Planting industry insurance evaluation method and device, computer equipment and storage medium

Abstract

The embodiment of the invention belongs to the field of information technology and financial science and technology, and relates to a planting industry insurance evaluation method, which comprises the steps of obtaining satellite remote sensing data, an unmanned aerial vehicle image and ground sensor data of a target farmland, and integrating the satellite remote sensing data, the unmanned aerial vehicle image and the ground sensor data into comprehensive monitoring data of the target farmland, the comprehensive monitoring data comprises a multispectral image, multispectral data and topographic data; performing boundary identification according to the multispectral image and the topographic data to obtain boundary information of the target farmland; performing comprehensive analysis according to the multispectral image and the multispectral data, and determining crop type information and crop health state information of the target farmland; and evaluating the planting risk level of the target farmland according to the boundary information, the crop type information and the health state information, and generating a corresponding evaluation report. According to the invention, intelligent identification of farmland boundaries, crop types and crop health states is realized, and the accuracy and efficiency of planting industry insurance evaluation are improved.

Description

Technical Field

[0001] The present application relates to the fields of information technology and financial technology, and is applied to scenarios for evaluating crop insurance, and in particular, to a crop insurance evaluation method, device, computer equipment, and storage medium. Background Art

[0002] With the rapid development of computer technology and information technology, their applications in the field of financial technology are becoming increasingly widespread, especially in various scenarios in the insurance industry.

[0003] As an important form of agricultural insurance, crop insurance mainly provides risk protection against economic losses caused by various natural disasters and accidents that crops may encounter during their growth and initial processing. Therefore, the assessment process of crop insurance is of great significance to the risk management of insurance companies.

[0004] Currently, crop insurance assessment usually relies on manual on-site surveys and statistics by loan officers or professionals. This method is time-consuming and labor-intensive, not only has the problem of poor timeliness, but also easily leads to inaccurate data and low efficiency in the assessment process, thus affecting the insurance company's underwriting and claims efficiency. Summary of the invention

[0005] The purpose of the embodiments of the present application is to propose a crop insurance assessment method, device, computer equipment and storage medium to solve the technical problems of inaccurate data and low efficiency in the assessment process of crop insurance.

[0006] In order to solve the above technical problems, the present application embodiment provides a method for evaluating crop insurance, which adopts the following technical solution:

[0007] A method for evaluating crop insurance includes the following steps:

[0008] Acquire satellite remote sensing data, drone images and ground sensor data of target farmland, and integrate them into comprehensive monitoring data of the target farmland, wherein the comprehensive monitoring data includes multispectral images, multispectral data and terrain data;

[0009] Performing boundary recognition according to the multispectral image and the terrain data to obtain boundary information of the target farmland;

[0010] Performing a comprehensive analysis based on the multispectral image and the multispectral data to determine the crop type information and crop health status information of the target farmland;

[0011] According to the boundary information, the crop type information and the health status information, the planting risk level of the target farmland is evaluated, and a corresponding evaluation report is generated.

[0012] Furthermore, the step of performing comprehensive analysis based on the multispectral image and the multispectral data to determine the crop type information and crop health status information of the target farmland specifically includes:

[0013] Perform crop type identification according to the multispectral data to obtain the crop type information;

[0014] Calculating the growth status index of the target farmland according to the multispectral data;

[0015] The crop health status information is obtained by analyzing the multispectral image and the growth status index.

[0016] Furthermore, the step of analyzing the multispectral image and the growth status index to obtain the crop health status information specifically includes:

[0017] Performing image recognition analysis on the multispectral image to obtain early signs of pests and diseases in the target farmland;

[0018] According to the growth status indicator, evaluating the crop growth status of the target farmland;

[0019] The crop health status information is obtained by analyzing the early signs of the pests and diseases and the crop growth status.

[0020] Furthermore, the growth status index includes a normalized vegetation index, and the step of calculating the growth status index of the target farmland according to the multispectral data specifically includes:

[0021] Extracting reflectance data of near infrared band and red light band from the multispectral data;

[0022] The normalized vegetation index is calculated by the formula: The normalized vegetation index is calculated based on the reflectivity data as the growth status indicator, wherein NIR represents the reflectivity of the near infrared band and Red represents the reflectivity of the red band.

[0023] Furthermore, the step of performing crop type identification according to the multispectral data to obtain the crop type information specifically includes:

[0024] Obtain multispectral features corresponding to samples of known crop types;

[0025] constructing a crop type recognition model according to the multispectral features;

[0026] The multispectral data is input into the crop type recognition model to obtain the crop type information.

[0027] Furthermore, the step of performing boundary recognition according to the multispectral image and the terrain data to obtain boundary information of the target farmland specifically includes:

[0028] Inputting the multispectral image into a preset boundary recognition model to obtain the boundary line of the target farmland;

[0029] A terrain feature is extracted from the terrain data, the boundary line is corrected according to the terrain feature, and the corrected boundary line is used as the boundary information.

[0030] Furthermore, the step of evaluating the planting risk level of the target farmland according to the boundary information, the crop type information and the health status information, and generating a corresponding evaluation report specifically includes:

[0031] Inputting the boundary information, the crop type information and the health status information into a preset risk assessment model to obtain the planting risk level;

[0032] According to the planting risk level, selecting a target template for the target farmland from a preset planting industry assessment report template;

[0033] The target template is filled according to the boundary information, the crop type information and the health status information, and the filled target template is used as the evaluation report

[0034] In order to solve the above technical problems, the embodiment of the present application further provides a planting insurance assessment device, which adopts the following technical solution:

[0035] A planting insurance assessment device, comprising:

[0036] An acquisition module is used to acquire satellite remote sensing data, drone images and ground sensor data of the target farmland, and integrate them into comprehensive monitoring data of the target farmland, wherein the comprehensive monitoring data includes multispectral images, multispectral data and terrain data;

[0037] A boundary recognition module, used for performing boundary recognition according to the multispectral image and the terrain data to obtain boundary information of the target farmland;

[0038] A comprehensive analysis module, used for performing comprehensive analysis based on the multispectral image and the multispectral data to determine the crop type information and crop health status information of the target farmland;

[0039] An evaluation module is used to evaluate the planting risk level of the target farmland according to the boundary information, the crop type information and the health status information, and generate a corresponding evaluation report.

[0040] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0041] A computer device includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the above-mentioned crop insurance assessment method when executing the computer-readable instructions.

[0042] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0043] A computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the crop insurance assessment method as described above.

[0044] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0045] The crop insurance assessment method disclosed in the present application obtains satellite remote sensing data, drone images and ground sensor data of the target farmland, and integrates them into the comprehensive monitoring data of the target farmland, wherein the comprehensive monitoring data includes multispectral images, multispectral data and terrain data; then, boundary identification is performed according to the multispectral images and the terrain data to obtain the boundary information of the target farmland; then, a comprehensive analysis is performed according to the multispectral images and the multispectral data to determine the crop type information and crop health status information of the target farmland; thus, according to the boundary information, the crop type information and the health status information, the planting risk level of the target farmland is assessed, and a corresponding assessment report is generated. The present application realizes the intelligent identification of farmland boundaries, crop types and crop health status through the comprehensive monitoring data obtained by integrating satellite remote sensing data, drone images and ground sensor data of farmland, so that the assessment process of crop insurance no longer needs to rely on manual on-site investigation and statistics, which greatly improves the accuracy and efficiency of crop insurance assessment and enhances the risk management capabilities of insurance companies. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0047] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0048] Figure 2 is a flow chart of an embodiment of a method for evaluating crop insurance according to the present application;

[0049] Figure 3 It is a structural schematic diagram of an embodiment of a planting insurance assessment device according to the present application;

[0050] Figure 4 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0051] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0052] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0053] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0054] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0055] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0056] The terminal devices 101, 102, and 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 (Moving Picture Experts Group Audio Layer III) players, MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, and the like.

[0057] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0058] It should be noted that the crop insurance assessment method provided in the embodiment of the present application is generally executed by a server, and accordingly, the crop insurance assessment device is generally arranged in the server.

[0059] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0060] Continue to refer Figure 2 , shows a flow chart of an embodiment of a method for evaluating crop insurance according to the present application. The method for evaluating crop insurance comprises the following steps:

[0061] Step S201, obtaining satellite remote sensing data, drone images and ground sensor data of the target farmland, and integrating them into comprehensive monitoring data of the target farmland, wherein the comprehensive monitoring data includes multispectral images, multispectral data and terrain data.

[0062] In this embodiment, the planting insurance assessment method is executed on an electronic device (eg Figure 1 The server shown in the figure) can send or receive data through a wired connection or a wireless connection. It should be noted that the above wireless connection method may include but is not limited to 3G / 4G / 5G connection, Wi-Fi connection, Bluetooth connection, Wi MAX connection, Zigbee connection, UWB (ultrawi deband) connection, and other wireless connection methods currently known or to be developed in the future.

[0063] It should be noted that the insurance industry is an important part of the financial industry. With the development of financial technology, it has been increasingly used in various business scenarios of the insurance industry. This also includes crop insurance, which is a form of agricultural insurance specifically for plant production activities such as crops and trees, and aims to provide economic protection for agricultural producers to reduce economic losses caused by unforeseen risk events such as natural disasters, pests and diseases.

[0064] Specifically, in the crop insurance assessment process, the farmland that needs to be assessed can be determined first, and taken as the target farmland, and the satellite remote sensing data, drone images and ground sensor data of the target farmland can be obtained from multiple data sources, wherein the satellite remote sensing data comes from the satellite platform, the drone images come from the camera carried by the drone, and the ground sensor data comes from the pre-laid ground sensors; by integrating the satellite remote sensing data, drone images and ground sensor data of the target farmland, the comprehensive monitoring data of the target farmland can be obtained through data fusion, and the comprehensive monitoring data includes at least multispectral images, multispectral data and terrain data, wherein the satellite remote sensing data can provide multispectral images and multispectral data, drone images can provide multispectral images, and the satellite remote sensing data, drone images and ground sensor data can all provide terrain data. Subsequently, based on the multispectral images, multispectral data and terrain data, the boundary information, crop type information and crop health status information of the target farmland can be obtained intelligently.

[0065] Optionally, based on the comprehensive monitoring data, combined with GIS (geographic information system) and AI image recognition algorithms, it is possible to automatically draw high-precision maps of the target farmland. The high-precision maps can quickly and accurately capture information such as farmland boundaries, crop types, and crop health status, greatly improving accuracy and efficiency compared to traditional manual measurements.

[0066] It can be understood that there is a close correlation between multispectral images and multispectral data, and the two can be converted into each other. Multispectral data can be extracted by processing multispectral images, and multispectral data can also be used to generate multispectral images. Multispectral images are data in the form of images, while multispectral data are data stored in numerical form. The data is reflectance data of different bands, which can be used to distinguish different types of crops and reflect the growth conditions of crops.

[0067] In addition, among the above-mentioned satellite remote sensing data, drone images and ground sensor data, satellite remote sensing data may also include but are not limited to high-resolution images, which can provide clear surface details and help identify farmland boundaries and crop types; drone images may also include but are not limited to high-definition RGB images and thermal infrared images, among which high-definition RGB images can be used to visualize the appearance and structure of farmland, and thermal infrared images can be used to detect temperature anomalies and help find potential problem areas; and ground sensor data include but are not limited to soil moisture, soil temperature, soil conductivity and other environmental parameters, among which soil moisture can be used to assess irrigation needs and water management, soil temperature can affect crop growth and root development, soil conductivity can reflect soil salt content and affect crop health, and other environmental parameters include light intensity, wind speed, rainfall, etc., which are very important for assessing crop growth conditions.

[0068] Step S202: performing boundary recognition based on the multispectral image and the terrain data to obtain boundary information of the target farmland.

[0069] It should be noted that terrain data comes from elevation data, which can be collected by satellites or drones. For example, elevation data can be obtained by using radar interferometry (InSAR) technology through satellite sensors, or by using laser radar (LiDAR) or structured light scanning technology carried by drones to obtain high-precision elevation data.

[0070] Specifically, after obtaining the comprehensive monitoring data of the target farmland, the multispectral image is input into a preset boundary recognition model. The boundary recognition model can select a deep learning model suitable for image segmentation tasks, such as U-Net or its variants. The boundary line of the target farmland is determined by the output of the boundary recognition model, and then the terrain features such as slope and slope direction are extracted from the terrain data. The boundary line is corrected according to the terrain features, and finally the corrected boundary line is used as the boundary information of the target farmland.

[0071] Step S203, performing a comprehensive analysis based on the multispectral image and the multispectral data to determine the crop type information and crop health status information of the target farmland.

[0072] Specifically, the main purpose of the comprehensive analysis is to analyze the type and health status of crops, wherein crop type information refers to specific characteristics and related information used to distinguish different types of crops, including crop name, crop category, botanical attributes of crops, crop uses and other information, wherein crop categories can be divided into food crops, cash crops, fodder crops, green manure crops, etc., and the botanical attributes of crops can include the plant family and plant class to which the crops belong, and crop uses include edible, industrial, medicinal, ornamental, energy crops, etc.; crop health status information refers to the overall growth status of crops during the growth process and whether there are any physiological or pathological problems, including growth status, appearance characteristics, physiological indicators, biotic and abiotic stresses and other information, wherein growth status includes growth rate, growth uniformity, development stage, etc., appearance characteristics include leaf color, leaf texture, leaf morphology, leaf texture, etc., physiological indicators may include photosynthesis efficiency, chlorophyll content, transpiration rate, growth hormone level, etc., biotic and abiotic stresses include diseases, insect pests, weed competition, adverse stress, etc.

[0073] Step S204, evaluating the planting risk level of the target farmland according to the boundary information, the crop type information and the health status information, and generating a corresponding evaluation report.

[0074] Specifically, in the crop insurance assessment process, the risk level can be divided into multiple crop risk levels in advance, such as low risk, medium risk, and high risk. After obtaining the boundary information, crop type information, and health status information of the target farmland, the preset risk assessment model can be used to perform risk assessment based on the boundary information, crop type information, and health status information to determine the crop risk level of the target farmland. Different crop assessment report templates are pre-set for different crop risk levels. According to the crop risk level of the target farmland, the corresponding crop assessment report template can be selected from each crop assessment report template as the target template for the target farmland, and then the boundary information, crop type information, and health status information are filled into the target template to obtain the corresponding assessment report for the target farmland.

[0075] It is understandable that the assessment report is a customized report for the target farmland, which may include modules such as crop distribution, crop health status, risk prediction, etc. It may also propose preventive measures and suggestions for different planting risk levels, and display insurance policy adjustment suggestions. Insurance companies can adjust the insurance policies for the target farmland according to the insurance policy adjustment suggestions, including customized insurance plans and rates, etc., as a basis for claims.

[0076] Optionally, during the crop insurance assessment process, the insurance company can update the risk assessment model based on the real-time comprehensive monitoring data of the target farmland, and can dynamically adjust the rates and terms of the crop insurance products to enhance the flexibility and adaptability of the crop insurance products.

[0077] This application achieves intelligent identification of farmland boundaries, crop types and crop health status through comprehensive monitoring data obtained by integrating satellite remote sensing data, drone images and ground sensor data of farmland, so that the assessment process of crop insurance no longer needs to rely on manual on-site investigation and statistics, which greatly improves the accuracy and efficiency of crop insurance assessment and enhances the risk management capabilities of insurance companies.

[0078] In some optional implementations of this embodiment, the step of performing comprehensive analysis based on the multispectral image and the multispectral data to determine the crop type information and crop health status information of the target farmland includes:

[0079] Perform crop type identification according to the multispectral data to obtain the crop type information;

[0080] Calculating the growth status index of the target farmland according to the multispectral data;

[0081] The crop health status information is obtained by analyzing the multispectral image and the growth status index.

[0082] In this embodiment, two steps are mainly included. The first step is to obtain crop type information of the target farmland, and the second step is to obtain crop health status information of the target farmland. Specifically, in the first step, feature data can be extracted from the multispectral data, and the feature data can be input into a pre-trained crop type recognition model, which is a random forest model suitable for multi-classification problems. Through the crop type recognition model, the crop type to which each area or each pixel of the target farmland belongs can be output to form the crop type information of the target farmland; in the second step, it is first necessary to extract the spectral features of the near-infrared band and the red light band from the multispectral data, calculate the normalized vegetation index (NDVI) of the target farmland as the growth status indicator of the target farmland, and evaluate the crop growth status of the target farmland based on the growth status indicator, such as the greenness and growth vitality of the crop. Secondly, it is necessary to perform image recognition analysis on the multispectral image to obtain early signs of pests and diseases in the target farmland, such as whether there are spots and defects caused by pests and diseases. Finally, based on the crop growth status and early signs of pests and diseases in the target farmland, the crop health status information of the target farmland can be analyzed to provide support for subsequent evaluation reports.

[0083] This application can intelligently obtain crop type information and crop health status information of farmland by identifying and analyzing multispectral images and multispectral data integrated in comprehensive monitoring data, thereby eliminating the need to rely on manual on-site investigations and statistics, greatly improving the accuracy and efficiency of crop insurance assessments.

[0084] In some optional implementations of this embodiment, the step of analyzing the multispectral image and the growth status index to obtain the crop health status information includes:

[0085] Performing image recognition analysis on the multispectral image to obtain early signs of pests and diseases in the target farmland;

[0086] According to the growth status indicator, evaluating the crop growth status of the target farmland;

[0087] The crop health status information is obtained by analyzing the early signs of the pests and diseases and the crop growth status.

[0088] In this embodiment, a preset image recognition model can be used to perform image recognition on the multispectral image to obtain early signs of pests and diseases in the target farmland. Specifically, an initial convolutional neural network (CNN) model can be established in advance, and the sample features of specific pests and diseases are used as a training set to train the model, and the trained model is used as the above-mentioned image recognition model. After the image features are extracted from the multispectral image, the image features can be input into the image recognition model, and the image recognition model outputs whether there are pest and disease features in each area or each pixel of the target farmland, such as whether there are spots or defects on the crops, etc., as early signs of pests and diseases in the target farmland. At the same time, the crop growth status of the target farmland is evaluated according to the growth status index of the target farmland. The growth status index can be the normalized difference vegetation index (NDVI). Since the normalized vegetation index is NDVI, the target crop growth status index can be used as the target crop growth status index. The upper and lower limits of the index are 1 and -1 respectively, and it can be divided into different intervals according to the preset thresholds, representing different crop growth states. For example, the crop growth state is divided into three intervals of good, general, and poor according to the preset thresholds. When evaluating the crop growth state, the normalized vegetation index of the target farmland is compared with the preset threshold to determine the interval to which the normalized vegetation index of the target farmland belongs, thereby determining the crop growth state of the target farmland, which is used to reflect the greenness and growth vitality of the crops. Finally, the early signs of pests and diseases and the crop growth state of the target farmland are integrated and analyzed to obtain the crop health status information of the target farmland, which is used to reflect the health status of the crops in the target farmland.

[0089] This application uses image recognition and indicator evaluation to intelligently obtain early signs of pests and diseases and crop growth status in farmland, and combines the two for analysis to obtain crop health status information in farmland, thereby eliminating the need to rely on manual on-site investigations and statistics, greatly improving the accuracy and efficiency of crop insurance assessments, and can subsequently serve as a basis for risk management recommendations, enhancing the risk management capabilities of insurance companies.

[0090] In some optional implementations of this embodiment, the growth status index includes a normalized vegetation index, and the step of calculating the growth status index of the target farmland according to the multispectral data includes:

[0091] Extracting reflectance data of near infrared band and red light band from the multispectral data;

[0092] The normalized vegetation index is calculated by the formula: The normalized vegetation index is calculated based on the reflectivity data as the growth status indicator, wherein NIR represents the reflectivity of the near infrared band and Red represents the reflectivity of the red band.

[0093] In this embodiment, the growth status index includes a normalized vegetation index, which can be calculated based on the reflectance data of the near infrared band and the red light band in the multispectral data. Specifically, the normalized vegetation index (NDVI) is generally used to evaluate the health status and density of vegetation in remote sensing analysis, and can be calculated by the following formula: Among them, NIR represents the reflectivity of the near-infrared band, and Red represents the reflectivity of the red band.

[0094] It is understandable that the results of the Normalized Difference Vegetation Index usually range between -1 and 1. Healthy green vegetation usually shows higher NDVI values ​​due to its strong reflection of the near-infrared band and absorption of most of the red light, while non-vegetation covered areas (such as water bodies, bare soil, etc.) usually show lower NDVI values.

[0095] Optionally, the growth status index may also include other vegetation indices, such as the normalized green vegetation index (GNDVI), the chlorophyll absorption ratio index (CAR I), etc. The normalized green vegetation index is calculated by the formula: The normalized green vegetation index (GNDVI) can be calculated, where NIR represents the reflectance of the near-infrared band and Green represents the reflectance of the green band; the chlorophyll absorption ratio index is calculated using the formula: The chlorophyll absorption ratio index (CAR I) can be calculated, where R blue Indicates the reflectivity in the blue band (usually around 450nm), R redIndicates the reflectivity of the red band (usually around 680nm), R green Indicates the reflectance of the green band (usually around 550nm). The above growth status indicators can more comprehensively reflect the growth status of crops.

[0096] This application evaluates specific growth status indicators to obtain the crop growth status of the farmland, which can then be combined with early signs of diseases and insect pests in the farmland for analysis to obtain crop health status information on the farmland, thereby improving the accuracy of crop health status information and eliminating the need to rely on manual on-site surveys and statistics, thereby improving the accuracy and efficiency of crop insurance assessments.

[0097] In some optional implementations of this embodiment, the step of performing crop type identification according to the multispectral data to obtain the crop type information includes:

[0098] Obtain multispectral features corresponding to samples of known crop types;

[0099] constructing a crop type recognition model according to the multispectral features;

[0100] The multispectral data is input into the crop type recognition model to obtain the crop type information.

[0101] In this embodiment, the crop type recognition model adopts a machine learning algorithm suitable for multi-classification problems, for example, a random forest algorithm which is a commonly used supervised learning algorithm. First, an initial random forest model can be established, and the multispectral features corresponding to samples of known crop types are used as a training set to train the model, and the trained model is used as the above-mentioned crop type recognition model. Feature data can then be extracted from the multispectral data and input into the crop type recognition model, so that crop type recognition is performed according to the crop type recognition model, and the crop type of each area or each pixel of the target farmland is output as the crop type information of the target farmland.

[0102] Through the crop type identification model, this application can intelligently obtain the crop type information of the farmland, thus eliminating the need to rely on manual on-site investigation and statistics, greatly improving the accuracy and efficiency of crop insurance assessment, and can subsequently serve as a basis for risk management recommendations, enhancing the risk management capabilities of insurance companies.

[0103] In some optional implementations of this embodiment, the step of performing boundary recognition according to the multispectral image and the terrain data to obtain boundary information of the target farmland includes:

[0104] Inputting the multispectral image into a preset boundary recognition model to obtain the boundary line of the target farmland;

[0105] A terrain feature is extracted from the terrain data, the boundary line is corrected according to the terrain feature, and the corrected boundary line is used as the boundary information.

[0106] In this embodiment, the preset boundary recognition model is a deep learning model suitable for image segmentation tasks, such as U-Net or its variants, which is particularly suitable for processing pixel-level classification tasks. First, an initial U-Net model can be established, and then the labeled farmland boundary data set is used as a training set to train the model, so that the trained model is used as the above-mentioned boundary recognition model. Specifically, the labeled farmland boundary data set usually includes examples of farmland boundaries under various terrain conditions. Using it as a training set can ensure that the boundary recognition model can accurately distinguish between farmland boundaries and non-farmland areas. After obtaining the boundary recognition model, it is necessary to extract image features from the multispectral image and input the image features into the boundary recognition model to output the possibility of each pixel being a boundary through the boundary recognition model, thereby determining the boundary line of the target farmland. The terrain data comes from the elevation data, which can be collected by satellites or drones and integrated into the comprehensive monitoring data. Terrain features, such as slope, slope direction, etc., can be extracted from the terrain data, and then the boundary line is corrected according to the terrain features. Finally, the corrected boundary line can be used as the boundary information of the target farmland.

[0107] This application determines the boundary line of farmland through a boundary recognition model and uses terrain data for correction. It can intelligently obtain the boundary information of farmland, thereby eliminating the need to rely on manual on-site investigation and statistics, thereby improving the accuracy and efficiency of crop insurance assessment, and can subsequently serve as a basis for risk management recommendations, enhancing the risk management capabilities of insurance companies.

[0108] In some optional implementations of this embodiment, the step of evaluating the planting risk level of the target farmland according to the boundary information, the crop type information and the health status information, and generating a corresponding evaluation report includes:

[0109] Inputting the boundary information, the crop type information and the health status information into a preset risk assessment model to obtain the planting risk level;

[0110] According to the planting risk level, selecting a target template for the target farmland from a preset planting industry assessment report template;

[0111] The target template is filled according to the boundary information, the crop type information and the health status information, and the filled target template is used as the evaluation report.

[0112] In this embodiment, the preset risk assessment model can be a statistical model or a machine learning model, such as logistic regression, decision tree, random forest, etc. Specifically, if the risk assessment model belongs to a machine learning model, historical data can be used to train the model and adjust the parameters to optimize the model performance to obtain the risk assessment model, which divides the risk level into multiple planting risk levels in advance, such as low risk, medium risk, and high risk. After extracting features according to the boundary information, crop type information, and health status information of the target farmland to obtain a feature data set, the feature data set can be input into the risk assessment model to obtain the planting risk level of the target farmland. For the planting risk level of the target farmland, a corresponding planting assessment report template can be selected from each preset planting assessment report template, and the boundary information, crop type information, and health status information are filled into the template to generate an assessment report corresponding to the target farmland. The assessment report can also add preventive measures and suggestions corresponding to the planting risk level of the target farmland. According to the assessment report, the insurance company can dynamically adjust the insurance strategy for the target farmland to rationalize the subsequent claims process, and can also dynamically adjust the rates and terms of the planting insurance products to achieve effective risk management.

[0113] This application provides a comprehensive and accurate assessment report by conducting risk assessment on intelligently obtained farmland boundary information, crop type information and health status information, so that the assessment process of crop insurance no longer needs to rely on manual on-site investigation and statistics, and improves the accuracy and efficiency of crop insurance assessment, while rationalizing the insurance policies of insurance companies and enhancing the risk management capabilities of insurance companies.

[0114] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0115] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0116] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0117] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0118] Further references Figure 3 , as a response to the above Figure 2 In order to realize the method shown in the figure, the present application provides an embodiment of a planting insurance assessment device, and the device embodiment is Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0119] like Figure 3 As shown, the crop insurance assessment device 300 described in this embodiment includes: an acquisition module 301, a boundary recognition module 302, a comprehensive analysis module 303 and an assessment module 304. Among them:

[0120] An acquisition module 301 is used to acquire satellite remote sensing data, drone images and ground sensor data of a target farmland, and integrate them into comprehensive monitoring data of the target farmland, wherein the comprehensive monitoring data includes multispectral images, multispectral data and terrain data;

[0121] A boundary recognition module 302 is used to perform boundary recognition based on the multispectral image and the terrain data to obtain boundary information of the target farmland;

[0122] A comprehensive analysis module 303 is used to perform comprehensive analysis based on the multispectral image and the multispectral data to determine the crop type information and crop health status information of the target farmland;

[0123] The evaluation module 304 is used to evaluate the planting risk level of the target farmland according to the boundary information, the crop type information and the health status information, and generate a corresponding evaluation report.

[0124] The crop insurance assessment device provided in this application realizes intelligent identification of farmland boundaries, crop types and crop health status through comprehensive monitoring data obtained by integrating satellite remote sensing data of farmland, drone images and ground sensor data, so that the assessment process of crop insurance no longer needs to rely on manual on-site investigation and statistics, which greatly improves the accuracy and efficiency of crop insurance assessment and enhances the risk management capabilities of insurance companies.

[0125] In some optional implementations of this embodiment, the comprehensive analysis module 303 is further used to:

[0126] Perform crop type identification according to the multispectral data to obtain the crop type information;

[0127] Calculating the growth status index of the target farmland according to the multispectral data;

[0128] The crop health status information is obtained by analyzing the multispectral image and the growth status index.

[0129] The crop insurance assessment device provided in the present application can intelligently obtain crop type information and crop health status information of farmland by identifying and analyzing multispectral images and multispectral data integrated in the comprehensive monitoring data, thereby eliminating the need to rely on manual on-site investigation and statistics, greatly improving the accuracy and efficiency of crop insurance assessment.

[0130] In some optional implementations of this embodiment, the comprehensive analysis module 303 is further used to:

[0131] Performing image recognition analysis on the multispectral image to obtain early signs of pests and diseases in the target farmland;

[0132] According to the growth status indicator, evaluating the growth status of the crops in the target farmland;

[0133] The crop health status information is obtained by analyzing the early signs of the pests and diseases and the crop growth status.

[0134] The crop insurance assessment device provided in the present application intelligently obtains early signs of pests and diseases and crop growth status in farmland through image recognition and indicator evaluation, and combines the two for analysis to obtain crop health status information in farmland, thereby eliminating the need to rely on manual on-site investigation and statistics, greatly improving the accuracy and efficiency of crop insurance assessment, and can subsequently serve as a basis for risk management recommendations, thereby enhancing the risk management capabilities of insurance companies.

[0135] In some optional implementations of this embodiment, the above growth status indicator includes a normalized vegetation index, and the comprehensive analysis module 303 is further used to:

[0136] Extracting reflectance data of near infrared band and red light band from the multispectral data;

[0137] The normalized vegetation index is calculated by the formula: The normalized vegetation index is calculated based on the reflectivity data as the growth status indicator, wherein NIR represents the reflectivity of the near infrared band and Red represents the reflectivity of the red band.

[0138] The crop insurance assessment device provided in the present application evaluates specific growth status indicators to obtain the crop growth status of the farmland, which can be subsequently combined with early signs of diseases and insect pests in the farmland for analysis to obtain the crop health status information of the farmland, thereby improving the accuracy of the crop health status information and no longer requiring manual on-site investigation and statistics, thereby improving the accuracy and efficiency of crop insurance assessments.

[0139] In some optional implementations of this embodiment, the comprehensive analysis module 303 is further used to:

[0140] Obtain multispectral features corresponding to samples of known crop types;

[0141] constructing a crop type recognition model according to the multispectral features;

[0142] The multispectral data is input into the crop type recognition model to obtain the crop type information.

[0143] The crop insurance assessment device provided in this application can intelligently obtain crop type information of farmland through a crop type recognition model, thereby eliminating the need to rely on manual on-site investigation and statistics, greatly improving the accuracy and efficiency of crop insurance assessment, and can subsequently be used as a basis for risk management recommendations, thereby enhancing the risk management capabilities of insurance companies.

[0144] In some optional implementations of this embodiment, the boundary identification module 302 is further used to:

[0145] Inputting the multispectral image into a preset boundary recognition model to obtain the boundary line of the target farmland;

[0146] A terrain feature is extracted from the terrain data, the boundary line is corrected according to the terrain feature, and the corrected boundary line is used as the boundary information.

[0147] The crop insurance assessment device provided in the present application determines the boundary line of the farmland through a boundary recognition model and uses terrain data for correction. It can intelligently obtain the boundary information of the farmland, thereby eliminating the need to rely on manual on-site investigation and statistics, thereby improving the accuracy and efficiency of the crop insurance assessment, and can subsequently be used as a basis for risk management recommendations, thereby enhancing the risk management capabilities of insurance companies.

[0148] In some optional implementations of this embodiment, the evaluation module 304 is further configured to:

[0149] Inputting the boundary information, the crop type information and the health status information into a preset risk assessment model to obtain the planting risk level;

[0150] According to the planting risk level, selecting a target template for the target farmland from a preset planting industry assessment report template;

[0151] The target template is filled according to the boundary information, the crop type information and the health status information, and the filled target template is used as the evaluation report.

[0152] The crop insurance assessment device provided in the present application provides a comprehensive and accurate assessment report by performing risk assessment on the intelligently obtained farmland boundary information, crop type information and health status information, so that the assessment process of crop insurance no longer needs to rely on manual on-site investigation and statistics, and improves the accuracy and efficiency of crop insurance assessment, while rationalizing the insurance policy of the insurance company and enhancing the risk management ability of the insurance company.

[0153] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0154] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 with components 41-43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital processors (DSPs), embedded devices, etc.

[0155] The computer device may be a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with the user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0156] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk equipped on the computer device 4, a smart memory card (Smart Med ia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of the crop insurance assessment method, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0157] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run computer-readable instructions or process data stored in the memory 41, such as computer-readable instructions for running the crop insurance assessment method.

[0158] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0159] The computer equipment provided in this application realizes intelligent identification of farmland boundaries, crop types and crop health status through comprehensive monitoring data obtained by integrating satellite remote sensing data, drone images and ground sensor data of farmland, so that the assessment process of crop insurance no longer needs to rely on manual on-site investigation and statistics, which greatly improves the accuracy and efficiency of crop insurance assessment and enhances the risk management capabilities of insurance companies.

[0160] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the crop insurance assessment method as described above.

[0161] The computer-readable storage medium provided in this application realizes intelligent identification of farmland boundaries, crop types and crop health status through comprehensive monitoring data obtained by integrating satellite remote sensing data, drone images and ground sensor data of farmland, so that the assessment process of crop insurance no longer needs to rely on manual on-site investigation and statistics, which greatly improves the accuracy and efficiency of crop insurance assessment and enhances the risk management capabilities of insurance companies.

[0162] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0163] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A method for assessing crop insurance. It is characterized in that The steps include: Acquire satellite remote sensing data, drone images and ground sensor data of target farmland, and integrate them into comprehensive monitoring data of the target farmland, wherein the comprehensive monitoring data includes multispectral images, multispectral data and terrain data; Performing boundary recognition according to the multispectral image and the terrain data to obtain boundary information of the target farmland; Performing a comprehensive analysis based on the multispectral image and the multispectral data to determine the crop type information and crop health status information of the target farmland; According to the boundary information, the crop type information and the health status information, the planting risk level of the target farmland is evaluated, and a corresponding evaluation report is generated.

2. The crop insurance assessment method according to claim 1, It is characterized in that The step of performing comprehensive analysis based on the multispectral image and the multispectral data to determine the crop type information and crop health status information of the target farmland specifically includes: Perform crop type identification according to the multispectral data to obtain the crop type information; Calculating the growth status index of the target farmland according to the multispectral data; The crop health status information is obtained by analyzing the multispectral image and the growth status index.

3. The crop insurance assessment method according to claim 2, It is characterized in that The step of analyzing the multispectral image and the growth status index to obtain the crop health status information specifically includes: Performing image recognition analysis on the multispectral image to obtain early signs of pests and diseases in the target farmland; According to the growth status indicator, evaluating the crop growth status of the target farmland; The crop health status information is obtained by analyzing the early signs of the pests and diseases and the crop growth status.

4. The crop insurance assessment method according to claim 2, It is characterized in that The growth status index includes a normalized vegetation index. The step of calculating the growth status index of the target farmland according to the multispectral data specifically includes: Extracting reflectance data of near infrared band and red light band from the multispectral data; The normalized vegetation index is calculated by the formula: The normalized vegetation index is calculated based on the reflectivity data as the growth status indicator, wherein NIR represents the reflectivity of the near infrared band and Red represents the reflectivity of the red band.

5. The crop insurance assessment method according to claim 2, It is characterized in that The step of performing crop type identification according to the multispectral data to obtain the crop type information specifically includes: Obtain multispectral features corresponding to samples of known crop types; constructing a crop type recognition model according to the multispectral features; The multispectral data is input into the crop type recognition model to obtain the crop type information.

6. The crop insurance assessment method according to claim 1, It is characterized in that The step of performing boundary recognition according to the multispectral image and the terrain data to obtain boundary information of the target farmland specifically includes: Inputting the multispectral image into a preset boundary recognition model to obtain the boundary line of the target farmland; A terrain feature is extracted from the terrain data, the boundary line is corrected according to the terrain feature, and the corrected boundary line is used as the boundary information.

7. The crop insurance assessment method according to any one of claims 1 to 6, It is characterized in that The step of evaluating the planting risk level of the target farmland according to the boundary information, the crop type information and the health status information, and generating a corresponding evaluation report specifically includes: Inputting the boundary information, the crop type information and the health status information into a preset risk assessment model to obtain the planting risk level; According to the planting risk level, selecting a target template for the target farmland from a preset planting industry assessment report template; The target template is filled according to the boundary information, the crop type information and the health status information, and the filled target template is used as the evaluation report.

8. A planting insurance assessment device, It is characterized in that include: An acquisition module is used to acquire satellite remote sensing data, drone images and ground sensor data of the target farmland, and integrate them into comprehensive monitoring data of the target farmland, wherein the comprehensive monitoring data includes multispectral images, multispectral data and terrain data; A boundary recognition module, used for performing boundary recognition according to the multispectral image and the terrain data to obtain boundary information of the target farmland; A comprehensive analysis module, used for performing comprehensive analysis based on the multispectral image and the multispectral data to determine the crop type information and crop health status information of the target farmland; An evaluation module is used to evaluate the planting risk level of the target farmland according to the boundary information, the crop type information and the health status information, and generate a corresponding evaluation report.

9. A computer device, It is characterized in that It comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the crop insurance assessment method as described in any one of claims 1 to 7 when executing the computer-readable instructions.

10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the crop insurance assessment method according to any one of claims 1 to 7.

Images