Repayment risk assessment method and device, storage medium and electronic equipment

Abstract

The invention discloses a repayment risk assessment method and device, a storage medium and electronic equipment. Relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining a satellite remote sensing image of a target grassland corresponding to a target object when a financial institution carries out the monitoring of the repayment capability of the target object, and carrying out the blocking processing of the satellite remote sensing image, and obtaining a plurality of satellite remote sensing sub-images; processing the satellite remote sensing sub-images through the biomass prediction model corresponding to each satellite remote sensing sub-image to obtain first prediction biomass corresponding to each satellite remote sensing sub-image; performing calculation according to the first predicted biomass corresponding to each satellite remote sensing sub-image, and determining a theoretical animal husbandry amount corresponding to the target grassland; and determining a repayment risk value of the target object according to the theoretical animal husbandry amount and the real animal husbandry amount. According to the method and the device, the problem that the repayment risk of the loan customer cannot be evaluated during grassland animal husbandry loan in the prior art, so that the repayment risk is relatively high is solved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and more specifically, to a repayment risk assessment method and device, a storage medium, and an electronic device. Background Art

[0002] Livestock loans refer to loans provided by financial institutions to agricultural producers and operators for agricultural production, operation or rural construction. The characteristics of livestock loans are short loan terms, small loan amounts, scattered loan recipients and high post-loan risks. In order to effectively control the risks of livestock loans, financial institutions need to conduct post-loan risk monitoring on the credit status of loan customers and the value of collateral.

[0003] However, traditional post-loan risk monitoring methods are mainly based on the repayment situation and financial indicators of loan customers for evaluation, but this method often cannot fully understand the actual operating conditions and risk status of the lender, for example, whether the grassland and animal husbandry are balanced.

[0004] With regard to the problem in related technologies that when providing grassland livestock loans, the repayment risk of loan customers cannot be assessed, resulting in a higher repayment risk, no effective solution has been proposed so far. Summary of the invention

[0005] The main purpose of this application is to provide a repayment risk assessment method and device, storage medium and electronic device to solve the problem in the related art that when providing grassland livestock loans, the repayment risk of the loan customer cannot be assessed, resulting in a higher repayment risk.

[0006] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a repayment risk assessment method is provided. The method comprises: when a financial institution monitors the repayment ability of a target object, a satellite remote sensing image of a target grassland corresponding to the target object is obtained, and the satellite remote sensing image is processed in blocks to obtain a plurality of satellite remote sensing sub-images, wherein the target object is an object that obtains a loan through livestock breeding in the target grassland; the satellite remote sensing sub-image is processed by a biomass prediction model corresponding to each satellite remote sensing sub-image to obtain a first predicted biomass corresponding to each satellite remote sensing sub-image; the theoretical livestock amount corresponding to the target grassland is determined by calculation based on the first predicted biomass corresponding to each satellite remote sensing sub-image; the repayment risk value of the target object is determined based on the theoretical livestock amount and the actual livestock amount.

[0007] Furthermore, the satellite remote sensing image is processed into blocks to obtain multiple satellite remote sensing sub-images, including: acquiring first geographic information of the target grassland, wherein the first geographic information at least includes: climate condition information, vegetation type information and topographic information; and processing the satellite remote sensing image into blocks based on the first geographic information to obtain the multiple satellite remote sensing sub-images.

[0008] Furthermore, before processing the satellite remote sensing sub-image through the biomass prediction model corresponding to each satellite remote sensing sub-image, the method also includes: determining second geographic information corresponding to each satellite remote sensing sub-image; and determining the biomass prediction model corresponding to each satellite remote sensing sub-image based on the second geographic information.

[0009] Furthermore, the satellite remote sensing sub-image is processed by a biomass prediction model corresponding to each satellite remote sensing sub-image to obtain a first predicted biomass corresponding to each satellite remote sensing sub-image, including: extracting vegetation features of the satellite remote sensing sub-image by the biomass prediction model to obtain a first feature vector; extracting features of second geographic information corresponding to the satellite remote sensing sub-image by the biomass prediction model to obtain a second feature vector; obtaining a target feature vector based on the first feature vector and the second feature vector; and processing the target feature vector by the biomass prediction model to obtain the first predicted biomass.

[0010] Furthermore, calculation is performed based on the first predicted biomass corresponding to each satellite remote sensing sub-image to determine the theoretical livestock amount corresponding to the target grassland, including: obtaining the second predicted biomass corresponding to each satellite remote sensing sub-image based on the normalized vegetation index, vegetation growth index and target fitting curve in the satellite remote sensing sub-image, wherein the target fitting curve is a relationship curve between the normalized vegetation index, vegetation growth index and biomass; calculating based on the first predicted biomass and the second predicted biomass to obtain the predicted total biomass corresponding to the satellite remote sensing image; and calculating based on the predicted total biomass to obtain the theoretical livestock amount.

[0011] Furthermore, before obtaining the second predicted biomass corresponding to each satellite remote sensing sub-image based on the vegetation index, vegetation growth index and target fitting curve in the satellite remote sensing sub-image, the method also includes: obtaining a historical satellite remote sensing image of the target grassland; calculating based on the reflectance value of the near-infrared band and the reflectance value of the red light band in the historical satellite remote sensing image to obtain a historical normalized vegetation index; obtaining the minimum normalized vegetation index and the maximum normalized vegetation index of the target grassland during the growing period; calculating based on the historical normalized vegetation index, the minimum normalized vegetation index and the maximum normalized vegetation index to obtain a historical vegetation growth index corresponding to the historical satellite remote sensing image; performing multivariate regression fitting based on the historical normalized vegetation index, the historical vegetation growth index and the real biomass corresponding to the historical satellite remote sensing image to obtain a target fitting curve.

[0012] Furthermore, determining the repayment risk value of the target object based on the theoretical livestock volume and the actual livestock volume includes: determining a third predicted biomass corresponding to the actual livestock volume; determining the repayment risk value of the target object based on the difference between the actual livestock volume and the theoretical livestock volume and the difference between the first predicted biomass and the third predicted biomass.

[0013] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a repayment risk assessment device is provided. The device includes: a first acquisition unit, which is used to acquire a satellite remote sensing image of a target grassland corresponding to the target object when a financial institution monitors the repayment ability of the target object, and to process the satellite remote sensing image in blocks to obtain a plurality of satellite remote sensing sub-images, wherein the target object is an object that obtains a loan through livestock farming in the target grassland; a processing unit, which is used to process the satellite remote sensing sub-image through a biomass prediction model corresponding to each satellite remote sensing sub-image to obtain a first predicted biomass corresponding to each satellite remote sensing sub-image; a first calculation unit, which is used to calculate based on the first predicted biomass corresponding to each satellite remote sensing sub-image to determine the theoretical livestock volume corresponding to the target grassland; and a first determination unit, which is used to determine the repayment risk value of the target object based on the theoretical livestock volume and the actual livestock volume.

[0014] Furthermore, the first acquisition unit includes: an acquisition module for acquiring first geographic information of the target grassland, wherein the first geographic information at least includes: climate condition information, vegetation type information and topography information; a first processing module for performing block processing on the satellite remote sensing image according to the first geographic information to obtain the multiple satellite remote sensing sub-images.

[0015] Furthermore, the device also includes: a second determination unit, used to determine the second geographic information corresponding to each satellite remote sensing sub-image before processing the satellite remote sensing sub-image through the biomass prediction model corresponding to each satellite remote sensing sub-image; and a third determination unit, used to determine the biomass prediction model corresponding to each satellite remote sensing sub-image based on the second geographic information.

[0016] Furthermore, the processing unit includes: a first extraction module, used to extract vegetation features of the satellite remote sensing sub-image through the biomass prediction model to obtain a first feature vector; a second extraction module, used to extract features of second geographic information corresponding to the satellite remote sensing sub-image through the biomass prediction model to obtain a second feature vector; a first determination module, used to obtain a target feature vector based on the first feature vector and the second feature vector; and a second processing module, used to process the target feature vector through the biomass prediction model to obtain the first predicted biomass.

[0017] Furthermore, the first calculation unit includes: a first calculation module, used to obtain a second predicted biomass corresponding to each satellite remote sensing sub-image based on the normalized vegetation index, vegetation growth index and target fitting curve in the satellite remote sensing sub-image, wherein the target fitting curve is a relationship curve between the normalized vegetation index, vegetation growth index and biomass; a second calculation module, used to calculate based on the first predicted biomass and the second predicted biomass to obtain the predicted total biomass corresponding to the satellite remote sensing image; a third calculation module, used to calculate based on the predicted total biomass to obtain the theoretical livestock amount.

[0018] Furthermore, the device also includes: a second acquisition unit, used to acquire the historical satellite remote sensing image of the target grassland before obtaining the second predicted biomass corresponding to each satellite remote sensing sub-image based on the vegetation index, vegetation growth index and target fitting curve in the satellite remote sensing sub-image; a second calculation unit, used to calculate based on the reflectance value of the near-infrared band and the reflectance value of the red light band in the historical satellite remote sensing image to obtain the historical normalized vegetation index; a third acquisition unit, used to acquire the minimum normalized vegetation index and the maximum normalized vegetation index of the target grassland during the growing period; a third calculation unit, used to calculate based on the historical normalized vegetation index, the minimum normalized vegetation index and the maximum normalized vegetation index to obtain the historical vegetation growth index corresponding to the historical satellite remote sensing image; a fitting unit, used to perform multivariate regression fitting based on the historical normalized vegetation index, the historical vegetation growth index and the real biomass corresponding to the historical satellite remote sensing image to obtain the target fitting curve.

[0019] Furthermore, the first determination unit includes: a second determination module, used to determine the third predicted biomass corresponding to the actual livestock volume; a third determination module, used to determine the repayment risk value of the target object based on the difference between the actual livestock volume and the theoretical livestock volume and the difference between the first predicted biomass and the third predicted biomass.

[0020] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein when the program is running, any one of the above-mentioned repayment risk assessment methods is executed.

[0021] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, wherein the storage medium stores a program, wherein when the program is running, the device where the storage medium is located is controlled to execute any one of the above-mentioned repayment risk assessment methods.

[0022] Through the present application, the following steps are adopted: when a financial institution monitors the repayment ability of a target object, a satellite remote sensing image of a target grassland corresponding to the target object is obtained, and the satellite remote sensing image is processed in blocks to obtain a plurality of satellite remote sensing sub-images, wherein the target object is an object that obtains a loan through livestock breeding in the target grassland; the satellite remote sensing sub-images are processed by a biomass prediction model corresponding to each satellite remote sensing sub-image to obtain a first predicted biomass corresponding to each satellite remote sensing sub-image; a theoretical livestock volume corresponding to the target grassland is determined based on the first predicted biomass corresponding to each satellite remote sensing sub-image; and a repayment risk value of the target object is determined based on the theoretical livestock volume and the actual livestock volume, thereby solving the problem in the related art that when carrying out grassland livestock loans, the repayment risk of the loan customer cannot be evaluated, resulting in a higher repayment risk. In this solution, after the financial institution lends money to the target object, it obtains the satellite remote sensing image of the target grassland involved in the loan business of the target object, and performs biomass prediction through the biomass prediction model corresponding to each satellite remote sensing sub-image to obtain the theoretical livestock volume corresponding to the target grassland, and determines the repayment risk value of the target object based on the theoretical livestock volume and the actual livestock volume. The theoretical livestock volume and the actual livestock volume can be used to effectively judge whether the grassland animal husbandry is balanced. Whether the grassland animal husbandry is balanced can be used to effectively evaluate whether there is a risk in the current breeding of the target object, that is, the repayment risk of the target object, thereby achieving the effect of accurately judging the repayment risk of the loan user. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0024] Figure 1The process of the repayment risk assessment method provided in the embodiment of the present application is as follows Figure 1 ;

[0025] Figure 2 The process of the repayment risk assessment method provided in the embodiment of the present application is as follows Figure 2 ;

[0026] Figure 3 is a schematic diagram of a repayment risk assessment device provided according to an embodiment of the present application;

[0027] Figure 4 is a schematic diagram of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0029] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings 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 should fall within the scope of protection of the present application.

[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] It should be noted that the relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties. For example, an interface is set between this system and the relevant user or organization. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or organization.

[0032] The present invention is described below in conjunction with preferred implementation steps. Figure 1 The process of the repayment risk assessment method provided in the embodiment of the present application is as follows Figure 1 ,like Figure 1 As shown, the method comprises the following steps:

[0033] Step S101, when a financial institution monitors the repayment ability of a target object, a satellite remote sensing image of a target grassland corresponding to the target object is obtained, and the satellite remote sensing image is processed into blocks to obtain a plurality of satellite remote sensing sub-images, wherein the target object is an object that obtains a loan through livestock farming in the target grassland;

[0034] Optionally, the user (i.e., the target object mentioned above) can apply for a loan from a financial institution based on the livestock raised. After the financial institution issues the loan to the user, in order to reduce the risk of subsequent repayment, the user's repayment ability needs to be monitored. According to the needs and objectives of remote sensing monitoring of grassland biomass, appropriate satellite image data is selected to obtain the above-mentioned satellite remote sensing image, and then the satellite remote sensing image can be divided into blocks according to factors such as topography, grassland type characteristics and spatial distribution to obtain multiple satellite remote sensing sub-images.

[0035] Step S102, processing the satellite remote sensing sub-images by using the biomass prediction model corresponding to each satellite remote sensing sub-image to obtain a first predicted biomass corresponding to each satellite remote sensing sub-image;

[0036] Optionally, after obtaining the above-mentioned satellite remote sensing sub-images, biomass prediction is performed using a biomass prediction model corresponding to the satellite remote sensing sub-images, thereby obtaining a first predicted biomass corresponding to each satellite remote sensing sub-image. For example, the biomass prediction model may be a deep learning model. The deep learning model may accurately evaluate the biomass of the area corresponding to the current satellite remote sensing sub-image.

[0037] Step S103, calculating according to the first predicted biomass corresponding to each satellite remote sensing sub-image to determine the theoretical livestock amount corresponding to the target grassland;

[0038] Optionally, after obtaining the first predicted biomass corresponding to each satellite remote sensing sub-image, the biomass corresponding to the target grassland is calculated based on the first predicted biomass, and then the theoretical livestock volume corresponding to the target grassland is determined based on the biomass corresponding to the target grassland. In an optional embodiment, the theoretical livestock volume corresponding to the target grassland can be obtained by calculating the reasonable carrying capacity of natural grassland according to the agricultural industry standard NY / T635-2015.

[0039] Step S104, determining the repayment risk value of the target object based on the theoretical livestock quantity and the actual livestock quantity.

[0040] Optionally, the user's current actual livestock volume is determined, and the repayment risk value of the target object is determined based on the theoretical livestock volume and the actual livestock volume. For example, the difference between the theoretical livestock volume and the actual livestock volume is calculated, and the repayment risk value is determined based on the difference. If the theoretical livestock volume is higher than the actual livestock volume, it means that there are problems with the current livestock breeding, that is, the user has a repayment risk. The larger the gap between the theoretical livestock volume and the actual livestock volume, the higher the repayment risk value of the user.

[0041] To summarize, after the financial institution lends money to the target object, it obtains the satellite remote sensing image of the target grassland involved in the loan business of the target object, and performs biomass prediction through the biomass prediction model corresponding to each satellite remote sensing sub-image to obtain the theoretical livestock volume corresponding to the target grassland, and determines the repayment risk value of the target object based on the theoretical livestock volume and the actual livestock volume. The theoretical livestock volume and the actual livestock volume can be used to effectively judge whether the grassland animal husbandry is balanced. Whether the grassland animal husbandry is balanced can be used to effectively assess whether there is a risk in the current breeding of the target object, that is, the repayment risk of the target object, thereby achieving the effect of accurately judging the repayment risk of the loan user.

[0042] Optionally, in the repayment risk assessment method provided in an embodiment of the present application, the satellite remote sensing image is processed in blocks to obtain multiple satellite remote sensing sub-images, including: obtaining first geographic information of the target grassland, wherein the first geographic information includes at least: climate condition information, vegetation type information and topography information; and the satellite remote sensing image is processed in blocks based on the first geographic information to obtain multiple satellite remote sensing sub-images.

[0043] In an optional embodiment, after acquiring the satellite remote sensing image of the target grassland, geographical information such as climate condition information, vegetation type information, and topography information of the target grassland is obtained, and the satellite remote sensing image is processed in blocks using the climate condition information, vegetation type information, and topography information to obtain multiple satellite remote sensing sub-images.

[0044] It should be noted that dividing satellite remote sensing images into blocks will help with subsequent targeted prediction of biomass and improve the accuracy of predicted biomass.

[0045] Optionally, in the repayment risk assessment method provided in an embodiment of the present application, before processing the satellite remote sensing sub-image through the biomass prediction model corresponding to each satellite remote sensing sub-image, the method also includes: determining the second geographic information corresponding to each satellite remote sensing sub-image; and determining the biomass prediction model corresponding to each satellite remote sensing sub-image based on the second geographic information.

[0046] In an optional embodiment, the biomass prediction model corresponding to the satellite remote sensing sub-image is determined based on the second geographic information corresponding to the satellite remote sensing sub-image, that is, climate condition information, vegetation type information and topographic information.

[0047] It should be noted that the biomass prediction model is obtained by training with remote sensing images and corresponding real biomass of areas with similar vegetation types, climate conditions, topography and other characteristics. The accuracy of biomass prediction can be improved through the corresponding biomass prediction model.

[0048] Optionally, in the repayment risk assessment method provided in the embodiment of the present application, the satellite remote sensing sub-image is processed by a biomass prediction model corresponding to each satellite remote sensing sub-image to obtain a first predicted biomass corresponding to each satellite remote sensing sub-image, including: extracting vegetation features of the satellite remote sensing sub-image by the biomass prediction model to obtain a first eigenvector; extracting features of second geographic information corresponding to the satellite remote sensing sub-image by the biomass prediction model to obtain a second eigenvector; obtaining a target eigenvector based on the first eigenvector and the second eigenvector; and processing the target eigenvector by the biomass prediction model to obtain a first predicted biomass.

[0049] In an optional embodiment, processing the satellite remote sensing sub-image by the biomass prediction model corresponding to each satellite remote sensing sub-image includes the following steps: first, the biomass prediction model extracts vegetation features from the satellite remote sensing sub-image to obtain a first feature vector, and the biomass prediction model extracts features from the second geographic information corresponding to the satellite remote sensing sub-image to obtain a second feature vector. Then, the first feature vector and the second feature vector are concatenated to obtain a concatenated feature vector, and then the concatenated feature vector is convoluted to obtain a target feature vector. Finally, the biomass prediction model processes the target feature vector to obtain the above-mentioned first predicted biomass.

[0050] The vegetation characteristics contained in the remote sensing images and the geographical features corresponding to the remote sensing images can be used to accurately grasp the biomass corresponding to the remote sensing images, thereby improving the accuracy of biomass prediction.

[0051] Optionally, in the repayment risk assessment method provided in the embodiment of the present application, calculation is performed based on the first predicted biomass corresponding to each satellite remote sensing sub-image to determine the theoretical livestock amount corresponding to the target grassland, including: obtaining the second predicted biomass corresponding to each satellite remote sensing sub-image based on the normalized vegetation index, vegetation growth index and target fitting curve in the satellite remote sensing sub-image, wherein the target fitting curve is a relationship curve between the normalized vegetation index, vegetation growth index and biomass; calculating based on the first predicted biomass and the second predicted biomass to obtain the predicted total biomass corresponding to the satellite remote sensing image; and calculating based on the predicted total biomass to obtain the theoretical livestock amount.

[0052] In an optional embodiment, when calculating according to the first predicted biomass corresponding to each satellite remote sensing sub-image, the following steps are also included: obtaining a normalized vegetation index by calculating the reflectivity of the near-infrared band and the reflectivity of the infrared band in the satellite remote sensing sub-image, and obtaining a vegetation growth index by calculating the normalized vegetation index, the minimum normalized vegetation index and the maximum normalized vegetation index in the satellite remote sensing sub-image.

[0053] Then, the target fitting curve obtained by fitting the normalized vegetation index, vegetation growth index and biomass in the historical remote sensing image is used to calculate the normalized vegetation index and vegetation growth index to obtain the second predicted biomass. The predicted total biomass corresponding to the satellite remote sensing image is calculated by calculating the first predicted biomass and the second predicted biomass. Finally, the theoretical livestock quantity is calculated based on the predicted total biomass.

[0054] The target curve in the above steps avoids the use of a single method to predict biomass, thereby improving the accuracy of biomass prediction.

[0055] Optionally, in the repayment risk assessment method provided in the embodiment of the present application, before obtaining the second predicted biomass corresponding to each satellite remote sensing sub-image based on the vegetation index, vegetation growth index and target fitting curve in the satellite remote sensing sub-image, the method also includes: obtaining historical satellite remote sensing images of the target grassland; calculating based on the reflectance values ​​of the near-infrared band and the reflectance values ​​of the red light band in the historical satellite remote sensing images to obtain a historical normalized vegetation index; obtaining the minimum normalized vegetation index and maximum normalized vegetation index of the target grassland during the growing period; calculating based on the historical normalized vegetation index, the minimum normalized vegetation index and the maximum normalized vegetation index to obtain the historical vegetation growth index corresponding to the historical satellite remote sensing image; performing multivariate regression fitting based on the historical normalized vegetation index, the historical vegetation growth index and the real biomass corresponding to the historical satellite remote sensing image to obtain the target fitting curve.

[0056] In an optional embodiment, the target fitting curve described above is obtained by the following steps: historical satellite remote sensing images of the target grassland are collected, and the historical normalized vegetation index is obtained by calculating the reflectance value of the near-infrared band and the reflectance value of the red light band in the historical satellite remote sensing images, and the historical vegetation growth index corresponding to the historical satellite remote sensing images is obtained by calculating the historical normalized vegetation index, the minimum normalized vegetation index and the maximum normalized vegetation index. And the real biomass corresponding to the historical satellite remote sensing images can be obtained by actual investigation. Finally, the target fitting curve described above is obtained by performing multivariate regression fitting of the historical normalized vegetation index, the historical vegetation growth index and the real biomass corresponding to the historical satellite remote sensing images.

[0057] Through the above steps, the relationship between the normalized vegetation index, the vegetation growth index and the biomass can be accurately fitted to obtain a fitting curve, and the predicted biomass can be quickly and accurately obtained through the fitting curve.

[0058] Optionally, in the repayment risk assessment method provided in the embodiment of the present application, determining the repayment risk value of the target object based on the theoretical livestock volume and the actual livestock volume includes: determining the third predicted biomass corresponding to the actual livestock volume; determining the repayment risk value of the target object based on the difference between the actual livestock volume and the theoretical livestock volume and the difference between the first predicted biomass and the third predicted biomass.

[0059] In an optional embodiment, the repayment risk value of the target object is determined by the following steps: inversion is performed based on the actual livestock volume to obtain a third predicted biomass, and then the repayment risk value of the target object is determined based on the difference between the actual livestock volume and the theoretical livestock volume and the difference between the first predicted biomass and the third predicted biomass.

[0060] In an optional embodiment, the Figure 2 The flowchart shown determines the repayment risk value of the user: obtain a satellite remote sensing image of the target grassland corresponding to the target object, divide the satellite remote sensing image into blocks according to the terrain, vegetation type and climate information of the target grassland to obtain remote sensing sub-images, predict the first biomass through the biomass prediction model corresponding to the remote sensing sub-image, calculate the second biomass based on the vegetation index in the remote sensing sub-image through the fitting curve, obtain the theoretical livestock volume through the first biomass and the second biomass, and finally determine the repayment risk of the user based on the theoretical livestock volume and the actual livestock volume.

[0061] The repayment risk assessment method provided in the embodiment of the present application obtains a satellite remote sensing image of a target grassland corresponding to a target object when a financial institution monitors the repayment ability of the target object, and processes the satellite remote sensing image in blocks to obtain a plurality of satellite remote sensing sub-images, wherein the target object is an object that obtains a loan through livestock breeding in the target grassland; processes the satellite remote sensing sub-images by a biomass prediction model corresponding to each satellite remote sensing sub-image to obtain a first predicted biomass corresponding to each satellite remote sensing sub-image; calculates based on the first predicted biomass corresponding to each satellite remote sensing sub-image to determine the theoretical livestock volume corresponding to the target grassland; determines the repayment risk value of the target object based on the theoretical livestock volume and the actual livestock volume, thereby solving the problem in the related art that when grassland livestock breeding loans are provided, the repayment risk of the loan customer cannot be assessed, resulting in a higher repayment risk. In this solution, after the financial institution lends money to the target object, it obtains the satellite remote sensing image of the target grassland involved in the loan business of the target object, and performs biomass prediction through the biomass prediction model corresponding to each satellite remote sensing sub-image to obtain the theoretical livestock volume corresponding to the target grassland, and determines the repayment risk value of the target object based on the theoretical livestock volume and the actual livestock volume. The theoretical livestock volume and the actual livestock volume can be used to effectively judge whether the grassland animal husbandry is balanced. Whether the grassland animal husbandry is balanced can be used to effectively evaluate whether there is a risk in the current breeding of the target object, that is, the repayment risk of the target object, thereby achieving the effect of accurately judging the repayment risk of the loan user.

[0062] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0063] The embodiment of the present application also provides a repayment risk assessment device. It should be noted that the repayment risk assessment device of the embodiment of the present application can be used to execute the repayment risk assessment method provided in the embodiment of the present application. The repayment risk assessment device provided in the embodiment of the present application is introduced below.

[0064] Figure 3 Schematic diagram of a repayment risk assessment device according to an embodiment of the present application. Figure 3 As shown, the device includes: a first acquisition unit 301, a processing unit 302, a first calculation unit 303 and a first determination unit 304.

[0065] The first acquisition unit 301 is used to acquire a satellite remote sensing image of a target grassland corresponding to the target object when the financial institution monitors the repayment ability of the target object, and to perform block processing on the satellite remote sensing image to obtain a plurality of satellite remote sensing sub-images, wherein the target object is an object that obtains a loan through livestock breeding in the target grassland;

[0066] The processing unit 302 is used to process the satellite remote sensing sub-images by using the biomass prediction model corresponding to each satellite remote sensing sub-image to obtain a first predicted biomass corresponding to each satellite remote sensing sub-image;

[0067] The first calculation unit 303 is used to calculate according to the first predicted biomass corresponding to each satellite remote sensing sub-image to determine the theoretical livestock quantity corresponding to the target grassland;

[0068] The first determination unit 304 is used to determine the repayment risk value of the target object according to the theoretical livestock quantity and the actual livestock quantity.

[0069] The repayment risk assessment device provided in the embodiment of the present application, when a financial institution monitors the repayment ability of a target object, obtains a satellite remote sensing image of a target grassland corresponding to the target object through a first acquisition unit 301, and processes the satellite remote sensing image in blocks to obtain a plurality of satellite remote sensing sub-images, wherein the target object is an object that obtains a loan through livestock breeding in the target grassland; the processing unit 302 processes the satellite remote sensing sub-image through a biomass prediction model corresponding to each satellite remote sensing sub-image to obtain a first predicted biomass corresponding to each satellite remote sensing sub-image; the first calculation unit 303 calculates based on the first predicted biomass corresponding to each satellite remote sensing sub-image to determine the theoretical livestock volume corresponding to the target grassland; the first determination unit 304 determines the repayment risk value of the target object based on the theoretical livestock volume and the actual livestock volume, thereby solving the problem in the related art that when grassland livestock breeding loans are made, the repayment risk of the loan customer cannot be assessed, resulting in a higher repayment risk. In this solution, after the financial institution lends money to the target object, it obtains the satellite remote sensing image of the target grassland involved in the loan business of the target object, and performs biomass prediction through the biomass prediction model corresponding to each satellite remote sensing sub-image to obtain the theoretical livestock volume corresponding to the target grassland, and determines the repayment risk value of the target object based on the theoretical livestock volume and the actual livestock volume. The theoretical livestock volume and the actual livestock volume can be used to effectively judge whether the grassland animal husbandry is balanced. Whether the grassland animal husbandry is balanced can be used to effectively evaluate whether there is a risk in the current breeding of the target object, that is, the repayment risk of the target object, thereby achieving the effect of accurately judging the repayment risk of the loan user.

[0070] Optionally, in the repayment risk assessment device provided in the embodiment of the present application, the first acquisition unit includes: an acquisition module, used to acquire first geographic information of the target grassland, wherein the first geographic information includes at least: climate condition information, vegetation type information and topography information; a first processing module, used to perform block processing on the satellite remote sensing image according to the first geographic information to obtain multiple satellite remote sensing sub-images.

[0071] Optionally, in the repayment risk assessment device provided in the embodiment of the present application, the device also includes: a second determination unit, used to determine the second geographic information corresponding to each satellite remote sensing sub-image before processing the satellite remote sensing sub-image through the biomass prediction model corresponding to each satellite remote sensing sub-image; a third determination unit, used to determine the biomass prediction model corresponding to each satellite remote sensing sub-image based on the second geographic information.

[0072] Optionally, in the repayment risk assessment device provided in the embodiment of the present application, the processing unit includes: a first extraction module, used to extract vegetation features of the satellite remote sensing sub-image through a biomass prediction model to obtain a first feature vector; a second extraction module, used to extract features of second geographic information corresponding to the satellite remote sensing sub-image through the biomass prediction model to obtain a second feature vector; a first determination module, used to obtain a target feature vector based on the first feature vector and the second feature vector; and a second processing module, used to process the target feature vector through the biomass prediction model to obtain a first predicted biomass.

[0073] Optionally, in the repayment risk assessment device provided in the embodiment of the present application, the first calculation unit includes: a first calculation module, used to obtain the second predicted biomass corresponding to each satellite remote sensing sub-image based on the normalized vegetation index, vegetation growth index and target fitting curve in the satellite remote sensing sub-image, wherein the target fitting curve is a relationship curve between the normalized vegetation index, vegetation growth index and biomass; a second calculation module, used to calculate based on the first predicted biomass and the second predicted biomass to obtain the predicted total biomass corresponding to the satellite remote sensing image; a third calculation module, used to calculate based on the predicted total biomass to obtain the theoretical livestock volume.

[0074] Optionally, in the repayment risk assessment device provided in the embodiment of the present application, the device also includes: a second acquisition unit, used to acquire a historical satellite remote sensing image of the target grassland before obtaining the second predicted biomass corresponding to each satellite remote sensing sub-image based on the vegetation index, vegetation growth index and target fitting curve in the satellite remote sensing sub-image; a second calculation unit, used to calculate based on the reflectance value of the near-infrared band and the reflectance value of the red light band in the historical satellite remote sensing image to obtain a historical normalized vegetation index; a third acquisition unit, used to obtain the minimum normalized vegetation index and maximum normalized vegetation index of the target grassland during the growing period; a third calculation unit, used to calculate based on the historical normalized vegetation index, the minimum normalized vegetation index and the maximum normalized vegetation index to obtain the historical vegetation growth index corresponding to the historical satellite remote sensing image; a fitting unit, used to perform multivariate regression fitting based on the historical normalized vegetation index, the historical vegetation growth index and the real biomass corresponding to the historical satellite remote sensing image to obtain a target fitting curve.

[0075] Optionally, in the repayment risk assessment device provided in the embodiment of the present application, the first determination unit includes: a second determination module, used to determine the third predicted biomass corresponding to the actual livestock volume; a third determination module, used to determine the repayment risk value of the target object based on the difference between the actual livestock volume and the theoretical livestock volume and the difference between the first predicted biomass and the third predicted biomass.

[0076] The repayment risk assessment device includes a processor and a memory. The above-mentioned first acquisition unit 301, processing unit 302, first calculation unit 303 and first determination unit 304 are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions.

[0077] The processor contains a kernel, which calls the corresponding program unit from the memory. One or more kernels can be set, and the repayment risk can be accurately judged by adjusting the kernel parameters.

[0078] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0079] An embodiment of the present invention provides a computer-readable storage medium having a program stored thereon, which implements a repayment risk assessment method when the program is executed by a processor.

[0080] An embodiment of the present invention provides a processor, which is used to run a program, wherein the repayment risk assessment method is executed when the program is running.

[0081] like Figure 4 As shown, an embodiment of the present invention provides an electronic device, the device includes a processor, a memory, and a program stored in the memory and executable on the processor, and the processor implements the following steps when executing the program: when a financial institution monitors the repayment ability of a target object, a satellite remote sensing image of a target grassland corresponding to the target object is obtained, and the satellite remote sensing image is processed in blocks to obtain a plurality of satellite remote sensing sub-images, wherein the target object is an object that obtains a loan through livestock breeding in the target grassland; the satellite remote sensing sub-images are processed by a biomass prediction model corresponding to each satellite remote sensing sub-image to obtain a first predicted biomass corresponding to each satellite remote sensing sub-image; a theoretical livestock amount corresponding to the target grassland is determined by calculation based on the first predicted biomass corresponding to each satellite remote sensing sub-image; and a repayment risk value of the target object is determined based on the theoretical livestock amount and the actual livestock amount.

[0082] Optionally, dividing the satellite remote sensing image into blocks to obtain multiple satellite remote sensing sub-images includes: acquiring first geographic information of the target grassland, wherein the first geographic information includes at least climate condition information, vegetation type information and topographic information; dividing the satellite remote sensing image into blocks based on the first geographic information to obtain multiple satellite remote sensing sub-images.

[0083] Optionally, before processing the satellite remote sensing sub-image using the biomass prediction model corresponding to each satellite remote sensing sub-image, the method further includes: determining second geographic information corresponding to each satellite remote sensing sub-image; and determining the biomass prediction model corresponding to each satellite remote sensing sub-image based on the second geographic information.

[0084] Optionally, the satellite remote sensing sub-image is processed by a biomass prediction model corresponding to each satellite remote sensing sub-image to obtain a first predicted biomass corresponding to each satellite remote sensing sub-image, including: extracting vegetation features of the satellite remote sensing sub-image by the biomass prediction model to obtain a first eigenvector; extracting features of second geographic information corresponding to the satellite remote sensing sub-image by the biomass prediction model to obtain a second eigenvector; obtaining a target eigenvector based on the first eigenvector and the second eigenvector; and processing the target eigenvector by the biomass prediction model to obtain a first predicted biomass.

[0085] Optionally, calculation is performed based on the first predicted biomass corresponding to each satellite remote sensing sub-image to determine the theoretical livestock amount corresponding to the target grassland, including: obtaining the second predicted biomass corresponding to each satellite remote sensing sub-image based on the normalized vegetation index, vegetation growth index and target fitting curve in the satellite remote sensing sub-image, wherein the target fitting curve is a relationship curve between the normalized vegetation index, vegetation growth index and biomass; calculating based on the first predicted biomass and the second predicted biomass to obtain the predicted total biomass corresponding to the satellite remote sensing image; and calculating based on the predicted total biomass to obtain the theoretical livestock amount.

[0086] Optionally, before obtaining the second predicted biomass corresponding to each satellite remote sensing sub-image based on the vegetation index, vegetation growth index and target fitting curve in the satellite remote sensing sub-image, the method also includes: obtaining historical satellite remote sensing images of the target grassland; calculating based on the reflectance values ​​of the near-infrared band and the reflectance values ​​of the red light band in the historical satellite remote sensing images to obtain a historical normalized vegetation index; obtaining the minimum normalized vegetation index and the maximum normalized vegetation index of the target grassland during the growing period; calculating based on the historical normalized vegetation index, the minimum normalized vegetation index and the maximum normalized vegetation index to obtain the historical vegetation growth index corresponding to the historical satellite remote sensing image; performing multivariate regression fitting based on the historical normalized vegetation index, the historical vegetation growth index and the real biomass corresponding to the historical satellite remote sensing image to obtain the target fitting curve.

[0087] Optionally, determining the repayment risk value of the target object based on the theoretical livestock volume and the actual livestock volume includes: determining the third predicted biomass corresponding to the actual livestock volume; determining the repayment risk value of the target object based on the difference between the actual livestock volume and the theoretical livestock volume and the difference between the first predicted biomass and the third predicted biomass.

[0088] The devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0089] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that initializes the following method steps: when a financial institution monitors the repayment ability of a target object, a satellite remote sensing image of a target grassland corresponding to the target object is obtained, and the satellite remote sensing image is processed in blocks to obtain multiple satellite remote sensing sub-images, wherein the target object is an object that obtains a loan through livestock farming in the target grassland; the satellite remote sensing sub-images are processed by a biomass prediction model corresponding to each satellite remote sensing sub-image to obtain a first predicted biomass corresponding to each satellite remote sensing sub-image; calculations are performed based on the first predicted biomass corresponding to each satellite remote sensing sub-image to determine the theoretical livestock volume corresponding to the target grassland; and the repayment risk value of the target object is determined based on the theoretical livestock volume and the actual livestock volume.

[0090] Optionally, dividing the satellite remote sensing image into blocks to obtain multiple satellite remote sensing sub-images includes: acquiring first geographic information of the target grassland, wherein the first geographic information includes at least climate condition information, vegetation type information and topographic information; dividing the satellite remote sensing image into blocks based on the first geographic information to obtain multiple satellite remote sensing sub-images.

[0091] Optionally, before processing the satellite remote sensing sub-image using the biomass prediction model corresponding to each satellite remote sensing sub-image, the method further includes: determining second geographic information corresponding to each satellite remote sensing sub-image; and determining the biomass prediction model corresponding to each satellite remote sensing sub-image based on the second geographic information.

[0092] Optionally, the satellite remote sensing sub-image is processed by a biomass prediction model corresponding to each satellite remote sensing sub-image to obtain a first predicted biomass corresponding to each satellite remote sensing sub-image, including: extracting vegetation features of the satellite remote sensing sub-image by the biomass prediction model to obtain a first eigenvector; extracting features of second geographic information corresponding to the satellite remote sensing sub-image by the biomass prediction model to obtain a second eigenvector; obtaining a target eigenvector based on the first eigenvector and the second eigenvector; and processing the target eigenvector by the biomass prediction model to obtain a first predicted biomass.

[0093] Optionally, calculation is performed based on the first predicted biomass corresponding to each satellite remote sensing sub-image to determine the theoretical livestock amount corresponding to the target grassland, including: obtaining the second predicted biomass corresponding to each satellite remote sensing sub-image based on the normalized vegetation index, vegetation growth index and target fitting curve in the satellite remote sensing sub-image, wherein the target fitting curve is a relationship curve between the normalized vegetation index, vegetation growth index and biomass; calculating based on the first predicted biomass and the second predicted biomass to obtain the predicted total biomass corresponding to the satellite remote sensing image; and calculating based on the predicted total biomass to obtain the theoretical livestock amount.

[0094] Optionally, before obtaining the second predicted biomass corresponding to each satellite remote sensing sub-image based on the vegetation index, vegetation growth index and target fitting curve in the satellite remote sensing sub-image, the method also includes: obtaining historical satellite remote sensing images of the target grassland; calculating based on the reflectance values ​​of the near-infrared band and the reflectance values ​​of the red light band in the historical satellite remote sensing images to obtain a historical normalized vegetation index; obtaining the minimum normalized vegetation index and the maximum normalized vegetation index of the target grassland during the growing period; calculating based on the historical normalized vegetation index, the minimum normalized vegetation index and the maximum normalized vegetation index to obtain the historical vegetation growth index corresponding to the historical satellite remote sensing image; performing multivariate regression fitting based on the historical normalized vegetation index, the historical vegetation growth index and the real biomass corresponding to the historical satellite remote sensing image to obtain the target fitting curve.

[0095] Optionally, determining the repayment risk value of the target object based on the theoretical livestock volume and the actual livestock volume includes: determining the third predicted biomass corresponding to the actual livestock volume; determining the repayment risk value of the target object based on the difference between the actual livestock volume and the theoretical livestock volume and the difference between the first predicted biomass and the third predicted biomass.

[0096] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0097] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0098] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0099] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0100] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0101] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0102] Computer readable media include 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 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.

[0103] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity 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, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0104] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0105] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A repayment risk assessment method, characterized in that: include: When a financial institution monitors the repayment ability of a target object, a satellite remote sensing image of a target grassland corresponding to the target object is obtained, and the satellite remote sensing image is processed into blocks to obtain a plurality of satellite remote sensing sub-images, wherein the target object is an object that obtains a loan through livestock farming in the target grassland; Processing the satellite remote sensing sub-images by using a biomass prediction model corresponding to each satellite remote sensing sub-image to obtain a first predicted biomass corresponding to each satellite remote sensing sub-image; Calculating according to the first predicted biomass corresponding to each satellite remote sensing sub-image to determine the theoretical livestock quantity corresponding to the target grassland; The repayment risk value of the target object is determined based on the theoretical livestock volume and the actual livestock volume.

2. The method according to claim 1, characterized in that The satellite remote sensing image is processed into blocks to obtain a plurality of satellite remote sensing sub-images including: Acquire first geographic information of the target grassland, wherein the first geographic information at least includes: climate condition information, vegetation type information and topographic information; The satellite remote sensing image is processed into blocks according to the first geographic information to obtain the multiple satellite remote sensing sub-images.

3. The method according to claim 1, characterized in that Before processing the satellite remote sensing sub-images using the biomass prediction model corresponding to each satellite remote sensing sub-image, the method further includes: Determining second geographic information corresponding to each satellite remote sensing sub-image; A biomass prediction model corresponding to each satellite remote sensing sub-image is determined based on the second geographic information.

4. The method according to claim 1, characterized in that Processing the satellite remote sensing sub-images by using the biomass prediction model corresponding to each satellite remote sensing sub-image to obtain the first predicted biomass corresponding to each satellite remote sensing sub-image includes: Extracting vegetation features from the satellite remote sensing sub-image using the biomass prediction model to obtain a first feature vector; Extracting features of the second geographic information corresponding to the satellite remote sensing sub-image by using the biomass prediction model to obtain a second feature vector; Obtaining a target feature vector according to the first feature vector and the second feature vector; The target feature vector is processed by the biomass prediction model to obtain the first predicted biomass.

5. The method according to claim 1, characterized in that Calculating according to the first predicted biomass corresponding to each satellite remote sensing sub-image to determine the theoretical livestock amount corresponding to the target grassland includes: According to the normalized vegetation index, the vegetation growth index and the target fitting curve in the satellite remote sensing sub-image, a second predicted biomass corresponding to each satellite remote sensing sub-image is obtained, wherein the target fitting curve is a relationship curve between the normalized vegetation index, the vegetation growth index and the biomass; Calculating according to the first predicted biomass and the second predicted biomass to obtain a predicted total biomass corresponding to the satellite remote sensing image; The theoretical livestock quantity is obtained by calculating based on the predicted total biomass.

6. The method according to claim 4, characterized in that Before obtaining the second predicted biomass corresponding to each satellite remote sensing sub-image according to the vegetation index, the vegetation growth index and the target fitting curve in the satellite remote sensing sub-image, the method further includes: Acquiring historical satellite remote sensing images of the target grassland; Calculating based on the reflectance value of the near infrared band and the reflectance value of the red light band in the historical satellite remote sensing image to obtain a historical normalized vegetation index; Obtaining the minimum normalized difference vegetation index and the maximum normalized difference vegetation index of the target grassland during the growing period; Calculating according to the historical normalized difference vegetation index, the minimum normalized difference vegetation index and the maximum normalized difference vegetation index to obtain a historical vegetation growth index corresponding to the historical satellite remote sensing image; A multivariate regression fitting is performed based on the historical normalized difference vegetation index, the historical vegetation growth index and the real biomass corresponding to the historical satellite remote sensing image to obtain a target fitting curve.

7. The method according to claim 1, characterized in that Determining the repayment risk value of the target object based on the theoretical livestock volume and the actual livestock volume includes: Determine a third predicted biomass corresponding to the actual livestock amount; The repayment risk value of the target object is determined according to the difference between the actual livestock amount and the theoretical livestock amount and the difference between the first predicted biomass and the third predicted biomass.

8. A repayment risk assessment device, characterized in that: include: A first acquisition unit is used to acquire a satellite remote sensing image of a target grassland corresponding to the target object when a financial institution monitors the repayment ability of the target object, and to perform block processing on the satellite remote sensing image to obtain a plurality of satellite remote sensing sub-images, wherein the target object is an object that obtains a loan through livestock breeding in the target grassland; A processing unit, configured to process the satellite remote sensing sub-images by using a biomass prediction model corresponding to each satellite remote sensing sub-image to obtain a first predicted biomass corresponding to each satellite remote sensing sub-image; A first calculation unit is used to calculate according to the first predicted biomass corresponding to each satellite remote sensing sub-image to determine the theoretical livestock quantity corresponding to the target grassland; The first determination unit is used to determine the repayment risk value of the target object according to the theoretical livestock volume and the actual livestock volume.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is run, the device where the storage medium is located is controlled to execute the repayment risk assessment method of any one of claims 1 to 7.

10. An electronic device, characterized in that: It includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the repayment risk assessment method described in any one of claims 1 to 7.

Images