Farmland planting data analysis method and device, computer equipment and storage medium

Abstract

The invention belongs to the field of artificial intelligence, and relates to a farmland planting data analysis method, which comprises the following steps: when a survey and loss assessment signal is received, acquiring a plurality of farmland planting images in real time, and preprocessing all the farmland planting images to obtain a plurality of images to be subjected to loss assessment; the images to be subjected to loss assessment are sequentially input into a preset loss assessment model for loss analysis, and multiple pieces of initial crop loss data output by the loss assessment model are obtained; performing screening operation on all the initial crop loss data to obtain target loss data; and performing claim analysis based on the target loss data to obtain a crop claim value. The invention further provides a farmland planting data analysis device, computer equipment and a storage medium. In addition, the invention also relates to a block chain technology, and the collected farmland planting image can be stored in a block chain. The method solves the problems of low claim settlement efficiency and insufficient claim settlement accuracy in the planting insurance claim settlement process.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to methods, devices, computer equipment and storage media for analyzing farmland planting data. Background Art

[0002] The traditional crop insurance claims process usually requires insurance personnel to go to the farmland for on-site inspection and assessment. This process includes communicating with farmers, measuring field parameters, collecting soil and crop samples, and filling out relevant reports, which increases the complexity and cost of the claims process. Factors such as weather conditions, remote geographical locations, and insufficient human resources often make it difficult for the survey work to proceed smoothly, affecting the timeliness and effectiveness of claims. In addition, the traditional claims process is also interfered by human factors, such as subjective judgments and inconsistent evaluation standards, which may lead to unfair or inaccurate claims results.

[0003] Therefore, the traditional crop insurance claims process has the problems of low claims efficiency and insufficient claims accuracy. An efficient and accurate crop insurance claims method is urgently needed. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose a method, device, computer equipment and storage medium for analyzing farmland planting data to solve the problems of low claims efficiency and insufficient claims accuracy in the crop insurance claims process.

[0005] In order to solve the above technical problems, the present application embodiment provides a method for analyzing farmland planting data, which adopts the following technical solution:

[0006] When receiving a damage assessment signal, multiple farmland planting images are collected in real time, and all the farmland planting images are preprocessed to obtain multiple images to be assessed;

[0007] Inputting the images to be assessed for damage into a preset damage assessment model in sequence for loss analysis, and obtaining a plurality of initial crop loss data output by the damage assessment model;

[0008] Performing a screening operation on all the initial crop loss data to obtain target crop loss data;

[0009] Claim calculation is performed based on the target loss data to obtain the crop claim value.

[0010] Furthermore, when the damage assessment signal is received, the step of collecting multiple farmland planting images in real time includes:

[0011] When receiving the damage assessment signal, the sending location of the damage assessment signal and the machine location of the standby UAV are obtained in real time;

[0012] According to the sending position and the machine position, the standby drone is selected to determine the drone that performs the collection task as the collection drone;

[0013] Generate a flight path and shooting parameters based on the sending position and the machine position, and send a flight signal to the collection drone, wherein the flight signal carries the flight path and the shooting parameters;

[0014] Receive the farmland planting image transmitted by the acquisition drone.

[0015] Furthermore, the step of preprocessing all the farmland planting images to obtain a plurality of images to be determined as damaged includes:

[0016] Acquire image parameters carried by each of the farmland planting images, wherein the image parameters include shooting height;

[0017] Classifying the farmland planting images according to the shooting heights to obtain a plurality of planting image groups;

[0018] Deduplication processing is performed on the farmland planting images in each of the planting image groups to obtain multiple target image groups;

[0019] Based on the shooting height corresponding to the target image group, the target image group is divided into a short-distance image group and a long-distance image group;

[0020] An image enhancement operation is performed on the long-distance image group based on the short-distance image group to obtain a target image group, and images in the target image group are used as the images to be determined as damaged.

[0021] Furthermore, the step of performing an image enhancement operation on the long-distance image group based on the short-distance image group to obtain a target image group includes:

[0022] Extracting image features and image details from the close-range image group;

[0023] Performing a feature matching operation on the image feature and the long-distance image group to obtain a region to be enhanced of the long-distance image group;

[0024] Injecting the image details into the corresponding area to be enhanced to obtain an initial enhanced image group;

[0025] Respectively identifying the contrast and brightness of the close-range image group to obtain a reference contrast and a reference brightness;

[0026] The initial enhanced image group is adjusted based on the reference contrast and the reference brightness to obtain the target image group.

[0027] Furthermore, the damage assessment model includes a Faster R-CNN model, and the step of sequentially inputting the damage assessment images into a preset damage assessment model for loss analysis to obtain a plurality of initial crop loss data output by the damage assessment model includes:

[0028] Performing a histogram equalization operation on the damage-to-be-assessed image to obtain a target damage-assessed image;

[0029] The target damage assessment image is input into the pre-trained Faster R-CNN model to obtain the initial crop loss data output by the Faster R-CNN model.

[0030] Furthermore, the step of screening all the initial crop loss data to obtain target crop loss data includes:

[0031] Detecting whether there are abnormal data in all the initial crop loss data by using a preset abnormality detection model;

[0032] If there is abnormal data, the initial crop loss data corresponding to the abnormal data is deleted, and the remaining initial crop loss data is used as the intermediate crop loss data;

[0033] If there is no abnormal data, all the initial crop loss data are directly used as the intermediate crop loss data;

[0034] The target loss data is generated based on the intermediate crop loss data.

[0035] Furthermore, the target loss data includes the type of disaster, and the step of performing claim calculation based on the target loss data to obtain the claim value of the crop includes:

[0036] Retrieving a corresponding loss calculation formula pre-stored in a database according to the disaster type;

[0037] Calculate based on the target loss data and the loss calculation formula to obtain a loss value;

[0038] Determine the corresponding insurance type based on the survey and damage assessment signal, and retrieve a preset claim calculation formula according to the insurance type;

[0039] The crop compensation value is obtained by performing calculation based on the loss value and the claim calculation formula.

[0040] In order to solve the above technical problems, the present application also provides a farmland planting data analysis device, which adopts the following technical solution:

[0041] A farmland planting data analysis device comprises:

[0042] A receiving module, for collecting a plurality of farmland planting images in real time upon receiving a survey and damage assessment signal, and preprocessing all the farmland planting images to obtain a plurality of images to be assessed for damage;

[0043] An analysis module, used for sequentially inputting the to-be-assessed damage images into a preset damage assessment model for damage analysis, and obtaining a plurality of initial crop loss data output by the damage assessment model;

[0044] A screening module, used for screening all the initial crop loss data to obtain target crop loss data;

[0045] A calculation module is used to perform claim calculation based on the target loss data to obtain a crop claim value.

[0046] 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:

[0047] 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 farmland planting data analysis method when executing the computer-readable instructions.

[0048] 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:

[0049] A computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the above-mentioned farmland planting data analysis method.

[0050] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0051] When receiving the survey and damage assessment signal, multiple farmland planting images are collected in real time, which improves the timeliness of survey and damage assessment. The collected farmland planting images need to be preprocessed to enhance the images, so as to obtain multiple clear and accurate images to be assessed; the images to be assessed are sequentially input into the preset damage assessment model for loss analysis, which can significantly improve the efficiency and accuracy of damage assessment, and obtain multiple initial crop loss data output by the damage assessment model; all the initial crop loss data are screened to obtain more accurate and reasonable target loss data; claims calculation is performed based on the target loss data to obtain the crop claim value. Rapid assessment of farmland losses and claims decision-making are achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] 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.

[0053] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0054] Figure 2 A flow chart of an embodiment of a method for analyzing farmland planting data according to the present application;

[0055] Figure 3 is a structural schematic diagram of an embodiment of a farmland planting data analysis device according to the present application;

[0056] Figure 4 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0057] 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.

[0058] 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.

[0059] 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.

[0060] like Figure 1As 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.

[0061] 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.

[0062] 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 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, etc.

[0063] 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 .

[0064] It should be noted that the farmland planting data analysis method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the farmland planting data analysis device is generally arranged in the server / terminal device.

[0065] 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.

[0066] Continue to refer Figure 2 , shows a flow chart of an embodiment of a method for analyzing farmland planting data according to the present application. The method for analyzing farmland planting data comprises the following steps:

[0067] Step S201, when receiving a damage assessment signal, multiple farmland planting images are collected in real time, and all the farmland planting images are pre-processed to obtain multiple damage assessment images;

[0068] In this embodiment, the farmland planting data analysis method is executed on an electronic device (eg Figure 1 The server / terminal device shown in the figure can check the damage assessment signal 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 (Ultra Wi deband) connection, and other wireless connection methods currently known or to be developed in the future.

[0069] In this embodiment, the damage investigation signal is a claim application issued by the disaster victim, and this signal carries information such as the name of the disaster victim and the location where the signal is sent. When the damage investigation signal is received, multiple farmland planting images are collected in real time, which improves the timeliness of the investigation. All the farmland planting images are preprocessed to enhance the image, thereby obtaining multiple clear and accurate damage images to be assessed. The preprocessing step is the basis for subsequent loss analysis and helps to improve the recognition accuracy of the damage assessment model.

[0070] Step S202, sequentially inputting the to-be-assessed damage images into a preset damage assessment model for damage analysis, and obtaining a plurality of initial crop loss data output by the damage assessment model;

[0071] In this embodiment, the damage assessment model may be a deep learning neural network model. The preprocessed damage assessment images are sequentially input into the preset damage assessment model. The damage assessment model can automatically identify key information such as crop type, growth status, and loss status in the damage assessment images, and perform loss analysis based on the information, and output multiple initial crop loss data, including the loss quantity, loss area, and disaster type.

[0072] Step S203, screening all the initial crop loss data to obtain target crop loss data;

[0073] In this embodiment, since the initial crop loss data may contain certain errors or redundant information, a screening operation is required to screen out the target loss data for the final claim calculation, thereby reducing the difficulty of calculation and improving the rationality of the claim.

[0074] Step S204, performing claim calculation based on the target loss data to obtain a crop claim value.

[0075] In this embodiment, the claim calculation is performed based on the screened target loss data to obtain the crop claim value, thereby realizing the automation and intelligence of the claim process and improving the claim efficiency and accuracy.

[0076] In this embodiment, when a survey and damage assessment signal is received, multiple farmland planting images are collected in real time, which improves the timeliness of survey and damage assessment. The collected farmland planting images need to be preprocessed to enhance the images, so as to obtain multiple clear and accurate images to be assessed; the images to be assessed are sequentially input into the preset damage assessment model for loss analysis, which can significantly improve the efficiency and accuracy of damage assessment, and obtain multiple initial crop loss data output by the damage assessment model; all the initial crop loss data are screened to obtain more accurate and reasonable target loss data; claims calculation is performed based on the target loss data to obtain the crop claim value. Rapid assessment of farmland losses and claims decision-making are achieved.

[0077] Specifically, step S201, i.e., when receiving the damage assessment signal, the step of collecting multiple farmland planting images in real time includes:

[0078] When receiving the damage assessment signal, the sending location of the damage assessment signal and the machine location of the standby UAV are obtained in real time;

[0079] According to the sending position and the machine position, the standby drone is selected to determine the drone that performs the collection task as the collection drone;

[0080] Generate a flight path and shooting parameters based on the sending position and the machine position, and send a flight signal to the collection drone, wherein the flight signal carries the flight path and the shooting parameters;

[0081] Receive the farmland planting image transmitted by the acquisition drone.

[0082] In this embodiment, when receiving the survey and damage assessment signal, the drone can respond quickly and fly to the designated farmland area according to the flight path, and use the high-resolution camera on board to collect multiple farmland planting images in real time according to the set shooting parameters (such as shooting height, shooting angle, etc.). This process is not limited by natural conditions such as weather and terrain, which greatly improves the timeliness and coverage of the survey.

[0083] Optionally, step S201, i.e., preprocessing all the farmland planting images to obtain a plurality of images to be determined for damage, includes:

[0084] Acquire image parameters carried by each of the farmland planting images, wherein the image parameters include shooting height;

[0085] Classifying the farmland planting images according to the shooting heights to obtain a plurality of planting image groups;

[0086] Deduplication processing is performed on the farmland planting images in each of the planting image groups to obtain multiple target image groups;

[0087] Based on the shooting height corresponding to the target image group, the target image group is divided into a short-distance image group and a long-distance image group;

[0088] An image enhancement operation is performed on the long-distance image group based on the short-distance image group to obtain a target image group, and images in the target image group are used as the images to be determined as damaged.

[0089] In this embodiment, the image parameters include shooting height, GPS geographic location of shooting, shooting angle, image size, image size, etc. By classifying the farmland planting images according to the shooting height, the complexity and calculation amount of subsequent processing can be significantly reduced. Because images at different heights may contain information of different scales, the classification process makes the subsequent deduplication operation simpler and faster. Deduplication is performed on each planting image group to remove similar images, effectively reduce data redundancy, and improve the subsequent data processing speed. After the image group is divided into a close-range image group and a long-range image group, an image enhancement operation is performed on the long-range image group based on the close-range image group, which can significantly improve the quality of the long-range image. This enhancement can include clarity enhancement, color correction, detail enhancement, etc., so that the farmland planting conditions in the long-range image are clearer and more discernible, which is helpful for subsequent loss analysis.

[0090] The step of performing an image enhancement operation on the long-distance image group based on the short-distance image group to obtain a target image group includes:

[0091] Extracting image features and image details from the close-range image group;

[0092] Performing a feature matching operation on the image feature and the long-distance image group to obtain a region to be enhanced of the long-distance image group;

[0093] Injecting the image details into the corresponding area to be enhanced to obtain an initial enhanced image group;

[0094] Respectively identifying the contrast and brightness of the close-range image group to obtain a reference contrast and a reference brightness;

[0095] The initial enhanced image group is adjusted based on the reference contrast and the reference brightness to obtain the target image group.

[0096] In this embodiment, by extracting image features and image details from the close-range image group and matching features with the long-range image group, the area in the long-range image that needs to be enhanced, i.e., the area to be enhanced, can be accurately located. By injecting the details in the close-range image into the area to be enhanced in the long-range image, the detail information lost in the long-range image due to the long shooting distance can be significantly restored, making the farmland planting conditions in the long-range image clearer, which is helpful for subsequent image analysis and application. By identifying the contrast and brightness of the close-range image group as a reference, the initial enhanced image group is adjusted to achieve reasonable adjustment of the initial enhanced image group.

[0097] Optionally, in this embodiment, the damage assessment model includes a Faster R-CNN model, and step S202, i.e., sequentially inputting the damage assessment images to be assessed into a preset damage assessment model for loss analysis, and obtaining a plurality of initial crop loss data output by the damage assessment model, includes:

[0098] Performing a histogram equalization operation on the damage-to-be-assessed image to obtain a target damage-assessed image;

[0099] The target damage assessment image is input into the pre-trained Faster R-CNN model to obtain the initial crop loss data output by the Faster R-CNN model.

[0100] In this embodiment, histogram equalization can improve the contrast of the image to be damaged, reduce noise, and improve the quality of the image. Faster R-CNN is a target detection algorithm that can quickly and accurately detect target objects in complex scenes. When applied to crop loss analysis, it can automatically identify damaged crop areas, effectively improving the efficiency and accuracy of the analysis.

[0101] In addition, step S203, i.e., the step of screening all the initial crop loss data to obtain target crop loss data, includes:

[0102] Detecting whether there are abnormal data in all the initial crop loss data by using a preset abnormality detection model;

[0103] If there is abnormal data, the initial crop loss data corresponding to the abnormal data is deleted, and the remaining initial crop loss data is used as the intermediate crop loss data;

[0104] If there is no abnormal data, all the initial crop loss data are directly used as the intermediate crop loss data;

[0105] The target loss data is generated based on the intermediate crop loss data.

[0106] In this embodiment, the abnormal data may be caused by image processing errors, model prediction deviations, etc., which will seriously affect the accuracy of loss assessment. Through the preset abnormality detection model, these abnormal data can be automatically identified to avoid their interference with the final claim value. The specific method of generating the target loss data according to the intermediate crop loss data can be: the data with the highest frequency in all the intermediate crop loss data is used as the target loss data.

[0107] Optionally, in this embodiment, the target loss data includes the disaster type, and step S204, i.e., the step of performing claim calculation based on the target loss data to obtain the crop claim value, includes:

[0108] Retrieving a corresponding loss calculation formula pre-stored in a database according to the disaster type;

[0109] Calculate based on the target loss data and the loss calculation formula to obtain a loss value;

[0110] Determine the corresponding insurance type based on the survey and damage assessment signal, and retrieve a preset claim calculation formula according to the insurance type;

[0111] The crop compensation value is obtained by performing calculation based on the loss value and the claim calculation formula.

[0112] In this embodiment, the target loss data includes the disaster type, disaster scope, crop loss type, the number of damaged crops of each type, etc. By respectively retrieving the corresponding loss calculation formula and claim calculation formula according to the disaster type and insurance type, the accuracy of loss assessment and claim calculation can be ensured and errors can be reduced. First, the corresponding loss calculation formula is determined according to the disaster type (such as floods, droughts, earthquakes, pests and diseases, etc.), and a preliminary calculation is performed to obtain the loss value. Then, the corresponding insurance type is determined in combination with the survey and loss assessment signal, so that the corresponding rate standard can be determined, and the claim calculation is performed to obtain an accurate and reasonable crop claim value.

[0113] It should be emphasized that in order to further ensure the privacy and security of the above-mentioned farmland planting images, the above-mentioned farmland planting images can also be stored in a blockchain node.

[0114] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0115] 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.

[0116] The basic technologies of artificial intelligence generally include sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics and other technologies. Artificial intelligence software technology mainly includes computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning. This application belongs to the field of smart claims, and this solution can promote the construction of smart cities.

[0117] 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).

[0118] 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.

[0119] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of a farmland planting data analysis device, and the device embodiment is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0120] like Figure 3 As shown, the farmland planting data analysis device 300 described in this embodiment includes: a receiving module 301, an analysis module 302, a screening module 303 and a calculation module 304. Among them: the receiving module 301 is used to collect multiple farmland planting images in real time when receiving the survey and damage assessment signal, and pre-process all the farmland planting images to obtain multiple images to be assessed for damage; the analysis module 302 is used to input the images to be assessed for damage into a preset damage assessment model in sequence for loss analysis, and obtain multiple initial crop loss data output by the damage assessment model; the screening module 303 is used to screen all the initial crop loss data to obtain target loss data; the calculation module 304 is used to perform claim calculation based on the target loss data to obtain the crop claim value.

[0121] In this embodiment, when a survey and damage assessment signal is received, multiple farmland planting images are collected in real time, which improves the timeliness of survey and damage assessment. The collected farmland planting images need to be preprocessed to enhance the images, so as to obtain multiple clear and accurate images to be assessed; the images to be assessed are sequentially input into the preset damage assessment model for loss analysis, which can significantly improve the efficiency and accuracy of damage assessment, and obtain multiple initial crop loss data output by the damage assessment model; all the initial crop loss data are screened to obtain more accurate and reasonable target loss data; claims calculation is performed based on the target loss data to obtain the crop claim value. Rapid assessment of farmland losses and claims decision-making are achieved.

[0122] The receiving module 301 includes a first receiving submodule, a selection submodule, a generation submodule and a second receiving submodule. The first receiving submodule is used to obtain the sending position of the survey and damage assessment signal and the machine position of the standby drone in real time when receiving the survey and damage assessment signal; the selection submodule is used to select the standby drone according to the sending position and the machine position, and determine the drone that performs the collection task as the collection drone; the generation submodule is used to generate a flight path and shooting parameters based on the sending position and the machine position, and send a flight signal to the collection drone, wherein the flight signal carries the flight path and the shooting parameters; the second receiving submodule is used to receive the farmland planting image transmitted by the collection drone.

[0123] In some optional implementations of this embodiment, the receiving module 301 also includes an acquisition submodule, a first classification submodule, a deduplication processing submodule, a second classification submodule and an enhancement submodule. The acquisition submodule is used to acquire the image parameters carried by each of the farmland planting images, wherein the image parameters include the shooting height; the first classification submodule is used to classify the farmland planting images according to the shooting height to obtain a plurality of planting image groups; the deduplication processing submodule is used to perform deduplication processing on the farmland planting images in each of the planting image groups respectively to obtain a plurality of target image groups; the second classification submodule is used to divide the target image group into a close-range image group and a long-range image group based on the shooting height corresponding to the target image group; the enhancement submodule is used to perform image enhancement operation on the long-range image group based on the close-range image group to obtain the target image group, and use the image in the target image group as the image to be determined.

[0124] In some optional implementations of this embodiment, the enhancement submodule includes an extraction unit, a feature matching unit, an injection unit, an identification unit, and an adjustment unit. The extraction unit is used to extract image features and image details from the close-range image group; the feature matching unit is used to perform feature matching operations on the image features and the long-range image group to obtain the area to be enhanced of the long-range image group; the injection unit is used to inject the image details into the corresponding area to be enhanced to obtain an initial enhanced image group; the identification unit is used to respectively identify the contrast and brightness of the close-range image group to obtain a reference contrast and a reference brightness; the adjustment unit is used to adjust the initial enhanced image group based on the reference contrast and the reference brightness to obtain the target image group.

[0125] In some optional implementations of this embodiment, the damage assessment model includes a Faster R-CNN model, and the analysis module 302 includes an equalization submodule and an input submodule. The equalization submodule is used to perform a histogram equalization operation on the damage assessment image to obtain a target damage assessment image; the input submodule is used to input the target damage assessment image into the pre-trained Faster R-CNN model to obtain the initial crop loss data output by the Faster R-CNN model.

[0126] In some optional implementations of this embodiment, the screening module 303 includes a detection submodule, a deletion submodule, a determination submodule, and a data generation submodule. The detection submodule is used to detect whether there is abnormal data in all the initial crop loss data through a preset abnormality detection model; the deletion submodule is used to delete the initial crop loss data corresponding to the abnormal data when there is abnormal data, and use the remaining initial crop loss data as intermediate crop loss data; the determination submodule is used to directly use all the initial crop loss data as intermediate crop loss data when there is no abnormal data; and the data generation submodule is used to generate the target loss data according to the intermediate crop loss data.

[0127] In some optional implementations of this embodiment, the calculation module 304 includes a first retrieval submodule, a first calculation submodule, a second retrieval submodule and a second calculation submodule. The first retrieval submodule is used to retrieve the corresponding loss calculation formula pre-stored in the database according to the disaster type; the first calculation submodule is used to calculate based on the target loss data and the loss calculation formula to obtain the loss value; the second retrieval submodule is used to determine the corresponding insurance type based on the survey and loss assessment signal, and retrieve the preset claim calculation formula according to the insurance type; the second calculation submodule is used to calculate based on the loss value and the claim calculation formula to obtain the crop claim value.

[0128] When receiving the survey and damage assessment signal, multiple farmland planting images are collected in real time, which improves the timeliness of survey and damage assessment. The collected farmland planting images need to be preprocessed to enhance the images, so as to obtain multiple clear and accurate images to be assessed; the images to be assessed are sequentially input into the preset damage assessment model for loss analysis, which can significantly improve the efficiency and accuracy of damage assessment, and obtain multiple initial crop loss data output by the damage assessment model; all the initial crop loss data are screened to obtain more accurate and reasonable target loss data; claims calculation is performed based on the target loss data to obtain the crop claim value. Rapid assessment of farmland losses and claims decision-making are achieved.

[0129] 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.

[0130] 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.

[0131] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0132] 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, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the computer device 4. 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 farmland planting data analysis 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.

[0133] 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 farmland planting data analysis method.

[0134] 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.

[0135] When receiving the survey and damage assessment signal, multiple farmland planting images are collected in real time, which improves the timeliness of survey and damage assessment. The collected farmland planting images need to be preprocessed to enhance the images, so as to obtain multiple clear and accurate images to be assessed; the images to be assessed are sequentially input into the preset damage assessment model for loss analysis, which can significantly improve the efficiency and accuracy of damage assessment, and obtain multiple initial crop loss data output by the damage assessment model; all the initial crop loss data are screened to obtain more accurate and reasonable target loss data; claims calculation is performed based on the target loss data to obtain the crop claim value. Rapid assessment of farmland losses and claims decision-making are achieved.

[0136] 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 farmland planting data analysis method as described above.

[0137] When receiving the survey and damage assessment signal, multiple farmland planting images are collected in real time, which improves the timeliness of survey and damage assessment. The collected farmland planting images need to be preprocessed to enhance the images, so as to obtain multiple clear and accurate images to be assessed; the images to be assessed are sequentially input into the preset damage assessment model for loss analysis, which can significantly improve the efficiency and accuracy of damage assessment, and obtain multiple initial crop loss data output by the damage assessment model; all the initial crop loss data are screened to obtain more accurate and reasonable target loss data; claims calculation is performed based on the target loss data to obtain the crop claim value. Rapid assessment of farmland losses and claims decision-making are achieved.

[0138] 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.

[0139] 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 analyzing farmland planting data, characterized in that: The steps include: When receiving a damage assessment signal, multiple farmland planting images are collected in real time, and all the farmland planting images are preprocessed to obtain multiple images to be assessed; Inputting the images to be assessed for damage into a preset damage assessment model in sequence for loss analysis, and obtaining a plurality of initial crop loss data output by the damage assessment model; Performing a screening operation on all the initial crop loss data to obtain target crop loss data; Claim calculation is performed based on the target loss data to obtain the crop claim value.

2. The farmland planting data analysis method according to claim 1, characterized in that: When the damage assessment signal is received, the step of collecting multiple farmland planting images in real time includes: When receiving the damage assessment signal, the sending location of the damage assessment signal and the machine location of the standby UAV are obtained in real time; According to the sending position and the machine position, the standby drone is selected to determine the drone that performs the collection task as the collection drone; Generate a flight path and shooting parameters based on the sending position and the machine position, and send a flight signal to the collection drone, wherein the flight signal carries the flight path and the shooting parameters; Receive the farmland planting image transmitted by the acquisition drone.

3. The farmland planting data analysis method according to claim 1, characterized in that: The step of preprocessing all the farmland planting images to obtain a plurality of images to be determined as damaged includes: Acquire image parameters carried by each of the farmland planting images, wherein the image parameters include shooting height; Classifying the farmland planting images according to the shooting heights to obtain a plurality of planting image groups; Deduplication processing is performed on the farmland planting images in each of the planting image groups to obtain multiple target image groups; Based on the shooting height corresponding to the target image group, the target image group is divided into a short-distance image group and a long-distance image group; An image enhancement operation is performed on the long-distance image group based on the short-distance image group to obtain a target image group, and images in the target image group are used as the images to be determined as damaged.

4. The farmland planting data analysis method according to claim 3, characterized in that: The step of performing an image enhancement operation on the long-distance image group based on the short-distance image group to obtain a target image group comprises: Extracting image features and image details from the close-range image group; Performing a feature matching operation on the image feature and the long-distance image group to obtain a region to be enhanced of the long-distance image group; Injecting the image details into the corresponding area to be enhanced to obtain an initial enhanced image group; Respectively identifying the contrast and brightness of the close-range image group to obtain a reference contrast and a reference brightness; The initial enhanced image group is adjusted based on the reference contrast and the reference brightness to obtain the target image group.

5. The farmland planting data analysis method according to claim 1, characterized in that: The damage assessment model includes a Faster R-CNN model. The steps of sequentially inputting the damage assessment images to be assessed into a preset damage assessment model for loss analysis to obtain a plurality of initial crop loss data output by the damage assessment model include: Performing a histogram equalization operation on the damage-to-be-assessed image to obtain a target damage-assessed image; The target damage assessment image is input into the pre-trained Faster R-CNN model to obtain the initial crop loss data output by the Faster R-CNN model.

6. The farmland planting data analysis method according to claim 1, characterized in that: The step of screening all the initial crop loss data to obtain target crop loss data includes: Detecting whether there are abnormal data in all the initial crop loss data by using a preset abnormality detection model; If there is abnormal data, the initial crop loss data corresponding to the abnormal data is deleted, and the remaining initial crop loss data is used as the intermediate crop loss data; If there is no abnormal data, all the initial crop loss data are directly used as the intermediate crop loss data; The target loss data is generated based on the intermediate crop loss data.

7. The farmland planting data analysis method according to claim 1, characterized in that: The target loss data includes the type of disaster, and the step of performing claim calculation based on the target loss data to obtain the claim value of the crop includes: Retrieving a corresponding loss calculation formula pre-stored in a database according to the disaster type; Calculate based on the target loss data and the loss calculation formula to obtain a loss value; Determine the corresponding insurance type based on the survey and damage assessment signal, and retrieve a preset claim calculation formula according to the insurance type; The crop compensation value is obtained by performing calculation based on the loss value and the claim calculation formula.

8. A farmland planting data analysis device, characterized in that: include: A receiving module, for collecting a plurality of farmland planting images in real time upon receiving a survey and damage assessment signal, and preprocessing all the farmland planting images to obtain a plurality of images to be assessed for damage; An analysis module, used for sequentially inputting the to-be-assessed damage images into a preset damage assessment model for damage analysis, and obtaining a plurality of initial crop loss data output by the damage assessment model; A screening module, used for screening all the initial crop loss data to obtain target crop loss data; A calculation module is used to perform claim calculation based on the target loss data to obtain a crop claim value.

9. A computer device, characterized in that: It includes a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the farmland planting data analysis method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps of the farmland planting data analysis method as described in any one of claims 1 to 7 are implemented.

Images