Land value evaluation method and device, electronic equipment and computer program product

Abstract

The invention discloses a land value evaluation method and device, electronic equipment and a computer program product, and relates to the field of artificial intelligence, the field of financial science and technology or other related technical fields, the value evaluation method comprises the steps that a loan request of a user side is received, and the loan request at least comprises a target land to be mortgage; acquiring a remote sensing image of the target land, and preprocessing the remote sensing image to obtain a preprocessed remote sensing image; inputting the preprocessed remote sensing image into a land evaluation model, and outputting area information and soil texture information of the target land; and performing value evaluation on the target land based on the area information and the soil property information of the target land. According to the method and the device, the technical problems of relatively single evaluation index and relatively low evaluation accuracy of a scheme for estimating the value of the land through a mathematical model in related technologies are solved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence, financial technology or other related technical fields, and specifically, to a land value assessment method and device, electronic equipment and computer program product. Background Art

[0002] As a popular loan project at present, agricultural loans have promoted the development of agriculture to a certain extent. For loans related to agricultural planting, users can apply for loan funds by using land as collateral. For collateral such as land, which has a large area and complex assessment conditions, it brings certain challenges to pre-loan assessment.

[0003] In related technologies, the value assessment of mortgaged land is usually achieved through manual visits or mathematical model estimation, which not only has the problems of high labor costs, single assessment indicators, and poor assessment efficiency, but also may lead to human cheating.

[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 land value assessment method and device, an electronic device and a computer program product to at least solve the technical problem in the related art that the value of land is estimated through a mathematical model, the assessment index is relatively single and the assessment accuracy is low.

[0006] According to one aspect of an embodiment of the present invention, a land value assessment method is provided, comprising: receiving a loan request from a user terminal, wherein the loan request includes at least: a target land to be mortgaged; acquiring a remote sensing image of the target land, and preprocessing the remote sensing image to obtain a preprocessed remote sensing image; inputting the preprocessed remote sensing image into a land assessment model, and outputting area information and soil quality information of the target land; and conducting a value assessment on the target land based on the area information and soil quality information of the target land.

[0007] Optionally, the step of preprocessing the remote sensing image includes: performing radiation correction and atmospheric correction on the remote sensing image to obtain a corrected remote sensing image; extracting spectral features from the corrected remote sensing image, wherein the spectral features are used to analyze soil quality information of the target land.

[0008] Optionally, the step of conducting a value assessment on the target land based on the area information and soil quality information of the target land includes: dividing the target land based on the soil quality information of the target land to obtain N sub-areas, wherein N is a positive integer and the soil types of each sub-area are different; acquiring crops to be planted that match the sub-areas based on the geographic information of the target land and the soil quality information of each sub-area; and conducting a value assessment on the target land based on the sub-area area of ​​the target land and the crops to be planted.

[0009] Optionally, the step of conducting a value assessment on the target land based on the sub-region area of ​​the target land and the crops to be planted includes: for any sub-region, obtaining the average value of the crops to be planted corresponding to the sub-region within the historical target time period; calculating the value data of the sub-region based on the area of ​​the sub-region and the average value of the crops to be planted; accumulating the value data of all sub-regions of the target land to obtain the value data of the target land, and conducting a value assessment on the target land based on the value data of the target land to obtain a value assessment result.

[0010] Optionally, after obtaining the value assessment result, it also includes: if the value data of the target land in the value assessment result is greater than or equal to the loan amount of the loan request, approving the loan request; if the value data of the target land in the value assessment result is less than the loan amount of the loan request, rejecting the loan request and returning a notification of loan failure to the user terminal.

[0011] Optionally, after the loan request is approved, the method further includes: generating a crop planting strategy based on the crops to be planted that match the sub-area; and sending the crop planting strategy to the user terminal.

[0012] Optionally, the land evaluation model is pre-trained, and the steps of training the land evaluation model include: obtaining remote sensing images of land within a historical time period, and obtaining area information and soil quality information of the land; preprocessing and feature extraction of the remote sensing images to obtain preprocessed remote sensing images and spectral features; constructing a sample set based on the preprocessed remote sensing images and the spectral features, the area information and the soil quality information; splitting the sample set based on a preset ratio to obtain a training set and a test set; training an initial neural network model based on the training set to obtain an initial land evaluation model; testing the initial land evaluation model based on the test set to obtain a test result, and when the test result indicates that the initial land evaluation model passes the test, obtaining the final land evaluation model.

[0013] According to another aspect of an embodiment of the present invention, a land value assessment device is also provided, including: a receiving unit, used to receive a loan request from a user terminal, wherein the loan request includes at least: a target land to be mortgaged; an acquisition unit, used to acquire a remote sensing image of the target land, and preprocess the remote sensing image to obtain a preprocessed remote sensing image; an output unit, used to input the preprocessed remote sensing image into a land assessment model, and output the area information and soil quality information of the target land; and an assessment unit, used to perform a value assessment on the target land based on the area information and soil quality information of the target land.

[0014] Optionally, the land value assessment device also includes: a first correction module, used to perform radiation correction and atmospheric correction on the remote sensing image to obtain a corrected remote sensing image; a first extraction module, used to extract spectral features from the corrected remote sensing image, wherein the spectral features are used to analyze the soil quality information of the target land.

[0015] Optionally, the evaluation unit includes: a first division module, used to divide the target land based on the soil information of the target land to obtain N sub-areas, where N is a positive integer and the soil types of each sub-area are different; a first acquisition module, used to acquire crops to be planted that match the sub-areas based on the geographic information of the target land and the soil information of each sub-area; and a first evaluation module, used to perform a value evaluation on the target land based on the sub-area area of ​​the target land and the crops to be planted.

[0016] Optionally, the first evaluation module includes: a first acquisition submodule, used to obtain, for any of the sub-regions, the average value of the crops to be planted corresponding to the sub-region within the historical target time period; a first calculation submodule, used to calculate the value data of the sub-region based on the area of ​​the sub-region and the average value of the crops to be planted; a first evaluation subunit, used to accumulate the value data of all sub-regions of the target land to obtain the value data of the target land, and perform value evaluation on the target land based on the value data of the target land to obtain a value evaluation result.

[0017] Optionally, the first evaluation module also includes: a first approval sub-module, used to approve the loan request if the value data of the target land in the value evaluation result is greater than or equal to the loan amount of the loan request; a first return sub-module, used to reject the loan request and return a notification of loan failure to the user terminal if the value data of the target land in the value evaluation result is less than the loan amount of the loan request.

[0018] Optionally, the first evaluation module further includes: a first generating submodule, used for generating a crop planting strategy based on the crops to be planted that match the sub-area; and a first sending submodule, used for sending the crop planting strategy to the user end.

[0019] Optionally, the land value assessment device also includes: a second acquisition module, used to obtain remote sensing images of land within a historical time period, and obtain the area information and soil quality information of the land; a second extraction module, used to preprocess and extract features of the remote sensing images to obtain preprocessed remote sensing images and spectral features; a first construction module, used to construct a sample set based on the preprocessed remote sensing images and the spectral features, the area information and the soil quality information; 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 train an initial neural network model based on the training set to obtain an initial land assessment model; a first testing module, used to test the initial land assessment model based on the test set to obtain a test result, and when the test result indicates that the initial land assessment model passes the test, obtain the final land assessment model.

[0020] 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 land value assessment methods.

[0021] According to another aspect of an embodiment of the present invention, a computer program product is further provided. The computer program product includes a computer program, wherein the computer program implements any one of the above land value assessment methods when executed by a processor.

[0022] In the present disclosure, the following steps are performed: first, a loan request from a user is received, wherein the loan request at least includes: target land to be mortgaged; then, a remote sensing image of the target land is obtained, and the remote sensing image is preprocessed to obtain a preprocessed remote sensing image; then, the preprocessed remote sensing image is input into a land evaluation model, and the area information and soil quality information of the target land are output; finally, the value of the target land is evaluated based on the area information and soil quality information of the target land.

[0023] In the present disclosure, the remote sensing image of the target land to be mortgaged is identified through the land evaluation model, and the area and soil quality information of the target land is output, and then the value data of the target land is evaluated based on the area information and soil quality information, so as to conduct a pre-loan evaluation. The soil quality information of each area of ​​the target land is used as one of the evaluation indicators, which can improve the accuracy of the value evaluation, thereby solving the technical problem in the related technology that the value of the land is estimated through mathematical models, the evaluation indicators are relatively single, and the evaluation accuracy is low. 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 land value assessment method according to an embodiment of the present invention;

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

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

[0028] Figure 4 The present invention is a hardware structure block diagram of an electronic device (or mobile device) for a land value assessment 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 land value assessment method and device thereof disclosed in the present invention can be used in the field of artificial intelligence when the target land is valued based on a land assessment model, and can also be used in any field other than the field of artificial intelligence when the target land is valued based on a land assessment model. The present invention does not limit the application field of the land value assessment method and device thereof.

[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 disclosure 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 the present disclosure, when collecting and analyzing customer information, corresponding operation entrances are provided for users to choose to agree or reject the automated decision results; if the user chooses to reject, the expert decision process is entered.

[0034] The following embodiments of the present invention can be applied to various land value assessment systems / applications / devices. The present invention combines wireless remote sensing technology to automatically assess the value of the target land. By adding the identification of the soil type of each sub-region and the prediction of suitable plants, the prediction accuracy of the model can be improved, thereby improving the accuracy of loan risk estimation and the appreciation of land.

[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 land value 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 land value 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, wherein the loan request at least includes: target land to be mortgaged;

[0040] Step S102, acquiring a remote sensing image of the target land, and preprocessing the remote sensing image to obtain a preprocessed remote sensing image;

[0041] Step S103, inputting the preprocessed remote sensing image into the land assessment model, and outputting the area information and soil quality information of the target land;

[0042] Step S104: assessing the value of the target land based on the area information and soil quality information of the target land.

[0043] Through the above steps, a loan request from a user is first received, wherein the loan request at least includes: the target land to be mortgaged, and then a remote sensing image of the target land is obtained, and the remote sensing image is preprocessed to obtain a preprocessed remote sensing image, and then the preprocessed remote sensing image is input into a land evaluation model, and the area information and soil quality information of the target land are output, and finally, the value of the target land is evaluated based on the area information and soil quality information of the target land.

[0044] In this embodiment, the remote sensing image of the target land to be mortgaged is identified through the land evaluation model, and the area and soil quality information of the target land is output. Then, the value data of the target land is evaluated based on the area information and the soil quality information, so as to conduct a pre-loan evaluation. The soil quality information of each area of ​​the target land is used as one of the evaluation indicators, which can improve the accuracy of the value evaluation, thereby solving the technical problem in the related technology of estimating the value of the land through mathematical models, the evaluation indicators are relatively single, and the evaluation accuracy is low.

[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 has also been promoted. Agricultural loan business has also gradually grown. Users of agricultural loans often use land as collateral for loans. Due to the special nature of the land, the pre-loan assessment of the land poses great challenges. If the assessment is inaccurate, the bad debt rate of financial institutions will increase.

[0047] The embodiment of the present invention uses a pre-trained land value assessment model to input the captured remote sensing images into the land assessment model, and can output the total area of ​​the target land and the soil quality information of each sub-region. The soil quality of each region is different, and the crops suitable for planting are also different. If unsuitable crops are planted in the sub-region, it may lead to poor returns, which in turn brings pressure and risks to repayment. Therefore, the embodiment of the present invention uses soil quality information as an indicator of value assessment, which can improve the precision and accuracy of value assessment and reduce the bad debt rate of financial institutions.

[0048] Step S101, receiving a loan request from a user.

[0049] It should be noted that the user submits a loan request based on the target land to be mortgaged, the loan amount and the user information. The business personnel of the financial institution need to evaluate the user's loan request based on the loan request, and predict whether the income of the target land to be mortgaged is greater than the loan amount of the loan request. Then, based on the results of the prediction and evaluation, the user's loan request will be approved or rejected, thereby enhancing the accuracy of the pre-loan assessment and reducing the bad debt rate of the financial institution.

[0050] Step S102, acquiring a remote sensing image of the target land, and preprocessing the remote sensing image to obtain a preprocessed remote sensing image.

[0051] It should be noted that the embodiment of the present invention combines remote sensing technology to evaluate the value of the target land. First, the target area and target features to be monitored are determined, and appropriate remote sensing satellites or aircraft are selected. For example, satellites equipped with infrared or multi-spectral sensors, or drones equipped with specific sensors are used. These sensors can capture radiation of specific wavelengths related to heat sources, and then accurate remote sensing images containing multiple features can be obtained.

[0052] Optionally, the step of preprocessing the remote sensing image includes: performing radiation correction and atmospheric correction on the remote sensing image to obtain a corrected remote sensing image; extracting spectral features from the corrected remote sensing image, wherein the spectral features are used to analyze soil quality information of the target land.

[0053] It should be noted that after collecting the remote sensing images of the target land, the remote sensing images need to be preprocessed to remove the noise in the images. Specific preprocessing operations may include: radiation correction, eliminating the errors 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; in addition to radiation correction and atmospheric correction, correction operations may also include: 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 contrast, brightness, color, etc. of the image, making specific features in the image more obvious for easy 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.

[0054] After preprocessing the remote sensing images, based on the soil information assessment of this application, it is also necessary to extract spectral features, land texture features, soil shape features, land surface biological activity features, etc. from the remote sensing images to facilitate the model to analyze the soil conditions of the target land based on the image.

[0055] In another optional embodiment, the step of obtaining the spectral characteristics of the remote sensing image includes: selecting the remote sensing band to be analyzed; plotting the remote sensing band values ​​of the pixel points of the remote sensing image into a curve on different remote sensing bands, thereby obtaining the spectral curve of the pixel point; based on the spectral curve, obtaining the spectral characteristics of the target land, such as vegetation index, soil index, spectral angle index, etc., these characteristics can be used to characterize the spectral characteristics of different soil types.

[0056] Another optional embodiment, when extracting land texture features, a texture feature extraction algorithm is applied to each pixel point or each area to calculate the corresponding texture features, such as contrast, uniformity, entropy, etc. The texture feature extraction algorithm may include: grayscale co-occurrence matrix, directional gradient histogram, local binary pattern, etc.

[0057] Step S103, input the preprocessed remote sensing image into the land assessment model, and output the area information and soil quality information of the target land.

[0058] It should be noted that after preprocessing and feature extraction of the remote sensing image, the processed remote sensing image and the extracted spectral features are input into the land assessment model, and the land assessment model outputs the area information and soil quality information of the target land.

[0059] In another optional embodiment, in order to obtain the area information of the target land, it is first necessary to adjust the flatness of the remote sensing image. The altitude variance algorithm can be used to calculate the flatness of the land, and the remote sensing image with a land flatness less than the flatness threshold can be processed for flatness adjustment. For example, the remote sensing image can be corrected using a digital elevation algorithm (DEM) to eliminate or reduce image deformation caused by terrain undulations.

[0060] It should be noted that soil quality information may include the combination ratio of particles of different sizes in the soil of the target land, such as sand, loam, clay, etc.; the water content in the soil; the distribution of particles of different particle sizes in the soil, such as sand, clay, loam, etc.; the thickness of each soil layer in the soil profile; the distribution and characteristics of different texture layers in the soil; the arrangement of soil particles, such as aggregate structure, block structure, etc.; the number and activity level of microorganisms in the soil, etc. The above soil quality information is helpful to determine the appropriate type of crop planting, fertilizer application and irrigation requirements, thereby improving agricultural production efficiency and crop yields. It is an important basis for land use and planning, and can improve the utilization rate of land resources.

[0061] Optionally, the land assessment model is pre-trained, and the steps of training the land assessment model include: obtaining remote sensing images of land within a historical time period, and obtaining area information and soil quality information of the land; preprocessing and feature extraction of the remote sensing images to obtain preprocessed remote sensing images and spectral features; constructing a sample set based on the preprocessed remote sensing images and spectral features, area information and soil quality information; splitting the sample set based on a preset ratio to obtain a training set and a test set; training an initial neural network model based on the training set to obtain an initial land assessment model; testing the initial land assessment model based on the test set to obtain test results, and when the test results indicate that the initial land assessment model passes the test, obtaining a final land assessment model.

[0062] It should be noted that the land assessment model is obtained by training the neural network model based on a large amount of remote sensing images and land information, specifically including: obtaining remote sensing images of land within a historical period of time, and obtaining the actual area information of the land and the soil information of each area, and then preprocessing and feature extraction of the remote sensing images, extracting relevant features that can assist in land value assessment from the remote sensing images, such as spectral features, land texture features, soil shape features, biological activity characteristics on the land surface, etc., and constructing a sample set based on remote sensing images, area information, spectral features and soil information, and then dividing the sample set based on a preset ratio, one part is a training set for training the model, and the other part is a test set for testing and optimizing the model, thereby obtaining a land assessment model.

[0063] Step S104: assessing the value of the target land based on the area information and soil quality information of the target land.

[0064] It should be noted that a crop planting strategy can be generated based on the land information of the target land, and the target land can be accurately evaluated based on the recommended crops, the area of ​​the region where each crop is located, and other information.

[0065] Optionally, the step of conducting a value assessment on the target land based on the area information and soil quality information of the target land includes: dividing the target land based on the soil quality information of the target land to obtain N sub-areas, where N is a positive integer and the soil types of each sub-area are different; acquiring crops to be planted that match the sub-areas based on the geographic information of the target land and the soil quality information of each sub-area; and conducting a value assessment on the target land based on the sub-area area of ​​the target land and the crops to be planted.

[0066] It should be noted that when conducting a value assessment on the target land, the target land is first divided according to the soil type to obtain multiple sub-areas, and then the crops to be planted that match the sub-area are determined with reference to the geographical information of the target land and the soil type of each sub-area. Then, the value of the target land is assessed based on the area of ​​the target land sub-area and the crops to be planted.

[0067] Optionally, the step of conducting a value assessment on the target land based on the sub-region area of ​​the target land and the crops to be planted shown includes: for any sub-region, obtaining the average value of the crops to be planted corresponding to the sub-region within the historical target time period; calculating the value data of the sub-region based on the area of ​​the sub-region and the average value of the crops to be planted; accumulating the value data of all sub-regions of the target land to obtain the value data of the target land, and conducting a value assessment on the target land based on the value data of the target land to obtain a value assessment result.

[0068] It should be noted that for any sub-region, the value data of the sub-region is calculated based on the historical average value of the crops to be planted that match the sub-region and the area of ​​the sub-region, and then the value data of multiple sub-regions are accumulated to obtain the total value data of the target land, and the loan application of the target user is evaluated based on the total value data.

[0069] Optionally, after obtaining the value assessment result, it also includes: if the value data of the target land in the value assessment result is greater than or equal to the loan amount of the loan request, approving the loan request; if the value data of the target land in the value assessment result is less than the loan amount of the loan request, rejecting the loan request and returning a notification of loan failure to the user end.

[0070] It should be noted that if the calculated value data of the target land is greater than or equal to the loan amount in the loan request, the target user's loan request will be approved. Conversely, if the calculated value data of the target land is less than the loan amount in the loan request, the target user's loan request will be rejected, and a notification of evaluation failure and loan failure will be sent to the user end.

[0071] Optionally, after the loan request is approved, the method further includes: generating a crop planting strategy based on the crops to be planted that match the sub-region; and sending the crop planting strategy to the user end.

[0072] It should be noted that the embodiment of the present invention matches the most suitable crops for planting for each sub-area based on soil information. If the loan request from the user side is approved, a crop planting strategy can be generated for the target land based on the matched target crops and sent to the user side.

[0073] Another optional embodiment, when the loan request is approved, it is also necessary to monitor the target land of the user who has passed the loan application in real time. If any abnormality is found, a repayment emergency strategy is adopted to reduce the bad debt rate, specifically including: collecting remote sensing images of the target land based on a preset period, and inputting the remote sensing images into an image recognition model to obtain the land change status corresponding to the target land, and adjusting the land assessment value based on the land change status.

[0074] Specifically, the step of obtaining the land change status corresponding to the target land includes: regularly collecting images of the target land at each time point based on a preset period, wherein the images at each time point can be remote sensing images, and the images at each time point at least include a first time point image and a second time point image, and inputting the images at each time point into an image recognition model to perform frame difference processing on the first time point image and the second time point image to obtain a difference matrix, and then inputting the difference matrix into a convolutional neural network in the image recognition model to perform a preset number of convolution and pooling alternating processing on the difference matrix to obtain a convolution and pooling alternating processing result, and fully connecting the convolution and pooling alternating processing result to obtain an image recognition vector, and then obtaining each image recognition feature code in the image recognition, determining the land change status based on each image recognition feature code, and then evaluating the value data of the target land based on the land change status. If the updated target land value data is less than the loan amount in the loan request, a risk warning is generated, and a repayment emergency strategy or a land emergency management strategy is provided to the target user based on the risk level.

[0075] Another optional specific implementation is described in detail below.

[0076] Figure 2 is a schematic diagram of an optional land value assessment process according to an embodiment of the present invention, such as Figure 2 As shown, the process of land value assessment includes:

[0077] Step 1: receiving a loan request, wherein the loan request at least includes the target land for mortgage and the applied loan funds.

[0078] Step 2: Control the drone or satellite to move above the target land to take pictures and obtain a remote sensing image of the target land;

[0079] Step 3: Input the image of the target land into a pre-trained neural network model (land assessment model), and the model outputs the area information of the target land and the soil quality information of each sub-area in the target land. The soil type of each sub-area is different, and the crops suitable for planting are also different;

[0080] Step 4: Determine the value data of each sub-region based on the soil quality information and area information of each sub-region;

[0081] Step 5: Calculate the total value of the target land by summing up the value data of each sub-area;

[0082] Step six, evaluating whether to approve the loan request based on the total value of the target land, wherein if the total value of the target land is greater than or equal to the applied loan amount, the loan request is approved; if the total value of the target land is less than the applied loan amount, the loan request is rejected.

[0083] Step 7: If the assessment fails, a loan failure notice will be returned;

[0084] Step eight, if the evaluation is passed, the crop planting strategy is returned to prompt the loan user with the crops suitable for planting in each sub-area, so as to achieve the appreciation of the overall target land.

[0085] In the embodiment of the present invention, wireless remote sensing technology is combined to automatically evaluate the value of the target land. Since the soil type identification of each sub-area and the prediction of suitable plants are added, the prediction accuracy of the model can be improved, thereby improving the accuracy of loan risk estimation and the appreciation of land.

[0086] The following is a detailed description in conjunction with another embodiment.

[0087] Embodiment 2

[0088] A land value assessment device provided in this embodiment includes multiple implementation units, each of which corresponds to each implementation step in the above-mentioned embodiment 1.

[0089] Figure 3 is a schematic diagram of an optional land value assessment device according to an embodiment of the present invention. Figure 3 As shown, the land value assessment device may include: a receiving unit 31, an acquisition unit 32, an output unit 33, and an assessment unit 34, wherein:

[0090] The receiving unit 31 is used to receive a loan request from a user, wherein the loan request at least includes: target land to be mortgaged;

[0091] An acquisition unit 32 is used to acquire a remote sensing image of the target land and preprocess the remote sensing image to obtain a preprocessed remote sensing image;

[0092] The output unit 33 is used to input the pre-processed remote sensing image into the land assessment model and output the area information and soil quality information of the target land;

[0093] The evaluation unit 34 is used to evaluate the value of the target land based on the area information and soil quality information of the target land.

[0094] The above-mentioned land value assessment device receives a loan request from a user terminal through a receiving unit 31, wherein the loan request at least includes: a target land to be mortgaged; a remote sensing image of the target land is acquired through an acquisition unit 32, and the remote sensing image is preprocessed to obtain a preprocessed remote sensing image; the preprocessed remote sensing image is input into a land assessment model through an output unit 33, and the area information and soil quality information of the target land are output; and a value assessment of the target land is performed based on the area information and soil quality information of the target land through an assessment unit 34.

[0095] In this embodiment, the remote sensing image of the target land to be mortgaged is identified through the land evaluation model, and the area and soil quality information of the target land is output. Then, the value data of the target land is evaluated based on the area information and the soil quality information, so as to conduct a pre-loan evaluation. The soil quality information of each area of ​​the target land is used as one of the evaluation indicators, which can improve the accuracy of the value evaluation, thereby solving the technical problem in the related technology of estimating the value of the land through mathematical models, the evaluation indicators are relatively single, and the evaluation accuracy is low.

[0096] 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 has also been promoted. Agricultural loan business has also gradually grown. Users of agricultural loans often use land as collateral for loans. Due to the special nature of the land, the pre-loan assessment of the land poses great challenges. If the assessment is inaccurate, the bad debt rate of financial institutions will increase.

[0097] The embodiment of the present invention uses a pre-trained land value assessment model to input the captured remote sensing images into the land assessment model, and can output the total area of ​​the target land and the soil quality information of each sub-region. The soil quality of each region is different, and the crops suitable for planting are also different. If unsuitable crops are planted in the sub-region, it may lead to poor returns, which in turn brings pressure and risks to repayment. Therefore, the embodiment of the present invention uses soil quality information as an indicator of value assessment, which can improve the precision and accuracy of value assessment and reduce the bad debt rate of financial institutions.

[0098] It should be noted that the user submits a loan request based on the target land to be mortgaged, the loan amount and the user information. The business personnel of the financial institution need to evaluate the user's loan request based on the loan request, and predict whether the income of the target land to be mortgaged is greater than the loan amount of the loan request. Then, based on the results of the prediction and evaluation, the user's loan request will be approved or rejected, thereby enhancing the accuracy of the pre-loan assessment and reducing the bad debt rate of the financial institution.

[0099] It should be noted that the embodiment of the present invention combines remote sensing technology to evaluate the value of the target land. First, the target area and target features to be monitored are determined, and appropriate remote sensing satellites or aircraft are selected. For example, satellites equipped with infrared or multi-spectral sensors, or drones equipped with specific sensors are used. These sensors can capture radiation of specific wavelengths related to heat sources, and then accurate remote sensing images containing multiple features can be obtained.

[0100] Optionally, the land value assessment device also includes: a first correction module, used to perform radiation correction and atmospheric correction on the remote sensing image to obtain a corrected remote sensing image; a first extraction module, used to extract spectral features from the corrected remote sensing image, wherein the spectral features are used to analyze the soil quality information of the target land.

[0101] It should be noted that after collecting the remote sensing images of the target land, the remote sensing images need to be preprocessed to remove the noise in the images. Specific preprocessing operations may include: radiation correction, eliminating the errors 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; in addition to radiation correction and atmospheric correction, correction operations may also include: 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 contrast, brightness, color, etc. of the image, making specific features in the image more obvious for easy 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.

[0102] After preprocessing the remote sensing images, based on the soil information assessment of this application, it is also necessary to extract spectral features, land texture features, soil shape features, land surface biological activity features, etc. from the remote sensing images to facilitate the model to analyze the soil conditions of the target land based on the image.

[0103] In another optional embodiment, the step of obtaining the spectral characteristics of the remote sensing image includes: selecting the remote sensing band to be analyzed; plotting the remote sensing band values ​​of the pixel points of the remote sensing image into a curve on different remote sensing bands, thereby obtaining the spectral curve of the pixel point; based on the spectral curve, obtaining the spectral characteristics of the target land, such as vegetation index, soil index, spectral angle index, etc., these characteristics can be used to characterize the spectral characteristics of different soil types.

[0104] Another optional embodiment, when extracting land texture features, a texture feature extraction algorithm is applied to each pixel point or each area to calculate the corresponding texture features, such as contrast, uniformity, entropy, etc. The texture feature extraction algorithm may include: grayscale co-occurrence matrix, directional gradient histogram, local binary pattern, etc.

[0105] It should be noted that after preprocessing and feature extraction of the remote sensing image, the processed remote sensing image and the extracted spectral features are input into the land assessment model, and the land assessment model outputs the area information and soil quality information of the target land.

[0106] In another optional embodiment, in order to obtain the area information of the target land, it is first necessary to adjust the flatness of the remote sensing image. The altitude variance algorithm can be used to calculate the flatness of the land, and the remote sensing image with a land flatness less than the flatness threshold can be processed for flatness adjustment. For example, the remote sensing image can be corrected using a digital elevation algorithm (DEM) to eliminate or reduce image deformation caused by terrain undulations.

[0107] It should be noted that soil quality information may include the combination ratio of particles of different sizes in the soil of the target land, such as sand, loam, clay, etc.; the water content in the soil; the distribution of particles of different particle sizes in the soil, such as sand, clay, loam, etc.; the thickness of each soil layer in the soil profile; the distribution and characteristics of different texture layers in the soil; the arrangement of soil particles, such as aggregate structure, block structure, etc.; the number and activity level of microorganisms in the soil, etc. The above soil quality information is helpful to determine the appropriate crop planting type, fertilizer application amount and irrigation requirements, thereby improving agricultural production efficiency and crop yields. It is an important basis for land use planning and can improve the utilization rate of land resources.

[0108] It should be noted that a crop planting strategy can be generated based on the land information of the target land, and the target land can be accurately evaluated based on the recommended crops, the area of ​​the region where each crop is located, and other information.

[0109] Optionally, the evaluation unit includes: a first division module, used to divide the target land based on the soil information of the target land to obtain N sub-areas, where N is a positive integer and the soil types of each sub-area are different; a first acquisition module, used to acquire crops to be planted that match the sub-areas based on the geographic information of the target land and the soil information of each sub-area; a first evaluation module, used to evaluate the value of the target land based on the sub-area area of ​​the target land and the crops to be planted.

[0110] It should be noted that when conducting a value assessment on the target land, the target land is first divided according to the soil type to obtain multiple sub-areas, and then the crops to be planted that match the sub-area are determined with reference to the geographical information of the target land and the soil type of each sub-area. Then, the value of the target land is assessed based on the area of ​​the target land sub-area and the crops to be planted.

[0111] Optionally, the first evaluation module includes: a first acquisition submodule, used to obtain, for any sub-region, the average value of the crops to be planted corresponding to the sub-region within the historical target time period; a first calculation submodule, used to calculate the value data of the sub-region based on the area of ​​the sub-region and the average value of the crops to be planted; a first evaluation subunit, used to accumulate the value data of all sub-regions of the target land to obtain the value data of the target land, and perform value evaluation on the target land based on the value data of the target land to obtain a value evaluation result.

[0112] It should be noted that for any sub-region, the value data of the sub-region is calculated based on the historical average value of the crops to be planted that match the sub-region and the area of ​​the sub-region, and then the value data of multiple sub-regions are accumulated to obtain the total value data of the target land, and the loan application of the target user is evaluated based on the total value data.

[0113] Optionally, the first evaluation module also includes: a first approval sub-module, used to approve the loan request when the value data of the target land in the value evaluation result is greater than or equal to the loan amount of the loan request; a first return sub-module, used to reject the loan request and return a notification of loan failure to the user end when the value data of the target land in the value evaluation result is less than the loan amount of the loan request.

[0114] It should be noted that if the calculated value data of the target land is greater than or equal to the loan amount in the loan request, the target user's loan request will be approved. Conversely, if the calculated value data of the target land is less than the loan amount in the loan request, the target user's loan request will be rejected, and a notification of evaluation failure and loan failure will be sent to the user end.

[0115] Optionally, the first evaluation module further includes: a first generating submodule, used for generating a crop planting strategy based on the crops to be planted that match the sub-region; and a first sending submodule, used for sending the crop planting strategy to the user end.

[0116] It should be noted that the embodiment of the present invention matches the most suitable crops for planting for each sub-area based on soil information. If the loan request from the user side is approved, a crop planting strategy can be generated for the target land based on the matched target crops and sent to the user side.

[0117] Another optional embodiment, when the loan request is approved, it is also necessary to monitor the target land of the user who has passed the loan application in real time. If any abnormality is found, a repayment emergency strategy is adopted to reduce the bad debt rate, specifically including: collecting remote sensing images of the target land based on a preset period, and inputting the remote sensing images into an image recognition model to obtain the land change status corresponding to the target land, and adjusting the land assessment value based on the land change status.

[0118] Specifically, the step of obtaining the land change status corresponding to the target land includes: regularly collecting images of the target land at each time point based on a preset period, wherein the images at each time point can be remote sensing images, and the images at each time point at least include a first time point image and a second time point image, and inputting the images at each time point into an image recognition model to perform frame difference processing on the first time point image and the second time point image to obtain a difference matrix, and then inputting the difference matrix into a convolutional neural network in the image recognition model to perform a preset number of convolution and pooling alternating processing on the difference matrix to obtain a convolution and pooling alternating processing result, and fully connecting the convolution and pooling alternating processing result to obtain an image recognition vector, and then obtaining each image recognition feature code in the image recognition, determining the land change status based on each image recognition feature code, and then evaluating the value data of the target land based on the land change status. If the updated target land value data is less than the loan amount in the loan request, a risk warning is generated, and a repayment emergency strategy or a land emergency management strategy is provided to the target user based on the risk level.

[0119] Optionally, the land value assessment device also includes: a second acquisition module, used to obtain remote sensing images of land within a historical time period, and obtain the area information and soil quality information of the land; a second extraction module, used to preprocess and extract features of the remote sensing images to obtain preprocessed remote sensing images and spectral features; a first construction module, used to construct a sample set based on the preprocessed remote sensing images and spectral features, area information and soil quality information; 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 train the initial neural network model based on the training set to obtain an initial land assessment model; a first testing module, used to test the initial land assessment model based on the test set to obtain a test result, and when the test result indicates that the initial land assessment model passes the test, obtain the final land assessment model.

[0120] It should be noted that the land assessment model is obtained by training the neural network model based on a large amount of remote sensing images and land information, specifically including: obtaining remote sensing images of land within a historical period of time, and obtaining the actual area information of the land and the soil information of each area, and then preprocessing and feature extraction of the remote sensing images, extracting relevant features that can assist in land value assessment from the remote sensing images, such as spectral features, land texture features, soil shape features, biological activity characteristics on the land surface, etc., and constructing a sample set based on remote sensing images, area information, spectral features and soil information, and then dividing the sample set based on a preset ratio, one part is a training set for training the model, and the other part is a test set for testing and optimizing the model, thereby obtaining a land assessment model.

[0121] The land value assessment device may further include a processor and a memory. The receiving unit 31, the acquisition unit 32, the output unit 33, the 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.

[0122] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the value of the target land to be mortgaged can be evaluated by adjusting kernel parameters.

[0123] 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.

[0124] 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, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned land value assessment method.

[0125] 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 the above-mentioned land value assessment method.

[0126] According to another aspect of an embodiment of the present invention, a computer program product is provided. The computer program product includes a computer program, wherein when the computer program is executed by a processor, any one of the above land value assessment methods is implemented.

[0127] 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, wherein the loan request at least includes: target land to be mortgaged; obtaining a remote sensing image of the target land, and preprocessing the remote sensing image to obtain a preprocessed remote sensing image; inputting the preprocessed remote sensing image into a land evaluation model, and outputting area information and soil quality information of the target land; and conducting a value evaluation on the target land based on the area information and soil quality information of the target land.

[0128] 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 preprocessing the remote sensing image includes: performing radiation correction and atmospheric correction on the remote sensing image to obtain a corrected remote sensing image; extracting spectral features from the corrected remote sensing image, wherein the spectral features are used to analyze the soil quality information of the target land.

[0129] 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 conducting a value assessment on the target land based on the area information and soil quality information of the target land includes: dividing the target land based on the soil quality information of the target land to obtain N sub-areas, where N is a positive integer and the soil types of each sub-area are different; obtaining crops to be planted that match the sub-areas based on the geographic information of the target land and the soil quality information of each sub-area; conducting a value assessment on the target land based on the sub-area area of ​​the target land and the crops to be planted.

[0130] 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 is initialized with the following method steps: the steps of conducting a value assessment of the target land based on the sub-region area of ​​the target land and the crops to be planted shown include: for any sub-region, obtaining the average value of the crops to be planted corresponding to the sub-region within the historical target time period; calculating the value data of the sub-region based on the area of ​​the sub-region and the average value of the crops to be planted; accumulating the value data of all sub-regions of the target land to obtain the value data of the target land, and conducting a value assessment on the target land based on the value data of the target land to obtain a value assessment result.

[0131] 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: after obtaining the value assessment result, it also includes: if the value data of the target land in the value assessment result is greater than or equal to the loan amount of the loan request, approve the loan request; if the value data of the target land in the value assessment result is less than the loan amount of the loan request, reject the loan request and return a notification of loan failure to the user end.

[0132] 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: after the loan request is approved, it also includes: generating a crop planting strategy based on the crops to be planted that match the sub-area; and sending the crop planting strategy to the user end.

[0133] 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 is initialized with the following method steps: the land evaluation model is obtained by pre-training, and the steps of training the land evaluation model include: obtaining remote sensing images of land within a historical time period, and obtaining area information and soil quality information of the land; pre-processing and feature extraction of the remote sensing images to obtain pre-processed remote sensing images and spectral features; constructing a sample set based on the pre-processed remote sensing images and spectral features, area information and soil quality information; splitting the sample set based on a preset ratio to obtain a training set and a test set; training an initial neural network model based on the training set to obtain an initial land evaluation model; testing the initial land evaluation model based on the test set to obtain a test result, and when the test result indicates that the initial land evaluation model passes the test, obtaining a final land evaluation model.

[0134] Figure 4 FIG. 1 is a hardware structure block diagram of an electronic device (or mobile device) for a land value assessment method according to an embodiment of the present invention. Figure 4 As shown, the electronic device may include one or more ( Figure 4402a, 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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 land value assessment method, characterized in that: include: receiving a loan request from a user, wherein the loan request at least includes: target land to be mortgaged; Acquiring a remote sensing image of the target land, and preprocessing the remote sensing image to obtain a preprocessed remote sensing image; Inputting the preprocessed remote sensing image into a land assessment model, and outputting area information and soil quality information of the target land; The value of the target land is assessed based on the area information and soil quality information of the target land.

2. The method according to claim 1, characterized in that The step of preprocessing the remote sensing image comprises: Performing radiation correction and atmospheric correction on the remote sensing image to obtain a corrected remote sensing image; Spectral features are extracted from the corrected remote sensing image, wherein the spectral features are used to analyze soil quality information of the target land.

3. The method according to claim 1, characterized in that The step of evaluating the value of the target land based on the area information and soil quality information of the target land includes: Dividing the target land based on the soil quality information of the target land to obtain N sub-areas, where N is a positive integer and the soil types of the sub-areas are different; Acquire crops to be planted that match the sub-regions based on the geographic information of the target land and the soil quality information of each sub-region; The target land is valued based on the sub-region area of ​​the target land and the crops to be planted.

4. The method according to claim 3, characterized in that The step of evaluating the value of the target land based on the sub-region area of ​​the target land and the crops to be planted includes: For any of the sub-regions, obtaining the average value of the crops to be planted corresponding to the sub-region within a historical target time period; Calculating value data of the sub-region based on the area of ​​the sub-region and the average value of the crops to be planted; The value data of all sub-areas of the target land are accumulated to obtain the value data of the target land, and the value of the target land is evaluated based on the value data of the target land to obtain a value evaluation result.

5. The method according to claim 4, characterized in that After obtaining the value assessment results, it also includes: If the value data of the target land in the value assessment result is greater than or equal to the loan amount of the loan request, approve the loan request; In the case where the value data of the target land in the value assessment result is less than the loan amount of the loan request, the loan request is rejected and a notification of loan failure is returned to the user terminal.

6. The method according to claim 5, characterized in that After the loan request is approved, it also includes: generating a crop planting strategy based on the crops to be planted that match the sub-region; And send the crop planting strategy to the user end.

7. The method according to claim 1, characterized in that The land assessment model is obtained by pre-training, and the steps of training the land assessment model include: Obtain remote sensing images of land within a historical period, and obtain land area information and soil quality information; Preprocessing and feature extraction are performed on the remote sensing image to obtain a preprocessed remote sensing image and spectral features; Constructing a sample set based on the preprocessed remote sensing image and the spectral characteristics, the area information and the soil quality information; Splitting the sample set based on a preset ratio to obtain a training set and a test set; Training the initial neural network model based on the training set to obtain an initial land assessment model; The initial land evaluation model is tested based on the test set to obtain a test result, and when the test result indicates that the initial land evaluation model passes the test, the final land evaluation model is obtained.

8. A land value assessment device, characterized in that: include: The receiving unit is used to receive a loan request from a user, wherein the loan request at least includes: target land to be mortgaged; An acquisition unit, used for acquiring a remote sensing image of the target land, and preprocessing the remote sensing image to obtain a preprocessed remote sensing image; An output unit, used to input the preprocessed remote sensing image into a land assessment model, and output area information and soil quality information of the target land; An evaluation unit is used to evaluate the value of the target land based on the area information and soil quality information of the target land.

9. 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 land value assessment method described in any one of claims 1 to 7.

10. A computer program product, characterized in that The computer program product comprises a computer program, wherein the computer program implements the land value assessment method according to any one of claims 1 to 7 when executed by a processor.

Images