Credit information analysis method and device, electronic equipment and storage medium

Abstract

The invention discloses a credit information analysis method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining position data of a target land parcel delineated by a loan user through a mobile terminal; analyzing the position data of the target land parcel to obtain position information of the target land parcel; acquiring a plurality of satellite remote sensing images of the current target plot according to the position information of the target plot; on the basis of each satellite remote sensing image of the current target land parcel, crop associated information of the current target land parcel is obtained; inputting the position information of the target plot and the crop association information of the current target plot into a pre-trained evaluation model, and analyzing various crop evaluation results of the current target plot through the evaluation model; calculating the comprehensive evaluation grade of the target plot according to the evaluation results of the crops of the current target plot; and adjusting the loan amount and interest rate of the loan user based on the comprehensive evaluation level of the target plot.

Description

Technical Field

[0001] The present application relates to the field of data analysis technology, and in particular to a credit information analysis method and device, electronic equipment, and storage medium. Background Art

[0002] Currently, many farmers are beginning to have a demand for credit. In order to reduce risks when applying for credit, it is necessary to analyze the relevant information of the borrower, such as valid collateral, guarantees, and personal information, and then handle credit business with reference to the results of the analysis. Therefore, the comprehensiveness and accuracy of information analysis are very important.

[0003] Since farmers usually lack conventional effective collateral or other guarantees, users are now allowed to use the crops on their land as collateral for loans. Therefore, in order to effectively reduce the risk of farmers using crops on their land as collateral for loans, farmers will manually fill in land data, land crop data, land data, etc. Then the staff will check and analyze these data. Finally, depending on the results of the analysis, it is determined whether to apply for a loan business, as well as the specific loan amount and interest rate.

[0004] However, since these data are filled in by farmers and manually checked and analyzed by staff, the customer-oriented and authenticity of the analysis results cannot be effectively guaranteed, and the accuracy cannot be guaranteed either, which leads to excessive risks. Summary of the invention

[0005] Based on the above-mentioned deficiencies of the prior art, the present application provides a credit information analysis method and device, electronic device, and storage medium to solve the problem that the prior art cannot guarantee the authenticity and accuracy of the analysis results.

[0006] In order to achieve the above objectives, this application provides the following technical solutions:

[0007] The first aspect of the present application provides a credit information analysis method, comprising:

[0008] Obtain the location data of the target plot drawn by the loan user through the mobile terminal;

[0009] Analyzing the location data of the target plot to obtain the location information of the target plot;

[0010] According to the location information of the target land parcel, a plurality of satellite remote sensing images of the current target land parcel are obtained; wherein each satellite remote sensing image of the target land parcel includes at least a current multispectral image, a hyperspectral image, a radar image and an infrared image of the target land parcel;

[0011] Based on each satellite remote sensing image of the current target plot, the crop-related information of the current target plot is obtained; wherein the crop-related information of the target plot includes the type and planting area of ​​each type of crop in the target plot and multiple information affecting the crop yield on the target plot;

[0012] Input the location information of the target plot and the crop-related information of the current target plot into a pre-trained evaluation model, and analyze the various crop evaluation results of the current target plot through the evaluation model; wherein the various crop evaluation results of the target plot at least include crop adaptability score, predicted per-acre yield, growth rating and potential disasters;

[0013] Calculate the comprehensive assessment grade of the target plot according to the current crop assessment results of the target plot;

[0014] Based on the comprehensive assessment level of the target plot of land, the loan amount and interest rate of the loan user are adjusted.

[0015] Optionally, in the above-mentioned credit information analysis method, the analyzing the location data of the target plot to obtain the location information of the target plot includes:

[0016] Verify the correctness of the location data of the target plot by comparing the location data of the target plot with the plot vector data of the land title confirmation certificate;

[0017] If it is verified that the location data of the target plot is correct, the location data of the target plot is converted into a coordinate system used by a geographic information system to obtain standard location data of the target plot;

[0018] The standard location data of the target plot is used to analyze the boundary and line segments of the target plot to obtain the location information of the target plot.

[0019] Optionally, in the above-mentioned credit information analysis method, before acquiring the crop-related information of the current target plot based on each satellite remote sensing image of the current target plot, the method further includes:

[0020] Preprocessing each satellite remote sensing image of the current target plot;

[0021] fusing the pre-processed satellite remote sensing images of the target plot;

[0022] The fused satellite remote sensing images of the target plot are converted into raster images of a unified format.

[0023] Optionally, in the above-mentioned credit information analysis method, the training method of the evaluation model includes:

[0024] Obtain historical data of multiple plots as sample data;

[0025] Annotating the sample data to obtain training sample data;

[0026] Encoding and feature processing the training sample data;

[0027] The evaluation model is iteratively trained using the processed training sample data until the evaluation model passes the verification.

[0028] Optionally, in the above credit information analysis method, it also includes:

[0029] At preset time intervals, obtaining crop-related information of the current target plot;

[0030] Input the location information of the target plot and the crop-related information of the current target plot into a pre-trained evaluation model, and analyze the evaluation results of various crops of the current target plot through the evaluation model;

[0031] According to the current crop assessment results of the target plot, the repayment capacity of the loan user is assessed, and a historical risk map of the target plot is drawn;

[0032] The repayment capacity value of the loan user and the historical risk map of the target plot are displayed.

[0033] A second aspect of the present application provides a credit information analysis device, comprising:

[0034] A location data acquisition unit, used to acquire location data of a target plot drawn by a loan user through a mobile terminal;

[0035] A location analysis unit, used to analyze the location data of the target plot to obtain the location information of the target plot;

[0036] An image data acquisition unit, configured to acquire a plurality of satellite remote sensing images of the current target land parcel according to the location information of the target land parcel; wherein each satellite remote sensing image of the target land parcel at least includes a current multispectral image, a hyperspectral image, a radar image, and an infrared image of the target land parcel;

[0037] A data analysis unit, configured to obtain crop-related information of the current target plot based on each satellite remote sensing image of the current target plot; wherein the crop-related information of the target plot includes the type and planting area of ​​each type of crop of the target plot and multiple information affecting the crop yield on the target plot;

[0038] An input unit is used to input the location information of the target plot and the crop-related information of the current target plot into a pre-trained evaluation model, and analyze various crop evaluation results of the current target plot through the evaluation model; wherein the various crop evaluation results of the target plot at least include crop adaptability scores, predicted per-acre yields, growth ratings, and potential disasters;

[0039] An evaluation unit, used to calculate a comprehensive evaluation grade of the target plot according to the evaluation results of various crops of the target plot;

[0040] An adjustment unit is used to adjust the loan amount and interest rate of the loan user based on the comprehensive evaluation level of the target plot of land.

[0041] Optionally, in the above-mentioned credit information analysis device, the location analysis unit includes:

[0042] A verification unit, used to verify the correctness of the location data of the target plot of land by comparing the location data of the target plot of land with the plot vector data of the land title confirmation certificate;

[0043] A coordinate conversion unit, for converting the position data of the target plot into a coordinate system used by a geographic information system to obtain standard position data of the target plot when the position data of the target plot is verified to be correct;

[0044] The position information analysis unit is used to analyze the boundary and line segment of the target plot by using the standard position data of the target plot to obtain the position information of the target plot.

[0045] Optionally, in the above-mentioned credit information analysis device, it also includes:

[0046] A preprocessing unit, used for preprocessing each satellite remote sensing image of the current target land parcel;

[0047] A fusion unit, used for fusing the pre-processed satellite remote sensing images of the target land plot;

[0048] The format conversion unit is used to convert the fused satellite remote sensing images of the target land into a raster image of a unified format.

[0049] Optionally, in the above-mentioned credit information analysis device, it also includes:

[0050] A sample acquisition unit, used for acquiring historical data of multiple plots as sample data;

[0051] A labeling unit, used to label the sample data to obtain training sample data;

[0052] A sample processing unit, used for encoding and feature processing the training sample data;

[0053] A training unit is used to iteratively train the evaluation model using the processed training sample data until the evaluation model passes the verification.

[0054] Optionally, in the above-mentioned credit information analysis device, it also includes:

[0055] A correlation information acquisition unit, used for acquiring crop correlation information of the current target plot at preset time intervals;

[0056] A real-time evaluation unit is used to input the location information of the target plot and the crop-related information of the current target plot into a pre-trained evaluation model, and analyze the evaluation results of various crops of the current target plot through the evaluation model;

[0057] A risk information processing unit, used to evaluate the repayment ability of the loan user according to the current crop evaluation results of the target plot, and to draw a historical risk map of the target plot;

[0058] A display unit is used to display the repayment ability value of the loan user and the historical risk map of the target plot of land.

[0059] A third aspect of the present application provides an electronic device, including:

[0060] Memory and processor;

[0061] Wherein, the memory is used to store programs;

[0062] The processor is used to execute the program, and when the program is executed, it is specifically used to implement the credit information analysis method as described in any one of the above.

[0063] A fourth aspect of the present application provides a computer storage medium for storing a computer program, wherein when the computer program is executed by a processor, the computer program is used to implement the credit information analysis method as described in any one of the above.

[0064] The present application provides a credit information analysis method, which obtains the location data of the target plot drawn by the loan user through the mobile terminal. Then the location data of the target plot is analyzed to obtain the location information of the target plot, so as to obtain the accurate location information of the target plot. Then, according to the location information of the target plot, multiple satellite remote sensing images of the current target plot are obtained. Among them, each satellite remote sensing image of the target plot at least includes the current multispectral image, hyperspectral image, radar image and infrared image of the target plot, so that a large number of features can be obtained through multiple types of images, thereby improving the precision and accuracy of the analysis results. Then, based on each satellite remote sensing image of the current target plot, the crop association information of the current target plot is obtained. Among them, the crop association information of the target plot includes the type of various crops of the target plot, the planting area and multiple information affecting the crop yield on the target plot. Then, the location information of the target plot and the crop association information of the current target plot are input into the pre-trained evaluation model, and the evaluation model is used to analyze the various crop evaluation results of the current target plot. Among them, the various crop assessment results of the target plot include at least crop adaptability score, predicted per-acre yield, growth rating and potential disasters, so as to obtain multiple information reflecting the benefits of the target plot. Finally, according to the various crop assessment results of the current target plot, the comprehensive assessment grade of the target plot is calculated, and finally based on the comprehensive assessment grade of the target plot, the loan amount and interest rate of the loan user are adjusted, thereby realizing a method for automatically obtaining and analyzing relevant information of the plot, without the need for manual analysis, and obtaining comprehensive and accurate analysis data, effectively ensuring the objectivity and authenticity of the analysis results. Therefore, referring to the analysis results for loans can effectively reduce the analysis of loans. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0066] Figure 1 A flowchart of a credit information analysis method provided in an embodiment of the present application;

[0067] Figure 2 A flowchart of a method for analyzing location information of a target plot provided in an embodiment of the present application;

[0068] Figure 3 A flowchart of a satellite remote sensing image preprocessing method provided in an embodiment of the present application;

[0069] Figure 4A flowchart of a training method for an evaluation model provided in an embodiment of the present application;

[0070] Figure 5 A flow chart of a dynamic risk control monitoring method provided in an embodiment of the present application;

[0071] Figure 6 A schematic diagram of the structure of a credit information analysis device provided in an embodiment of the present application;

[0072] Figure 7 A schematic diagram of the architecture of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0073] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0074] In this application, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0075] This application embodiment provides a credit information analysis method, such as Figure 1 As shown, the specific steps include:

[0076] S101. Obtaining location data of a target plot of land drawn by a loan user through a mobile terminal.

[0077] Specifically, the satellite map can be displayed in the mini-program or client on the mobile terminal, and the loan user can outline the business plot from the satellite map, and the location data of the target plot will be obtained at this time.

[0078] S102: Analyze the location data of the target plot to obtain the location information of the target plot.

[0079] It should be noted that since the target plot drawn by the user is not accurate enough and cannot be used for subsequent analysis, in order to calibrate the position of the target plot and obtain accurate data that can be used for subsequent analysis, it is necessary to further analyze the position data of the target plot, that is, to calibrate the position data of the target plot, and perform data extraction and conversion to obtain the location information of the target plot.

[0080] Optionally, in another embodiment of the present application, a specific implementation of step S102 is as follows: Figure 2 As shown, the following steps are included:

[0081] S201. Verify the correctness of the location data of the target plot by comparing the location data of the target plot with the plot vector data of the land title confirmation certificate.

[0082] Specifically, in order to determine whether the target land being outlined belongs to the loan user and whether the outlined range is accurate. Therefore, in the embodiment of the present application, the location data of the target plot is automatically compared with the plot vector data of the land title certificate. If the two are completely consistent, it is determined that the location data of the target plot is correct. If the two are completely inconsistent, it is determined that there is an error in the location data of the target plot. At this time, the user can be reminded through the mobile client to facilitate re-outlining and confirmation.

[0083] S202: Determine whether the location data of the target plot is correct.

[0084] If it is determined that the location data of the target plot is correct, step S202 may be executed.

[0085] S203: Convert the location data of the target plot into a coordinate system used by a geographic information system to obtain standard location data of the target plot.

[0086] In order to standardize the location data of the target plot and facilitate the next step of analysis, it is necessary to convert the location data of the target plot into the coordinate system used by the geographic information system.

[0087] S204: Analyze the boundary and line segments of the target plot using the standard location data of the target plot to obtain location information of the target plot.

[0088] Optionally, the spatial analysis functions of the geographic information system, such as cache area analysis, topological relationship check, etc., can be used to analyze the standard location data of the target plot, thereby identifying the boundary point coordinates and line segments of the target plot, and then generating closed plot boundary information, that is, obtaining the location information of the target plot.

[0089] S103. Acquire multiple satellite remote sensing images of the current target land parcel according to the location information of the target land parcel.

[0090] The satellite remote sensing images of the target land parcel at least include the current multispectral image, hyperspectral image, radar image and infrared image of the target land parcel.

[0091] It should be noted that, since different crops have different values, and different crop growth conditions, climates, etc. all affect the final returns, the loan needs to ensure that the plot has matching returns in order to effectively reduce the risk. Therefore, it is necessary to analyze the associated information of the crops on the plot. Therefore, in the embodiment of the present application, based on the location information of the target plot, multispectral images, hyperspectral images, radar images, and infrared images of the target plot are collected through satellite remote sensing technology, so that the required comprehensive and accurate crop-related data can be analyzed based on these multiple types of image data.

[0092] Optionally, in another embodiment of the present application, before executing step S104, the satellite remote sensing image may be pre-processed. Figure 3 As shown, a satellite remote sensing image preprocessing method provided in an embodiment of the present application includes the following steps:

[0093] S301, pre-processing each satellite remote sensing image of the current target plot.

[0094] Specifically, each satellite remote sensing image is subjected to cloud and fog interference removal, atmospheric correction, radiation calibration, etc., to improve the image quality.

[0095] S302: Fusing the pre-processed satellite remote sensing images of the target land parcel.

[0096] Specifically, the pre-processed satellite remote sensing images of the target plot are fused to increase the amount of information, that is, to obtain different types of data from different types of satellite remote sensing images, thereby improving the precision and accuracy of the analysis.

[0097] S303: Convert the fused satellite remote sensing images of the target land parcel into a raster image of a unified format.

[0098] In order to facilitate subsequent data analysis, the satellite remote sensing images are converted into raster images in a unified format.

[0099] S104: Acquire crop-related information of the current target plot based on each satellite remote sensing image of the current target plot.

[0100] The crop-related information of the target plot includes the types of various crops of the target plot, the planting area, and multiple information affecting the crop yield on the target plot. The multiple information affecting the crop yield on the target plot may specifically include but is not limited to soil information, meteorological information, climate information, etc.

[0101] Specifically, by identifying each satellite remote sensing image of the current target plot, the types of crops in the target plot can be identified, and then the planting area of ​​each crop can be determined based on the area of ​​each crop in the image. In addition, based on each satellite remote sensing image, multiple pieces of information that affect the crop yield on the target plot can be obtained.

[0102] S105 , inputting the location information of the target plot and the crop-related information of the current target plot into a pre-trained evaluation model, and analyzing the evaluation results of various crops of the current target plot through the evaluation model.

[0103] Among them, the crop assessment results of the target plots include at least crop adaptability score, predicted per-acre yield, growth rating and potential disasters.

[0104] Optionally, another embodiment of the present application provides a training method for an evaluation model, such as Figure 4 As shown, the following steps are included:

[0105] S401. Obtain historical data of multiple plots of land as sample data.

[0106] The acquired historical data of the plot includes the location information of the plot and the geographical crop association information.

[0107] S402: Label the sample data to obtain training sample data.

[0108] Specifically, the yield, growth, disasters, etc. are labeled based on the sample data, and the lightGBM algorithm can be used to build a model.

[0109] S403: Encode and feature process the training sample data.

[0110] Specifically, categorical variables such as crop types and disaster types are one-hot encoded or label encoded.

[0111] S404: Iteratively train the evaluation model using the processed training sample data until the evaluation model passes the verification.

[0112] Specifically, the training sample data can be divided into training set, validation set and test set, and the ratio can be set to 7:1:2. Then set the hyperparameters of the model, such as learning rate, tree depth, number of leaf nodes, etc. Then use the training set to iteratively train the evaluation model.

[0113] Optionally, a five-fold cross validation method can be used for training. Specifically, in each round, four copies are selected as training data and the remaining copy is used as validation data to calculate model performance indicators, such as AUC, F1 score, etc. Based on the performance on the validation set, the hyperparameters are adjusted according to the model performance indicators until the optimal combination is found.

[0114] S106. Calculate the comprehensive assessment grade of the target plot according to the assessment results of various crops in the current target plot.

[0115] Optionally, different ranges of scores can be pre-divided for each crop evaluation result, so as to determine the score corresponding to each crop evaluation result according to the access to each crop evaluation result of the current target plot, and then the scores corresponding to each crop evaluation result are summarized to determine the comprehensive score of the target plot. Then, the grade of the target plot is determined according to the comprehensive score, for example, a score of 90 or more is a high-quality plot, a score of 60-90 is a good plot, and a score of less than 60 is an inefficient plot.

[0116] S107. Based on the comprehensive assessment level of the target land parcel, the loan amount and interest rate of the loan user are adjusted.

[0117] Optionally, the credit rating of the loan user can be determined by combining the comprehensive evaluation grade of the target plot and the personal information of the loan user, such as age, region, education and other internal data. Then, based on the credit rating of the loan user and the comprehensive evaluation grade of the target plot, the loan amount and interest rate are dynamically adjusted. Among them, the higher the comprehensive evaluation grade of the target plot, the higher its loan amount and the lower the interest rate. Finally, these analyzed data are output to the staff for reference.

[0118] Optionally, since the crop conditions are constantly changing, in order to be able to perform wind control monitoring in real time, in the embodiment of the present application, dynamic wind control monitoring is further included. Figure 5 As shown, a dynamic risk control monitoring method provided in an embodiment of the present application includes the following steps:

[0119] S501. Obtain crop-related information of the current target plot at preset time intervals.

[0120] S502: input the location information of the target plot and the crop-related information of the current target plot into a pre-trained evaluation model, and analyze the evaluation results of various crops of the current target plot through the evaluation model.

[0121] S503. According to the crop assessment results of the current target plot, the repayment capacity of the loan user is assessed, and a historical risk map of the target plot is drawn.

[0122] It should be noted that the various crop assessment results of the current target plot can reflect the income of the current target plot, and accordingly reflect the repayment ability of the loan user, so a value reflecting the repayment ability of the loan user can be assessed based on this and fed back to the user. The various crop assessment results of the target plot include the growth of the crop, disasters, etc., so based on the current and previously generated crop assessment results, the changes in various information can be plotted over time, so as to facilitate the estimation of subsequent situations and thus timely warnings.

[0123] Optionally, the historical risk map of the target land parcel may also include weather and climate information.

[0124] S504: Display the loan user's repayment ability value and the historical risk map of the target plot.

[0125] The embodiment of the present application provides a credit information analysis method, which obtains the location data of the target plot drawn by the loan user through the mobile terminal. Then the location data of the target plot is analyzed to obtain the location information of the target plot, so as to obtain the accurate location information of the target plot. Then, according to the location information of the target plot, multiple satellite remote sensing images of the current target plot are obtained. Among them, each satellite remote sensing image of the target plot at least includes the current multi-spectral image, hyperspectral image, radar image and infrared image of the target plot, so that a large number of features can be obtained through multiple types of images, thereby improving the precision and accuracy of the analysis results. Then, based on each satellite remote sensing image of the current target plot, the crop association information of the current target plot is obtained. Among them, the crop association information of the target plot includes the type of various crops of the target plot, the planting area and multiple information affecting the crop yield on the target plot. Then, the location information of the target plot and the crop association information of the current target plot are input into the pre-trained evaluation model, and the evaluation model is used to analyze the various crop evaluation results of the current target plot. Among them, the various crop assessment results of the target plot include at least crop adaptability score, predicted per-acre yield, growth rating and potential disasters, so as to obtain multiple information reflecting the benefits of the target plot. Finally, according to the various crop assessment results of the current target plot, the comprehensive assessment grade of the target plot is calculated, and finally based on the comprehensive assessment grade of the target plot, the loan amount and interest rate of the loan user are adjusted, thereby realizing a method for automatically obtaining and analyzing relevant information of the plot, without the need for manual analysis, and obtaining comprehensive and accurate analysis data, effectively ensuring the objectivity and authenticity of the analysis results. Therefore, referring to the analysis results for loans can effectively reduce the analysis of loans.

[0126] Another embodiment of the present application provides a credit information analysis device, such as Figure 6 As shown, including:

[0127] The location data acquisition unit 601 is used to acquire the location data of the target plot drawn by the loan user through the mobile terminal.

[0128] The location analysis unit 602 is used to analyze the location data of the target plot to obtain the location information of the target plot.

[0129] The image data acquisition unit 603 is used to acquire multiple satellite remote sensing images of the current target land parcel according to the location information of the target land parcel, wherein each satellite remote sensing image of the target land parcel at least includes the current multispectral image, hyperspectral image, radar image and infrared image of the target land parcel.

[0130] The data analysis unit 604 is used to obtain crop-related information of the current target plot based on each satellite remote sensing image of the current target plot, wherein the crop-related information of the target plot includes the type of each crop of the target plot, the planting area, and multiple information affecting the crop yield on the target plot.

[0131] The input unit 605 is used to input the location information of the target plot and the crop-related information of the current target plot into the pre-trained evaluation model, and analyze the various crop evaluation results of the current target plot through the evaluation model. Among them, the various crop evaluation results of the target plot at least include crop adaptability score, predicted per mu yield, growth rating and potential disasters.

[0132] The evaluation unit 606 is used to calculate the comprehensive evaluation level of the target plot according to the evaluation results of various crops in the current target plot.

[0133] The adjustment unit 607 is used to adjust the loan amount and interest rate of the loan user based on the comprehensive evaluation level of the target land parcel.

[0134] Optionally, in the credit information analysis device provided in another embodiment of the present application, the location analysis unit includes:

[0135] The verification unit is used to verify the correctness of the location data of the target plot by comparing the location data of the target plot with the plot vector data of the land title confirmation certificate.

[0136] The coordinate conversion unit is used to convert the position data of the target plot into the coordinate system used by the geographic information system to obtain the standard position data of the target plot when the position data of the target plot is verified to be correct.

[0137] The position information analysis unit is used to analyze the boundary and line segment of the target plot by using the standard position data of the target plot to obtain the position information of the target plot.

[0138] Optionally, in another embodiment of the present application, the credit information analysis device further includes:

[0139] The preprocessing unit is used to preprocess each satellite remote sensing image of the current target plot.

[0140] The fusion unit is used to fuse the pre-processed satellite remote sensing images of the target land.

[0141] The format conversion unit is used to convert the fused satellite remote sensing images of the target plot into a raster image of a unified format.

[0142] Optionally, in another embodiment of the present application, the credit information analysis device further includes:

[0143] The sample acquisition unit is used to acquire historical data of multiple plots of land as sample data.

[0144] The labeling unit is used to label the sample data to obtain training sample data.

[0145] The sample processing unit is used to encode and process the features of the training sample data.

[0146] The training unit is used to iteratively train the evaluation model using the processed training sample data until the evaluation model passes the verification.

[0147] Optionally, in another embodiment of the present application, the credit information analysis device further includes:

[0148] The associated information acquisition unit is used to acquire the crop associated information of the current target plot at every preset time interval.

[0149] The real-time evaluation unit is used to input the location information of the target plot and the crop-related information of the current target plot into a pre-trained evaluation model, and analyze the various crop evaluation results of the current target plot through the evaluation model.

[0150] The risk information processing unit is used to evaluate the repayment ability of the loan user based on the crop evaluation results of the current target plot, and to draw a historical risk map of the target plot.

[0151] The display unit is used to display the repayment ability value of the loan user and the historical risk map of the target plot.

[0152] It should be noted that the specific working process of each unit provided in the above embodiments of the present application can refer to the implementation process of the corresponding steps provided in the above method embodiments, and will not be repeated here.

[0153] Another embodiment of the present application provides an electronic device, such as Figure 7As shown, including:

[0154] Memory 701 and processor 702 .

[0155] The memory 701 is used to store programs.

[0156] The processor 702 is used to execute the program stored in the memory 701. When the program is executed, it is specifically used to implement the credit information analysis method provided in any one of the above embodiments.

[0157] Another embodiment of the present application provides a computer storage medium for storing a computer program, which, when executed by a processor, is used to implement a credit information analysis method as provided in any of the above embodiments.

[0158] Computer storage media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0159] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0160] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A credit information analysis method, characterized in that: include: Obtain the location data of the target plot drawn by the loan user through the mobile terminal; Analyzing the location data of the target plot to obtain the location information of the target plot; According to the location information of the target plot, a plurality of satellite remote sensing images of the current target plot are obtained; wherein each satellite remote sensing image of the target plot at least includes a current multispectral image, a hyperspectral image, a radar image and an infrared image of the target plot; Based on each satellite remote sensing image of the current target plot, the crop-related information of the current target plot is obtained; wherein the crop-related information of the target plot includes the type and planting area of ​​each type of crop in the target plot and multiple information affecting the crop yield on the target plot; Input the location information of the target plot and the crop-related information of the current target plot into a pre-trained evaluation model, and analyze the various crop evaluation results of the current target plot through the evaluation model; wherein the various crop evaluation results of the target plot at least include crop adaptability score, predicted per-acre yield, growth rating and potential disasters; Calculate the comprehensive assessment grade of the target plot according to the current crop assessment results of the target plot; Based on the comprehensive assessment level of the target plot of land, the loan amount and interest rate of the loan user are adjusted.

2. The method according to claim 1, characterized in that The step of analyzing the location data of the target plot to obtain the location information of the target plot includes: Verify the correctness of the location data of the target plot by comparing the location data of the target plot with the plot vector data of the land title confirmation certificate; If it is verified that the location data of the target plot is correct, the location data of the target plot is converted into a coordinate system used by a geographic information system to obtain standard location data of the target plot; The standard location data of the target plot is used to analyze the boundary and line segments of the target plot to obtain the location information of the target plot.

3. The method according to claim 1, characterized in that Before acquiring crop-related information of the current target plot based on each satellite remote sensing image of the current target plot, the method further includes: Preprocessing each satellite remote sensing image of the current target plot; fusing the pre-processed satellite remote sensing images of the target plot; The fused satellite remote sensing images of the target plot are converted into raster images of a unified format.

4. The method according to claim 1, characterized in that: The training method of the evaluation model comprises: Obtain historical data of multiple plots as sample data; Annotating the sample data to obtain training sample data; Encoding and feature processing the training sample data; The evaluation model is iteratively trained using the processed training sample data until the evaluation model passes the verification.

5. The method according to claim 1, characterized in that Also includes: At preset time intervals, obtaining crop-related information of the current target plot; Input the location information of the target plot and the crop-related information of the current target plot into a pre-trained evaluation model, and analyze the evaluation results of various crops of the current target plot through the evaluation model; According to the current crop assessment results of the target plot, the repayment capacity of the loan user is assessed, and a historical risk map of the target plot is drawn; The repayment capacity value of the loan user and the historical risk map of the target plot are displayed.

6. A credit information analysis device, characterized in that: include: A location data acquisition unit, used to acquire location data of a target plot drawn by a loan user through a mobile terminal; A location analysis unit, used to analyze the location data of the target plot to obtain the location information of the target plot; An image data acquisition unit, configured to acquire a plurality of satellite remote sensing images of the current target land parcel according to the location information of the target land parcel; wherein each satellite remote sensing image of the target land parcel at least includes a current multispectral image, a hyperspectral image, a radar image, and an infrared image of the target land parcel; A data analysis unit, configured to obtain crop-related information of the current target plot based on each satellite remote sensing image of the current target plot; wherein the crop-related information of the target plot includes the type and planting area of ​​each type of crop of the target plot and multiple information affecting the crop yield on the target plot; An input unit is used to input the location information of the target plot and the crop-related information of the current target plot into a pre-trained evaluation model, and analyze various crop evaluation results of the current target plot through the evaluation model; wherein the various crop evaluation results of the target plot at least include crop adaptability scores, predicted per-acre yields, growth ratings, and potential disasters; An evaluation unit, used to calculate a comprehensive evaluation grade of the target plot according to the evaluation results of various crops of the target plot; An adjustment unit is used to adjust the loan amount and interest rate of the loan user based on the comprehensive evaluation level of the target plot of land.

7. The device according to claim 6, characterized in that The position analysis unit comprises: A verification unit, used to verify the correctness of the location data of the target plot of land by comparing the location data of the target plot of land with the plot vector data of the land title confirmation certificate; A coordinate conversion unit, for converting the position data of the target plot into a coordinate system used by a geographic information system to obtain standard position data of the target plot when the position data of the target plot is verified to be correct; The position information analysis unit is used to analyze the boundary and line segment of the target plot by using the standard position data of the target plot to obtain the position information of the target plot.

8. The device according to claim 6, characterized in that Also includes: A preprocessing unit, used for preprocessing each satellite remote sensing image of the current target land parcel; A fusion unit, used for fusing the pre-processed satellite remote sensing images of the target land plot; The format conversion unit is used to convert the fused satellite remote sensing images of the target land into a raster image of a unified format.

9. An electronic device, characterized in that: include: Memory and processor; Wherein, the memory is used to store programs; The processor is used to execute the program, and when the program is executed, it is specifically used to implement the credit information analysis method as described in any one of claims 1 to 5.

10. A computer storage medium, characterized in that: Used to store a computer program, which, when executed by a processor, is used to implement the credit information analysis method as described in any one of claims 1 to 5.

Images