Data processing method and device, storage medium and electronic equipment

Abstract

The invention discloses a data processing method and device, a storage medium and electronic equipment. Relates to the technical field of data processing, the field of financial science and technology and other related technical fields. Identifying the target remote sensing image according to a target identification model to obtain first information of the target forest land, and determining a tree species value of the target forest land according to the first information; processing the target remote sensing image to obtain second information of the target forest land, and predicting the target forest land based on the second information according to a target prediction model to obtain a carbon sink value of the target forest land; and determining the loan risk of the target forest land according to the tree species value and the carbon sink value. Through the method and the device, the problem that the efficiency of determining the loan risk is relatively low due to the fact that the tree value of the target forest land is determined through experience of forestry experts and field investigation conditions and the loan risk of the target forest land is determined according to the tree value in related technologies is solved.

Description

Technical Field

[0001] The present application relates to the fields of data processing technology, financial technology and other related technical fields, and specifically, to a data processing method and device, a storage medium and an electronic device. Background Art

[0002] Forestry resources are one of the precious natural resources and an important tool for achieving the "dual carbon" goals. Valuation of forestry resources is conducive to the sustainable management of forest land, maximizing economic value and ecological protection, balancing economic and ecological benefits, and also helps financial institutions determine the loan risks of their clients, reducing the losses of financial institutions to a certain extent. In the traditional method, forestry experts personally visit the client's forest land to conduct on-site inspections, assess natural conditions such as soil, climate, water resources, and topography to determine the value of trees in the forest land. Financial institutions assess the potential loan risks of forestry clients based on the value of trees. Although this method has high accuracy and reliability in assessing forestry resources, it has problems such as difficulty in data collection, large workload and high cost, which leads to relatively low efficiency in determining loan risks.

[0003] Currently, no effective solution has been proposed to the problem that the relevant technology determines the tree value of the target forest land through the experience and field investigation of forestry experts, and determines the loan risk of the target forest land based on the tree value, which leads to low efficiency in determining the loan risk. Summary of the invention

[0004] The main purpose of this application is to provide a data processing method and device, a storage medium and an electronic device to solve the problem in the related art that the tree value of the target forest land is determined through the experience and field investigation of forestry experts, and the loan risk of the target forest land is determined based on the tree value, which leads to low efficiency in determining the loan risk.

[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a data processing method is provided. The method comprises: obtaining a target remote sensing image of a target forest land, wherein the target forest land is an asset used for agricultural loans; identifying the target remote sensing image according to a target recognition model to obtain first information of the target forest land, and determining the tree species value of the target forest land according to the first information, wherein the first information at least includes: the tree planting area, tree species and the planting area of ​​each type of tree of the target forest land; processing the target remote sensing image to obtain second information of the target forest land, and predicting the target forest land based on the second information according to a target prediction model to obtain the carbon sink value of the target forest land, wherein the second information at least includes: the tree coverage area of ​​the target forest land, the normalized index corresponding to the target remote sensing image and the gray value corresponding to the target remote sensing image; determining the loan risk of the target forest land according to the tree species value and the carbon sink value.

[0006] Furthermore, the target remote sensing image is identified according to the target recognition model to obtain the first information of the target forest land, including: extracting features of the target remote sensing image according to the convolutional layer in the target recognition model to obtain initial feature information of the target forest land; performing dimensionality reduction processing on the initial feature information according to the linear layer in the target recognition model to obtain target feature information of the target forest land; identifying the target forest land based on the target feature information according to the activation function layer in the target recognition model to obtain the first information of the target forest land.

[0007] Furthermore, based on the first information, determining the tree species value of the target forest land includes: obtaining the unit area value of each type of trees; calculating based on the unit area value of each type of trees and the planting area of ​​each type of trees to obtain the tree species value of each type of trees; calculating based on the tree species value of each type of trees and the tree species to obtain the tree species value of the target forest land.

[0008] Furthermore, processing the target remote sensing image to obtain the second information of the target forest land includes: cropping the target remote sensing image to obtain remote sensing images in different bands; calculating the normalized vegetation index of the remote sensing image in the red band of the remote sensing images in the different bands to obtain the normalized index; calculating the grayscale value of the remote sensing image in the green band of the remote sensing images in the different bands to obtain the grayscale value; calculating the thermal radiation values ​​of multiple ground objects in the remote sensing image in the infrared band of the remote sensing images in the different bands to obtain the thermal radiation value, and determining the tree coverage area based on the thermal radiation value and the normalized index; obtaining the second information of the target forest land based on the normalized index, the grayscale value and the tree coverage area.

[0009] Furthermore, determining the tree coverage area based on the thermal radiation value and the normalized index includes: determining the vegetation category information of the tree based on the normalized index; performing classification based on the thermal radiation value to obtain the category of the object in the target remote sensing image; performing edge extraction and region segmentation on the target remote sensing image based on an edge extraction algorithm and the category of the object to obtain edge information of multiple objects, wherein the edge information of the multiple objects includes at least: the coverage area and geographical location of each object; and determining the tree coverage area from the edge information of the multiple objects based on the vegetation category information of the tree.

[0010] Furthermore, predicting the target forest land based on the second information according to the target prediction model to obtain the carbon sink value of the target forest land includes: obtaining the carbon credit value, wherein the carbon credit value is used to characterize the ecological value corresponding to the reduced carbon emissions of trees in the target forest land; predicting the target forest land based on the second information according to the target prediction model to obtain the total biomass of the target forest land; calculating based on the total biomass of the target forest land to obtain the carbon storage of the target forest land; calculating based on the carbon storage and the carbon credit value to obtain the carbon sink value of the target forest land.

[0011] Furthermore, obtaining a target remote sensing image of a target forest land includes: obtaining an initial remote sensing image of the target forest land; performing radiation correction and atmospheric correction on the initial remote sensing image to obtain a corrected initial remote sensing image; performing image enhancement and image fusion on the corrected initial remote sensing image to obtain the target remote sensing image.

[0012] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a data processing device is provided. The device includes: an acquisition unit, which is used to acquire a target remote sensing image of a target forest land, wherein the target forest land is an asset used for agricultural loans; an identification unit, which is used to identify the target remote sensing image according to a target identification model, obtain first information of the target forest land, and determine the tree species value of the target forest land according to the first information, wherein the first information at least includes: the tree planting area, tree species and the planting area of ​​each type of tree of the target forest land; a prediction unit, which is used to process the target remote sensing image, obtain second information of the target forest land, and predict the target forest land based on the second information according to a target prediction model, and obtain the carbon sink value of the target forest land, wherein the second information at least includes: the tree coverage area of ​​the target forest land, the normalized index corresponding to the target remote sensing image and the grayscale value corresponding to the target remote sensing image; a determination unit, which is used to determine the loan risk of the target forest land according to the tree species value and the carbon sink value.

[0013] Furthermore, the recognition unit includes: a feature extraction module, used to extract features of the target remote sensing image according to the convolution layer in the target recognition model, so as to obtain initial feature information of the target forest land; a dimensionality reduction processing module, used to perform dimensionality reduction processing on the initial feature information according to the linear layer in the target recognition model, so as to obtain target feature information of the target forest land; and a recognition module, used to identify the target forest land based on the target feature information according to the activation function layer in the target recognition model, so as to obtain first information of the target forest land.

[0014] Furthermore, the identification unit includes: a first acquisition module, used to obtain the unit area value of each type of trees; a first calculation module, used to calculate based on the unit area value of each type of trees and the planting area of ​​each type of trees, to obtain the tree species value of each type of trees; a second calculation module, used to calculate based on the tree species value of each type of trees and the tree species, to obtain the tree species value of the target forest land.

[0015] Furthermore, the prediction unit includes: a cropping module, which is used to crop the target remote sensing image to obtain remote sensing images under different bands; a third calculation module, which is used to calculate the normalized vegetation index of the remote sensing image under the red band in the remote sensing images under different bands to obtain the normalized index; a fourth calculation module, which is used to calculate the grayscale value of the remote sensing image under the green band in the remote sensing images under different bands to obtain the grayscale value; a fifth calculation module, which is used to calculate the thermal radiation values ​​of multiple ground objects in the remote sensing image under the infrared band in the remote sensing images under different bands to obtain the thermal radiation value, and determine the tree coverage area based on the thermal radiation value and the normalized index; a determination module, which is used to obtain the second information of the target forest land based on the normalized index, the grayscale value and the tree coverage area.

[0016] Furthermore, the fifth calculation module includes: a first determination submodule, used to determine the vegetation category information of the tree based on the normalized index; a classification submodule, used to classify according to the thermal radiation value to obtain the category of the land object in the target remote sensing image; an edge extraction submodule, used to perform edge extraction and region segmentation on the target remote sensing image according to the edge extraction algorithm and the land object category to obtain edge information of multiple land objects, wherein the edge information of the multiple land objects at least includes: the coverage area and geographical location of each land object; a second determination submodule, used to determine the tree coverage area in the edge information of the multiple land objects based on the vegetation category information of the tree.

[0017] Furthermore, the prediction unit includes: a second acquisition module, used to obtain a carbon credit value, wherein the carbon credit value is used to characterize the ecological value corresponding to the reduced carbon emissions of trees in the target forest land; a prediction module, used to predict the target forest land based on the second information according to the target prediction model, and obtain the total biomass of the target forest land; a sixth calculation module, used to calculate based on the total biomass of the target forest land, and obtain the carbon storage of the target forest land; a seventh calculation module, used to calculate based on the carbon storage and the carbon credit value, and obtain the carbon sink value of the target forest land.

[0018] Furthermore, the acquisition unit includes: a third acquisition module, used to acquire the initial remote sensing image of the target forest land; a correction module, used to perform radiation correction and atmospheric correction on the initial remote sensing image to obtain a corrected initial remote sensing image; and a processing module, used to perform image enhancement and image fusion on the corrected initial remote sensing image to obtain the target remote sensing image.

[0019] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a computer-readable storage medium is provided, wherein the storage medium stores a program, wherein when the program is running, the device where the storage medium is located is controlled to execute any one of the data processing methods described above.

[0020] In order to achieve the above-mentioned purpose, according to another aspect of the present application, an electronic device is further provided, the electronic device includes one or more processors and a memory, and the memory is used to store the data processing method implemented by one or more processors as described above.

[0021] Through the present application, the following steps are adopted: obtaining a target remote sensing image of a target forest land, wherein the target forest land is an asset used for agricultural loans; identifying the target remote sensing image according to a target recognition model to obtain first information of the target forest land, and determining the tree species value of the target forest land according to the first information, wherein the first information at least includes: the tree planting area of ​​the target forest land, the tree species and the planting area of ​​each type of trees; processing the target remote sensing image to obtain second information of the target forest land, and predicting the target forest land based on the second information according to a target prediction model to obtain the carbon sink value of the target forest land, wherein the second information at least includes: the tree coverage area of ​​the target forest land, the normalized index corresponding to the target remote sensing image and the grayscale value corresponding to the target remote sensing image; determining the loan risk of the target forest land according to the tree species value and the carbon sink value. Through the present application, the problem of low efficiency in determining the loan risk, which is caused by determining the tree value of the target forest land through the experience and field investigation of forestry experts in the related art, and determining the loan risk of the target forest land according to the tree value, is solved. In this scheme, first, the target remote sensing image of the target forest land is obtained by satellite remote sensing, and the target remote sensing image is identified by the target recognition model to obtain information such as the tree planting area, tree species and planting area of ​​each type of trees in the target forest land, and the tree species value of the target forest land is determined based on this information; then, the target remote sensing image is processed to extract the second information such as tree coverage area, normalized index and gray value, and the target prediction model is used to predict the target forest land based on the second information to obtain the carbon sink value of the target forest land. Finally, the loan risk is comprehensively determined based on the tree species value and carbon sink value of the target forest land. The tree species value and carbon sink value of the target forest land are evaluated by the remote sensing image of the target forest land, the target recognition model and the target prediction model, and the loan risk of the target forest land is comprehensively determined by the tree species value and the carbon sink value, which avoids the problems of subjectivity and limitations of the evaluation caused by the traditional method of evaluating the tree value of the forest land through the experience and field investigation of forestry experts, improves the accuracy of the evaluation, and thus achieves the effect of improving the efficiency of determining the loan risk. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0023] Figure 1 is a flow chart of a data processing method provided according to an embodiment of the present application;

[0024] Figure 2 is a schematic diagram of a data processing method provided according to an embodiment of the present application;

[0025] Figure 3is a schematic diagram of a data processing device provided according to an embodiment of the present application;

[0026] Figure 4 is a schematic diagram of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0028] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] It should be noted that the relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties. For example, an interface is set between this system and the relevant user or organization. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or organization.

[0031] The present invention is described below in conjunction with preferred implementation steps. Figure 1 is a flow chart of a data processing method provided according to an embodiment of the present application, such as Figure 1 As shown, the method comprises the following steps:

[0032] Step S101, obtaining a target remote sensing image of a target forest land, wherein the target forest land is an asset used for agricultural loans.

[0033] Optionally, high-resolution images of the target forest land are collected by satellites (eg, Landsat, Sentinel, SPOT, etc.) to obtain target remote sensing images.

[0034] Step S102, identifying the target remote sensing image according to the target recognition model, obtaining the first information of the target forest land, and determining the tree species value of the target forest land according to the first information, wherein the first information at least includes: the tree planting area of ​​the target forest land, the tree species and the planting area of ​​each type of tree.

[0035] Optionally, according to the characteristics and needs of the target forest land, select a suitable target recognition model (such as support vector machine, random forest, neural network, YOLO, Faster R-CNN, etc.) to identify the target remote sensing image, and obtain information such as the tree planting area, tree species and planting area of ​​each type of tree in the target forest land. Based on the above information and economic factors such as the market price of different tree species, wood use, market demand, etc., the tree species value of the target forest land is comprehensively determined.

[0036] Step S103, processing the target remote sensing image to obtain second information of the target forest land, and predicting the target forest land based on the second information according to the target prediction model to obtain the carbon sink value of the target forest land, wherein the second information includes at least: the tree coverage area of ​​the target forest land, the normalized index corresponding to the target remote sensing image, and the grayscale value corresponding to the target remote sensing image.

[0037] Optionally, information is extracted from the target remote sensing image to obtain information such as the tree coverage area of ​​the target forest, the normalized index corresponding to the target remote sensing image, and the grayscale value corresponding to the target remote sensing image. According to the characteristics and needs of the target forest, a suitable target prediction model (such as random forest, gradient boosting machine, neural network, etc.) is selected to predict the target forest based on the extracted second information to obtain the carbon sink value of the target forest.

[0038] Step S104, determining the loan risk of the target forest land based on the tree species value and the carbon sink value.

[0039] Optionally, the economic benefits, ecological benefits and carbon sequestration benefits of the target forest land can be evaluated by comprehensively considering factors such as the tree species value, growth adaptability, ecological benefits and carbon sequestration value of the target forest land, and the loan risk of the target forest land can be comprehensively evaluated on this basis.

[0040] In summary, firstly, the target remote sensing image of the target forest land is obtained by satellite remote sensing, wherein the target forest land is an asset used for agricultural loans, and the target remote sensing image is identified by the target recognition model to obtain information such as the tree planting area, tree species and the planting area of ​​each type of trees in the target forest land, and the tree species value of the target forest land is determined based on this information; then, the target remote sensing image is processed to extract the second information such as tree coverage area, normalized index and gray value, and the target prediction model is used to predict the target forest land based on the second information to obtain the carbon sink value of the target forest land. Finally, the loan risk is comprehensively determined based on the tree species value and carbon sink value of the target forest land. The tree species value and carbon sink value of the target forest land are evaluated by the remote sensing image of the target forest land, the target recognition model and the target prediction model, and the loan risk of the target forest land is comprehensively determined by the tree species value and the carbon sink value, which avoids the problems of subjectivity and limitations of the evaluation caused by the traditional method of evaluating the tree value of the forest land through the experience and field investigation of forestry experts, improves the accuracy of the evaluation, and thus achieves the effect of improving the efficiency of determining the loan risk.

[0041] Optionally, in the data processing method provided in the embodiment of the present application, the target remote sensing image is identified according to the target recognition model to obtain the first information of the target forest land, including: extracting features of the target remote sensing image according to the convolutional layer in the target recognition model to obtain initial feature information of the target forest land; performing dimensionality reduction processing on the initial feature information according to the linear layer in the target recognition model to obtain target feature information of the target forest land; identifying the target forest land based on the target feature information according to the activation function layer in the target recognition model to obtain the first information of the target forest land.

[0042] In an optional embodiment, the parameters of the convolution layer (CNN) in the target recognition model are configured, such as: convolution kernel size, stride, padding, etc., and the configured convolution layer is used to extract features of the target remote sensing image, and the weighted sum of the local area is calculated by sliding the convolution kernel (or filter) on the image to obtain the initial feature information of the target forest. Then, the linear layer in the target recognition model is used to reduce the dimension of the extracted initial feature information to obtain the target feature information of the target forest. The linear layer can convert the high-dimensional feature vector into a lower-dimensional representation to reduce the dimension of the feature space, while reducing the complexity and computational burden of the data and improving the computational efficiency of the model. Finally, an activation function layer (such as ReLU, Sigmoid, Tanh, etc.) is used to introduce nonlinear factors into the model, so that the model can capture more complex feature relationships, and identify and classify the target forest based on the target feature information to obtain the first information of the target forest.

[0043] The convolutional layer, linear layer and activation function layer of the target recognition model can quickly extract and identify the features of the target remote sensing image, and then accurately obtain the first information of the target forest land.

[0044] Optionally, in the data processing method provided in the embodiment of the present application, determining the tree species value of the target forest land based on the first information includes: obtaining the unit area value of each type of trees; calculating based on the unit area value of each type of trees and the planting area of ​​each type of trees to obtain the species value of each type of trees; calculating based on the species value of each type of trees and the tree species to obtain the tree species value of the target forest land.

[0045] In an optional embodiment, the market value of each type of tree is obtained, and the wood volume per unit area of ​​each type of tree is estimated based on information such as the average diameter at breast height, tree height, and wood density of the trees. The wood volume per unit area is multiplied by the corresponding market price to obtain the value per unit area of ​​each type of tree. Then, the value per unit area of ​​each type of tree is multiplied by its corresponding planting area to obtain the species value of each type of tree, and the contribution of each type of tree to the value of the forest land is quantified by the species value of each type of tree. Finally, the species value of each type of tree is summarized to obtain the overall species value of the target forest land. In this way, the contribution of different tree species in the entire forest land can be comprehensively considered, thereby evaluating the overall economic benefits of the target forest land.

[0046] Through the tree species value of each type of tree and the tree species of the target forest land, the tree species value of the target forest land can be calculated quickly and accurately.

[0047] Optionally, in the data processing method provided in the embodiment of the present application, processing the target remote sensing image to obtain the second information of the target forest land includes: cropping the target remote sensing image to obtain remote sensing images in different bands; calculating the normalized vegetation index of the remote sensing image in the red band in the remote sensing images in different bands to obtain the normalized index; calculating the grayscale value of the remote sensing image in the green band in the remote sensing images in different bands to obtain the grayscale value; calculating the thermal radiation values ​​of multiple ground objects in the remote sensing image in the infrared band in the remote sensing images in different bands to obtain the thermal radiation value, and determining the tree coverage area based on the thermal radiation value and the normalized index; obtaining the second information of the target forest land based on the normalized index, grayscale value and tree coverage area.

[0048] In an optional embodiment, the target remote sensing image is cropped according to the geographical location of the target forest, and remote sensing images in different bands are selected, including: red band, green band and infrared band. For remote sensing images in the red band, the normalized vegetation index (NDVI) is calculated, and the formula is: NDVI = (NIR-Red) / (NIR + Red), where NIR represents the reflectance value of the near infrared band and Red represents the reflectance value of the red band; for remote sensing images in the green band, the gray value of each pixel is calculated, which is usually the reflectance value of the green band; for remote sensing images in the infrared band, the thermal radiation value of the ground object is calculated by analyzing the temperature distribution in the remote sensing image, and the tree coverage area of ​​the target forest is determined by using NDVI and thermal radiation values. Generally, high NDVI values ​​and low thermal radiation values ​​indicate that there is vegetation coverage in the area.

[0049] By cropping the target remote sensing image, remote sensing images in the red band, green band and infrared band can be quickly obtained, and the remote sensing images in the above different bands are calculated to accurately obtain the second information of the target forest land.

[0050] Optionally, in the data processing method provided in the embodiment of the present application, determining the tree coverage area based on the thermal radiation value and the normalized index includes: determining the vegetation category information of the tree based on the normalized index; classifying according to the thermal radiation value to obtain the category of the object in the target remote sensing image; performing edge extraction and region segmentation on the target remote sensing image based on the edge extraction algorithm and the object category to obtain edge information of multiple objects, wherein the edge information of the multiple objects includes at least: the coverage area and geographical location of each object; determining the tree coverage area from the edge information of multiple objects based on the vegetation category information of the tree.

[0051] In an optional embodiment, the vegetation category information of the trees is determined based on the range of NDVI values, such as forest, grassland, shrub, etc. The objects in the remote sensing image are classified based on the thermal radiation value and other spectral information, such as distinguishing water bodies, woodlands, buildings, roads, etc. Edge extraction algorithms (such as Canny edge detection, Sobel operator, etc.) are used to identify the edges of different objects in the target remote sensing image, and image segmentation techniques (such as threshold segmentation, region growing, clustering algorithms, etc.) are used to segment the remote sensing image into multiple object regions. The edge information of each object is extracted from the results of edge extraction and region segmentation, including: coverage area and geographical location. According to the vegetation category information, the area covered by trees is identified in the edge information of multiple objects, and its coverage area is calculated to obtain the tree coverage area.

[0052] The tree coverage area of ​​the target forest land can be calculated quickly and accurately through the thermal radiation value and normalized index.

[0053] Optionally, in the data processing method provided in the embodiment of the present application, the target forest land is predicted based on the second information according to the target prediction model to obtain the carbon sink value of the target forest land, including: obtaining the carbon credit value, wherein the carbon credit value is used to characterize the ecological value corresponding to the reduced carbon emissions of trees in the target forest land; predicting the target forest land based on the second information according to the target prediction model to obtain the total biomass of the target forest land; calculating based on the total biomass of the target forest land to obtain the carbon storage of the target forest land; calculating based on the carbon storage and the carbon credit value to obtain the carbon sink value of the target forest land.

[0054] In an optional embodiment, the price of the carbon credit market is determined based on regional, market supply and demand, and policy factors. Then, a suitable target prediction model (such as random forest, gradient boosting machine (GBM), neural network, etc.) is selected to predict the target forest land based on the second information to obtain the total biomass of the target forest land. The carbon storage of the target forest land is calculated based on the predicted total biomass and the species-specific biomass conversion factor. The calculated carbon storage is multiplied by the carbon credit value to obtain the carbon sink value of the target forest land. The carbon sink value can be expressed as an economic value or the number of carbon credits.

[0055] It should be noted that carbon credit, also known as carbon rights, refers to the carbon emission measurement unit that can enter the carbon trading market when an enterprise reduces carbon emissions by increasing energy efficiency, reducing pollution or reducing development under the condition of being certified by an emission reduction organization. One carbon credit is equivalent to one ton of carbon dioxide emissions.

[0056] By predicting the target forest land based on the second information through the target prediction model, the carbon sink value of the target forest land can be obtained quickly and accurately.

[0057] Optionally, in the data processing method provided in the embodiment of the present application, obtaining a target remote sensing image of a target forest land, wherein the target forest land is an asset used for agricultural loans, includes: obtaining an initial remote sensing image of the target forest land; performing radiation correction and atmospheric correction on the initial remote sensing image to obtain a corrected initial remote sensing image; performing image enhancement and image fusion on the corrected initial remote sensing image to obtain a target remote sensing image.

[0058] In an optional embodiment, first, an initial remote sensing image of the target forest is obtained by satellite, UAV or other remote sensing equipment. Then, the initial remote sensing image is subjected to radiation correction and atmospheric correction to eliminate the influence of factors such as atmosphere, cloud layer, land and water body on the image, so as to obtain a corrected initial remote sensing image that more accurately reflects the surface characteristics. The corrected initial remote sensing image is subjected to image enhancement processing, and the contrast, clarity and features of the image are enhanced using techniques such as histogram equalization, filtering, and sharpening, so as to better display the details and features of the target forest. Finally, the enhanced image is subjected to fusion processing, and the image data from multiple bands or sensors are fused to obtain more ground object information and features, and to improve the spatial, spectral and temporal resolution of the image.

[0059] By preprocessing the initial remote sensing image, high-quality target remote sensing images can be obtained quickly and accurately, so as to facilitate subsequent applications such as recognition and prediction based on the target remote sensing image.

[0060] It should be noted that Figure 2 Schematic diagram of a data processing method according to an embodiment of the present application. Figure 2 As shown, first, the initial remote sensing image of the target forest land is obtained, and the initial remote sensing image is preprocessed by radiation correction, atmospheric correction, image enhancement and image fusion, so as to obtain the target remote sensing image.

[0061] At the same time, the convolution layer in the target recognition model is used to extract features from the target remote sensing image to obtain the initial feature information of the target forest land, and the linear layer in the target recognition model is used to reduce the dimension of the initial feature information to obtain the target feature information of the target forest land. The activation function layer in the target recognition model is used to introduce nonlinear factors into the model, so that the model can capture more complex feature relationships, and identify and classify the target forest land based on the target feature information to obtain the first information of the target forest land. Based on the first information, the tree species value of the target forest land is determined.

[0062] Then, the target remote sensing image is cropped to obtain remote sensing images in different bands: the normalized vegetation index is calculated for the remote sensing image in the red band; the grayscale value is calculated for the remote sensing image in the green band; the thermal radiation value of multiple objects is calculated for the remote sensing image in the infrared band, and the tree coverage area of ​​the target forest is determined based on the thermal radiation value and the normalized vegetation index. The target forest is predicted based on the second information using the target prediction model to obtain the total biomass of the target forest, and the total biomass of the target forest is calculated to obtain the carbon storage of the target forest, and the carbon storage and carbon credit value are multiplied to obtain the carbon sink value of the target forest. Finally, the loan risk of the target forest is comprehensively evaluated based on the tree species value and carbon sink value of the target forest.

[0063] The data processing method provided in the embodiment of the present application obtains a target remote sensing image of a target forest land, wherein the target forest land is an asset used for agricultural loans; identifies the target remote sensing image according to a target recognition model to obtain first information of the target forest land, and determines the tree species value of the target forest land according to the first information, wherein the first information at least includes: the tree planting area, tree species and the planting area of ​​each type of trees of the target forest land; processes the target remote sensing image to obtain second information of the target forest land, and predicts the target forest land based on the second information according to a target prediction model to obtain the carbon sink value of the target forest land, wherein the second information at least includes: the tree coverage area of ​​the target forest land, the normalized index corresponding to the target remote sensing image and the grayscale value corresponding to the target remote sensing image; determines the loan risk of the target forest land according to the tree species value and the carbon sink value, thereby solving the problem in the related art that the tree value of the target forest land is determined by the experience and field investigation of forestry experts, and the loan risk of the target forest land is determined according to the tree value, which leads to relatively low efficiency in determining the loan risk. In summary, in this scheme, first, the target remote sensing image of the target forest land is obtained by satellite remote sensing, wherein the target forest land is an asset used for agricultural loans, and the target remote sensing image is identified by using the target recognition model to obtain information such as the tree planting area, tree species and planting area of ​​each type of trees in the target forest land, and the tree species value of the target forest land is determined based on this information; then, the target remote sensing image is processed to extract the second information such as tree coverage area, normalized index and gray value, and the target prediction model is used to predict the target forest land based on the second information to obtain the carbon sink value of the target forest land. Finally, the loan risk is comprehensively determined based on the tree species value and carbon sink value of the target forest land. The tree species value and carbon sink value of the target forest land are evaluated through remote sensing images, target recognition models and target prediction models, and the loan risk of the target forest land is determined comprehensively through the tree species value and carbon sink value. This avoids the problems of subjectivity and limitations in evaluation caused by the traditional method of evaluating the tree value of the forest land through the experience and field investigations of forestry experts, improves the accuracy of the evaluation, and thus achieves the effect of improving the efficiency of determining loan risks.

[0064] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0065] The embodiment of the present application also provides a data processing device. It should be noted that the data processing device of the embodiment of the present application can be used to execute the data processing method provided by the embodiment of the present application. The data processing device provided by the embodiment of the present application is introduced below.

[0066] Figure 3 is a schematic diagram of a data processing device according to an embodiment of the present application. Figure 3 As shown, the device includes: an acquisition unit 301, an identification unit 302, a prediction unit 303, and a determination unit 304.

[0067] An acquisition unit 301 is used to acquire a target remote sensing image of a target forest land, wherein the target forest land is an asset used for agricultural loans;

[0068] The recognition unit 302 is used to recognize the target remote sensing image according to the target recognition model, obtain the first information of the target forest land, and determine the tree species value of the target forest land according to the first information, wherein the first information at least includes: the tree planting area, tree species and the planting area of ​​each tree species of the target forest land;

[0069] The prediction unit 303 is used to process the target remote sensing image to obtain second information of the target forest land, and predict the target forest land based on the second information according to the target prediction model to obtain the carbon sink value of the target forest land, wherein the second information at least includes: the tree coverage area of ​​the target forest land, the normalized index corresponding to the target remote sensing image, and the gray value corresponding to the target remote sensing image;

[0070] The determination unit 304 is used to determine the loan risk of the target forest land based on the tree species value and the carbon sink value.

[0071] In the data processing device provided by the embodiment of the present application, the acquisition unit 301 acquires a target remote sensing image of a target forest land, wherein the target forest land is an asset used for agricultural loans; the identification unit 302 identifies the target remote sensing image according to the target identification model to obtain first information of the target forest land, and determines the tree species value of the target forest land according to the first information, wherein the first information at least includes: the tree planting area, tree species and the planting area of ​​each type of trees of the target forest land; the prediction unit 303 processes the target remote sensing image to obtain second information of the target forest land, and predicts the target forest land based on the second information according to the target prediction model to obtain the carbon sink value of the target forest land, wherein the second information at least includes: the tree coverage area of ​​the target forest land, the normalized index corresponding to the target remote sensing image and the gray value corresponding to the target remote sensing image; the determination unit 304 determines the loan risk of the target forest land according to the tree species value and the carbon sink value, which solves the problem in the related art that the tree value of the target forest land is determined by the experience and field investigation of forestry experts, and the loan risk of the target forest land is determined according to the tree value, which leads to a relatively low efficiency in determining the loan risk. In this scheme, first, a target remote sensing image of a target forest land is obtained by satellite remote sensing, wherein the target forest land is an asset for agricultural loans, and the target remote sensing image is identified by using a target recognition model to obtain information such as the tree planting area, tree species, and the planting area of ​​each type of trees in the target forest land, and the tree species value of the target forest land is determined based on this information; then, the target remote sensing image is processed to extract second information such as tree coverage area, normalized index, and grayscale value, and the target prediction model is used to predict the target forest land based on the second information to obtain the carbon sink value of the target forest land. Finally, the loan risk is comprehensively determined based on the tree species value and carbon sink value of the target forest land. The tree species value and carbon sink value of the target forest land are evaluated by using the remote sensing image of the target forest land, the target recognition model, and the target prediction model, and the loan risk of the target forest land is comprehensively determined by using the tree species value and the carbon sink value, which avoids the problems of subjectivity and limitations of the evaluation caused by evaluating the tree value of the forest land through the experience and field investigation of forestry experts in the traditional method, improves the accuracy of the evaluation, and thus achieves the effect of improving the efficiency of determining the loan risk.

[0072] Optionally, in the data processing device provided in the embodiment of the present application, the recognition unit includes: a feature extraction module, used to extract features of the target remote sensing image according to the convolution layer in the target recognition model, and obtain initial feature information of the target forest land; a dimensionality reduction processing module, used to perform dimensionality reduction processing on the initial feature information according to the linear layer in the target recognition model, and obtain target feature information of the target forest land; and a recognition module, used to identify the target forest land based on the target feature information according to the activation function layer in the target recognition model, and obtain first information of the target forest land.

[0073] Optionally, in the data processing device provided in the embodiment of the present application, the identification unit includes: a first acquisition module, used to obtain the unit area value of each type of trees; a first calculation module, used to calculate based on the unit area value of each type of trees and the planting area of ​​each type of trees, to obtain the tree species value of each type of trees; a second calculation module, used to calculate based on the tree species value and tree type of each type of trees, to obtain the tree species value of the target forest land.

[0074] Optionally, in the data processing device provided in the embodiment of the present application, the prediction unit includes: a cropping module, which is used to crop the target remote sensing image to obtain remote sensing images in different bands; a third calculation module, which is used to calculate the normalized vegetation index of the remote sensing image in the red band in the remote sensing images in different bands to obtain the normalized index; a fourth calculation module, which is used to calculate the grayscale value of the remote sensing image in the green band in the remote sensing images in different bands to obtain the grayscale value; a fifth calculation module, which is used to calculate the thermal radiation values ​​of multiple ground objects in the remote sensing image in the infrared band in the remote sensing images in different bands to obtain the thermal radiation value, and determine the tree coverage area based on the thermal radiation value and the normalized index; a determination module, which is used to obtain the second information of the target forest land based on the normalized index, the grayscale value and the tree coverage area.

[0075] Optionally, in the data processing device provided in the embodiment of the present application, the fifth calculation module includes: a first determination submodule, used to determine the vegetation category information of the tree based on the normalized index; a classification submodule, used to classify according to the thermal radiation value to obtain the category of the object in the target remote sensing image; an edge extraction submodule, used to perform edge extraction and region segmentation on the target remote sensing image based on the edge extraction algorithm and the object category to obtain edge information of multiple objects, wherein the edge information of the multiple objects includes at least: the coverage area and geographical location of each object; a second determination submodule, used to determine the tree coverage area in the edge information of multiple objects based on the vegetation category information of the tree.

[0076] Optionally, in the data processing device provided in the embodiment of the present application, the prediction unit includes: a second acquisition module, used to obtain a carbon credit value, wherein the carbon credit value is used to characterize the ecological value corresponding to the reduced carbon emissions of trees in the target forest land; a prediction module, used to predict the target forest land based on the second information according to the target prediction model, and obtain the total biomass of the target forest land; a sixth calculation module, used to calculate based on the total biomass of the target forest land, and obtain the carbon storage of the target forest land; a seventh calculation module, used to calculate based on the carbon storage and the carbon credit value, and obtain the carbon sink value of the target forest land.

[0077] Optionally, in the data processing device provided in the embodiment of the present application, the acquisition unit includes: a third acquisition module, used to acquire the initial remote sensing image of the target forest land; a correction module, used to perform radiation correction and atmospheric correction on the initial remote sensing image to obtain a corrected initial remote sensing image; a processing module, used to perform image enhancement and image fusion on the corrected initial remote sensing image to obtain a target remote sensing image.

[0078] The data processing device includes a processor and a memory. The acquisition unit 301, identification unit 302, prediction unit 303, determination unit 304, etc. are all stored in the memory as program units. The processor executes the program units stored in the memory to achieve efficient determination of loan risks.

[0079] The processor includes a kernel, which calls the corresponding program unit from the memory. One or more kernels can be set, and the efficient determination of loan risks can be achieved by adjusting kernel parameters.

[0080] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0081] An embodiment of the present invention provides a computer-readable storage medium on which a program is stored. When the program is executed by a processor, a data processing method is implemented.

[0082] An embodiment of the present invention provides a processor, which is used to run a program, wherein the program executes a data processing method when it is run.

[0083] like Figure 4 As shown, an embodiment of the present invention provides an electronic device, the device includes a processor, a memory, and a program stored in the memory and executable on the processor, and the processor implements the following steps when executing the program: obtaining a target remote sensing image of a target forest land, wherein the target forest land is an asset used for agricultural loans; identifying the target remote sensing image according to a target recognition model to obtain first information of the target forest land, and determining the tree species value of the target forest land according to the first information, wherein the first information at least includes: the tree planting area, tree species and the planting area of ​​each type of tree of the target forest land; processing the target remote sensing image to obtain second information of the target forest land, and predicting the target forest land based on the second information according to a target prediction model to obtain the carbon sink value of the target forest land, wherein the second information at least includes: the tree coverage area of ​​the target forest land, the normalized index corresponding to the target remote sensing image and the grayscale value corresponding to the target remote sensing image; determining the loan risk of the target forest land according to the tree species value and the carbon sink value.

[0084] Optionally, identifying the target remote sensing image according to the target recognition model to obtain the first information of the target forest land includes: extracting features of the target remote sensing image according to the convolutional layer in the target recognition model to obtain initial feature information of the target forest land; performing dimensionality reduction processing on the initial feature information according to the linear layer in the target recognition model to obtain target feature information of the target forest land; identifying the target forest land based on the target feature information according to the activation function layer in the target recognition model to obtain the first information of the target forest land.

[0085] Optionally, based on the first information, determining the tree species value of the target forest land includes: obtaining the unit area value of each type of trees; calculating based on the unit area value of each type of trees and the planting area of ​​each type of trees to obtain the species value of each type of trees; calculating based on the species value of each type of trees and the tree species to obtain the tree species value of the target forest land.

[0086] Optionally, processing the target remote sensing image to obtain the second information of the target forest land includes: cropping the target remote sensing image to obtain remote sensing images in different bands; calculating the normalized vegetation index of the remote sensing image in the red band of the remote sensing images in different bands to obtain the normalized index; calculating the grayscale value of the remote sensing image in the green band of the remote sensing images in different bands to obtain the grayscale value; calculating the thermal radiation values ​​of multiple ground objects in the remote sensing image in the infrared band of the remote sensing images in different bands to obtain the thermal radiation value, and determining the tree coverage area based on the thermal radiation value and the normalized index; obtaining the second information of the target forest land based on the normalized index, the grayscale value and the tree coverage area.

[0087] Optionally, determining the tree coverage area based on the thermal radiation value and the normalized index includes: determining the vegetation category information of the tree based on the normalized index; performing classification based on the thermal radiation value to obtain the category of the object in the target remote sensing image; performing edge extraction and region segmentation on the target remote sensing image based on the edge extraction algorithm and the category of the object to obtain edge information of multiple objects, wherein the edge information of the multiple objects includes at least: the coverage area and geographical location of each object; and determining the tree coverage area from the edge information of the multiple objects based on the vegetation category information of the tree.

[0088] Optionally, predicting the target forest land based on the second information according to the target prediction model to obtain the carbon sink value of the target forest land includes: obtaining the carbon credit value, wherein the carbon credit value is used to characterize the ecological value corresponding to the reduced carbon emissions of trees in the target forest land; predicting the target forest land based on the second information according to the target prediction model to obtain the total biomass of the target forest land; calculating based on the total biomass of the target forest land to obtain the carbon storage of the target forest land; calculating based on the carbon storage and the carbon credit value to obtain the carbon sink value of the target forest land.

[0089] Optionally, obtaining a target remote sensing image of a target forest land, wherein the target forest land is an asset used for agricultural loans, includes: obtaining an initial remote sensing image of the target forest land; performing radiation correction and atmospheric correction on the initial remote sensing image to obtain a corrected initial remote sensing image; performing image enhancement and image fusion on the corrected initial remote sensing image to obtain a target remote sensing image.

[0090] The devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0091] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that initializes the following method steps: obtaining a target remote sensing image of a target forest land, wherein the target forest land is an asset used for agricultural loans; identifying the target remote sensing image based on a target recognition model to obtain first information about the target forest land, and determining the tree species value of the target forest land based on the first information, wherein the first information at least includes: the tree planting area, tree species and the planting area of ​​each type of tree in the target forest land; processing the target remote sensing image to obtain second information about the target forest land, and predicting the target forest land based on the second information according to a target prediction model to obtain the carbon sink value of the target forest land, wherein the second information at least includes: the tree coverage area of ​​the target forest land, the normalized index corresponding to the target remote sensing image and the grayscale value corresponding to the target remote sensing image; determining the loan risk of the target forest land based on the tree species value and the carbon sink value.

[0092] Optionally, identifying the target remote sensing image according to the target recognition model to obtain the first information of the target forest land includes: extracting features of the target remote sensing image according to the convolutional layer in the target recognition model to obtain initial feature information of the target forest land; performing dimensionality reduction processing on the initial feature information according to the linear layer in the target recognition model to obtain target feature information of the target forest land; identifying the target forest land based on the target feature information according to the activation function layer in the target recognition model to obtain the first information of the target forest land.

[0093] Optionally, based on the first information, determining the tree species value of the target forest land includes: obtaining the unit area value of each type of trees; calculating based on the unit area value of each type of trees and the planting area of ​​each type of trees to obtain the species value of each type of trees; calculating based on the species value of each type of trees and the tree species to obtain the tree species value of the target forest land.

[0094] Optionally, processing the target remote sensing image to obtain the second information of the target forest land includes: cropping the target remote sensing image to obtain remote sensing images in different bands; calculating the normalized vegetation index of the remote sensing image in the red band of the remote sensing images in different bands to obtain the normalized index; calculating the grayscale value of the remote sensing image in the green band of the remote sensing images in different bands to obtain the grayscale value; calculating the thermal radiation values ​​of multiple ground objects in the remote sensing image in the infrared band of the remote sensing images in different bands to obtain the thermal radiation value, and determining the tree coverage area based on the thermal radiation value and the normalized index; obtaining the second information of the target forest land based on the normalized index, the grayscale value and the tree coverage area.

[0095] Optionally, determining the tree coverage area based on the thermal radiation value and the normalized index includes: determining the vegetation category information of the tree based on the normalized index; performing classification based on the thermal radiation value to obtain the category of the object in the target remote sensing image; performing edge extraction and region segmentation on the target remote sensing image based on the edge extraction algorithm and the category of the object to obtain edge information of multiple objects, wherein the edge information of the multiple objects includes at least: the coverage area and geographical location of each object; and determining the tree coverage area from the edge information of the multiple objects based on the vegetation category information of the tree.

[0096] Optionally, predicting the target forest land based on the second information according to the target prediction model to obtain the carbon sink value of the target forest land includes: obtaining the carbon credit value, wherein the carbon credit value is used to characterize the ecological value corresponding to the reduced carbon emissions of trees in the target forest land; predicting the target forest land based on the second information according to the target prediction model to obtain the total biomass of the target forest land; calculating based on the total biomass of the target forest land to obtain the carbon storage of the target forest land; calculating based on the carbon storage and the carbon credit value to obtain the carbon sink value of the target forest land.

[0097] Optionally, obtaining a target remote sensing image of a target forest land, wherein the target forest land is an asset used for agricultural loans, includes: obtaining an initial remote sensing image of the target forest land; performing radiation correction and atmospheric correction on the initial remote sensing image to obtain a corrected initial remote sensing image; performing image enhancement and image fusion on the corrected initial remote sensing image to obtain a target remote sensing image.

[0098] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0099] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0100] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0101] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0102] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0103] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0104] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0105] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0106] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0107] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A data processing method, characterized in that: include: Acquiring a target remote sensing image of a target forest land, wherein the target forest land is an asset for agricultural loans; Identify the target remote sensing image according to the target recognition model to obtain first information of the target forest land, and determine the tree species value of the target forest land according to the first information, wherein the first information at least includes: the tree planting area, tree species and the planting area of ​​each type of tree in the target forest land; Processing the target remote sensing image to obtain second information of the target forest land, and predicting the target forest land based on the second information according to a target prediction model to obtain the carbon sink value of the target forest land, wherein the second information at least includes: the tree coverage area of ​​the target forest land, the normalized index corresponding to the target remote sensing image, and the grayscale value corresponding to the target remote sensing image; The loan risk of the target forest land is determined based on the tree species value and the carbon sink value.

2. The method according to claim 1, characterized in that: The target remote sensing image is identified according to the target recognition model to obtain the first information of the target forest land, including: Extracting features of the target remote sensing image according to the convolutional layer in the target recognition model to obtain initial feature information of the target forest land; Performing dimensionality reduction processing on the initial feature information according to the linear layer in the target recognition model to obtain target feature information of the target forest land; The target forest land is identified based on the target feature information according to the activation function layer in the target recognition model to obtain first information of the target forest land.

3. The method according to claim 1, characterized in that Determining the tree species value of the target forest land based on the first information includes: Get the unit area value of each type of tree; Calculating the value of each type of tree species based on the unit area value of each type of tree and the planting area of ​​each type of tree species to obtain the tree species value of each type of tree species; The tree species value of the target forest land is obtained by calculating based on the tree species value of each type of trees and the tree types.

4. The method according to claim 1, characterized in that: Processing the target remote sensing image to obtain the second information of the target forest land includes: Cropping the target remote sensing image to obtain remote sensing images in different bands; Calculating the normalized vegetation index of the remote sensing image in the red band among the remote sensing images in the different bands to obtain the normalized index; Calculating the grayscale value of the remote sensing image in the green band among the remote sensing images in the different bands to obtain the grayscale value; Calculating the thermal radiation values ​​of a plurality of ground objects in the remote sensing images under the infrared band in the remote sensing images under the different bands to obtain the thermal radiation value, and determining the tree coverage area according to the thermal radiation value and the normalized index; The second information of the target forest land is obtained according to the normalized index, the gray value and the tree coverage area.

5. The method according to claim 4, characterized in that Determining the tree coverage area according to the heat radiation value and the normalized index includes: Determining vegetation category information of the tree according to the normalized index; Classifying according to the thermal radiation value to obtain the category of the ground object in the target remote sensing image; According to the edge extraction algorithm and the object category, edge extraction and region segmentation are performed on the target remote sensing image to obtain edge information of multiple objects, wherein the edge information of the multiple objects at least includes: the coverage area and geographical location of each object; The tree coverage area is determined in the edge information of the plurality of land objects according to the vegetation category information of the tree.

6. The method according to claim 1, characterized in that Predicting the target forest land based on the second information according to the target prediction model to obtain the carbon sink value of the target forest land includes: Obtaining a carbon credit value, wherein the carbon credit value is used to represent the ecological value corresponding to the amount of carbon emissions reduced by the trees in the target forest land; Predicting the target forest land based on the second information according to the target prediction model to obtain the total biomass of the target forest land; Calculating based on the total biomass of the target forest land to obtain the carbon storage of the target forest land; The carbon sink value of the target forest land is obtained by calculation based on the carbon storage amount and the carbon credit value.

7. The method according to claim 1, characterized in that Acquiring target remote sensing images of target forest land includes: Acquiring an initial remote sensing image of the target forest land; Performing radiation correction and atmospheric correction on the initial remote sensing image to obtain a corrected initial remote sensing image; The corrected initial remote sensing image is subjected to image enhancement and image fusion to obtain the target remote sensing image.

8. A data processing device, characterized in that: include: An acquisition unit, used for acquiring a target remote sensing image of a target forest land, wherein the target forest land is an asset used for agricultural loans; an identification unit, configured to identify the target remote sensing image according to a target identification model, obtain first information of the target forest land, and determine the tree species value of the target forest land according to the first information, wherein the first information at least includes: the tree planting area, tree species and the planting area of ​​each type of tree of the target forest land; A prediction unit, used for processing the target remote sensing image to obtain second information of the target forest land, and predicting the target forest land based on the second information according to a target prediction model to obtain the carbon sink value of the target forest land, wherein the second information at least includes: the tree coverage area of ​​the target forest land, the normalized index corresponding to the target remote sensing image, and the grayscale value corresponding to the target remote sensing image; A determination unit is used to determine the loan risk of the target forest land based on the tree species value and the carbon sink value.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the storage medium is controlled to execute the data processing method according to any one of claims 1 to 7 on a device.

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

Images