Loan evaluation method and device, electronic equipment and storage medium

Abstract

The invention discloses a loan evaluation method and device, electronic equipment and a storage medium, and relates to the field of artificial intelligence, the field of financial science and technology or other related technical fields, and the evaluation method comprises the steps: receiving a loan request of a user side, and determining a to-be-evaluated target forest region based on the loan request; a remote sensing image of the target forest region is obtained, a remote sensing data set of the atmosphere above the target forest region is extracted based on the remote sensing image, and the remote sensing data set comprises at least one of meteorological data, carbon dioxide data and nitrogen dioxide data; inputting the remote sensing data in the remote sensing data set into the deep learning model one by one, and outputting the carbon dioxide concentration of the target forest region; and evaluating the loan request according to the carbon dioxide concentration to obtain a loan evaluation result. According to the method and the device, the technical problem of relatively low evaluation efficiency of carrying out risk evaluation on the loan request by manually measuring and calculating the carbon dioxide concentration of the target forest region in related technologies is solved.

Description

Technical Field

[0001] The present invention relates to the fields of artificial intelligence, financial technology and other related technical fields, and in particular to a loan assessment method and device, an electronic device and a storage medium. Background Art

[0002] As the main business of financial institutions, loan business is divided into many types according to user needs, such as housing loans, agricultural loans, forestry loans, etc. Among them, agricultural and forestry loans, as the current popular loan project, have promoted the development of agriculture and forestry to a certain extent. When applying for forestry loans, users can use forest areas as collateral for loans. When financial institutions apply for forestry loans, they need to conduct a value assessment of the mortgaged forest areas based on the actual situation of the forest areas, so as to achieve pre-loan risk assessment, which can reduce the bad debt rate of financial institutions.

[0003] As an important carbon sink, forest areas can absorb carbon dioxide in the atmosphere and convert it into organic matter for storage. Therefore, the carbon dioxide concentration in forest areas can be used as an indicator to measure the value of forest areas. In related technologies, the carbon dioxide concentration in target forest areas can be measured based on manual visits, thereby conducting a value assessment of the target forest area based on the carbon dioxide concentration, and then conducting a risk assessment of the loan request. However, since the mortgaged forest areas are generally large in area and widely distributed, manual measurement is costly and inefficient, resulting in low assessment efficiency.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present invention provide a loan assessment method and device, an electronic device and a storage medium, so as to at least solve the technical problem of low assessment efficiency in the related art of risk assessment of loan requests by manually measuring the carbon dioxide concentration in the target forest area.

[0006] According to one aspect of an embodiment of the present invention, there is provided a loan assessment method, comprising: receiving a loan request from a user terminal, and determining a target forest area to be assessed based on the loan request; acquiring a remote sensing image of the target forest area, and extracting a remote sensing data set of the atmosphere above the target forest area based on the remote sensing image, wherein the remote sensing data set comprises at least one of the following: meteorological data, carbon dioxide data, and nitrogen dioxide data; inputting the remote sensing data in the remote sensing data set into a deep learning model one by one, and outputting the carbon dioxide concentration of the target forest area, wherein the deep learning model is a pre-built model for predicting the carbon dioxide concentration of a forest area; and evaluating the loan request according to the carbon dioxide concentration to obtain a loan assessment result.

[0007] Optionally, the step of extracting the meteorological data in the remote sensing data set of the atmosphere above the target forest area based on the remote sensing image includes: determining a first remote sensing band, wherein the first remote sensing band is a band related to meteorological data; extracting meteorological spectral features from the remote sensing image based on the first remote sensing band; analyzing the meteorological spectral features based on an inversion algorithm to obtain the meteorological data of the atmosphere above the target forest area, wherein the meteorological data includes at least one of the following: temperature data, precipitation data, wind direction data, wind speed data, humidity data, and air pressure data.

[0008] Optionally, the step of extracting the carbon dioxide data in the remote sensing data set of the atmosphere above the target forest area based on the remote sensing image includes: determining a second remote sensing band, wherein the second remote sensing band is a band related to the carbon dioxide data; drawing a carbon dioxide spectral curve of pixel points in the remote sensing image based on the second remote sensing band; obtaining carbon dioxide spectral characteristics of the target forest area based on the carbon dioxide spectral curve; and obtaining the carbon dioxide data of the target forest area based on the carbon dioxide spectral characteristics.

[0009] Optionally, the step of extracting the nitrogen dioxide data in the remote sensing data set of the atmosphere above the target forest area based on the remote sensing image includes: determining a third remote sensing band, wherein the third remote sensing band is a band related to the nitrogen dioxide data; drawing a nitrogen dioxide spectral curve of pixel points in the remote sensing image based on the third remote sensing band; obtaining nitrogen dioxide spectral characteristics of the target forest area based on the nitrogen dioxide spectral curve; and obtaining the nitrogen dioxide data of the target forest area based on the nitrogen dioxide spectral characteristics.

[0010] Optionally, the step of evaluating the loan request based on the carbon dioxide concentration also includes: obtaining market carbon information, determining value data of the target forest area based on the market carbon information and the carbon dioxide concentration; comparing the value data of the target forest area with the loan amount in the loan request to obtain a comparison result, and evaluating the loan request based on the comparison result.

[0011] Optionally, the step of evaluating the loan request based on the comparison result also includes: if the comparison result indicates that the value data of the target forest area is greater than or equal to the loan amount, approving the loan request; or, if the comparison result indicates that the value data of the target forest area is less than the loan amount, rejecting the loan request.

[0012] Optionally, the step of constructing the deep learning model includes: obtaining historical remote sensing images of the forest area within the historical time period, and obtaining the carbon dioxide concentration of the forest area within the historical time period based on ground monitoring equipment; extracting historical remote sensing data from the historical remote sensing images; constructing a sample set based on the historical remote sensing images of the forest area and the carbon dioxide concentration; splitting the sample set based on a preset ratio to obtain a training set and a test set; iteratively training the initial model based on the training set to obtain an initial deep learning model; testing the initial deep learning model based on the test set to obtain a test result, and when the test result indicates that the initial deep learning model passes the test, the trained deep learning model is obtained.

[0013] According to another aspect of an embodiment of the present invention, a loan assessment device is also provided, including: a determination unit, used to receive a loan request from a user terminal, and determine a target forest area to be assessed based on the loan request; an extraction unit, used to obtain a remote sensing image of the target forest area, and extract a remote sensing data set of the atmosphere above the target forest area based on the remote sensing image, wherein the remote sensing data set includes at least one of the following: meteorological data, carbon dioxide data, and nitrogen dioxide data; an output unit, used to input the remote sensing data in the remote sensing data set into a deep learning model one by one, and output the carbon dioxide concentration of the target forest area, wherein the deep learning model is a pre-built model for predicting the carbon dioxide concentration of a forest area; an assessment unit, used to evaluate the loan request based on the carbon dioxide concentration to obtain a loan assessment result.

[0014] Optionally, the extraction unit includes: a first determination module, used to determine a first remote sensing band, wherein the first remote sensing band is a band related to meteorological data; a first extraction module, used to extract meteorological spectral features from the remote sensing image based on the first remote sensing band; a first analysis module, used to analyze the meteorological spectral features based on an inversion algorithm to obtain the meteorological data of the atmosphere above the target forest area, wherein the meteorological data includes at least one of the following: temperature data, precipitation data, wind direction data, wind speed data, humidity data, and air pressure data.

[0015] Optionally, the extraction unit also includes: a second determination module, used to determine a second remote sensing band, wherein the second remote sensing band is a band related to the carbon dioxide data; a first drawing module, used to draw a carbon dioxide spectrum curve of pixel points in the remote sensing image based on the second remote sensing band; a first acquisition module, used to acquire the carbon dioxide spectrum characteristics of the target forest area based on the carbon dioxide spectrum curve; and a second acquisition module, used to acquire the carbon dioxide data of the target forest area based on the carbon dioxide spectrum characteristics.

[0016] Optionally, the extraction unit also includes: a third determination module, used to determine a third remote sensing band, wherein the third remote sensing band is a band related to the nitrogen dioxide data; a second drawing module, used to draw a nitrogen dioxide spectrum curve of pixel points in the remote sensing image based on the third remote sensing band; a third acquisition module, used to acquire nitrogen dioxide spectrum characteristics of the target forest area based on the nitrogen dioxide spectrum curve; and a fourth acquisition module, used to acquire the nitrogen dioxide data of the target forest area based on the nitrogen dioxide spectrum characteristics.

[0017] Optionally, the evaluation unit includes: a fourth determination module, used to obtain market carbon information, and determine the value data of the target forest area based on the market carbon information and the carbon dioxide concentration; a first comparison module, used to compare the value data of the target forest area with the loan amount in the loan request to obtain a comparison result, and evaluate the loan request based on the comparison result.

[0018] Optionally, the evaluation unit also includes: a first approval module, used to approve the loan request when the comparison result indicates that the value data of the target forest area is greater than or equal to the loan amount; a first rejection module, used to reject the loan request when the comparison result indicates that the value data of the target forest area is less than the loan amount.

[0019] Optionally, the loan assessment device also includes: a fifth acquisition module, used to acquire historical remote sensing images of the forest area within the historical time period, and acquire the carbon dioxide concentration of the forest area within the historical time period based on ground monitoring equipment; a second extraction module, used to extract historical remote sensing data from the historical remote sensing images; a first construction module, used to construct a sample set based on the historical remote sensing images of the forest area and the carbon dioxide concentration; a first splitting module, used to split the sample set based on a preset ratio to obtain a training set and a test set; a first training module, used to iteratively train the initial model based on the training set to obtain an initial deep learning model; a first testing module, used to test the initial deep learning model based on the test set to obtain a test result, and when the test result indicates that the initial deep learning model passes the test, the trained deep learning model is obtained.

[0020] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned loan assessment methods.

[0021] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, comprising 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 any one of the above-mentioned loan assessment methods.

[0022] In the present application, the following steps are performed: first, a loan request from a user is received; based on the loan request, a target forest area to be evaluated is determined; then, a remote sensing image of the target forest area is obtained; and based on the remote sensing image, a remote sensing data set of the atmosphere above the target forest area is extracted; wherein the remote sensing data set includes at least one of the following: meteorological data, carbon dioxide data, and nitrogen dioxide data; and then, the remote sensing data in the remote sensing data set are input into a deep learning model one by one, and the carbon dioxide concentration of the target forest area is output; wherein the deep learning model is a pre-built model for predicting the carbon dioxide concentration of a forest area; and finally, the loan request is evaluated based on the carbon dioxide concentration to obtain a loan evaluation result.

[0023] In this application, remote sensing technology is combined with loan assessment. Remote sensing images of the target forest area are collected through remote sensing technology, and remote sensing data is extracted based on the remote sensing images. Then, the remote sensing data is analyzed based on the deep learning model, and the carbon dioxide concentration of the target forest area is directly output. The risk of loan requests based on the target forest area is assessed based on the carbon dioxide concentration. There is no need for manual visits and manual measurement of the carbon dioxide concentration in the forest area, which improves the assessment efficiency. At the same time, meteorological data and nitrogen dioxide data are used to assist in the analysis of carbon dioxide concentration in the forest area, which improves the calculation accuracy and thus enhances the accuracy of the assessment results. This solves the technical problem of low assessment efficiency in the related technology of manually measuring the carbon dioxide concentration in the target forest area to conduct risk assessment of loan requests. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0025] Figure 1 is a flow chart of an optional loan assessment method according to an embodiment of the present invention;

[0026] Figure 2 is a schematic diagram of an optional loan evaluation process according to an embodiment of the present invention;

[0027] Figure 3 is a schematic diagram of an optional loan assessment device according to an embodiment of the present invention;

[0028] Figure 4The figure is a hardware structure block diagram of an electronic device (or mobile device) for a loan evaluation method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

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

[0031] It should be noted that the loan assessment method and device in the present application can be used in the field of artificial intelligence when risk assessment of loan requests is performed based on artificial intelligence, and can also be used in any field other than the field of artificial intelligence when risk assessment of loan requests is performed based on artificial intelligence. The present application does not limit the application field of the loan assessment method and device.

[0032] 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 used for analysis, stored data, displayed data, etc.) involved in this application are information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant regions, take necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation entrances for users to choose to authorize or refuse. For example, an interface is set up between this system and relevant users or organizations. 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.

[0033] It should be noted that in this application, when collecting and analyzing customer information, corresponding operation entrances are provided for users to choose to agree or reject the automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered.

[0034] The following embodiments of the present invention can be applied to various loan assessment systems / applications / devices. The present invention obtains meteorological data, carbon dioxide data, and nitrogen dioxide data through satellite remote sensing technology, and uses them as training data to train a deep learning model. The model can estimate the actual carbon dioxide data on the ground based on meteorological data, satellite-monitored carbon dioxide data, and satellite-monitored nitrogen dioxide data, without the need for manual visits and calculations of carbon dioxide concentrations in forest areas, saving costs while improving assessment efficiency. In addition, since meteorological conditions and nitrogen dioxide concentrations affect the generation of carbon dioxide, assessments based on meteorological data and nitrogen dioxide data can improve the accuracy of estimates, thereby improving the effectiveness and accuracy of risk assessments.

[0035] The present invention is described in detail below in conjunction with various embodiments.

[0036] Embodiment 1

[0037] According to an embodiment of the present invention, an embodiment of a loan assessment method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0038] Figure 1 is a flow chart of an optional loan assessment method according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0039] Step S101, receiving a loan request from a user, and determining a target forest area to be evaluated based on the loan request;

[0040] Step S102, acquiring a remote sensing image of a target forest area, and extracting a remote sensing data set of an atmosphere above the target forest area based on the remote sensing image, wherein the remote sensing data set includes at least one of the following: meteorological data, carbon dioxide data, and nitrogen dioxide data;

[0041] Step S103, inputting the remote sensing data in the remote sensing data set into the deep learning model one by one, and outputting the carbon dioxide concentration of the target forest area, wherein the deep learning model is a pre-built model for predicting the carbon dioxide concentration of the forest area;

[0042] Step S104, evaluating the loan request according to the carbon dioxide concentration to obtain a loan evaluation result.

[0043] Through the above steps, a loan request from a user is first received, a target forest area to be evaluated is determined based on the loan request, a remote sensing image of the target forest area is obtained, and a remote sensing data set of the atmosphere above the target forest area is extracted based on the remote sensing image, wherein the remote sensing data set includes at least one of the following: meteorological data, carbon dioxide data, and nitrogen dioxide data. Then, the remote sensing data in the remote sensing data set are input into the deep learning model one by one, and the carbon dioxide concentration of the target forest area is output, wherein the deep learning model is a pre-built model for predicting the carbon dioxide concentration of the forest area. Finally, the loan request is evaluated based on the carbon dioxide concentration to obtain a loan evaluation result.

[0044] In this embodiment, remote sensing technology is combined with loan assessment. Remote sensing images of the target forest area are collected through remote sensing technology, and remote sensing data is extracted based on the remote sensing images. Then, the remote sensing data is analyzed based on the deep learning model, and the carbon dioxide concentration of the target forest area is directly output. The risk of loan requests based on the target forest area is assessed based on the carbon dioxide concentration. There is no need for manual visits and manual measurement of the carbon dioxide concentration in the forest area, which improves the assessment efficiency. At the same time, meteorological data and nitrogen dioxide data are used to assist in the analysis of the carbon dioxide concentration in the forest area, which improves the calculation accuracy and thus enhances the accuracy of the assessment results. This solves the technical problem of low assessment efficiency in the related art of manually measuring the carbon dioxide concentration in the target forest area to conduct risk assessment of loan requests.

[0045] The embodiment of the present invention is described in detail below in combination with the above steps.

[0046] It should be noted that loan business is one of the main businesses of financial institutions. With the rapid development of information technology and e-commerce industries, the development of agriculture and forestry has also been promoted. The loan business based on forestry has gradually grown. Users of forestry loans often use forest areas as collateral for loans. Due to the special characteristics of forest areas such as large areas and complex biological species, pre-loan assessments of forest areas pose huge challenges. If the assessment is inaccurate, the bad debt rate of financial institutions will increase.

[0047] It should be noted that the carbon dioxide concentration in the forest area is a key parameter. The carbon dioxide concentration can be used to characterize the ability of the forest area to fix carbon. The larger the biomass of the forest, the more carbon it usually fixes, which means that the forest has a greater potential to absorb carbon dioxide. The different components of the forest area (such as trees, shrubs, herbs and mosses, etc.) all contribute to carbon absorption. Therefore, the carbon dioxide concentration in the forest area can reflect the carbon fixation capacity of the entire ecosystem. The stronger the carbon fixation capacity, the higher the value of the forest area. By calculating the carbon dioxide concentration in the forest area and conducting a value assessment of the target forest area, the value of the forest area can be well reflected, and then a risk assessment of loan requests based on the forest area can be conducted, thereby enhancing the accuracy and effectiveness of the assessment results.

[0048] It should be noted that the embodiment of the present invention collects remote sensing images of the target forest area through satellite remote sensing. The remote sensing images contain multi-dimensional information. By analyzing the remote sensing images, multi-dimensional data of the target forest area can be obtained. The embodiment of the present invention extracts meteorological data, carbon dioxide data and nitrogen dioxide data of the atmosphere above the target forest area from the remote sensing images, and estimates the carbon dioxide concentration on the ground of the target forest area through a pre-trained deep learning model, thereby realizing the automation of forest area value assessment and loan risk assessment. Meteorological conditions and nitrogen dioxide will affect the generation of carbon dioxide, so adding the above two factors to assist in analysis can improve the accuracy of the estimation.

[0049] Step S101, receiving a loan request from a user, and determining a target forest area to be evaluated based on the loan request.

[0050] It should be noted that the user submits a loan request based on the forest area to be mortgaged, the loan amount and user-related information. After the business end of the financial institution receives the loan request from the user, it needs to first conduct a risk assessment on the loan request, which is actually a value assessment of the target forest area to be assessed submitted by the user, to determine whether the value of the target forest area is greater than the loan amount requested by the user, and then approve or reject the user's loan request, thereby enhancing the accuracy of the pre-loan assessment and reducing the bad debt rate of financial institutions.

[0051] Step S102, obtaining a remote sensing image of the target forest area, and extracting a remote sensing data set of the atmosphere above the target forest area based on the remote sensing image.

[0052] It should be noted that carbon dioxide data can be used as an important factor in assessing the value of a forest area. The carbon dioxide concentration in a forest area can reflect the carbon sequestration capacity of the forest. The survival of organisms in the forest and the production of organic matter are inseparable from carbon dioxide. When obtaining carbon dioxide data in a target forest area, remote sensing images collected through satellite remote sensing technology can be used for analysis. Multi-dimensional remote sensing data can be extracted based on remote sensing images.

[0053] The remote sensing data set of the embodiment of the present invention may include: meteorological data, carbon dioxide data, and nitrogen dioxide data. Meteorological conditions and nitrogen dioxide will affect the generation of carbon dioxide. Therefore, extracting meteorological data and nitrogen dioxide data to assist in calculating carbon dioxide data can improve the accuracy of the calculation results.

[0054] It should be noted that after acquiring the remote sensing image of the target forest area, the remote sensing image needs to be preprocessed to remove the noise in the image. Specific preprocessing operations may include: radiation correction, eliminating the error of the sensor itself and the impact of external factors such as changes in the atmosphere and solar radiation on the image, to ensure that the image data reflects the true situation of the surface; atmospheric correction, correcting the scattering and absorption of radiation by the atmosphere, converting the image data into surface reflectivity or radiation brightness, so that images acquired at different times and with different sensors can be compared; geometric correction, adjusting the geometric distortion of the image, such as distortion caused by terrain, changes in the sensor's field of view, etc., to ensure that the image matches the actual geographical location; image enhancement, by adjusting the image's contrast, brightness, color, etc., to make specific features in the image more obvious, so as to facilitate identification and analysis; cloud removal, identifying and removing clouds and cloud shadows in the image, because clouds will affect the observation of surface features; image segmentation, dividing the image into multiple regions or objects, each region containing pixels with similar attributes. Image fusion combines image data from different sensors or different bands to obtain richer surface information; noise removal uses filters to remove random noise in the image and improve the signal-to-noise ratio of the image. Preprocessing operations help improve the usability of remote sensing images and the accuracy of analysis results.

[0055] It should be noted that remote sensing images can provide rich surface and atmospheric information in different bands. Remote sensing sensors can capture electromagnetic waves of different wavelengths, which are usually divided into different bands, each of which corresponds to specific material properties and environmental characteristics. After preprocessing the remote sensing images, meteorological data, carbon dioxide data, and nitrogen dioxide data need to be extracted from the remote sensing images. Different bands are usually involved when extracting data, because the absorption characteristics and spectral characteristics of different gases are located in different regions of the electromagnetic spectrum. At the same time, different meteorological characteristics correspond to different spectral characteristics. Therefore, when extracting different data, multiple different remote sensing bands will be involved.

[0056] Optionally, the step of extracting meteorological data from a remote sensing data set of the atmosphere above the target forest area based on the remote sensing image includes: determining a first remote sensing band, wherein the first remote sensing band is a band related to meteorological data; extracting meteorological spectral features from the remote sensing image based on the first remote sensing band; analyzing the meteorological spectral features based on an inversion algorithm to obtain meteorological data of the atmosphere above the target forest area, wherein the meteorological data includes at least one of the following: temperature data, precipitation data, wind direction data, wind speed data, humidity data, and air pressure data.

[0057] It should be noted that when analyzing meteorological data based on remote sensing images, it is first necessary to determine the first remote sensing band related to the meteorological data, and then extract the spectral characteristics of the remote sensing band in the first remote sensing band to obtain the meteorological spectral characteristics, and then select a suitable inversion algorithm based on the meteorological parameters to be inverted and the characteristics of the remote sensing data. These algorithms may be based on physical models, empirical models or machine learning models. The inversion algorithm is used to invert the meteorological data of the atmosphere above the target forest area, and the image data is converted into actual physical quantities. For example: the temperature of the cloud top and the surface is inverted based on infrared data; or the water vapor content and precipitation rate in the atmosphere are inverted based on microwave data.

[0058] It should be noted that different meteorological parameters require different remote sensing bands to obtain information. For example, the infrared band can be used to measure the temperature at the top of the cloud layer, while the microwave band can penetrate the cloud layer and provide temperature and humidity information at different levels in the atmosphere. Satellite images in the visible and infrared bands are used to monitor the movement trends of clouds, identify cloud cover types, and estimate the possibility of precipitation. Through infrared detectors and microwave radiometers, the vertical distribution of temperature and humidity in the clear sky atmosphere, as well as the water content in the clouds and precipitation intensity can be calculated.

[0059] Optionally, the step of extracting carbon dioxide data from a remote sensing data set of the atmosphere above a target forest area based on a remote sensing image includes: determining a second remote sensing band, wherein the second remote sensing band is a band related to carbon dioxide data; drawing a carbon dioxide spectral curve of pixel points in the remote sensing image based on the second remote sensing band; obtaining carbon dioxide spectral characteristics of the target forest area based on the carbon dioxide spectral curve; and obtaining carbon dioxide data of the target forest area based on the carbon dioxide spectral characteristics.

[0060] It should be noted that when extracting carbon dioxide data from remote sensing images, the second remote sensing band related to carbon dioxide is first determined. Remote sensing monitoring of carbon dioxide mainly relies on the absorption band of carbon dioxide in the atmosphere, especially in the short-wave infrared and thermal infrared regions. Carbon dioxide has specific absorption spectra. Then, the carbon dioxide spectral curve of the pixel points in the remote sensing image is drawn according to the second remote sensing band, and the carbon dioxide spectral characteristics are extracted from the spectral curve. The carbon dioxide data of the atmosphere above the target forest area, such as the carbon dioxide concentration, is obtained by analyzing the carbon dioxide spectral characteristics.

[0061] Optionally, the step of extracting nitrogen dioxide data from a remote sensing data set of the atmosphere above a target forest area based on a remote sensing image includes: determining a third remote sensing band, wherein the third remote sensing band is a band related to nitrogen dioxide data; drawing a nitrogen dioxide spectral curve of pixel points in the remote sensing image based on the third remote sensing band; obtaining nitrogen dioxide spectral characteristics of the target forest area based on the nitrogen dioxide spectral curve; and obtaining nitrogen dioxide data of the target forest area based on the nitrogen dioxide spectral characteristics.

[0062] It should be noted that the concentration of nitrogen dioxide will affect the generation of carbon dioxide. Therefore, the concentration of nitrogen dioxide in the target forest area can be used as auxiliary data for analyzing carbon dioxide. When obtaining nitrogen dioxide data above the target forest area, the third remote sensing band related to the nitrogen dioxide data is first determined. Remote sensing monitoring of nitrogen dioxide mainly depends on its absorption characteristics in the visible light and near-infrared regions, especially in the band around 410nm, where nitrogen dioxide exhibits strong absorption characteristics. Then, based on the third remote sensing band, the nitrogen dioxide spectral curve of each pixel in the remote sensing image on the third remote sensing band is drawn, and the nitrogen dioxide spectral characteristics are extracted from the nitrogen dioxide spectral curve. Finally, the nitrogen dioxide data of the target forest area is obtained based on the spectral characteristics.

[0063] Step S103, input the remote sensing data in the remote sensing data set into the deep learning model one by one, and output the carbon dioxide concentration of the target forest area.

[0064] It should be noted that the deep learning model of the embodiment of the present invention is a pre-built model for predicting the carbon dioxide concentration in forest areas. The meteorological data, carbon dioxide data and nitrogen dioxide data of the atmosphere above the target forest area extracted based on remote sensing technology and the actual carbon dioxide concentration on the ground measured are used as sample data to iteratively train the initial model to obtain a model for estimating the actual carbon dioxide concentration on the ground in the forest area.

[0065] Optionally, the step of constructing a deep learning model includes: obtaining historical remote sensing images of the forest area within the historical time period, and obtaining the carbon dioxide concentration of the forest area within the historical time period based on ground monitoring equipment; extracting historical remote sensing data from the historical remote sensing images; constructing a sample set based on the historical remote sensing images and carbon dioxide concentrations of the forest area; splitting the sample set based on a preset ratio to obtain a training set and a test set; iteratively training the initial model based on the training set to obtain an initial deep learning model; testing the initial deep learning model based on the test set to obtain test results, and when the test results indicate that the initial deep learning model passes the test, a trained deep learning model is obtained.

[0066] It should be noted that when constructing a deep learning model, we first obtain historical remote sensing images of the forest area within the historical time period, and obtain the carbon dioxide concentration of the forest area within the historical time period based on ground monitoring equipment, which is used as label data of historical data. Historical remote sensing data is extracted from the historical remote sensing images, and a sample set is constructed based on the historical remote sensing data and the label data to obtain sample data for training. The sample set is then divided into a training set and a test set. The model is iteratively trained using the training set, and the trained model is tested using the test set. If the test passes, a trained deep learning model is obtained.

[0067] Step S104, evaluating the loan request according to the carbon dioxide concentration to obtain a loan evaluation result.

[0068] It should be noted that after the carbon dioxide data on the ground of the target forest area is output based on the deep learning model, the value data of the target forest area is determined based on the carbon dioxide concentration, and the value data of the target forest area is compared with the loan amount requested in the loan request to determine whether there is a risk in the loan request, and then a risk assessment is conducted on the loan request.

[0069] Optionally, the step of evaluating the loan request based on the carbon dioxide concentration also includes: obtaining market carbon information, determining the value data of the target forest area based on the market carbon information and the carbon dioxide concentration; comparing the value data of the target forest area with the loan amount in the loan request to obtain a comparison result, and evaluating the loan request based on the comparison result.

[0070] Optionally, the step of evaluating the loan request based on the comparison result also includes: approving the loan request when the comparison result indicates that the value data of the target forest area is greater than or equal to the loan amount; or rejecting the loan request when the comparison result indicates that the value data of the target forest area is less than the loan amount.

[0071] It should be noted that after calculating the carbon dioxide concentration in the target forest area, the loan request can be evaluated through carbon dioxide. First, market carbon information is collected, and the value data of the target forest area is calculated based on the current market value of carbon and the analyzed carbon dioxide concentration. The value data is compared with the loan amount of the loan request, so as to conduct a risk assessment of the loan request on the user side. If the value data of the target forest area is less than the loan amount, it indicates that there is a risk in the loan request and the loan request from the user side needs to be rejected. If the value data of the target forest area is greater than or equal to the loan amount, then the loan request from the user side can be processed through pre-loan risk assessment, which can reduce the bad debt rate of financial institutions.

[0072] Another optional specific implementation is described in detail below.

[0073] Figure 2 is a schematic diagram of an optional loan evaluation process according to an embodiment of the present invention, such as Figure 2 As shown, the loan assessment process includes:

[0074] Step 1, start;

[0075] Step 2: Obtain meteorological data, carbon dioxide data, and nitrogen dioxide data of the atmosphere above the target forest area based on remote sensing technology;

[0076] Step 3: Input meteorological data, carbon dioxide data, and nitrogen dioxide data into a pre-trained deep learning model to output carbon dioxide concentration;

[0077] The deep learning model is a pre-trained model for estimating the actual carbon dioxide concentration in the target forest area. It obtains meteorological data, carbon dioxide data, and nitrogen dioxide data in the atmosphere above the forest area through satellite remote sensing technology. The meteorological data, carbon dioxide data, and nitrogen dioxide data obtained above are then used as training data, and the actual carbon dioxide data monitored on the ground in the forest area is used as label data. The training data and label data are then input into the deep learning neural network, and the deep learning model is obtained through iterative training.

[0078] Step 4: Evaluate the land value based on the carbon dioxide concentration to obtain the value data of the target land;

[0079] Step 5: Conduct risk assessment on loan request based on value data;

[0080] Step six, end.

[0081] In an embodiment of the present invention, meteorological data, carbon dioxide data and nitrogen dioxide data are obtained through satellite remote sensing technology, and are used as training data to train a deep learning model. The model can estimate the actual carbon dioxide data on the ground based on the meteorological data, carbon dioxide data monitored by satellite, and nitrogen dioxide data monitored by satellite. There is no need to manually visit and calculate the carbon dioxide concentration in the forest area, which saves costs and improves the evaluation efficiency. In addition, since meteorological conditions and nitrogen dioxide concentrations can affect the generation of carbon dioxide, evaluation based on meteorological data and nitrogen dioxide data can improve the accuracy of the estimation, thereby improving the effectiveness and accuracy of risk assessment.

[0082] The following is a detailed description in conjunction with another embodiment.

[0083] Embodiment 2

[0084] A loan assessment device provided in this embodiment includes multiple implementation units, each of which corresponds to each implementation step in the above-mentioned embodiment 1. Its specific implementation methods and beneficial effects can refer to the above-mentioned method embodiments, which will not be repeated here.

[0085] Figure 3 is a schematic diagram of an optional loan assessment device according to an embodiment of the present invention, such as Figure 3 As shown, the loan evaluation device may include: a determination unit 31, an extraction unit 32, an output unit 33, and an evaluation unit 34, wherein:

[0086] A determination unit 31 is used to receive a loan request from a user and determine a target forest area to be evaluated based on the loan request;

[0087] The extraction unit 32 is used to obtain a remote sensing image of a target forest area, and extract a remote sensing data set of an atmosphere above the target forest area based on the remote sensing image, wherein the remote sensing data set includes at least one of the following: meteorological data, carbon dioxide data, and nitrogen dioxide data;

[0088] An output unit 33 is used to input the remote sensing data in the remote sensing data set into the deep learning model one by one, and output the carbon dioxide concentration of the target forest area, wherein the deep learning model is a pre-built model for predicting the carbon dioxide concentration of the forest area;

[0089] The evaluation unit 34 is used to evaluate the loan request according to the carbon dioxide concentration to obtain a loan evaluation result.

[0090] The above-mentioned loan evaluation device receives a loan request from a user terminal through a determination unit 31, and determines a target forest area to be evaluated based on the loan request; obtains a remote sensing image of the target forest area through an extraction unit 32, and extracts a remote sensing data set of the atmosphere above the target forest area based on the remote sensing image, wherein the remote sensing data set includes at least one of the following: meteorological data, carbon dioxide data, and nitrogen dioxide data; inputs the remote sensing data in the remote sensing data set into a deep learning model one by one through an output unit 33, and outputs the carbon dioxide concentration of the target forest area, wherein the deep learning model is a pre-built model for predicting the carbon dioxide concentration of the forest area; and evaluates the loan request according to the carbon dioxide concentration through an evaluation unit 34 to obtain a loan evaluation result.

[0091] In this embodiment, remote sensing technology is combined with loan assessment. Remote sensing images of the target forest area are collected through remote sensing technology, and remote sensing data is extracted based on the remote sensing images. Then, the remote sensing data is analyzed based on the deep learning model, and the carbon dioxide concentration of the target forest area is directly output. The risk of loan requests based on the target forest area is assessed based on the carbon dioxide concentration. There is no need for manual visits and manual measurement of the carbon dioxide concentration in the forest area, which improves the assessment efficiency. At the same time, meteorological data and nitrogen dioxide data are used to assist in the analysis of the carbon dioxide concentration in the forest area, which improves the calculation accuracy and thus enhances the accuracy of the assessment results. This solves the technical problem of low assessment efficiency in the related art of manually measuring the carbon dioxide concentration in the target forest area to conduct risk assessment of loan requests.

[0092] Optionally, the extraction unit 32 includes: a first determination module, used to determine a first remote sensing band, wherein the first remote sensing band is a band related to meteorological data; a first extraction module, used to extract meteorological spectral features from a remote sensing image based on the first remote sensing band; a first analysis module, used to analyze the meteorological spectral features based on an inversion algorithm to obtain meteorological data of the atmosphere above the target forest area, wherein the meteorological data includes at least one of the following: temperature data, precipitation data, wind direction data, wind speed data, humidity data, and air pressure data.

[0093] Optionally, the extraction unit 32 also includes: a second determination module, used to determine a second remote sensing band, wherein the second remote sensing band is a band related to carbon dioxide data; a first drawing module, used to draw a carbon dioxide spectrum curve of pixel points in the remote sensing image based on the second remote sensing band; a first acquisition module, used to acquire carbon dioxide spectrum characteristics of the target forest area based on the carbon dioxide spectrum curve; and a second acquisition module, used to acquire carbon dioxide data of the target forest area based on the carbon dioxide spectrum characteristics.

[0094] Optionally, the extraction unit 32 also includes: a third determination module, used to determine a third remote sensing band, wherein the third remote sensing band is a band related to nitrogen dioxide data; a second drawing module, used to draw a nitrogen dioxide spectrum curve of pixel points in the remote sensing image based on the third remote sensing band; a third acquisition module, used to acquire nitrogen dioxide spectrum characteristics of the target forest area based on the nitrogen dioxide spectrum curve; and a fourth acquisition module, used to acquire nitrogen dioxide data of the target forest area based on the nitrogen dioxide spectrum characteristics.

[0095] Optionally, the evaluation unit 34 includes: a fourth determination module, used to obtain market carbon information, and determine the value data of the target forest area based on the market carbon information and the carbon dioxide concentration; a first comparison module, used to compare the value data of the target forest area with the loan amount in the loan request, obtain a comparison result, and evaluate the loan request based on the comparison result.

[0096] Optionally, the evaluation unit 34 also includes: a first approval module, used to approve the loan request when the comparison result indicates that the value data of the target forest area is greater than or equal to the loan amount; a first rejection module, used to reject the loan request when the comparison result indicates that the value data of the target forest area is less than the loan amount.

[0097] Optionally, the loan assessment device also includes: a fifth acquisition module, used to acquire historical remote sensing images of the forest area within the historical time period, and acquire the carbon dioxide concentration of the forest area within the historical time period based on ground monitoring equipment; a second extraction module, used to extract historical remote sensing data from the historical remote sensing images; a first construction module, used to construct a sample set based on the historical remote sensing images and carbon dioxide concentrations of the forest area; a first splitting module, used to split the sample set based on a preset ratio to obtain a training set and a test set; a first training module, used to iteratively train the initial model based on the training set to obtain an initial deep learning model; a first testing module, used to test the initial deep learning model based on the test set to obtain a test result, and when the test result indicates that the initial deep learning model passes the test, a trained deep learning model is obtained.

[0098] The loan assessment device may further include a processor and a memory. The determination unit 31, extraction unit 32, output unit 33, assessment unit 34, etc. are all stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions.

[0099] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the risk assessment of the loan request can be performed by adjusting the kernel parameters.

[0100] The above-mentioned 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 memory (fl ash RAM), and the memory includes at least one storage chip.

[0101] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium includes a stored computer program. When the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute any one of the above loan assessment methods.

[0102] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, comprising 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 one or more processors, the one or more processors implement any one of the above-mentioned loan assessment methods.

[0103] 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: receiving a loan request from a user end, and determining a target forest area to be evaluated based on the loan request; obtaining a remote sensing image of the target forest area, and extracting a remote sensing data set of the atmosphere above the target forest area based on the remote sensing image, wherein the remote sensing data set includes at least one of the following: meteorological data, carbon dioxide data, and nitrogen dioxide data; inputting the remote sensing data in the remote sensing data set into a deep learning model one by one, and outputting the carbon dioxide concentration of the target forest area, wherein the deep learning model is a pre-built model for predicting the carbon dioxide concentration of the forest area; evaluating the loan request based on the carbon dioxide concentration to obtain a loan evaluation result.

[0104] The present application also provides a computer program product, which, when executed on a data processing device, is also suitable for executing a program that initializes the following method steps: the step of extracting meteorological data from a remote sensing data set of the atmosphere above a target forest area based on a remote sensing image includes: determining a first remote sensing band, wherein the first remote sensing band is a band related to meteorological data; extracting meteorological spectral features from the remote sensing image based on the first remote sensing band; analyzing the meteorological spectral features based on an inversion algorithm to obtain meteorological data of the atmosphere above the target forest area, wherein the meteorological data includes at least one of the following: temperature data, precipitation data, wind direction data, wind speed data, humidity data, and air pressure data.

[0105] The present application also provides a computer program product, which, when executed on a data processing device, is also suitable for executing a program that initializes the following method steps: the steps of extracting carbon dioxide data in a remote sensing data set of the atmosphere above a target forest area based on a remote sensing image include: determining a second remote sensing band, wherein the second remote sensing band is a band related to carbon dioxide data; drawing a carbon dioxide spectrum curve for pixel points in the remote sensing image based on the second remote sensing band; obtaining carbon dioxide spectrum characteristics of the target forest area based on the carbon dioxide spectrum curve; and obtaining carbon dioxide data of the target forest area based on the carbon dioxide spectrum characteristics.

[0106] The present application also provides a computer program product, which, when executed on a data processing device, is also suitable for executing a program that initializes the following method steps: the steps of extracting nitrogen dioxide data in a remote sensing data set of the atmosphere above a target forest area based on a remote sensing image include: determining a third remote sensing band, wherein the third remote sensing band is a band related to nitrogen dioxide data; drawing a nitrogen dioxide spectral curve of pixel points in the remote sensing image based on the third remote sensing band; obtaining nitrogen dioxide spectral characteristics of the target forest area based on the nitrogen dioxide spectral curve; and obtaining nitrogen dioxide data of the target forest area based on the nitrogen dioxide spectral characteristics.

[0107] The present application also provides a computer program product, which, when executed on a data processing device, is also suitable for executing a program that initializes the following method steps: the step of evaluating a loan request based on carbon dioxide concentration, also including: obtaining market carbon information, determining value data of a target forest area based on the market carbon information and carbon dioxide concentration; comparing the value data of the target forest area with the loan amount in the loan request to obtain a comparison result, and evaluating the loan request based on the comparison result.

[0108] The present application also provides a computer program product, which, when executed on a data processing device, is also suitable for executing a program that initializes the following method steps: a step of evaluating a loan request based on a comparison result, and also includes: if the comparison result indicates that the value data of the target forest area is greater than or equal to the loan amount, approving the loan request; or, if the comparison result indicates that the value data of the target forest area is less than the loan amount, rejecting the loan request.

[0109] The present application also provides a computer program product, which, when executed on a data processing device, is also suitable for executing a program that initializes the following method steps: the steps of constructing a deep learning model include: obtaining historical remote sensing images of the forest area within a historical time period, and obtaining the carbon dioxide concentration of the forest area within the historical time period based on ground monitoring equipment; extracting historical remote sensing data from the historical remote sensing images; constructing a sample set based on the historical remote sensing images and carbon dioxide concentration of the forest area; splitting the sample set based on a preset ratio to obtain a training set and a test set; iteratively training the initial model based on the training set to obtain an initial deep learning model; testing the initial deep learning model based on the test set to obtain a test result, and when the test result indicates that the initial deep learning model passes the test, a trained deep learning model is obtained.

[0110] Figure 4 FIG. 1 is a hardware structure block diagram of an electronic device (or mobile device) according to a loan evaluation method according to an embodiment of the present invention. Figure 4 As shown, the electronic device may include one or more ( Figure 4 402a, 402b, ..., 402n are used to illustrate) processor 402 (processor 402 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), memory 404 for storing data. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a keyboard, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 4 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 4 More or fewer components as shown, or with Figure 4 Different configurations are shown.

[0111] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0112] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0113] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0114] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0115] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0116] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0117] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A loan assessment method, characterized in that: include: receiving a loan request from a user, and determining a target forest area to be evaluated based on the loan request; Acquire a remote sensing image of the target forest area, and extract a remote sensing data set of the atmosphere above the target forest area based on the remote sensing image, wherein the remote sensing data set includes at least one of the following: meteorological data, carbon dioxide data, and nitrogen dioxide data; Inputting the remote sensing data in the remote sensing data set into the deep learning model one by one, and outputting the carbon dioxide concentration of the target forest area, wherein the deep learning model is a pre-built model for predicting the carbon dioxide concentration of the forest area; The loan request is evaluated according to the carbon dioxide concentration to obtain a loan evaluation result.

2. The evaluation method according to claim 1, characterized in that: The step of extracting the meteorological data in the remote sensing data set of the atmosphere above the target forest area based on the remote sensing image comprises: Determining a first remote sensing band, wherein the first remote sensing band is a band related to meteorological data; extracting meteorological spectral features from the remote sensing image based on the first remote sensing band; The meteorological spectral characteristics are analyzed based on an inversion algorithm to obtain the meteorological data of the atmosphere above the target forest area, wherein the meteorological data includes at least one of the following: temperature data, precipitation data, wind direction data, wind speed data, humidity data, and air pressure data.

3. The evaluation method according to claim 1, characterized in that: The step of extracting the carbon dioxide data in the remote sensing data set of the atmosphere above the target forest area based on the remote sensing image comprises: determining a second remote sensing band, wherein the second remote sensing band is a band associated with the carbon dioxide data; Draw a carbon dioxide spectrum curve of a pixel point in the remote sensing image based on the second remote sensing band; Acquire the carbon dioxide spectrum characteristics of the target forest area based on the carbon dioxide spectrum curve; The carbon dioxide data of the target forest area is acquired based on the carbon dioxide spectral characteristics.

4. The evaluation method according to claim 1, characterized in that: The step of extracting the nitrogen dioxide data in the remote sensing data set of the atmosphere above the target forest area based on the remote sensing image comprises: Determining a third remote sensing band, wherein the third remote sensing band is a band related to the nitrogen dioxide data; Draw a nitrogen dioxide spectrum curve of a pixel point in the remote sensing image based on the third remote sensing band; Acquire the nitrogen dioxide spectrum characteristics of the target forest area based on the nitrogen dioxide spectrum curve; The nitrogen dioxide data of the target forest area is obtained based on the nitrogen dioxide spectral characteristics.

5. The evaluation method according to claim 1, characterized in that: The step of evaluating the loan request based on the carbon dioxide concentration further comprises: Obtaining market carbon information, and determining value data of the target forest area based on the market carbon information and the carbon dioxide concentration; The value data of the target forest area is compared with the loan amount in the loan request to obtain a comparison result, and the loan request is evaluated based on the comparison result.

6. The evaluation method according to claim 5, characterized in that: The step of evaluating the loan request based on the comparison result further includes: If the comparison result indicates that the value data of the target forest area is greater than or equal to the loan amount, approve the loan request; or When the comparison result indicates that the value data of the target forest area is less than the loan amount, the loan request is rejected.

7. The evaluation method according to claim 1, characterized in that: The steps of constructing the deep learning model include: Obtain historical remote sensing images of forest areas within historical time periods, and obtain carbon dioxide concentrations in forest areas within historical time periods based on ground monitoring equipment; extracting historical remote sensing data from the historical remote sensing images; Constructing a sample set based on the historical remote sensing images of the forest area and the carbon dioxide concentration; Splitting the sample set based on a preset ratio to obtain a training set and a test set; Iteratively training the initial model based on the training set to obtain an initial deep learning model; The initial deep learning model is tested based on the test set to obtain a test result. When the test result indicates that the initial deep learning model passes the test, the trained deep learning model is obtained.

8. A loan evaluation device, characterized in that: include: A determination unit, configured to receive a loan request from a user terminal and determine a target forest area to be evaluated based on the loan request; An extraction unit, used to obtain a remote sensing image of the target forest area, and extract a remote sensing data set of the atmosphere above the target forest area based on the remote sensing image, wherein the remote sensing data set includes at least one of the following: meteorological data, carbon dioxide data, and nitrogen dioxide data; An output unit, used to input the remote sensing data in the remote sensing data set into the deep learning model one by one, and output the carbon dioxide concentration of the target forest area, wherein the deep learning model is a pre-built model for predicting the carbon dioxide concentration of the forest area; An evaluation unit is used to evaluate the loan request according to the carbon dioxide concentration to obtain a loan evaluation result.

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

10. An electronic device, characterized in that: The invention comprises 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 loan assessment method according to any one of claims 1 to 7.

Images