] calculating a rainfall variance value of each preset rainfall index based on the index information, and calculating a claim variance value of the claim index based on the rainfall claim information;

[0123] calculating an index correlation degree of each preset rainfall index and the claim index based on the covariance value, the rainfall variance value, and the claim variance value;

[0124] determining n preset rainfall indices with the largest absolute value of the index correlation degree as the target index, n being a positive integer.

[0125] The claim index can include the number of claims, the amount of claims, etc.

[0126] The calculation formula of the index correlation degree is: Wherein, s represents the index correlation degree, a represents the covariance value, b represents the rainfall variance value, and c represents the claim variance value.

[0127] n can be set according to actual needs, for example, n=5.

[0128] The covariance value, the rainfall variance value and the claim variance value can accurately generate the index correlation degree, thereby improving the selection accuracy of the target index.

[0129] 106, based on the target site rainfall data, the target information is corrected to obtain the correction data corresponding to the target index, and the correction data includes intensity data and frequency data.

[0130] In at least one embodiment of the present application, the correction data refers to the data generated by the target site rainfall data after the site data of the target index is corrected and updated to the target information.

[0131] The intensity data refers to the correction data representing the intensity index, and the frequency data refers to the correction data representing the frequency index. For example, the intensity index can include cumulative continuous rainfall and the like, and the frequency index can include maximum continuous rainfall days and the like.

[0132] In at least one embodiment of the present application, the electronic device corrects the target information based on the target site rainfall data to obtain the correction data corresponding to the target index, which includes:

[0133] Based on the target site rainfall data, the site index data of each site in the target index is calculated.

[0134] Based on the plurality of sites and the preset radius, the area information corresponding to each site is identified, and the site index data is associated with the area information.

[0135] The target information of each grid is compared with the site index data of the corresponding area information.

[0136] If the target information is less than the corresponding site index data, the corresponding site index data is determined as the correction data of the grid corresponding to the target information; or

[0137] If the target information is greater than or equal to the corresponding site index data, the target information is determined as the correction data of the grid corresponding to the target information.

[0138] The station index data can call a function relationship calculation of the target index and the target station rainfall data to generate.

[0139] The preset radius can be set according to actual needs, for example, the preset radius can be 100 m. The area information is generally a circular area with each station as the center and the preset radius.

[0140] Through the correction processing of the target information in the above embodiment, the underestimation of the rainfall risk caused by the target information can be avoided, and other risks caused by the underestimation of the rainfall risk can be avoided.

[0141] 107, updating the intensity data based on the frequency data to obtain the risk values of the plurality of grids.

[0142] In at least one embodiment of the present application, the risk value refers to a numerical value obtained after quantifying the risk of the plurality of grids.

[0143] In at least one embodiment of the present application, the electronic device updates the intensity data based on the frequency data to obtain the risk values of the plurality of grids, including:

[0144] The intensity data is preprocessed to obtain target intensity, and the frequency data is preprocessed to obtain initial frequency;

[0145] Data greater than a preset frequency is extracted from the initial frequency as target frequency;

[0146] The target frequency is compared with the corresponding target intensity;

[0147] If the target frequency is greater than the corresponding target intensity, the target frequency is determined as the risk value; or

[0148] If the target frequency is less than or equal to the corresponding target intensity, the corresponding target intensity is determined as the risk value.

[0149] The preset frequency can be set according to actual needs, for example, the preset frequency is 9.5.

[0150] Through the above embodiment, the underestimation of the rainfall risk caused by the target intensity can be avoided.

[0151] Specifically, the electronic device preprocesses the intensity data to obtain target intensity, including:

[0152] The intensity data is normalized to obtain normalized rainfall data;

[0153] Eliminate data greater than a preset intensity from the normalized rainfall data to obtain a preliminary screening intensity;

[0154] Weight and process a plurality of the preliminary screening intensities to obtain the target intensity.

[0155] The preset intensity can be set according to actual needs.

[0156] By eliminating data greater than the preset intensity, overestimation of the risk value due to heavy rain in some areas caused by geographical reasons can be avoided, thereby improving the rationality of generating the risk value.

[0157] Specifically, the electronic device pre-processes the frequency data to obtain an initial frequency, and the manner of pre-processing the intensity data to obtain a target intensity is similar, which will not be repeated here.

[0158] 108, identify a preset map based on the risk value to obtain a rainfall risk map.

[0159] It should be emphasized that, in order to further ensure the privacy and security of the above-mentioned rainfall risk map, the above-mentioned rainfall risk map can also be stored in a node of a block chain.

[0160] In at least one embodiment of the present application, the preset map can be set according to actual needs, for example, the preset map can be a region of country A, etc. The rainfall risk map refers to a preset map identified with the risk value.

[0161] In other embodiments, when the data corresponding to the plurality of sites and the plurality of grids respectively collected is data of other scenarios, the risk map generated by the electronic device can also be a map corresponding to the other scenarios, for example, the other scenarios can be a certain disaster scenario.

[0162] From the above technical scheme can be seen, the application can avoid the problems of data repetition or different data of the same station caused by repeated collection of the same station, thereby improving the data quality of the target station rainfall data, by selecting the target index from the plurality of preset rainfall indexes, the influence of the index with less influence on insurance claim on risk value identification can be avoided, thereby improving the generation accuracy of the rainfall risk map generation, and since the data quality of the target station rainfall data is higher than that of the grid rainfall data, the accuracy of the corrected data can be improved by correcting the target information with the target station rainfall data, and the influence of local areas on the risk value due to the particularity of the area can be avoided by updating the intensity data with the frequency data, thereby further improving the generation accuracy of the rainfall risk map generation. In addition, since the data range of the grid rainfall data is wide, the comprehensiveness of the rainfall risk map can be improved.

[0163] The application can generate the rainfall risk map by combining the rainfall claim information and other insurance information related to the insurance business scenario, which can convert the rainfall claim information into risk value identification in the rainfall risk map, thereby assisting relevant insurance enterprises in reasonably allocating the number of employees at the geographic location in the rainfall risk map, and assisting relevant insurance enterprises in reasonably pricing insurance at the geographic location in the rainfall risk map, etc.

[0164] In addition, the application can also send early warning information to the associated device corresponding to the risk position in the rainfall risk map according to the rainfall risk map, so as to realize early warning of the risk, which is beneficial to relevant personnel to take certain measures to reduce the disaster caused by the risk, and remind the relevant departments to reserve certain support teams to assist disaster repair matters, etc., wherein the risk position refers to the position of the upcoming risk in the rainfall risk map.

[0165] Meanwhile, the application can also screen out key areas according to the rainfall risk map, so as to realize the reconstruction of facilities and buildings in key areas, avoid secondary damage caused by the recurrence of disasters, and thereby promote the development of smart cities, wherein the key area can be a position with a risk value greater than a preset value.

[0166] As Figure 2As shown is a functional module diagram of a preferred embodiment of the risk map generation apparatus of the present application. The risk map generation apparatus 11 comprises an acquisition unit 110, a preprocessing unit 111, a calculation unit 112, a selection unit 113, a correction unit 114, an update unit 115, an identification unit 116, an identification unit 117, a detection unit 118, and an acquisition unit 119. The modules / units referred to in the present application refer to a series of computer-readable instruction segments capable of being acquired by the processor 13 and capable of completing a fixed function, which are stored in the memory 12. In the present embodiment, the functions of each module / unit will be described in detail in subsequent embodiments.

[0167] The acquisition unit 110 acquires initial site rainfall data of a plurality of sites in a preset time period.

[0168] In at least one embodiment of the present application, the plurality of sites refers to a place where a test sensor is stored in advance, wherein the test sensor can detect the initial site rainfall data.

[0169] The preset time period can be set according to actual needs, for example, the preset time period is 2018-2019.

[0170] The initial site rainfall data includes rainfall of the plurality of sites, etc.

[0171] In at least one embodiment of the present application, the acquisition unit 110 acquires detection data of the plurality of sites in the preset time period from the test sensor as the initial site rainfall data.

[0172] The preprocessing unit 111 preprocesses the initial site rainfall data to obtain target site rainfall data.

[0173] In at least one embodiment of the present application, the target site rainfall data refers to data obtained after de-duplication processing and abnormal data processing.

[0174] In at least one embodiment of the present application, the preprocessing unit 111 preprocesses the initial site rainfall data to obtain target site rainfall data, comprising:

[0175] standardizing the initial site rainfall data to obtain standard data;

[0176] generating a data identifier of the standard data based on the acquisition site and the acquisition timestamp of the initial site rainfall data;

[0177] performing de-duplication processing on the standard data based on the data identifier to obtain intermediate site rainfall data;

[0178] counting a data amount of the intermediate station rainfall data greater than a preset rainfall value;

[0179] If the data amount is greater than a configuration amount, it is identified that the intermediate station rainfall data has abnormal data;

[0180] The abnormal data is excluded from the intermediate station rainfall data to obtain the target station rainfall data.

[0181] The standard data refers to unit uniform data, for example, the standard data is all data in millimeters.

[0182] The collection station refers to the station corresponding to the initial station rainfall data obtained by the test sensor, the collection timestamp refers to the time point corresponding to the initial station rainfall data obtained by the test sensor, and the data identifier refers to the identifier generated after splicing the collection station and the collection timestamp.

[0183] The preset rainfall value and the configuration amount can be set according to actual needs, for example, the preset rainfall value can be 1000 millimeters. The configuration amount can be 1% of the total amount of the intermediate station rainfall data. That is, the total amount is 1000, and the configuration amount is 10.

[0184] By standardizing the initial station rainfall data, the initial station rainfall data can be avoided to be mistakenly excluded, by the data identifier, the standard data can be de-duplicated to avoid the problem that the same station has multiple data values at the same time in the intermediate station rainfall data, and further, when the data amount is greater than the configuration amount, by identifying the abnormal data, the influence of a large amount of abnormal data on the rainfall risk map can be avoided.

[0185] Specifically, the preprocessing unit 111 de-duplicates the standard data based on the data identifier to obtain intermediate station rainfall data, including:

[0186] Identify the data corresponding to the same data identifier from the standard data as duplicate data;

[0187] Identify a plurality of collection sensors of the duplicate data;

[0188] The duplicate data corresponding to the collection sensor with the largest weight is determined as the intermediate station rainfall data.

[0189] The plurality of collection sensors refers to the test sensor that collects the duplicate data, and the weight of the test sensor is positively correlated with the accuracy and the collection amount of the data collected by the test sensor itself.

[0190] The intermediate station rainfall data is identified by the weight, so that the accuracy of the intermediate station rainfall data is improved.

[0191] Specifically, the preprocessing unit 111 identifies abnormal data of the intermediate station rainfall data by using the LIDAR criterion.

[0192] In other embodiments, if the data amount is less than or equal to the configuration amount, data greater than the preset rainfall value in the intermediate station rainfall data is removed to obtain the intermediate station rainfall data.

[0193] The collection unit 110 collects grid rainfall data of a plurality of grids based on the preset time period, and collects rainfall claim information corresponding to each grid and the preset time period.

[0194] In at least one embodiment of the present application, the plurality of grids refers to a region obtained by grid processing based on a preset region.

[0195] The rainfall claim information includes claim quantity, claim amount, etc.

[0196] In at least one embodiment of the present application, the grid rainfall data and the rainfall claim information can be collected from different preset websites.

[0197] In at least one embodiment of the present application, the identification unit 117 identifies a target grid from the plurality of grids based on a preset map.

[0198] The detection unit 118 detects whether the target grid is null based on the grid rainfall data.

[0199] If the target grid is null, the acquisition unit 119 acquires an adjacent grid adjacent to the target grid from the plurality of grids, and acquires data corresponding to the adjacent grid from the grid rainfall data as the grid rainfall data of the target grid.

[0200] The target grid can be a grid corresponding to a sea-land junction region.

[0201] Through the above embodiments, the collection comprehensiveness of the grid rainfall data can be improved.

[0202] The calculation unit 112 calculates index information corresponding to each preset rainfall index of the plurality of grids based on the grid rainfall data.

[0203] In at least one embodiment of the present application, the plurality of preset rainfall indexes can include, but are not limited to, maximum continuous rainfall, maximum continuous rainfall days, cumulative continuous rainfall, cumulative continuous rainfall days, maximum continuous heavy rainfall, maximum continuous heavy rainfall days, total rainfall days, total heavy rainfall days, total rainfall, total heavy rainfall, maximum rainfall, maximum heavy rainfall, etc.

[0204] In at least one embodiment of the present application, the index information corresponding to each preset rainfall index calculated by the computing unit 112 based on the grid rainfall data includes:

[0205] Obtaining a calculation function of each preset rainfall index;

[0206] Based on the number of indexes of the plurality of preset rainfall indexes, an execution thread is constructed, and based on the number of grids of the plurality of grids and each calculation function, a thread task of each execution thread is created;

[0207] Controlling a plurality of execution threads to process a plurality of thread tasks in parallel to obtain the index information.

[0208] The execution thread is constructed by the number of indexes, and the thread task is constructed by the number of grids, so that the index information can be generated in parallel, thereby improving the generation efficiency of the index information.

[0209] The selection unit 113 selects a target index from the plurality of preset rainfall indexes based on the index information and the rainfall claim information, and extracts target information from the index information based on the target index.

[0210] In at least one embodiment of the present application, the target index refers to a preset rainfall index with a higher correlation degree with a claim index corresponding to the rainfall claim information. The target information refers to index information corresponding to the target index.

[0211] In at least one embodiment of the present application, the selection unit 113 selects a target index from the plurality of preset rainfall indexes based on the index information and the rainfall claim information includes:

[0212] Identifying a claim index corresponding to the rainfall claim information;

[0213] Calculating a covariance value of each preset rainfall index and the claim index based on the index information and the rainfall claim information;

[0214] Calculating a rainfall variance value of each preset rainfall index based on the index information, and calculating a claim variance value of the claim index based on the rainfall claim information;

[0215] calculate an index correlation degree of each preset rainfall index and the claim index based on the covariance value, the rainfall variance value and the claim variance value;

[0216] determine n preset rainfall indexes with the maximum absolute value of the index correlation degree as the target indexes, n being a positive integer.

[0217] The claim index can include the number of claims, the claim amount, etc.

[0218] The calculation formula of the index correlation degree is: Wherein, s represents the index correlation degree, a represents the covariance value, b represents the rainfall variance value, and c represents the claim variance value.

[0219] n can be set according to actual needs, for example, n = 5.

[0220] The covariance value, the rainfall variance value and the claim variance value can be used to accurately generate the index correlation degree, thereby improving the selection accuracy of the target index.

[0221] The correction unit 114 corrects the target information based on the target site rainfall data to obtain correction data corresponding to the target index, and the correction data includes intensity data and frequency data.

[0222] In at least one embodiment of the present application, the correction data refers to data generated after the target site rainfall data corrects and updates the target information based on the site data of the target index.

[0223] The intensity data refers to correction data representing an intensity index, and the frequency data refers to correction data representing a frequency index. For example, the intensity index can include cumulative continuous rainfall, etc., and the frequency index can include the maximum number of consecutive rainfall days, etc.

[0224] In at least one embodiment of the present application, the correction unit 114 corrects the target information based on the target site rainfall data to obtain correction data corresponding to the target index, which includes:

[0225] Based on the target site rainfall data, calculate the site index data of each site in the target index;

[0226] Based on the plurality of sites and the preset radius, identify the area information corresponding to each site, and associate the site index data with the area information;

[0227] Compare the target information of each grid with the site index data of the corresponding area information;

[0228] If the target information is less than the corresponding site index data, the corresponding site index data is determined as the correction data of the grid corresponding to the target information; or

[0229] If the target information is greater than or equal to the corresponding site index data, the target information is determined as the correction data of the grid corresponding to the target information.

[0230] The site index data can be calculated by calling a function relationship between the target index and the target site rainfall data.

[0231] The preset radius can be set according to actual needs, for example, the preset radius can be 100 m. The area information is usually a circular area with each site as the center and the preset radius.

[0232] The above embodiment corrects the target information, which can avoid underestimating the rainfall risk caused by the target information, thereby avoiding other risks caused by underestimating the rainfall risk.

[0233] The updating unit 115 updates the intensity data based on the frequency data to obtain the risk values of the plurality of grids.

[0234] In at least one embodiment of the present application, the risk value refers to a numerical value obtained after quantifying the risk of the plurality of grids.

[0235] In at least one embodiment of the present application, the updating unit 115 updates the intensity data based on the frequency data to obtain the risk values of the plurality of grids, which includes:

[0236] The intensity data is preprocessed to obtain target intensity, and the frequency data is preprocessed to obtain initial frequency;

[0237] Data greater than a preset frequency is extracted from the initial frequency as target frequency;

[0238] The target frequency is compared with the corresponding target intensity;

[0239] If the target frequency is greater than the corresponding target intensity, the target frequency is determined as the risk value; or

[0240] If the target frequency is less than or equal to the corresponding target intensity, the corresponding target intensity is determined as the risk value.

[0241] The preset frequency can be set according to actual needs, for example, the preset frequency is 9.5.

[0242] Through the above embodiment, the underestimation of the target intensity to the rainfall risk can be avoided.

[0243] Specifically, the updating unit 115 pre-processes the intensity data to obtain the target intensity, including:

[0244] The intensity data is normalized to obtain normalized rainfall data;

[0245] Data greater than a preset intensity is removed from the normalized rainfall data to obtain a preliminary screening intensity;

[0246] The plurality of preliminary screening intensities are weighted and processed to obtain the target intensity.

[0247] The preset intensity can be set according to actual needs.

[0248] By removing data greater than the preset intensity, the overestimation of the risk value by a heavy rain in a certain region due to geographical reasons can be avoided, thereby improving the rationality of generating the risk value.

[0249] Specifically, the updating unit 115 pre-processes the frequency data to obtain an initial frequency, and the manner of obtaining the initial frequency is similar to the manner of obtaining the target intensity by the updating unit 115 pre-processing the intensity data, which will not be repeated here.

[0250] The identification unit 116 identifies a preset map based on the risk value to obtain a rainfall risk map.

[0251] It should be emphasized that, in order to further ensure the privacy and security of the above rainfall risk map, the above rainfall risk map can also be stored in a node of a block chain.

[0252] In at least one embodiment of the present application, the preset map can be set according to actual needs, for example, the preset map can be a region of country A, etc. The rainfall risk map refers to a preset map marked with the risk value.

[0253] In other embodiments, when the data corresponding to the plurality of sites and the plurality of grids respectively collected is other scene data, the risk map generated by the identification unit 116 can also be a map corresponding to the other scene, for example, the other scene can be a certain disaster scene.

[0254] From the above technical scheme can be seen, the application can avoid the problems of data repetition or different data of the same station caused by repeated collection of the same station, thereby improving the data quality of the target station rainfall data, by selecting the target index from the plurality of preset rainfall indexes, the influence of the index with less influence on insurance claim on risk value identification can be avoided, thereby improving the generation accuracy of the rainfall risk map generation, and since the data quality of the target station rainfall data is higher than that of the grid rainfall data, the accuracy of the corrected data can be improved by correcting the target information with the target station rainfall data, and the influence of local areas on the risk value due to the particularity of the local areas can be avoided by updating the intensity data with the frequency data, thereby further improving the generation accuracy of the rainfall risk map generation. In addition, since the data range of the grid rainfall data is wide, the comprehensiveness of the rainfall risk map can be improved.

[0255] The application can convert the rainfall claim information into a risk value and mark it in the rainfall risk map by generating the rainfall risk map by combining the rainfall claim information and other insurance information related to the insurance business scenario, thereby assisting relevant insurance companies in reasonably allocating the number of employees at the geographic location in the rainfall risk map, and assisting relevant insurance companies in reasonably pricing insurance at the geographic location in the rainfall risk map, etc.

[0256] In addition, the application can also send early warning information to the associated device corresponding to the risk position in the rainfall risk map according to the rainfall risk map, so as to realize early warning of the risk, which is beneficial to relevant personnel to take certain measures to reduce the disaster caused by the risk, and remind the relevant departments to reserve a certain number of support teams to assist in disaster repair matters, etc., wherein the risk position refers to the position of the upcoming risk in the rainfall risk map.

[0257] Meanwhile, the application can also screen out key areas according to the rainfall risk map, so as to realize the reconstruction of facilities and buildings in key areas, avoid secondary damage caused by the recurrence of disasters, and thereby promote the development of smart cities, wherein the key area can be a position with a risk value greater than a preset value.

[0258] As Figure 3 shown, it is a structure schematic diagram of an electronic device of a preferred embodiment of the risk map generation method of the application.

[0259] In an embodiment of the application, the electronic device 1 includes, but is not limited to, a memory 12, a processor 13, and computer readable instructions stored in the memory 12 and executable on the processor 13, such as a risk map generation program.

[0260] Those skilled in the art can understand that the schematic diagram is only an example of the electronic device 1, and does not constitute a limitation on the electronic device 1, and can include more or fewer components than the diagram, or combine certain components, or different components, for example, the electronic device 1 can also include an input / output device, a network access device, a bus, etc.

[0261] The processor 13 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The processor 13 is the operation core and control center of the electronic device 1, and connects each part of the entire electronic device 1 through various interfaces and lines, and executes the operating system and installed various application programs, program codes, etc. of the electronic device 1.

[0262] For example, the computer readable instructions can be divided into one or more modules / units, which are stored in the memory 12 and executed by the processor 13 to complete the present application. The one or more modules / units can be a series of computer readable instruction segments capable of completing a specific function, which are used to describe the execution process of the computer readable instructions in the electronic device 1. For example, the computer readable instructions can be divided into an acquisition unit 110, a preprocessing unit 111, a calculation unit 112, a selection unit 113, a correction unit 114, an update unit 115, an identification unit 116, an identification unit 117, a detection unit 118 and an acquisition unit 119.

[0263] The memory 12 can be used to store the computer readable instructions and / or modules, and the processor 13 realizes various functions of the electronic device 1 by running or executing the computer readable instructions and / or modules stored in the memory 12, and calling the data stored in the memory 12. The memory 12 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application program required by a function (such as a sound playing function, an image playing function, etc.), and the like; and the data storage area can store data created according to the use of the electronic device, etc. The memory 12 can include non-volatile and volatile memories, for example: a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash storage device, or other storage devices.

[0264] The memory 12 can be an external memory and / or an internal memory of the electronic device 1. Further, the memory 12 can be a memory having a physical form, such as a memory stick, a TF card (Trans-flash Card), and the like.

[0265] The modules / units integrated in the electronic device 1, if implemented in the form of software function units and sold or used as independent products, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by computer readable instructions instructing related hardware, and the computer readable instructions can be stored in a computer readable storage medium. When the computer readable instructions are executed by a processor, the steps of the above-mentioned various method embodiments can be implemented.

[0266] The computer readable instructions include computer readable instruction codes, which can be in the form of source code, object code, executable files, or some intermediate forms, etc. The computer readable medium can include any entity or device capable of carrying the computer readable instruction codes, recording media, U disks, mobile hard disks, magnetic disks, optical disks, computer memories, read-only memories (ROMs), random access memories (RAMs).

[0267] The blockchain referred to in the present application is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, and encryption algorithm. The blockchain is essentially a decentralized database, and is a series of data blocks associated using cryptographic methods, each of which contains information of a batch of network transactions, for verifying the validity (anti-fake) of the information and generating the next block. The blockchain can include a blockchain underlying platform, a platform product service layer, and an application service layer.

[0268] In combination Figure 1 The memory 12 in the electronic device 1 stores computer readable instructions to implement a risk map generation method, and the processor 13 can execute the computer readable instructions to implement:

[0269] Collect initial site rainfall data of a plurality of sites in a preset time period;

[0270] Pretreat the initial site rainfall data to obtain target site rainfall data;

[0271] Collect grid rainfall data of a plurality of grids based on the preset time period, and collect rainfall claim information corresponding to each grid and the preset time period at the same time;

[0272] Calculate index information corresponding to each preset rainfall index of the plurality of grids based on the grid rainfall data;

[0273] Select a target index from a plurality of preset rainfall indexes based on the index information and the rainfall claim information, and extract target information from the index information based on the target index;

[0274] Correct the target information based on the target site rainfall data to obtain correction data corresponding to the target index, the correction data including intensity data and frequency data;

[0275] Update the intensity data based on the frequency data to obtain risk values of the plurality of grids;

[0276] Identify a preset map based on the risk values to obtain a rainfall risk map.

[0277] Specifically, the specific implementation method of the processor 13 on the above computer readable instructions can refer to the description of related steps in the corresponding embodiments, which will not be repeated here. Figure 1

[0278] ​In several embodiments provided by the present application, it should be understood that the disclosed system, device and method can be implemented in other manners. For example, the described device embodiments are merely schematic. For example, the division of the modules is merely a logical function division. There can be another division manner for the actual implementation.

[0279] The computer readable storage medium stores computer readable instructions, wherein the computer readable instructions are executed by the processor 13 to implement the following steps:

[0280] Collect initial site rainfall data of a plurality of sites in a preset time period;

[0281] Preprocess the initial site rainfall data to obtain target site rainfall data;

[0282] Collect grid rainfall data of a plurality of grids based on the preset time period, and collect rainfall claim information corresponding to each grid and the preset time period at the same time;

[0283] Calculate index information corresponding to each preset rainfall index of the plurality of grids based on the grid rainfall data;

[0284] Select a target index from the plurality of preset rainfall indexes based on the index information and the rainfall claim information, and extract target information from the index information based on the target index;

[0285] Correct the target information based on the target site rainfall data to obtain correction data corresponding to the target index, wherein the correction data includes intensity data and frequency data;

[0286] Update the intensity data based on the frequency data to obtain risk values of the plurality of grids;

[0287] Identify a preset map based on the risk values to obtain a rainfall risk map.

[0288] The modules described as separate components can or can not be physically separate, and the components displayed as modules can or can not be physical units, i.e., they can be located in one place or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment according to actual needs.

[0289] In addition, each functional module in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of hardware plus software functional modules.

[0290] Thus, the embodiments should be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. No single feature or combination of features should be considered limiting of the claims in isolation.

[0291] Furthermore, the term "comprising" does not exclude other elements or steps, and the singular does not exclude the plural and vice-versa, unless the context clearly requires these exclusions. The terms "comprising", "comprise" and "when comprising" should be construed to be inclusive and not exclusive. Any reference signs in the claims should not be construed as limiting the claim. Any reference signs in the claims should not be construed as limiting the claim.

[0292] Finally, it should be noted that the above-mentioned embodiments illustrate rather than limit the application, since the skilled person, having regard to the disclosure, will be able to devise modifications and equivalents without departing from the scope of the application.

Claims

1. A risk map generation method characterized by, The risk map generation method comprises: Collect initial station rainfall data of a plurality of stations in a preset time period; Pretreat the initial station rainfall data to obtain target station rainfall data, including: standardizing the initial station rainfall data to obtain standard data; generating a data identifier for the standard data based on the collection station and collection timestamp of the initial station rainfall data; performing deduplication processing on the standard data based on the data identifier to obtain intermediate station rainfall data; counting the amount of data greater than a preset rainfall value in the intermediate station rainfall data; if the data amount is greater than a configured amount, identifying abnormal data of the intermediate station rainfall data; excluding the abnormal data from the intermediate station rainfall data to obtain the target station rainfall data; Collect grid rainfall data of a plurality of grids based on the preset time period, and collect rainfall claim information corresponding to each grid and the preset time period; Calculate index information corresponding to each preset rainfall index of the plurality of grids based on the grid rainfall data, including: obtaining a calculation function of each preset rainfall index; constructing an execution thread based on the index quantity of a plurality of preset rainfall indexes, and creating a thread task of each execution thread based on the grid of the plurality of grids and each calculation function; control a plurality of execution threads to process a plurality of thread tasks in parallel to obtain the index information; Select a target index from a plurality of preset rainfall indexes based on the index information and the rainfall claim information, and extract target information from the index information based on the target index, wherein the target index is selected from a plurality of preset rainfall indexes based on the index information and the rainfall claim information, including: identifying a claim index corresponding to the rainfall claim information; calculating a covariance value of each preset rainfall index and the claim index based on the index information and the rainfall claim information; calculating a rainfall variance value of each preset rainfall index based on the index information, and calculating a claim variance value of the claim index based on the rainfall claim information; calculating an index correlation degree of each preset rainfall index and the claim index based on the covariance value, the rainfall variance value, and the claim variance value; determining n preset rainfall indexes with the largest absolute value of the index correlation degree as the target index, n being a positive integer; Correct the target information based on the target station rainfall data to obtain correction data corresponding to the target index, the correction data including intensity data and frequency data; Update the intensity data based on the frequency data to obtain risk values of the plurality of grids; Identify a preset map based on the risk values to obtain a rainfall risk map.

2. The risk map generation method according to claim 1, wherein The correction of the target information based on the target station rainfall data to obtain the correction data corresponding to the target index comprises: Calculate station index data of each station in the target index based on the target station rainfall data; Identify area information corresponding to each station based on the plurality of stations and a preset radius, and associate the station index data with the area information; Compare the target information of each grid with the site index data of the corresponding area information; If the target information is less than the corresponding site index data, the corresponding site index data is determined as the correction data of the grid corresponding to the target information; or If the target information is greater than or equal to the corresponding site index data, the target information is determined as the correction data of the grid corresponding to the target information.

3. The risk map generation method according to claim 1, wherein The updating of the intensity data based on the frequency data to obtain the risk values of the plurality of grids comprises: Pretreating the intensity data to obtain target intensity, and pretreating the frequency data to obtain initial frequency; Extracting data greater than a preset frequency from the initial frequency as target frequency; Comparing the target frequency with the corresponding target intensity; If the target frequency is greater than the corresponding target intensity, the target frequency is determined as the risk value; or If the target frequency is less than or equal to the corresponding target intensity, the corresponding target intensity is determined as the risk value.

4. The risk map generation method of claim 1, wherein, The risk map generation further comprises: Identifying a target grid from the plurality of grids based on the preset map; Detecting whether the target grid is null based on the grid rainfall data; If the target grid is null, acquiring adjacent grids adjacent to the target grid from the plurality of grids, and acquiring data corresponding to the adjacent grids from the grid rainfall data as the grid rainfall data of the target grid.

5. A risk map generating apparatus characterized by comprising: The risk map generation device comprises: A collection unit configured to collect initial site rainfall data of a plurality of sites in a preset time period; A preprocessing unit configured to pretreat the initial site rainfall data to obtain target site rainfall data, comprising: standardizing the initial site rainfall data to obtain standard data; generating a data identifier of the standard data based on the collection site and collection timestamp of the initial site rainfall data; de-duplicating the standard data based on the data identifier to obtain intermediate site rainfall data; counting the amount of data greater than a preset rainfall value in the intermediate site rainfall data; identifying abnormal data of the intermediate site rainfall data if the amount of data is greater than a configuration amount; and excluding the abnormal data from the intermediate site rainfall data to obtain the target site rainfall data; The collection unit is further configured to collect grid rainfall data of a plurality of grids based on the preset time period, and collect rainfall claim information corresponding to each grid and the preset time period at the same time; A calculation unit configured to calculate index information corresponding to each preset rainfall index based on the grid rainfall data of the plurality of grids, comprising: acquiring a calculation function of each preset rainfall index; constructing an execution thread based on the number of indices of a plurality of preset rainfall indices, and creating a thread task of each execution thread based on the grid of the plurality of grids and each calculation function; and controlling a plurality of execution threads to process a plurality of thread tasks in parallel to obtain the index information; The selecting unit is configured to select a target index from the plurality of preset rainfall indexes based on the index information and the rainfall claim information, and extract target information from the index information based on the target index. The selection of the target index from the plurality of preset rainfall indexes based on the index information and the rainfall claim information includes: identifying a claim index corresponding to the rainfall claim information; calculating a covariance value of each preset rainfall index and the claim index based on the index information and the rainfall claim information; calculating a rainfall variance value of each preset rainfall index based on the index information, and calculating a claim variance value of the claim index based on the rainfall claim information; calculating an index correlation degree of each preset rainfall index and the claim index based on the covariance value, the rainfall variance value, and the claim variance value; and determining n preset rainfall indexes with the maximum absolute value of the index correlation degree as the target index, where n is a positive integer. The correcting unit is configured to correct the target information based on the target site rainfall data to obtain corrected data corresponding to the target index, where the corrected data includes intensity data and frequency data. The updating unit is configured to update the intensity data based on the frequency data to obtain risk values of the plurality of grids. The identifying unit is configured to identify a preset map based on the risk values to obtain a rainfall risk map.

6. An electronic device, comprising: The electronic device includes: a memory storing computer readable instructions; and a processor executing the computer readable instructions stored in the memory to implement the risk map generation method according to any one of claims 1 to 4.

7. 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 in an electronic device to implement the risk map generation method according to any one of claims 1 to 4.

Images