Agricultural loan risk prediction method, device, equipment, medium and program product

Abstract

The invention provides an agricultural loan risk prediction method which can be applied to the technical field of artificial intelligence and can also be applied to the field of financial science and technology. The agricultural loan risk prediction method comprises the steps that first data and second data of a target user are acquired, the first data represents basic information of the user, and the second data represents environmental data related to agricultural production; inputting the first data into a first processing model to obtain a first risk value which represents credit evaluation data of the target user; inputting the second data into a second processing model to obtain a second risk value which represents the influence degree of the environmental data on the target user; and determining an evaluation value of the loan of the target user according to the first risk value and the second risk value. The invention further provides an agricultural loan risk prediction device and equipment, a storage medium and a program product.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence, and more specifically to a method, apparatus, device, medium, and program product for predicting agricultural loan risks. Background Art

[0002] Agricultural lending refers to the act of banks or other financial institutions taking farmers as loan targets, issuing a certain amount of loans to farmers, and having farmers purchase agricultural production materials, carry out agricultural production on farms such as cultivated land and greenhouses using their own labor or agricultural machinery and equipment, and then repay the loans with the funds obtained from the sale of agricultural products.

[0003] In the agricultural loan process, banks or financial institutions usually conduct risk assessments through regular manual inspections, while ignoring the impact of factors such as natural disasters, resulting in low accuracy in agricultural loan risk assessments. Summary of the Invention

[0004] In view of the above problems, the present disclosure provides a method, device, equipment, medium and program product for improving agricultural loan risk prediction.

[0005] According to a first aspect of the present disclosure, a method for predicting agricultural loan risks is provided, the method comprising: obtaining first data and second data of a target user, the first data representing basic information of the user, and the second data representing environmental data related to agricultural production; inputting the first data into a first processing model to obtain a first risk value, the first risk value representing credit assessment data of the target user; inputting the second data into a second processing model to obtain a second risk value, the second risk value representing the degree of influence of the environmental data on the target user; and determining an assessment value of the target user's loan based on the first risk value and the second risk value.

[0006] According to an embodiment of the present disclosure, determining the evaluation value of the target user's loan based on the first risk value and the second risk value includes: obtaining a first weight corresponding to the first risk value and a second weight corresponding to the second risk value; and determining the evaluation value of the target user's loan based on the first risk value, the first weight, the second risk value, and the second weight.

[0007] According to an embodiment of the present disclosure, the method includes: when the second risk value is greater than the first risk value, adjusting the second weight to be greater than the first weight; or when the first risk value is greater than the second risk value, adjusting the first weight to be greater than the second weight; wherein the sum of the first weight and the second weight is 1.

[0008] According to an embodiment of the present disclosure, the second data is input into the second processing model to obtain a second risk value, including: obtaining a remote sensing image of the target area, where the target area is the planting area of ​​the target user; inputting the remote sensing image into the classification model to obtain target data corresponding to the target area, where the target data represents the target object category; determining the distribution data of each target object based on the remote sensing image; inputting the target data and the distribution data into the second processing model to obtain a second risk value.

[0009] According to an embodiment of the present disclosure, a remote sensing image is input into a classification model to obtain target data corresponding to a target area, including: extracting features from the remote sensing image to obtain a feature map, where the feature map represents a representation of high-dimensional features extracted from the remote sensing image; selecting a main area of ​​the feature map to obtain at least one feature point set; and analyzing the at least one feature point set to obtain a target object type corresponding to each feature point set.

[0010] According to an embodiment of the present disclosure, feature extraction is performed on a remote sensing image to obtain a feature map, including: determining erased pixels in each feature point set based on at least one feature point set; performing pixel erasing on the remote sensing image based on the erased pixels to obtain an erased perspective image; and performing feature extraction on the remote sensing image and the erased perspective image to obtain a feature map.

[0011] According to an embodiment of the present disclosure, the method further includes: determining a third risk value of a neighboring area associated with the target area according to the second risk value of the target area.

[0012] According to an embodiment of the present disclosure, the method also includes: when the evaluation value is greater than the first threshold and the second risk value is greater than the second threshold, extending the first repayment period of the target user's loan to a second repayment period, and the second repayment period is greater than the first repayment period.

[0013] A second aspect of the present disclosure provides an agricultural loan risk prediction device, which includes: an acquisition module for acquiring first data and second data of a target user, the first data representing basic information of the user, and the second data representing environmental data related to agricultural production; a first processing module for inputting the first data into a first processing model to obtain a first risk value, and the first risk value represents the credit assessment data of the target user; a second processing module for inputting the second data into a second processing model to obtain a second risk value, and the second risk value represents the degree of influence of the environmental data on the target user; and a determination module for determining the assessment value of the target user's loan based on the first risk value and the second risk value.

[0014] A third aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the above method.

[0015] The fourth aspect of the present disclosure further provides a computer-readable storage medium having a computer program or instructions stored thereon, which implements the steps of the above method when the computer program or instructions are executed by a processor.

[0016] The fifth aspect of the present disclosure further provides a computer program product, comprising a computer program or instructions, which implement the steps of the above method when executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The above contents and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0018] Figure 1 Schematically illustrates an application scenario diagram of the agricultural loan risk prediction method, apparatus, device, medium, and program product according to an embodiment of the present disclosure;

[0019] Figure 2 The flowchart of the agricultural loan risk prediction method according to the embodiment of the present disclosure is schematically shown;

[0020] Figure 3 A flowchart of a method for determining an assessment value according to a first risk value and a second risk value according to an embodiment of the present disclosure is schematically shown;

[0021] Figure 4 A flowchart of a method for inputting second data into a second processing model to obtain a second risk value according to an embodiment of the present disclosure is schematically shown;

[0022] Figure 5 A flowchart schematically illustrates a method for inputting a remote sensing image into a classification model to obtain target data corresponding to a target area according to an embodiment of the present disclosure;

[0023] Figure 6 The flowchart of the method for extracting features from a remote sensing image to obtain a feature map according to an embodiment of the present disclosure is schematically shown;

[0024] Figure 7 Schematically shows a structural block diagram of an agricultural loan risk prediction device according to an embodiment of the present disclosure; and

[0025] Figure 8 A block diagram of an electronic device suitable for implementing the agricultural loan risk prediction method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0026] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present disclosure. In the detailed description below, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0027] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise," "include," etc. used herein indicate the presence of the features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0028] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0029] When expressions such as "at least one of A, B, and C, etc." are used, they should generally be interpreted in accordance with the meaning commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0030] It should be noted that the method and device for predicting agricultural loan risks disclosed herein can be used in the field of financial technology, and can also be used in any field other than the field of financial technology. The application field of the method and device for predicting agricultural loan risks disclosed herein is not limited.

[0031] In the embodiments of the present disclosure, the user information involved (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0032] In scenarios where personal information is used for automated decision-making, the methods, devices, and systems provided by the embodiments of the present disclosure all provide users with corresponding operation portals for them to choose to agree or reject the automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered. The expression "automated decision-making" here refers to the activity of automatically analyzing and evaluating an individual's behavioral habits, interests and hobbies, or economic, health, credit status, etc. through computer programs and making decisions. The expression "expert decision-making" here refers to the activity of making decisions by people who specialize in a certain field, have specialized experience, knowledge, and skills, and have reached a certain level of professionalism.

[0033] The embodiment of the present disclosure provides a method for predicting agricultural loan risks. Before introducing the technical solution provided by the embodiment of the present disclosure, the relevant technologies involved in the present disclosure are first described.

[0034] Agricultural lending refers to the act of banks or other financial institutions taking farmers as loan targets, issuing a certain amount of loans to farmers, and having farmers purchase agricultural production materials, carry out agricultural production on farms such as cultivated land and greenhouses using their own labor or agricultural machinery and equipment, and then repay the loans with the funds obtained from the sale of agricultural products.

[0035] In the agricultural loan process, banks or financial institutions usually conduct risk assessments through regular manual inspections, while ignoring the impact of factors such as natural disasters, resulting in low accuracy in agricultural loan risk assessments.

[0036] For example, locust plagues will cause serious damage to crops, which will lead to losses in agricultural loans.

[0037] An embodiment of the present disclosure provides a method for predicting agricultural loan risks, which includes: obtaining first data and second data of a target user, the first data representing basic information of the user, and the second data representing environmental data related to agricultural production; inputting the first data into a first processing model to obtain a first risk value, the first risk value representing the credit assessment data of the target user; inputting the second data into a second processing model to obtain a second risk value, the second risk value representing the degree of influence of the environmental data on the target user; and determining the assessment value of the target user's loan based on the first risk value and the second risk value.

[0038] Figure 1 The application scenario diagram of the agricultural loan risk prediction method, device, equipment, medium and program product according to the embodiment of the present disclosure is schematically shown.

[0039] like Figure 1As shown, the application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is used as a medium for providing a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired or wireless communication links or optical fiber cables.

[0040] A user may use a first terminal device 101, a second terminal device 102, or a third terminal device 103 to interact with a server 105 via a network 104 to receive or send messages, etc. Various communication client applications may be installed on the first terminal device 101, the second terminal device 102, or the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (for example only).

[0041] The first terminal device 101 , the second terminal device 102 , and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0042] The server 105 may be a server that provides various services, such as a background management server (for example only) that supports websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process received data such as user requests, and feed back processing results (e.g., web pages, information, or data obtained or generated based on user requests) to the terminal devices.

[0043] It should be noted that the agricultural loan risk prediction method provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the agricultural loan risk prediction device provided in the embodiment of the present disclosure can generally be set in the server 105. The agricultural loan risk prediction method provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Accordingly, the agricultural loan risk prediction device provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105.

[0044] It should be understood that Figure 1The number of terminal devices, networks and servers in the embodiment is merely illustrative. Any number of terminal devices, networks and servers may be provided as required.

[0045] The following will be based on Figure 1 The scene described by Figures 2 to 6 The agricultural loan risk prediction method of the disclosed embodiment is described in detail.

[0046] Figure 2 A flowchart of a method for predicting agricultural loan risks according to an embodiment of the present disclosure is schematically shown.

[0047] like Figure 2 As shown, the agricultural loan risk prediction method of this embodiment includes operations S210 to S240.

[0048] In operation S210 , first data and second data of a target user are acquired, where the first data represents basic information of the user, and the second data represents environmental data related to agricultural production.

[0049] For example, the basic information may include the target user's production history, financial status, loan history, credit score, historical loan records, income sources, operating costs, debt status, cash flow, etc.

[0050] Environmental data may include remote sensing images of the target user's land, climate data (precipitation, temperature, humidity, etc.), land area, crop type, soil quality, irrigation conditions, market prices of crops, etc.

[0051] In operation S220 , the first data is input into a first processing model to obtain a first risk value, where the first risk value represents credit assessment data of the target user.

[0052] Exemplarily, the first processing model is used to evaluate the credit risk of the target user.

[0053] After the basic information of the target user (first data) is input into the first processing model, the first processing model analyzes the first data to obtain a credit risk score value (first risk value) of the target user.

[0054] In operation S230 , the second data is input into a second processing model to obtain a second risk value, where the second risk value represents the degree of impact of the environmental data on the target user.

[0055] For example, the second processing model is used to evaluate the environmental risk of the target user. The environmental risk can be the degree of impact of soil, natural disasters, market prices, etc. on the crops grown on the land owned by the target user.

[0056] The environmental data (second data) of the land belonging to the target user is input into the second processing model, and the second processing model analyzes the second data to obtain a score value (second risk value) of the environmental risk of the target user.

[0057] For example, when the second data is a remote sensing image, the remote sensing image can be analyzed to obtain the risk value of a locust plague occurring in the land belonging to the target user.

[0058] In operation S240 , an evaluation value of the target user's loan is determined based on the first risk value and the second risk value.

[0059] For example, after obtaining the user's credit risk (first risk value) and the environmental risk of the land (second risk value), a comprehensive analysis is performed based on multiple risk factors to obtain an assessment of the target user's loan risk. If the assessment value is above a threshold, the user's loan repayment risk is high. If the assessment value is below the threshold, the user's loan repayment risk is low. Based on the assessment value, banks or financial institutions can determine whether to lend to the target user, the loan amount, and the term of the loan.

[0060] It is understandable that on the basis of assessing loan risks based on basic user information, risk assessment of environmental data is added. Environmental data can introduce the impact of factors such as natural disasters, market prices, and soil conditions on the agricultural production of target users, thereby realizing the prediction of loan risks for target users and making the loan prediction more closely matched with the risks of target users.

[0061] The extent of natural disasters on land is also used to assess bank loan limits and provide risk warnings after loans are made. This provides a basis for post-disaster reconstruction and agricultural subsidies in disaster-stricken areas, and can be supported by lowering loan interest rates and granting credit to entire villages.

[0062] In an embodiment of the present disclosure, before obtaining the user's basic information, the user's consent or authorization may be obtained. For example, before operation S210, a request to obtain user information may be issued to the user. If the user agrees or authorizes the acquisition of user information, operation S210 is performed.

[0063] Figure 3 The flowchart of the method for determining an assessment value according to a first risk value and a second risk value according to an embodiment of the present disclosure is schematically shown.

[0064] As described above, in operation S240, the evaluation value of the target user's loan is determined based on the first risk value and the second risk value. Figure 3 As shown, the operation may further include operations S310 to S320.

[0065] In operation S310 , a first weight corresponding to a first risk value and a second weight corresponding to a second risk value are acquired.

[0066] In operation S320 , an evaluation value of the target user's loan is determined based on the first risk value, the first weight, the second risk value, and the second weight.

[0067] Exemplarily, the first risk value and the second risk value adopt the same value range, for example, both can be set to a value of 0-100.

[0068] Because different factors have varying degrees of impact on loans, different risk values ​​can be assigned different weights during the comprehensive analysis process. For example, the first risk value for user credit risk might correspond to a first weight of 0.7, while the second risk value for environmental risk might correspond to a second weight of 0.3. Alternatively, the first risk value for user credit risk might correspond to a first weight of 0.6, while the second risk value for environmental risk might correspond to a second weight of 0.4.

[0069] It should be noted that the embodiment of the present disclosure does not impose any specific limitation on the value of the weight of each factor, and the value can be adjusted according to actual application conditions.

[0070] In some embodiments, the agricultural loan risk prediction method of this embodiment may further include: when the second risk value is greater than the first risk value, adjusting the second weight to be greater than the first weight.

[0071] The sum of the first weight and the second weight is 1.

[0072] For example, if the first risk value is 30 and the second risk value is 40, and the second risk value is greater than the first risk value, then the second weight may be greater than the first weight, that is, the first weight is 0.5 and the second weight is 0.6.

[0073] In some embodiments, the agricultural loan risk prediction method of this embodiment may further include: when the first risk value is greater than the second risk value, adjusting the first weight to be greater than the second weight;

[0074] For example, if the first risk value is 50 and the second risk value is 40, and the first risk value is greater than the second risk value, then the first weight may be greater than the second weight, that is, the first weight is 0.6 and the second weight is 0.5.

[0075] It is understandable that when the risk value is larger, the corresponding weight will also become larger, thereby ensuring that the risk of a certain factor is not easily neutralized, so as to ensure that the risk prediction will not be unbalanced.

[0076] Figure 4The flowchart of the method for inputting second data into the second processing model to obtain the second risk value according to an embodiment of the present disclosure is schematically shown.

[0077] As described above, in operation S230, the second data is input into the second processing model to obtain a second risk value. Figure 4 As shown, the operation may further include operations S410 to S440.

[0078] In operation S410 , a remote sensing image of a target area is acquired, where the target area is a planting area of ​​a target user.

[0079] In operation S420 , the remote sensing image is input into a classification model to obtain target data corresponding to the target area, where the target data represents a target object category.

[0080] In operation S430 , distribution data of each target object is determined based on the remote sensing image.

[0081] In operation S440 , the target data and the distribution data are input into a second processing model to obtain a second risk value.

[0082] For example, the target object may be an object that can affect the crops in the target area, such as locusts, disease spots, weeds, etc.

[0083] The second data is related data about natural disasters such as locusts, which can be used to predict the risk level of locust plagues on the land owned by the target user.

[0084] For example, satellite remote sensing technology and Internet of Things technology are used to conduct 24-hour dynamic monitoring of the farmland belonging to the target user, and farmland images marked with longitude and latitude are collected regularly using satellite remote sensing, Internet of Things (GPS positioning, sensors, fixed-point cameras and non-fixed-point shooting aircraft, etc.) and electronic tag equipment. The images obtained from different channels are then processed and analyzed separately.

[0085] By inputting remote sensing images into the classification model, the category of locusts in the target area (target data) can be obtained. For example, the target area may contain desert locusts, grassland locusts, etc.

[0086] At the same time, remote sensing images can be used to analyze the distribution data of different types of locusts, such as the distribution density of desert locusts.

[0087] The species and distribution density of locusts are input into the second processing model to obtain the risk level (second risk value) of locust plagues in the target area.

[0088] During the training of the second processing model, the sample data may include: different locust species, distribution density, and whether a locust plague occurs.

[0089] At the same time, in the embodiment of the present disclosure, after unified processing of images taken by fixed cameras and dynamic aircraft, convolutional neural network technology is used to identify locusts and mark the longitude and latitude; for satellite remote sensing images, the movement trajectory of locust populations is dynamically identified and the longitude and latitude are marked.

[0090] In some embodiments, the second processing model includes a first processing sub-model and a second processing sub-model. For short crops, such as wheat and rice, the first processing sub-model is used to identify and dynamically detect the number and density of locusts to determine whether the farmland is at risk of suffering a locust plague;

[0091] Tall crops like corn and sorghum can obscure locusts, leading to inaccurate identification results. A second processing sub-model is used to identify and dynamically monitor locust population size and density. During the analysis and prediction process, the large model can be combined with locust reports to analyze locust plagues and assist in forecasting them.

[0092] Figure 5 The flowchart of the method for inputting a remote sensing image into a classification model to obtain target data corresponding to a target area according to an embodiment of the present disclosure is schematically shown.

[0093] As described above, in operation S420, the remote sensing image is input into the classification model to obtain target data corresponding to the target area. Figure 5 As shown, the operation may further include operations S510 to S530.

[0094] In operation S510 , feature extraction is performed on the remote sensing image to obtain a feature map, where the feature map represents a representation of high-dimensional features extracted from the remote sensing image.

[0095] In operation S520 , a main area selection is performed on the feature map to obtain at least one feature point set.

[0096] In operation S530 , at least one feature point set is analyzed to obtain a target object type corresponding to each feature point set.

[0097] For example, the feature point set can be some key points or regions extracted from the feature map. Each feature point represents an important area or information point in the image, and these points will be used for further analysis.

[0098] Remote sensing images and erase perspective image Feature extraction is performed separately to obtain feature maps 、 . Get feature map , the feature map size is (where H and W represent the height and width of the feature map, respectively, and Y represents the number of channels), the feature map The set of all feature points in is , Representation feature map The feature vector of the jth feature point. Please refer to the following Figure 6 The operation is obtained, which will not be repeated here.

[0099] Feature Map 、 Select the main area and obtain the feature point set 、 For example, the subject area selection can be to select the area where the locust's wings, legs, glasses, etc. are located. Feature point set and erase perspective image Feature point set Perform average pooling operation. During the average pooling process, the feature point set of the locust The regional features of all feature points in the global average pooling are used to obtain the main perspective and erased perspective features respectively. Then the features after average pooling of each perspective are Input classification model. The classification model is based on the input perspective features Perform classification and obtain the recognition results under this perspective .in, Indicates that the nth element is a remote sensing image The confidence level of a locust belonging to the nth class.

[0100] The recognition results of each view Perform weighted fusion to obtain the final recognition result :

[0101]

[0102] in, They represent preset weights respectively, and the sum of the two is 1.

[0103] Recognition results The locust category represented by the maximum confidence value will be used as the final identification category (locust species).

[0104] Among them, the fully connected layer is used to transform the feature map Each feature point in 、 Classification prediction is performed as an independent regional feature to obtain the locust species confidence vector of each feature point , and finally output to the main feature point screening; the main feature point screening selects the largest confidence value from the confidence vectors of the locust species predicted by all the received feature points as the discriminant weight of the feature point representing the local area, sorts the discriminant weights of all feature points from large to small, and selects the set of the first W feature points according to actual needs , as region W. It can be understood as: based on the confidence vector of the locust species predicted by each feature point, the feature points that are most likely to belong to locusts are screened out. For each feature point, the locust species corresponding to the maximum value in its confidence vector is selected as the "discriminant weight" of the feature point. The discriminant weights of all feature points (that is, the maximum confidence of each feature point) are sorted, and feature points with high weights are more likely to represent the key areas of locusts. Finally, the top W feature points are selected from the sorted feature points as "region W". These feature points represent important local areas in the image, and they are most likely to contain key information about locusts.

[0105] Figure 6 The flowchart of the method for extracting features from a remote sensing image to obtain a feature map according to an embodiment of the present disclosure is schematically shown.

[0106] As described above, in operation S510, feature extraction is performed on the remote sensing image to obtain a feature map. In one possible implementation, Figure 6 As shown, the operation may further include operations S610 to S630.

[0107] In operation S610 , erased pixels in each feature point set are determined based on at least one feature point set.

[0108] In operation S620, pixels of the remote sensing image are erased according to the erased pixels to obtain an erased viewing angle image.

[0109] In operation S630 , feature extraction is performed on the remote sensing image and the erased view image to obtain a feature map.

[0110] For example, erasing a perspective may be generating a new image version by erasing or processing certain areas of the image.

[0111] This module is used to According to the main area feature point set Generate a wiped perspective of the locust First, randomly select Select K ( ) feature points , k=1,...K,K; then according to the image and feature maps The mapping relationship of the pixels in the image is used to map the K feature points and obtain K pixel points. , taking the pixel as the center, from the image Erases K preset shapes and finally obtains and outputs the erased perspective image .

[0112] This can be understood as randomly selecting K feature points from the feature point set of the main area, where K is a number indicating the number of feature points to be selected. The value of K ranges from 1 to a certain upper limit (i.e., K = 1, ..., K_max). These feature points represent important locations or regions in the locust image. Based on the relationship between the feature map (which may be the output of a deep learning model) and the pixels in the image, the K selected feature points are mapped to the corresponding pixels in the image. The feature map may be image features obtained through a convolution operation, which helps locate the location of the feature points in the original image. Each feature point corresponds to a pixel in the image, which serves as the center of the erasing operation. For each selected pixel, a certain area around it is erased. The erased area is typically a preset shape (such as a rectangle, circle, or other shape). A new image is generated by erasing the image. The erased area makes the image incomplete or produces a specific occlusion effect, mimicking situations that may occur in reality (for example, a locust being partially obscured).

[0113] In some embodiments, the agricultural loan risk prediction may further include operation S710.

[0114] In operation S710 , a third risk value of a neighboring area associated with the target area is determined according to the second risk value of the target area.

[0115] For example, the degree of damage caused by the primary locust plague on farmland i (target area) is calculated based on the locust population type, average density and the degree of impact on a certain type of crop. Scoring; the degree of damage to the neighboring farmland j is based on the distance from i to j Attenuation, and superimposed on the score of the original locust plague suffered by the farmland (target area), the formula is as follows:

[0116]

[0117] This is used as a comprehensive score for the risk level of locust plague on farmland j. .

[0118] It is understandable that if users in neighboring areas of the target area have also taken out loans, when conducting a locust plague risk assessment on the target area, the risk of locust plagues in neighboring areas can also be assessed to help banks or financial institutions issue risk warnings for loans to users in neighboring areas.

[0119] In some embodiments, the agricultural loan risk prediction may further include: when the assessment value is greater than a first threshold and the second risk value is greater than a second threshold, extending the first repayment period of the target user's loan to a second repayment period, and the second repayment period is greater than the first repayment period.

[0120] For example, if the predicted evaluation value (60) of the target user is greater than the first threshold (50), it indicates that the target user has a repayment risk. And if the second risk value (60) generated by the impact of environmental factors on the target user's loan is greater than the second threshold (40), it means that environmental factors (such as natural disasters and locust plagues) have a major impact on the risk. Since natural disasters are uncontrollable factors, the repayment period of the target user can be extended to reduce the loan risk.

[0121] Based on the above agricultural loan risk prediction method, the present disclosure also provides an agricultural loan risk prediction device. Figure 7 The device is described in detail.

[0122] Figure 7 The structural block diagram of the agricultural loan risk prediction device according to an embodiment of the present disclosure is schematically shown.

[0123] like Figure 7 As shown, the agricultural loan risk prediction device 800 of this embodiment includes an acquisition module 810 , a first processing module 820 , a second processing module 830 and a determination module 840 .

[0124] The acquisition module 810 is used to acquire first data and second data of the target user, where the first data represents basic information of the user and the second data represents environmental data related to agricultural production. In one embodiment, the acquisition module 810 can be used to perform the operation S210 described above, which will not be repeated here.

[0125] The first processing module 820 is used to input the first data into the first processing model to obtain a first risk value, which represents the credit assessment data of the target user. In one embodiment, the first processing module 820 can be used to perform the operation S220 described above, which will not be repeated here.

[0126] The second processing module 830 is used to input the second data into the second processing model to obtain a second risk value, which represents the impact of the environmental data on the target user. In one embodiment, the second processing module 830 can be used to perform the operation S230 described above, which will not be repeated here.

[0127] The determination module 840 is used to determine the evaluation value of the target user's loan based on the first risk value and the second risk value. In one embodiment, the determination module 840 can be used to perform the operation S240 described above, which will not be repeated here.

[0128] According to an embodiment of the present disclosure, the determination module includes a first acquisition submodule and a first determination submodule.

[0129] The first acquisition submodule is used to acquire a first weight corresponding to the first risk value and a second weight corresponding to the second risk value.

[0130] The first determination submodule is used to determine the evaluation value of the target user's loan according to the first risk value, the first weight, the second risk value and the second weight.

[0131] According to an embodiment of the present disclosure, the device further includes an adjustment module.

[0132] The adjustment module is used to adjust the second weight to be greater than the first weight when the second risk value is greater than the first risk value; or to adjust the first weight to be greater than the second weight when the first risk value is greater than the second risk value; wherein the sum of the first weight and the second weight is 1.

[0133] According to an embodiment of the present disclosure, the second processing module includes a second acquisition submodule, a first analysis submodule, a second determination submodule, and a second analysis submodule.

[0134] The second acquisition submodule is used to acquire a remote sensing image of a target area, where the target area is a planting area of ​​a target user.

[0135] The first analysis submodule is used to input the remote sensing image into the classification model to obtain target data corresponding to the target area, and the target data represents the target object category.

[0136] The second determination submodule is used to determine the distribution data of each target object based on the remote sensing image.

[0137] The second analysis submodule is used to input the target data and the distribution data into a second processing model to obtain a second risk value.

[0138] According to an embodiment of the present disclosure, the first analysis submodule includes an extraction unit, a selection unit, and an analysis unit.

[0139] The extraction unit is used to extract features from the remote sensing image to obtain a feature map, which represents the representation of high-dimensional features extracted from the remote sensing image.

[0140] The selection unit is used to select a main area of ​​the feature map to obtain at least one feature point set.

[0141] The analyzing unit is used to analyze at least one feature point set to obtain a target object type corresponding to each feature point set.

[0142] According to an embodiment of the present disclosure, the extraction unit includes a determination subunit, an erasure subunit, and an extraction subunit.

[0143] The determining subunit is configured to determine the erased pixels in each feature point set according to at least one feature point set.

[0144] The erasing subunit is used to perform pixel erasing on the remote sensing image according to the erased pixels to obtain an erased perspective image.

[0145] The extraction subunit is used to extract features from the remote sensing image and the erased view image to obtain a feature map.

[0146] According to an embodiment of the present disclosure, the device further includes a second determining module.

[0147] The second determination module is used to determine the third risk value of the adjacent area associated with the target area according to the second risk value of the target area.

[0148] According to an embodiment of the present disclosure, the device further includes an extension module.

[0149] The extension module is used to extend the first repayment period of the target user's loan to a second repayment period when the evaluation value is greater than the first threshold and the second risk value is greater than the second threshold, and the second repayment period is greater than the first repayment period.

[0150] According to embodiments of the present disclosure, any multiple modules among the acquisition module 810, the first processing module 820, the second processing module 830, and the determination module 840 may be combined into a single module, or any one of these modules may be split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of other modules and implemented in a single module. According to embodiments of the present disclosure, at least one of the acquisition module 810, the first processing module 820, the second processing module 830, and the determination module 840 may be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or may be implemented in hardware or firmware through any other reasonable means of circuit integration or packaging, or may be implemented in any one of the three implementation methods of software, hardware, and firmware, or in any appropriate combination of any of these. Alternatively, at least one of the acquisition module 810 , the first processing module 820 , the second processing module 830 and the determination module 840 may be at least partially implemented as a computer program module, which may perform corresponding functions when executed.

[0151] Figure 8 A block diagram of an electronic device suitable for implementing the agricultural loan risk prediction method according to an embodiment of the present disclosure is schematically shown.

[0152] like Figure 8 As shown, the electronic device 900 according to an embodiment of the present disclosure includes a processor 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage unit 908 into a random access memory (RAM) 903. The processor 901 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 901 may also include onboard memory for caching purposes. The processor 901 may include a single processing unit or multiple processing units for performing different actions of the method flow according to the embodiment of the present disclosure.

[0153] Various programs and data required for the operation of the electronic device 900 are stored in the RAM 903. The processor 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. The processor 901 performs various operations of the method flow according to the embodiment of the present disclosure by executing the programs in the ROM 902 and / or the RAM 903. It should be noted that the programs may also be stored in one or more memories other than the ROM 902 and the RAM 903. The processor 901 may also perform various operations of the method flow according to the embodiment of the present disclosure by executing the programs stored in the one or more memories.

[0154] According to an embodiment of the present disclosure, electronic device 900 may further include an input / output (I / O) interface 905, which is also connected to bus 904. Electronic device 900 may also include one or more of the following components connected to I / O interface 905: an input section 906 including a keyboard, mouse, etc.; an output section 907 including devices such as a cathode ray tube (CRT), liquid crystal display (LCD), and speakers; a storage section 908 including a hard disk; and a communication section 909 including a network interface card such as a LAN card or modem. Communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to I / O interface 905 as needed. Removable media 911, such as a magnetic disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed in drive 910 as needed, so that computer programs read from the removable media can be installed into storage section 908 as needed.

[0155] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments, or may exist independently and not be incorporated into the device / apparatus / system. The computer-readable storage medium carries one or more programs, and when executed, implements the method according to the embodiments of the present disclosure.

[0156] According to an embodiment of the present disclosure, a computer-readable storage medium may be a non-volatile computer-readable storage medium, and may include, for example, but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to an embodiment of the present disclosure, a computer-readable storage medium may include the ROM 902 and / or RAM 903 described above, and / or one or more memories other than ROM 902 and RAM 903.

[0157] The present disclosure also includes a computer program product comprising a computer program containing program code for executing the method shown in the flowchart. When the computer program product is executed in a computer system, the program code is used to cause the computer system to implement the agricultural loan risk prediction method provided by the present disclosure.

[0158] The computer program executes the above functions defined in the system / device of the embodiment of the present disclosure when the processor 901 executes the computer program. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0159] In one embodiment, the computer program may be stored on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may be transmitted and distributed in the form of a signal on a network medium, downloaded and installed via the communication portion 909, and / or installed from a removable medium 911. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0160] In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 909, and / or installed from a removable medium 911. When the computer program is executed by the processor 901, the above-described functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the systems, devices, means, modules, units, etc. described above can be implemented by computer program modules.

[0161] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computer programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C" or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect via the Internet).

[0162] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the above-mentioned module, program segment, or a part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0163] Those skilled in the art will appreciate that the features described in the various embodiments of the present disclosure may be combined and / or coupled in various ways, even if such combinations or couplings are not explicitly described in the present disclosure. In particular, the features described in the various embodiments of the present disclosure may be combined and / or coupled in various ways without departing from the spirit and teachings of the present disclosure. All such combinations and / or couplings fall within the scope of the present disclosure.

[0164] The above describes the embodiments of the present disclosure. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although each embodiment has been described separately above, this does not mean that the measures in each embodiment cannot be advantageously used in combination. Without departing from the scope of the present disclosure, those skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A method for predicting agricultural loan risks, characterized in that: The method comprises: Acquire first data and second data of a target user, wherein the first data represents basic information of the user, and the second data represents environmental data related to agricultural production; Inputting the first data into a first processing model to obtain a first risk value, where the first risk value represents the credit assessment data of the target user; Inputting the second data into a second processing model to obtain a second risk value, where the second risk value represents the degree of impact of the environmental data on the target user; An assessment value of the target user's loan is determined based on the first risk value and the second risk value.

2. The method according to claim 1, characterized in that Determining an assessment value of the target user's loan based on the first risk value and the second risk value includes: Obtaining a first weight corresponding to the first risk value and a second weight corresponding to the second risk value; An assessment value of the target user's loan is determined based on the first risk value, the first weight, the second risk value, and the second weight.

3. The method according to claim 2, characterized in that The method comprises: When the second risk value is greater than the first risk value, adjusting the second weight to be greater than the first weight; or When the first risk value is greater than the second risk value, adjusting the first weight to be greater than the second weight; The sum of the first weight and the second weight is 1.

4. The method according to claim 1, wherein Inputting the second data into a second processing model to obtain a second risk value includes: Acquiring a remote sensing image of a target area, where the target area is a planting area of ​​the target user; Inputting the remote sensing image into a classification model to obtain target data corresponding to the target area, wherein the target data represents a target object category; determining distribution data of each target object according to the remote sensing image; The target data and the distribution data are input into the second processing model to obtain a second risk value.

5. The method according to claim 4, characterized in that Inputting the remote sensing image into a classification model to obtain target data corresponding to the target area includes: Performing feature extraction on the remote sensing image to obtain a feature map, wherein the feature map represents a representation of high-dimensional features extracted from the remote sensing image; Performing subject area selection on the feature map to obtain at least one feature point set; The at least one feature point set is analyzed to obtain a target object type corresponding to each feature point set.

6. The method according to claim 5, characterized in that Performing feature extraction on the remote sensing image to obtain a feature map includes: Determining, based on the at least one feature point set, erased pixels in each of the feature point sets; Erasing pixels of the remote sensing image according to the erased pixels to obtain an erased perspective image; Feature extraction is performed on the remote sensing image and the erased view image to obtain a feature map.

7. The method according to claim 4, characterized in that The method further comprises: A third risk value of a neighboring area associated with the target area is determined according to the second risk value of the target area.

8. The method according to claim 1, characterized in that The method further comprises: When the evaluation value is greater than a first threshold and the second risk value is greater than a second threshold, the first repayment period of the target user's loan is extended to a second repayment period, and the second repayment period is greater than the first repayment period.

9. An agricultural loan risk prediction device, characterized in that: The device comprises: An acquisition module, configured to acquire first data and second data of a target user, wherein the first data represents basic information of the user, and the second data represents environmental data related to agricultural production; a first processing module, configured to input the first data into a first processing model to obtain a first risk value, where the first risk value represents the credit assessment data of the target user; a second processing module, configured to input the second data into a second processing model to obtain a second risk value, where the second risk value represents the degree of impact of the environmental data on the target user; A determination module is used to determine the evaluation value of the target user's loan based on the first risk value and the second risk value.

10. An electronic device comprising: one or more processors; a memory for storing one or more computer programs, It is characterized in that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

12. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images