Credit granting management method based on multi-temporal satellite remote sensing and related equipment

Abstract

The invention provides a credit management method and related equipment based on multi-temporal satellite remote sensing, and the method comprises the steps: determining a to-be-analyzed land parcel in response to a credit management instruction; acquiring a multi-temporal satellite remote sensing image of the land parcel to be analyzed; analyzing the multi-temporal satellite remote sensing image by using a preset image analysis system to obtain a normalized difference vegetation index (NDVI) sequence of the land parcel to be analyzed; determining crop species of the to-be-analyzed plot according to the NDVI sequence of the to-be-analyzed plot; inputting the NDVI sequence into a pre-constructed yield analysis model to obtain a crop yield prediction result of the crop variety; and carrying out credit granting on the credit granting object to which the to-be-analyzed land parcel belongs according to the crop yield prediction result of the crop type. By applying the method provided by the embodiment of the invention, the credit can be accurately granted to the customer.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a credit management method and related equipment based on multi-temporal satellite remote sensing. Background Art

[0002] In the traditional farmer loan process, account managers play a vital role. They usually need to go to the farmer's location in person for field visits to collect and analyze key data such as the farmer's basic information, farmland asset status, and income source. This traditional method is not only time-consuming and labor-intensive, but also has significant subjective judgment problems in the information collection and asset evaluation process.

[0003] Specifically, when collecting customer information on the spot, account managers often rely on their personal expertise and experience to evaluate farmland assets, lacking unified, objective data standards and evaluation models. Although account managers may record the actual conditions of farmland by taking photos, these photos can only provide intuitive visual information, but cannot fully and accurately reflect the key attributes of farmland, such as crop types and yield potential. Therefore, this evaluation method based on photos and subjective judgment has great uncertainty in its accuracy and reliability, and it is difficult to serve as an effective basis for financial institutions to make credit decisions. Summary of the invention

[0004] The technical problem to be solved by this application is to provide a credit management method and related equipment based on multi-temporal satellite remote sensing, which can accurately grant credit to customers. The specific solution is as follows:

[0005] A credit management method based on multi-temporal satellite remote sensing, comprising:

[0006] In response to the credit management instruction, determining the land parcel to be analyzed;

[0007] Acquire multi-temporal satellite remote sensing images of the land parcel to be analyzed;

[0008] Analyzing the multi-temporal satellite remote sensing images using a preset image analysis system to obtain a normalized difference vegetation index (NDVI) sequence of the plot to be analyzed;

[0009] Determining the crop type of the plot to be analyzed according to the NDVI sequence of the plot to be analyzed;

[0010] Inputting the NDVI sequence into a pre-built yield analysis model to obtain a crop yield prediction result for the crop type;

[0011] The credit object to which the analyzed land parcel belongs is granted credit according to the crop yield prediction result of the crop type.

[0012] In the above method, optionally, the determining of the plot to be analyzed includes:

[0013] Starting a preset positioning system to obtain position information obtained by the positioning system, and determining the plot to which the position information belongs as the plot to be analyzed; or,

[0014] A plot selection interface is displayed, and when a selection operation of the user in the plot selection interface is received, the plot corresponding to the selection operation is determined as the plot to be analyzed.

[0015] The above method, optionally, a process for pre-building a yield analysis model, includes:

[0016] Obtain multi-temporal satellite remote sensing images and crop yield data of the test plots in historical periods;

[0017] Analyze the multi-temporal satellite remote sensing images of the historical period to obtain the NDVI sequence of the test plot in the historical period;

[0018] According to the crop yield data of the test plot in the historical period and the NDVI sequence, obtaining a correlation curve between the crop yield data of the test plot and the NDVI sequence;

[0019] A yield analysis model is constructed based on the correlation curve.

[0020] The above method may optionally include granting credit to the credit object to which the to-be-analyzed plot belongs according to the crop yield prediction result of the crop type, including:

[0021] Acquire historical planting information and trade information of the credit object to which the plot to be analyzed belongs, wherein the trade information includes at least one of accounts receivable, transaction notes, contracts and transaction data;

[0022] Evaluating the planting stability of the credit subject according to the historical planting information;

[0023] Verify the trade information of the credit object and obtain the verification result;

[0024] A preset credit model is used to generate a credit limit for the credit object based on the crop yield prediction result of the crop type, the planting stability and the verification result to complete the credit for the credit object.

[0025] The above method may, optionally, further include, after granting credit to the credit object to which the to-be-analyzed plot belongs according to the crop yield prediction result of the crop type:

[0026] When the preset monitoring time point is reached, the current multi-temporal satellite remote sensing image of the land parcel to be analyzed is obtained;

[0027] Analyzing the multi-temporal satellite remote sensing images acquired at the monitoring time point using a preset image analysis system to obtain an NDVI sequence corresponding to the monitoring time point;

[0028] Matching the NDVI sequence corresponding to the monitoring time point with a preset crop growth curve;

[0029] In the case where the monitoring time point fails to match the crop growth curve, the step of inputting the NDVI sequence into a pre-built yield analysis model to obtain a crop yield prediction result for the crop type is returned to execution.

[0030] A credit management device based on multi-temporal satellite remote sensing, comprising:

[0031] A first determining unit, configured to determine a land parcel to be analyzed in response to a credit management instruction;

[0032] An acquisition unit, used for acquiring multi-temporal satellite remote sensing images of the land parcel to be analyzed;

[0033] An analysis unit, used to analyze the multi-temporal satellite remote sensing image using a preset image analysis system to obtain a normalized difference vegetation index NDVI sequence of the plot to be analyzed;

[0034] A second determination unit is used to determine the crop type of the plot to be analyzed according to the NDVI sequence of the plot to be analyzed;

[0035] A processing unit, used for inputting the NDVI sequence into a pre-built yield analysis model to obtain a crop yield prediction result of the crop type;

[0036] The credit granting unit is used to grant credit to the credit object to which the to-be-analyzed land parcel belongs according to the crop yield prediction result of the crop type.

[0037] In the above device, optionally, the first determining unit includes: a starting unit or a display unit;

[0038] The starting unit is used to start a preset positioning system to obtain the position information obtained by the positioning system, and determine the land parcel to which the position information belongs as the land parcel to be analyzed;

[0039] The display unit is used to display a plot selection interface, and when receiving a selection operation of a user in the plot selection interface, determines the plot corresponding to the selection operation as the plot to be analyzed.

[0040] In the above device, optionally, the processing unit includes:

[0041] The acquisition subunit is used to obtain multi-temporal satellite remote sensing images and crop yield data of the test plot in historical periods;

[0042] An analysis subunit, used for analyzing the multi-temporal satellite remote sensing images of the historical period to obtain the NDVI sequence of the test plot in the historical period;

[0043] According to the crop yield data of the test plot in the historical period and the NDVI sequence, obtaining a correlation curve between the crop yield data of the test plot and the NDVI sequence;

[0044] A yield analysis model is constructed based on the correlation curve.

[0045] A storage medium includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to execute the credit management method based on multi-temporal satellite remote sensing as described above.

[0046] An electronic device includes a memory and one or more instructions, wherein the one or more instructions are stored in the memory and are configured to be executed by one or more processors to execute the credit management method based on multi-temporal satellite remote sensing as described above.

[0047] Based on the above-mentioned implementation of this application, a credit management method based on multi-temporal satellite remote sensing and related equipment are provided, the method comprising: in response to a credit management instruction, determining the plot to be analyzed; obtaining the multi-temporal satellite remote sensing image of the plot to be analyzed; using a preset image analysis system to analyze the multi-temporal satellite remote sensing image to obtain the normalized vegetation index NDVI sequence of the plot to be analyzed; determining the crop type of the plot to be analyzed according to the NDVI sequence of the plot to be analyzed; inputting the NDVI sequence into a pre-constructed yield analysis model to obtain the crop yield prediction result of the crop type; and granting credit to the credit object to which the plot to be analyzed belongs according to the crop yield prediction result of the crop type. By using the method provided in the embodiment of the present application, through the acquisition and analysis of multi-temporal satellite remote sensing images, the growth status of vegetation on the plot to be analyzed can be objectively and continuously monitored, avoiding the uncertainty caused by the subjective judgment of the account manager in the traditional method. Using the normalized vegetation index (NDVI) as an evaluation indicator, the lushness and health of vegetation can be accurately quantified, providing a scientific basis for determining the crop type. Through continuous monitoring of NDVI and forecasting of crop yields, financial institutions can adjust credit strategies in a timely manner, effectively respond to unforeseen factors such as market fluctuations and natural disasters, and improve the timeliness of risk management. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0049] Figure 1 A method flow chart of a credit management method based on multi-temporal satellite remote sensing provided in this application;

[0050] Figure 2 A flowchart of the process of a pre-built yield analysis model provided for this application;

[0051] Figure 3 A flowchart of the financing process based on multi-temporal satellite remote sensing provided for this application;

[0052] Figure 4 A flowchart of a multi-temporal satellite remote sensing image data processing process provided for this application;

[0053] Figure 5 An example graph of NDVI time series for multiple types of crops provided for this application;

[0054] Figure 6 A schematic diagram of the structure of a credit management device based on multi-temporal satellite remote sensing provided in this application;

[0055] Figure 7 A schematic diagram of the structure of an electronic device provided in this application. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0057] In this application, the terms "comprises", "comprising" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element.

[0058] The embodiment of the present application provides a credit management method based on multi-temporal satellite remote sensing. The method can be applied to electronic devices, and the electronic devices can include one or more of a controller, a server, a personal computer, a tablet, a mobile phone, etc. The method flow chart of the method is as follows: Figure 1 As shown, specifically including:

[0059] S101: In response to a credit management instruction, determine a land parcel to be analyzed.

[0060] In this embodiment, the credit management instruction can be an instruction triggered when a bank or other financial institution needs to conduct a credit assessment on a credit subject; it can also be an instruction triggered by a user such as an employee of a financial institution or a credit subject clicking a virtual control in a credit assessment interface of an electronic device.

[0061] Optionally, the plot to be analyzed may be determined based on the current location of the electronic device or a location selected by the user.

[0062] S102: Acquire multi-temporal satellite remote sensing images of the land parcel to be analyzed.

[0063] In this embodiment, based on the location information or the identifier of the land parcel to be analyzed, the pre-processed multi-temporal satellite remote sensing image of the land parcel to be analyzed can be obtained from a preset remote sensing image storage module.

[0064] In an embodiment provided in the present application, based on the above solution, optionally, determining the plot to be analyzed includes:

[0065] Starting a preset positioning system to obtain position information obtained by the positioning system, and determining the plot to which the position information belongs as the plot to be analyzed; or,

[0066] A plot selection interface is displayed, and when a selection operation of the user in the plot selection interface is received, the plot corresponding to the selection operation is determined as the plot to be analyzed.

[0067] In this embodiment, the plots can be automatically segmented and a plot layer can be generated in advance based on field surveys or longitude and latitude information provided by the enterprise. The plot layer is displayed as crop planting areas cut based on land information, and then a plot selection interface is displayed. The plot layer is displayed in the plot selection interface, so that the user can select the plot to be analyzed in the plot selection interface.

[0068] S103: Analyze the multi-temporal satellite remote sensing images using a preset image analysis system to obtain a Normalized Difference Vegetation Index (NDVI) sequence of the land parcel to be analyzed.

[0069] In this embodiment, the NDVI sequence includes the NDVI obtained by the image analysis system for each phase of satellite remote sensing image recognition. The red light band and the near infrared band can be selected, and the serial numbers of the red light band and the near infrared band are searched and confirmed in the image analysis system, and then the NDVI is calculated.

[0070] In this embodiment, the calculation method of NDVI is as follows:

[0071] NDVI=(ρ NIR -ρ N ) / (ρ NIR +ρ N )

[0072] Among them, ρ NIR is the surface reflectivity in the near-infrared band, ρ N It is the surface reflectance in the red light band. The range of NDVI is (-1,1). The NDVI value of surface vegetation is generally between 0.2-0.8, and the higher the value, the more obvious the vegetation characteristics. Since the NDVI sequence has a significant linear correlation with the density of crop distribution on the surface, it has become the best indicator to reflect the ground coverage, self-generation and biomass of surface crops. In addition, since NDVI is obtained through normalization, it eliminates the interference of atmospheric radiation, sensor deflection, solar altitude angle and other factors to a certain extent.

[0073] S104: Determine the crop type of the land to be analyzed according to the NDVI sequence of the land to be analyzed.

[0074] In some embodiments, a crop distribution probability map can be obtained based on multi-temporal satellite remote sensing images, NDVI sequences of the plots to be analyzed, prior phenological period information, and a preset semantic segmentation deep learning model, and then a crop classification label map can be generated based on the probability map, in which each pixel is assigned a specific crop type label, thereby obtaining the crop type of the plot to be analyzed.

[0075] Optionally, the crop types may include at least one of corn, wheat, cotton and vegetables.

[0076] S105: Inputting the NDVI sequence into a pre-constructed yield analysis model to obtain a crop yield prediction result for the crop type.

[0077] In this embodiment, the yield analysis model may be a fitting model of crop yield and NDVI sequence, and the NDVI sequence of the plot to be analyzed may be input into the yield analysis model to obtain the crop yield prediction result of the crop type.

[0078] S106: granting credit to the credit object to which the to-be-analyzed land parcel belongs according to the crop yield prediction result of the crop type.

[0079] In this embodiment, credit can be granted to the credit subject based on the crop yield prediction result, the historical planting information and trade information of the credit subject.

[0080] By using the method provided in the embodiment of the present application, through the acquisition and analysis of multi-phase satellite remote sensing images, it is possible to objectively and continuously monitor the growth status of vegetation on the plot to be analyzed, avoiding the uncertainty caused by the subjective judgment of the account manager in the traditional method. Using the Normalized Difference Vegetation Index (NDVI) as an evaluation indicator, the lushness and health of the vegetation can be accurately quantified, providing a scientific basis for determining the type of crop. Through continuous monitoring of NDVI and prediction of crop yields, financial institutions can adjust credit strategies in a timely manner, effectively respond to unforeseen factors such as market fluctuations and natural disasters, and improve the timeliness of risk management.

[0081] In one embodiment provided in the present application, based on the above scheme, optionally, a process of pre-constructing a yield analysis model, such as Figure 2 As shown, specifically including:

[0082] S201: Obtain multi-temporal satellite remote sensing images and crop yield data of the test plots in historical periods.

[0083] In this embodiment, multi-temporal satellite remote sensing images of the test plot in the historical period can be obtained from the preset remote sensing impact storage module, and the crop yield data of the plot to be analyzed can be obtained from the preset database. The crop yield data can come from field test experiments, agricultural statistics or farmer reports, etc.

[0084] S202: Analyze the multi-temporal satellite remote sensing images of the historical period to obtain the NDVI sequence of the test plot in the historical period.

[0085] In this embodiment, the process and principle of obtaining the NDVI sequence of the test plot in the historical period are consistent with S103, and reference may be made to the description of S103, which will not be repeated here.

[0086] S203: Obtaining a correlation curve between the crop yield data of the test plot and the NDVI sequence according to the crop yield data of the test plot in the historical period and the NDVI sequence.

[0087] In this embodiment, the NDVI sequence value at each time point is associated with the crop yield data at the corresponding time point. Statistical analysis software or methods (such as scatter plot, linear regression, nonlinear regression, etc.) are used to draw and analyze the correlation curve between the crop yield data and the NDVI sequence. The shape and trend of the curve are observed to determine the optimal relationship model (such as linear, polynomial, exponential, etc.) between the NDVI sequence and the crop yield.

[0088] S204: constructing a yield analysis model according to the correlation curve.

[0089] In this embodiment, after obtaining the correlation curve between crop yield and NDVI, the yield estimation model can be constructed. The NDVI image is superimposed with the planting distribution map extracted by crop remote sensing, and the NDVI information of each planting map is extracted using the regional statistical function to establish the relationship between crop yield and the NDVI of the optimal yield period. The relationship function between the two is obtained through the quantitative regression method, and a univariate linear regression equation (yield analysis model) for the relationship between the NDVI cumulative value and the corresponding crop yield function is constructed:

[0090] Y=a+b*∑ NDVI

[0091] Where Y is the output; ∑ NDVI is the sum of the NDVI of all crop pixels in the area; a and b are regression constants. By selecting the optimal phase, the yield and NDVI model of various crops can be obtained, and the model can be deployed to the image analysis system for automatic call.

[0092] In an embodiment provided by the present application, based on the above solution, optionally, granting credit to the credit object to which the to-be-analyzed plot belongs according to the crop yield prediction result of the crop type includes:

[0093] Acquire historical planting information and trade information of the credit object to which the plot to be analyzed belongs, wherein the trade information includes at least one of accounts receivable, transaction notes, contracts and transaction data;

[0094] Evaluating the planting stability of the credit subject according to the historical planting information;

[0095] Verify the trade information of the credit object and obtain the verification result;

[0096] A preset credit model is used to generate a credit limit for the credit object based on the crop yield prediction result of the crop type, the planting stability and the verification result to complete the credit for the credit object.

[0097] In this embodiment, the historical crop planting area and crop type of the enterprise can be evaluated, and the planting stability can be evaluated. At the same time, the current node crop planting situation can be analyzed, and two-way verification can be performed to verify the authenticity of the trade and generate a credit line in combination with the credit model.

[0098] In some embodiments, after the location of the area to be analyzed is determined, the remote sensing image in the area is obtained through the image acquisition device, and the image analysis system analyzes the NDVI sequence related index to obtain the crop category. At the same time, multi-temporal remote sensing image data are compared, and the crop yield is estimated according to the yield estimation model, and finally the credit model is used to generate the enterprise credit line.

[0099] In an embodiment provided by the present application, based on the above solution, optionally, after granting credit to the credit object to which the to-be-analyzed plot belongs according to the crop yield prediction result of the crop type, the method further includes:

[0100] When the preset monitoring time point is reached, the current multi-temporal satellite remote sensing image of the land parcel to be analyzed is obtained;

[0101] Analyzing the multi-temporal satellite remote sensing images acquired at the monitoring time point using a preset image analysis system to obtain an NDVI sequence corresponding to the monitoring time point;

[0102] Matching the NDVI sequence corresponding to the monitoring time point with a preset crop growth curve;

[0103] In the case where the monitoring time point fails to match the crop growth curve, the step of inputting the NDVI sequence into a pre-built yield analysis model to obtain a crop yield prediction result for the crop type is returned to execution.

[0104] In this embodiment, a series of preset monitoring time points can be set according to the crop growth cycle and monitoring requirements, and when each preset monitoring time point is reached, the subsequent monitoring and analysis process is triggered.

[0105] Optionally, the NDVI value corresponding to the monitoring time point is compared with a preset crop growth curve. The crop growth curve is constructed based on historical data and crop growth characteristics to describe the changing trend of the NDVI value during crop growth. If the NDVI value matches the crop growth curve successfully, it indicates that the crop growth is normal; if the match is unsuccessful, it indicates that there may be growth abnormalities.

[0106] In this embodiment, the plot information is monitored and the credit limit is adjusted dynamically. At the same time, early warning clues are generated to prompt the handling personnel for behaviors such as failure to expand reproduction, abandonment, disasters, and growth degradation.

[0107] See also Figure 3 , is a flowchart of the financing process based on multi-temporal satellite remote sensing provided by this application, and the specific steps are as follows:

[0108] Step 1: The electronic device retrieves the 3S system and displays it based on the satellite map layer. In this embodiment, the basic 3S system has a geographic information system (GIS), a global positioning system (GPS), and a remote sensing system (GS). Based on the sub-meter images provided by commercial satellite companies, tile data can be produced for satellite map display. The handling personnel can search, locate or view a certain geographic location information based on the 3S system.

[0109] Step 2: Based on the field survey or the longitude and latitude information provided by the enterprise, the land parcels can be automatically segmented and a land parcel layer can be generated. The land parcel layer is displayed as crop planting areas cut based on the land information.

[0110] Step 3: Based on the customer plot management system, customers or account managers can hold a mobile device and the 3S system can automatically locate the current plot. Alternatively, they can use a PC or mobile device to outline or select the plot on the device to determine the plot to be analyzed. At the same time, combined with the upstream planting basic information obtained by the core enterprise, binding management is carried out.

[0111] Step 4: After determining the plot to be analyzed, based on the map coordinates and GPS information, the remote sensing image can be loaded through the remote sensing image acquisition and storage device to obtain the pre-processed multi-temporal satellite remote sensing image.

[0112] Step 5: Perform crop analysis, growth monitoring, and yield estimation based on the image analysis system combined with deep learning models and crop characteristic models.

[0113] Step 6: Evaluate the company's historical crop planting area and crop types, and evaluate the stability of planting. At the same time, analyze the current node crop planting situation, combine accounts receivable, bills, contracts, transaction data and other information, conduct two-way verification, verify the authenticity of the trade, and generate a credit line based on the credit model.

[0114] Step 7: Customer applies for loan.

[0115] Step 8: Set a monitoring cycle to determine whether the current customer has completed repayment. If not, return to Step 4, monitor the plot information and dynamically adjust the credit limit. At the same time, generate early warning clues to prompt the handling personnel for behaviors such as failure to expand reproduction, abandonment, disasters, and growth degradation.

[0116] In this embodiment, the processing process of multi-temporal satellite remote sensing image data is as follows: Figure 4 As shown, the multi-temporal satellite remote sensing images can be preprocessed by the image processing system and stored in a preset remote sensing image storage module. After the plot to be analyzed is determined, the preprocessed multi-temporal satellite remote sensing images of the plot to be analyzed are obtained in the remote sensing image storage module, and then the preprocessed multi-temporal satellite remote sensing images of the plot to be analyzed are identified to obtain the NDVI sequence.

[0117] Next, the model can be used for semantic segmentation, and the red, green, blue, and near-infrared channels of each phase can be merged with the NDVI channel to form a time series data set. Combined with the prior phenological period information, the model can be imported to obtain the crop distribution tiff result data of the entire image. Then, according to the longitude and latitude of the plot, the crop conditions in the plot are read. For crop identification, it is necessary to consider the phenological period of the crop. The type, state, and population structure of the crop are the main factors affecting the spectral characteristics of the crop. For grass crops, from sowing to maturity and yellowing, as the crop phenological period changes, the reflectivity of the red light band decreases due to the increase in crop coverage and leaf area coefficient, and the reflectivity of the near-infrared band increases. Moreover, at a certain time point, the state and structure of various crops are significantly different due to different phenological periods. Therefore, through the NDVI time series of the phenological period of various crops, the crops can be clearly distinguished, such as Figure 5 As shown, the NDVI time series of crops such as spring corn, spring wheat, vegetables and cotton are shown.

[0118] By analyzing the correlation between NDVI values ​​and prior yields in various phenological periods of crops, the optimal yield estimation period of crops can be determined. The crop yield and NDVI fitting model can be constructed using regression analysis to estimate crop yields, and the accuracy of the model simulation results can be verified based on yield data.

[0119] Crop yield is the cumulative result of crop growth conditions during the key growth period. Crop yield is closely related to crop growth conditions during the key growth period, and the staged growth of crops is very important for the formation of final yield. For general crop growth analysis, it is necessary to select the period when the crop growth information in the remote sensing parameters contributes the most and plays a key role in the later yield formation for crop remote sensing yield estimation. Therefore, the best phase for yield estimation is the key to measuring yield. The correlation analysis between vegetation indices in different growth periods and yields is performed, and the phase when the correlation reaches the maximum is the best phase for crop remote sensing yield estimation. The yield estimation phases of different crops are different. In general, combined with ground crop yield data, the NDVI sequence values ​​of each image period are extracted, and polynomial correlation analysis is performed with ground yield data to obtain the correlation between the NDVI sequence and yield during the crop growth period with high accuracy.

[0120] After obtaining the correlation curve between crop yield and NDVI sequence, the yield estimation model can be constructed. The NDVI sequence image is superimposed with the crop remote sensing extraction planting distribution map, and the regional statistical function is used to extract the NDVI sequence information of each planting map. The relationship between crop yield and the NDVI sequence of the best stock yield period is established. The relationship function between the two is obtained through the quantitative regression method, and the relationship between the cumulative value of the NDVI sequence and the corresponding crop yield function is constructed. In the actual scene, after the location of the area to be analyzed is determined, the remote sensing image in the area is obtained through the image acquisition device, and the NDVI sequence correlation index is analyzed by the image analysis system to obtain the crop category. At the same time, compare the multi-phase remote sensing image data, estimate the crop yield according to the yield estimation model, and finally use the credit model to generate the enterprise credit limit.

[0121] During the effective period of the customer's contract, a monitoring cycle can be set, remote sensing data can be obtained regularly, and the growth of the land and crops can be monitored. If lodging, abandonment, disease and insect pests occur in the area, the NDVI sequence index will change significantly and will not match the crop growth curve. At this time, the crop yield can be recalculated and the credit can be adjusted dynamically. At the same time, intelligent early warnings can be issued for growth degradation, abandonment, etc., to promptly remind the loan account manager to pay attention to the business situation of the enterprise.

[0122] Through the above method, historical planting situation analysis and transaction data verification methods can be provided for supply chain financing, and risk monitoring can be carried out before, during and after the loan, so that agricultural products can be traced and tracked, the purpose of the loan can be verified, the flow of funds can be controlled, the planting income can be predicted, and data falsification can be prevented.

[0123] and Figure 1 Corresponding to the method described above, the embodiment of the present application also provides a credit management device based on multi-temporal satellite remote sensing, which is used to Figure 1 The specific implementation of the method is shown in the following diagram: Figure 6 As shown, specifically including:

[0124] The first determining unit 601 is used to determine the land parcel to be analyzed in response to the credit management instruction;

[0125] An acquisition unit 602 is used to acquire multi-temporal satellite remote sensing images of the land parcel to be analyzed;

[0126] The analysis unit 603 is used to analyze the multi-temporal satellite remote sensing image using a preset image analysis system to obtain a normalized difference vegetation index NDVI sequence of the land to be analyzed;

[0127] A second determining unit 604 is used to determine the crop type of the plot to be analyzed according to the NDVI sequence of the plot to be analyzed;

[0128] The processing unit 605 is used to input the NDVI sequence into a pre-built yield analysis model to obtain a crop yield prediction result of the crop type;

[0129] The credit granting unit 606 is used to grant credit to the credit object to which the to-be-analyzed land parcel belongs according to the crop yield prediction result of the crop type.

[0130] In an embodiment provided in the present application, based on the above solution, optionally, the first determining unit 601 includes: a starting unit or a display unit;

[0131] The starting unit is used to start a preset positioning system to obtain the position information obtained by the positioning system, and determine the land parcel to which the position information belongs as the land parcel to be analyzed;

[0132] The display unit is used to display a plot selection interface, and when receiving a selection operation of a user in the plot selection interface, determines the plot corresponding to the selection operation as the plot to be analyzed.

[0133] In an embodiment provided in the present application, based on the above solution, optionally, the processing unit 605 includes:

[0134] The acquisition subunit is used to obtain multi-temporal satellite remote sensing images and crop yield data of the test plot in historical periods;

[0135] An analysis subunit, used for analyzing the multi-temporal satellite remote sensing images of the historical period to obtain the NDVI sequence of the test plot in the historical period;

[0136] An execution subunit, configured to obtain a correlation curve between the crop yield data of the test plot and the NDVI sequence according to the crop yield data of the test plot in the historical period and the NDVI sequence;

[0137] The construction subunit is used to construct a yield analysis model according to the correlation curve.

[0138] The specific principles and execution processes of each unit and module in the credit management device based on multi-temporal satellite remote sensing disclosed in the above-mentioned embodiment of the present application are the same as the credit management method based on multi-temporal satellite remote sensing disclosed in the above-mentioned embodiment of the present application. Please refer to the corresponding parts of the credit management method based on multi-temporal satellite remote sensing provided in the above-mentioned embodiment of the present application, and they will not be repeated here.

[0139] An embodiment of the present application further provides a storage medium, which includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to execute the above-mentioned credit management method based on multi-temporal satellite remote sensing.

[0140] The present application also provides an electronic device, whose structural diagram is as follows: Figure 7 As shown, it specifically includes a memory 701 and one or more instructions 702, wherein the one or more instructions 702 are stored in the memory 701 and are configured to be executed by one or more processors 703 to perform the following operations:

[0141] In response to the credit management instruction, determining the land parcel to be analyzed;

[0142] Acquire multi-temporal satellite remote sensing images of the land parcel to be analyzed;

[0143] Analyzing the multi-temporal satellite remote sensing images using a preset image analysis system to obtain a normalized difference vegetation index (NDVI) sequence of the plot to be analyzed;

[0144] Determining the crop type of the plot to be analyzed according to the NDVI sequence of the plot to be analyzed;

[0145] Inputting the NDVI sequence into a pre-built yield analysis model to obtain a crop yield prediction result for the crop type;

[0146] The credit object to which the analyzed land parcel belongs is granted credit according to the crop yield prediction result of the crop type.

[0147] It should be noted that each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0148] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations.

[0149] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0150] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present application or certain parts of the embodiments.

[0151] The above is a detailed introduction to the credit management method based on multi-temporal satellite remote sensing provided by the present application. This article uses specific examples to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A credit management method based on multi-temporal satellite remote sensing, characterized in that: include: In response to the credit management instruction, determining the land parcel to be analyzed; Acquire multi-temporal satellite remote sensing images of the land parcel to be analyzed; Analyzing the multi-temporal satellite remote sensing images using a preset image analysis system to obtain a normalized difference vegetation index (NDVI) sequence of the plot to be analyzed; Determining the crop type of the plot to be analyzed according to the NDVI sequence of the plot to be analyzed; Inputting the NDVI sequence into a pre-built yield analysis model to obtain a crop yield prediction result for the crop type; The credit object to which the analyzed land parcel belongs is granted credit according to the crop yield prediction result of the crop type.

2. The method according to claim 1, characterized in that The step of determining the plot to be analyzed includes: Starting a preset positioning system to obtain position information obtained by the positioning system, and determining the plot to which the position information belongs as the plot to be analyzed; or, A plot selection interface is displayed, and when a selection operation of the user in the plot selection interface is received, the plot corresponding to the selection operation is determined as the plot to be analyzed.

3. The method according to claim 1, characterized in that Pre-built yield analysis model process, including: Obtain multi-temporal satellite remote sensing images and crop yield data of the test plots in historical periods; Analyze the multi-temporal satellite remote sensing images of the historical period to obtain the NDVI sequence of the test plot in the historical period; According to the crop yield data of the test plot in the historical period and the NDVI sequence, obtaining a correlation curve between the crop yield data of the test plot and the NDVI sequence; A yield analysis model is constructed based on the correlation curve.

4. The method according to claim 1, characterized in that: Granting credit to the credit object to which the analyzed plot belongs according to the crop yield prediction result of the crop type includes: Acquire historical planting information and trade information of the credit object to which the plot to be analyzed belongs, wherein the trade information includes at least one of accounts receivable, transaction notes, contracts and transaction data; Evaluating the planting stability of the credit subject according to the historical planting information; Verify the trade information of the credit object and obtain the verification result; A preset credit model is used to generate a credit limit for the credit object based on the crop yield prediction result of the crop type, the planting stability and the verification result to complete the credit for the credit object.

5. The method according to claim 1, characterized in that: After granting credit to the credit object to which the analyzed plot belongs according to the crop yield prediction result of the crop type, the method further includes: When the preset monitoring time point is reached, the current multi-temporal satellite remote sensing image of the land parcel to be analyzed is obtained; Analyzing the multi-temporal satellite remote sensing images acquired at the monitoring time point using a preset image analysis system to obtain an NDVI sequence corresponding to the monitoring time point; Matching the NDVI sequence corresponding to the monitoring time point with a preset crop growth curve; In the case where the monitoring time point fails to match the crop growth curve, the step of inputting the NDVI sequence into a pre-built yield analysis model to obtain a crop yield prediction result for the crop type is returned to.

6. A credit management device based on multi-temporal satellite remote sensing, characterized in that: include: A first determining unit, configured to determine a land parcel to be analyzed in response to a credit management instruction; An acquisition unit, used for acquiring multi-temporal satellite remote sensing images of the land parcel to be analyzed; An analysis unit, used to analyze the multi-temporal satellite remote sensing image using a preset image analysis system to obtain a normalized difference vegetation index NDVI sequence of the plot to be analyzed; A second determination unit is used to determine the crop type of the plot to be analyzed according to the NDVI sequence of the plot to be analyzed; A processing unit, used for inputting the NDVI sequence into a pre-built yield analysis model to obtain a crop yield prediction result of the crop type; The credit granting unit is used to grant credit to the credit object to which the to-be-analyzed land parcel belongs according to the crop yield prediction result of the crop type.

7. The device according to claim 6, characterized in that The first determining unit includes: a starting unit or a display unit; The starting unit is used to start a preset positioning system to obtain the position information obtained by the positioning system, and determine the land parcel to which the position information belongs as the land parcel to be analyzed; The display unit is used to display a plot selection interface, and when receiving a selection operation of a user in the plot selection interface, determines the plot corresponding to the selection operation as the plot to be analyzed.

8. The device according to claim 6, characterized in that The processing unit comprises: The acquisition subunit is used to obtain multi-temporal satellite remote sensing images and crop yield data of the test plot in historical periods; An analysis subunit, used for analyzing the multi-temporal satellite remote sensing images of the historical period to obtain the NDVI sequence of the test plot in the historical period; An execution subunit, configured to obtain a correlation curve between the crop yield data of the test plot and the NDVI sequence according to the crop yield data of the test plot in the historical period and the NDVI sequence; The construction subunit is used to construct a yield analysis model according to the correlation curve.

9. A storage medium, characterized in that: The storage medium includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to execute the credit management method based on multi-temporal satellite remote sensing according to any one of claims 1 to 5.

10. An electronic device, characterized in that: It comprises a memory and one or more instructions, wherein the one or more instructions are stored in the memory and are configured to be executed by one or more processors to execute the credit management method based on multi-temporal satellite remote sensing as described in any one of claims 1 to 5.

Images