Data evaluation method and device, computer equipment and storage medium
The forest land information is obtained through remote sensing satellites, and forestry insurance loss assessment is used to evaluate forestry insurance losses, solving the problems of inefficient and high cost of traditional manual exploration, and achieving automated and accurate assessment of forestry insurance losses.
Patent Information
- Application Number
- CN202411178624.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-26
- Publication Date
- 2024-12-27
AI Technical Summary
The forestry insurance loss assessment method adopted by forestry insurance companies relies on manual surveys and sample surveys, resulting in inefficient and costly assessments.
Remote sensing satellites are used to obtain forest land information, extract features through image processing algorithms, and generate evaluation results using loss evaluation models, and visually display them in combination with geographic information systems.
It has realized the automated and accurate assessment of forestry insurance losses, saved manpower and material costs, reduced the influence of subjective factors, and improved the evaluation efficiency and accuracy.
Smart Images
Figure CN119206525A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of artificial intelligence development technology and financial technology, and in particular to data evaluation methods, devices, computer equipment and storage media. Background Art
[0002] Forestry is an important economic and ecological resource, but natural disasters and human factors may cause destruction and loss of forests, bringing huge claims pressure to forestry insurance companies. At present, the loss assessment method adopted by forestry insurance companies for forestry insurance mainly relies on manual surveys and sample surveys. This processing method requires a long time for data collection, collation and analysis, resulting in problems such as low efficiency and high costs. Summary of the invention
[0003] The purpose of the embodiments of the present application is to propose a data evaluation method, device, computer equipment and storage medium to solve the technical problem that the loss assessment method for forestry insurance adopted by existing forestry insurance companies takes a long time to collect, organize and analyze data, resulting in low evaluation efficiency and high cost.
[0004] In order to solve the above technical problems, the present application provides a data evaluation method, which adopts the following technical solution:
[0005] Determine whether a forestry insurance assessment request triggered by a user is received; wherein the forestry insurance assessment request carries forest land information of the target forest land;
[0006] If so, obtaining forest remote sensing image data corresponding to the forest information from a preset remote sensing satellite;
[0007] Based on a preset image processing algorithm, extracting target features from the forest remote sensing image data;
[0008] The target characteristics are evaluated based on a preset loss assessment model to generate a loss assessment result corresponding to the target forest land;
[0009] The loss assessment results are displayed.
[0010] Furthermore, the step of extracting target features from the forest remote sensing image data based on a preset image processing algorithm specifically includes:
[0011] Extracting features from the forest remote sensing image data based on the image processing algorithm to obtain corresponding initial features;
[0012] Get the preset specified feature type;
[0013] Filtering out designated features corresponding to the designated feature type from the initial features;
[0014] The designated feature is used as the target feature.
[0015] Furthermore, the step of displaying the loss assessment result specifically includes:
[0016] Get the preset map;
[0017] Based on geographic information system technology, the loss assessment results are presented on the map in a visual manner;
[0018] The map is displayed in a preset interactive interface.
[0019] Furthermore, before the step of evaluating the target feature based on the preset loss assessment model to generate a loss assessment result corresponding to the target forest land, the method further includes:
[0020] Access to pre-collected historical forestland loss data;
[0021] Preprocessing the historical forestland loss data to obtain corresponding target forestland loss data, and constructing sample data based on the target forestland loss data;
[0022] Call the preset machine learning model;
[0023] Optimizing the machine learning model based on a preset parameter adjustment strategy to obtain a corresponding prediction model;
[0024] The prediction model is processed by model construction using the sample data to obtain a loss assessment model that meets preset construction requirements.
[0025] Furthermore, the step of preprocessing the historical forest land loss data to obtain the corresponding target forest land loss data specifically includes:
[0026] Performing data cleaning on the historical forest land loss data to obtain corresponding first loss data;
[0027] Performing data supplementation processing on the first loss data to obtain corresponding second loss data;
[0028] performing standardization processing on the second loss data to obtain corresponding third loss data;
[0029] The third loss data is used as the target loss forest land data.
[0030] Furthermore, the step of optimizing the machine learning model based on a preset parameter adjustment strategy to obtain a corresponding prediction model specifically includes:
[0031] Get preset multiple parameter adjustment strategies;
[0032] Selecting a target parameter adjustment strategy from the plurality of parameter adjustment strategies;
[0033] Performing model optimization processing on the machine learning model based on the target parameter adjustment strategy to obtain an optimized machine learning model;
[0034] The optimized machine learning model is used as the prediction model.
[0035] Furthermore, the step of using the sample data to perform model construction processing on the prediction model to obtain a loss assessment model that meets the preset construction requirements specifically includes:
[0036] Dividing the sample data into a training data set and a test data set based on a preset division value;
[0037] Training the prediction model using the training data set to obtain a trained prediction model;
[0038] Testing the trained prediction model using the test data set, and calculating a model evaluation index value corresponding to the trained prediction model;
[0039] Determine whether the model evaluation index value is greater than a preset index threshold;
[0040] If the model evaluation index value is greater than the index threshold, the trained prediction model is used as the loss assessment model.
[0041] In order to solve the above technical problems, the embodiment of the present application further provides a data evaluation device, which adopts the following technical solution:
[0042] A judgment module, used to judge whether a forestry insurance assessment request triggered by a user is received; wherein the forestry insurance assessment request carries forest land information of the target forest land;
[0043] A first acquisition module is used to acquire forest remote sensing image data corresponding to the forest information from a preset remote sensing satellite;
[0044] An extraction module, used for extracting target features from the forest remote sensing image data based on a preset image processing algorithm;
[0045] An assessment module, used to assess the target features based on a preset loss assessment model and generate a loss assessment result corresponding to the target forest land;
[0046] A display module is used to display the loss assessment results.
[0047] 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:
[0048] Determine whether a forestry insurance assessment request triggered by a user is received; wherein the forestry insurance assessment request carries forest land information of the target forest land;
[0049] If so, obtaining forest remote sensing image data corresponding to the forest information from a preset remote sensing satellite;
[0050] Based on a preset image processing algorithm, extracting target features from the forest remote sensing image data;
[0051] The target characteristics are evaluated based on a preset loss assessment model to generate a loss assessment result corresponding to the target forest land;
[0052] The loss assessment results are displayed.
[0053] 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:
[0054] Determine whether a forestry insurance assessment request triggered by a user is received; wherein the forestry insurance assessment request carries forest land information of the target forest land;
[0055] If so, obtaining forest remote sensing image data corresponding to the forest information from a preset remote sensing satellite;
[0056] Based on a preset image processing algorithm, extracting target features from the forest remote sensing image data;
[0057] The target characteristics are evaluated based on a preset loss assessment model to generate a loss assessment result corresponding to the target forest land;
[0058] The loss assessment results are displayed.
[0059] Compared with the prior art, the embodiments of the present application have the following beneficial effects:
[0060] The embodiment of the present application first determines whether a forestry risk assessment request triggered by a user is received; if so, forest remote sensing image data corresponding to the forest information is obtained from a preset remote sensing satellite; then, based on a preset image processing algorithm, target features are extracted from the forest remote sensing image data; subsequently, the target features are evaluated and processed based on a preset loss assessment model to generate a loss assessment result corresponding to the target forest; and finally, the loss assessment result is displayed and processed. After receiving a forestry risk assessment request triggered by a user, the embodiment of the present application uses remote sensing satellite technology to quickly obtain forest remote sensing image data corresponding to the forest information, and based on the use of an image processing algorithm, target features are extracted from the forest remote sensing image data, and then the target features are evaluated and processed based on a loss assessment model to generate a loss assessment result corresponding to the target forest, thereby achieving an automated and accurate assessment of the loss of the target forest. Compared with traditional manual survey and sample survey methods, it can save a lot of manpower and material costs, reduce the influence of subjective factors on the assessment results, effectively improve the assessment efficiency and accuracy of the loss of the target forest, and ensure the accuracy of the generated loss assessment results. BRIEF DESCRIPTION OF THE DRAWINGS
[0061] 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.
[0062] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;
[0063] Figure 2 A flowchart of an embodiment of a data evaluation method according to the present application;
[0064] Figure 3 is a schematic structural diagram of an embodiment of a data evaluation device according to the present application;
[0065] Figure 4 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION
[0066] 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.
[0067] 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.
[0068] 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.
[0069] 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.
[0070] 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.
[0071] 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, and the like.
[0072] 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 .
[0073] It should be noted that the data evaluation method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the data evaluation device is generally arranged in the server / terminal device.
[0074] 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.
[0075] Continue to refer Figure 2 , showing a flow chart of an embodiment of the data evaluation method according to the present application. According to different requirements, the order of the steps in the flow chart can be changed, and some steps can be omitted. The data evaluation method provided in the embodiment of the present application can be applied to any scenario that requires forestry insurance loss assessment, and the data evaluation method can be applied to products in these scenarios, for example, forestry insurance loss assessment in the field of financial insurance. The data evaluation method comprises the following steps:
[0076] Step S201, determining whether a forestry insurance assessment request triggered by a user is received; wherein the forestry insurance assessment request carries forest land information of a target forest land.
[0077] In this embodiment, the electronic device (eg Figure 1The server / terminal device shown in the figure) can obtain the forest information of the target forest through a wired connection or a wireless connection. It should be pointed out that the above-mentioned 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. The executor of the above-mentioned data evaluation method may specifically be a forestry insurance intelligent loss assessment system. In actual scenarios where natural disasters and human factors may cause destruction and loss of forests, the above-mentioned forestry insurance assessment request is a user-triggered request for applying for a claim for the target forest. The above-mentioned forest information may include the geographical location information of the target forest.
[0078] Step S202: If yes, obtain forest remote sensing image data corresponding to the forest information from a preset remote sensing satellite.
[0079] In this embodiment, the remote sensing satellite can obtain high-resolution, complete and continuous forest remote sensing image data of the target forest corresponding to the forest information based on remote sensing technology, thereby ensuring the quality and accuracy of the obtained forest remote sensing image data. The forest remote sensing image data may at least include forest information such as vegetation coverage, tree species type, and forest density.
[0080] Step S203: extracting target features from the forest remote sensing image data based on a preset image processing algorithm.
[0081] In this embodiment, the specific implementation process of extracting target features from the forest remote sensing image data based on the preset image processing algorithm will be further described in detail in subsequent specific embodiments of the present application and will not be elaborated on here.
[0082] Step S204: evaluating the target features based on a preset loss assessment model to generate a loss assessment result corresponding to the target forest land.
[0083] In this embodiment, the target feature can be input into the loss assessment model so that the target feature can be evaluated and processed by the loss assessment model, and a loss assessment result corresponding to the target forest land can be output. The construction process of the above-mentioned loss assessment model will be further described in detail in the subsequent specific embodiments of this application, and will not be elaborated on here.
[0084] Step S205: display the loss assessment results.
[0085] In this embodiment, the specific implementation process of displaying and processing the loss assessment results mentioned above will be described in further detail in the subsequent specific embodiments of this application, and will not be elaborated on here. Among them, the intelligent loss assessment system for forestry insurance based on remote sensing technology proposed in this application is an innovative and efficient assessment method. The system combines remote sensing data acquisition, image processing and feature extraction, loss assessment models and visualization and analysis of geographic information system technology to achieve automatic and accurate assessment of losses in forestry insurance. The system has a wide range of application value and can provide objective and accurate assessment results for forestry insurance companies, improve work efficiency, save costs, and provide a scientific basis for decision-making.
[0086] The present application first determines whether a forestry risk assessment request triggered by a user is received; if so, the forest remote sensing image data corresponding to the forest information is obtained from a preset remote sensing satellite; then, based on a preset image processing algorithm, the target features are extracted from the forest remote sensing image data; subsequently, the target features are evaluated and processed based on a preset loss assessment model to generate a loss assessment result corresponding to the target forest; and finally, the loss assessment result is displayed and processed. After receiving a forestry risk assessment request triggered by a user, the present application uses remote sensing satellite technology to quickly obtain forest remote sensing image data corresponding to the forest information, and based on the use of an image processing algorithm, the target features are extracted from the forest remote sensing image data, and then the target features are evaluated and processed based on a loss assessment model to generate a loss assessment result corresponding to the target forest, thereby realizing an automated and accurate assessment of the loss of the target forest. Compared with traditional manual survey and sample survey methods, it can save a lot of manpower and material costs, reduce the influence of subjective factors on the assessment results, effectively improve the assessment efficiency and accuracy of the loss of the target forest, and ensure the accuracy of the generated loss assessment results.
[0087] In some optional implementations, step S203 includes the following steps:
[0088] Based on the image processing algorithm, feature extraction is performed on the forest remote sensing image data to obtain corresponding initial features.
[0089] In this embodiment, the feature extraction may include spectral feature extraction, texture feature extraction, and shape feature extraction. The image processing algorithm may include principal component analysis (PCA) and maximum likelihood classification (MLC) applied to spectral feature extraction, gray level co-occurrence matrix method (GLCM) and local binary pattern method (LBP) applied to texture feature extraction, and edge detection operator, Hough transform and other algorithms applied to shape feature extraction.
[0090] Gets the specified feature type of a preset.
[0091] In this embodiment, the above-mentioned specified feature types may at least include feature types such as vegetation index, texture feature, color distribution, etc.
[0092] Specified features corresponding to the specified feature type are screened out from the initial features.
[0093] In this embodiment, the initial features may be screened by using the specified feature type to screen out features corresponding to the vegetation index, texture features, and color distribution of the woodland in the initial features.
[0094] The designated feature is used as the target feature.
[0095] The present application performs feature extraction on the forest remote sensing image data based on the image processing algorithm to obtain the corresponding initial features; then obtains the preset designated feature type; then filters out the designated features corresponding to the designated feature type from the initial features; and subsequently uses the designated features as the target features. The present application performs feature extraction on the forest remote sensing image data based on the image processing algorithm to obtain the corresponding initial features, and then filters out the designated features corresponding to the designated feature type from the initial features and uses them as target features, which effectively improves the extraction efficiency of the target features and ensures the accuracy of the obtained target features.
[0096] In some optional implementations of this embodiment, step S205 includes the following steps:
[0097] Get a preset map.
[0098] In this embodiment, the map refers to a map including the target forest land.
[0099] Based on geographic information system technology, the loss assessment results are presented on the map in a visual manner.
[0100] In this embodiment, the Geographic Information System (GIS) is sometimes referred to as a "geo-information system". It is a specific and very important spatial information system. It is a technical system that collects, stores, manages, calculates, analyzes, displays and describes the geographical distribution data in the entire or part of the earth's surface (including the atmosphere) space with the support of computer hardware and software systems. The loss assessment results can be presented in a visual manner on the map by using the GIS technology. Through the visual presentation and further analysis of GIS technology, insurance companies can better understand the loss situation in different regions and provide a scientific basis for formulating insurance strategies and claims decisions.
[0101] The map is displayed in a preset interactive interface.
[0102] In this embodiment, the above-mentioned interactive interface is a pre-built interface for information interaction with the user.
[0103] The present application obtains a preset map; then based on geographic information system technology, the loss assessment results are presented in a visual manner on the map; and subsequently the map is displayed in a preset interactive interface. The present application presents the loss assessment results in a visual manner on a preset map based on the use of geographic information system technology, and then displays the map in a preset interactive interface, thereby providing a more intuitive and comprehensive loss assessment result, so that the user can intelligently and quickly view the loss assessment situation of different areas in the forest by viewing the map showing the loss assessment results displayed in the interactive interface, and can further analyze and compare the loss situation of the forest, effectively improving the user experience and improving the user's work efficiency.
[0104] In some optional implementations of this embodiment, before step S204, the electronic device may further perform the following steps:
[0105] Access pre-collected historical forestland loss data.
[0106] In this embodiment, the above-mentioned historical forest loss data can be forest loss data collected in advance within a preset time period. There is no limitation on the selection of the value of the preset time period, which can be determined according to actual business usage needs. For example, it can be set to within one year before the current time.
[0107] The historical forest land loss data is preprocessed to obtain corresponding target forest land loss data, and sample data is constructed based on the target forest land loss data.
[0108] In this embodiment, the specific implementation process of preprocessing the historical forest loss data to obtain the corresponding target forest loss data will be described in further detail in subsequent specific embodiments of the present application and will not be elaborated on here.
[0109] Call the preset machine learning model.
[0110] In this embodiment, there is no specific limitation on the selection of the above-mentioned machine learning model. For example, a linear regression model, a logistic regression model, a decision tree model, a random forest model, a support vector machine model, etc. can be used.
[0111] The machine learning model is optimized based on a preset parameter adjustment strategy to obtain a corresponding prediction model.
[0112] In this embodiment, the specific implementation process of optimizing the machine learning model based on the preset parameter adjustment strategy to obtain the corresponding prediction model will be further described in detail in subsequent specific embodiments of the present application and will not be elaborated in detail here.
[0113] The prediction model is processed by model construction using the sample data to obtain a loss assessment model that meets preset construction requirements.
[0114] In this embodiment, the above-mentioned specific implementation process of using the sample data to construct the prediction model to obtain a loss assessment model that meets the preset construction requirements will be described in further detail in subsequent specific embodiments of the present application and will not be elaborated on here.
[0115] The present application obtains pre-collected historical forest loss data; then pre-processes the historical forest loss data to obtain the corresponding target forest loss data, and constructs sample data based on the target forest loss data; then calls a preset machine learning model; subsequently optimizes the machine learning model based on a preset parameter adjustment strategy to obtain a corresponding prediction model; finally, uses the sample data to perform model construction processing on the prediction model to obtain a loss assessment model that meets the preset construction requirements. The present application constructs sample data based on pre-collected historical forest loss data; then optimizes the preset machine learning model based on a preset parameter adjustment strategy to obtain a corresponding prediction model, and then uses the sample data to perform model construction processing on the prediction model to obtain a loss assessment model that meets the preset construction requirements, thereby completing the model construction process of the loss assessment model, effectively ensuring the model effect and prediction accuracy of the generated loss assessment model, and improving the construction efficiency of the loss assessment model.
[0116] In some optional implementations, the preprocessing of the historical forestland loss data to obtain the corresponding target forestland loss data comprises the following steps:
[0117] The historical forest loss data is cleaned to obtain corresponding first loss data.
[0118] In this embodiment, the historical forest loss data can be cleaned by using a general data cleaning tool, for example, the historical forest loss data can be cleaned of abnormal values, duplicate data, and null values to obtain the corresponding first loss data. The selection of the above data cleaning tool is not specifically limited and can be determined according to actual business usage requirements.
[0119] The first loss data is subjected to data supplementation processing to obtain corresponding second loss data.
[0120] In this embodiment, the first loss data may be supplemented by using a general data supplementation tool to obtain the corresponding second loss data. The selection of the data supplementation tool is not specifically limited and may be determined according to actual business usage requirements.
[0121] The second loss data is standardized to obtain corresponding third loss data.
[0122] In this embodiment, the second loss data may be standardized by using a common standardization tool to obtain the corresponding third loss data. The selection of the above standardization tool is not specifically limited and may be determined according to actual business usage requirements.
[0123] The third loss data is used as the target loss forest land data.
[0124] The present application performs data cleaning processing on the historical forest loss data to obtain the corresponding first loss data; then performs data supplementation processing on the first loss data to obtain the corresponding second loss data; then performs standardization processing on the second loss data to obtain the corresponding third loss data; and subsequently uses the third loss data as the target forest loss data. The present application performs data cleaning processing, data supplementation processing, and standardization processing on the obtained historical forest loss data, thereby realizing the rapid and accurate construction of the required target forest loss data, and effectively ensuring the data accuracy and data standardization of the generated target forest loss data.
[0125] In some optional implementations, optimizing the machine learning model based on a preset parameter adjustment strategy to obtain a corresponding prediction model includes the following steps:
[0126] Get various preset parameter adjustment strategies.
[0127] In this embodiment, the above parameter adjustment strategies may at least include random search, grid search, Bayesian optimization and other strategies.
[0128] A target parameter adjustment strategy is selected from the multiple parameter adjustment strategies.
[0129] In this embodiment, there is no specific limitation on the screening method of the target parameter adjustment strategy, and a strategy can be randomly selected from all the parameter adjustment strategies as the target parameter adjustment strategy. Specifically, it is preferred to use a grid search strategy as the target parameter adjustment strategy. By using the grid search strategy to optimize the parameters of the machine learning model, the overfitting probability of the machine learning model can be effectively reduced.
[0130] The machine learning model is optimized based on the target parameter adjustment strategy to obtain an optimized machine learning model.
[0131] In this embodiment, the above-mentioned model optimization processing may refer to the processing of optimizing the model parameters of the machine learning model.
[0132] The optimized machine learning model is used as the prediction model.
[0133] The present application obtains a plurality of preset parameter adjustment strategies; then selects a target parameter adjustment strategy from the plurality of parameter adjustment strategies; then optimizes the machine learning model based on the target parameter adjustment strategy to obtain an optimized machine learning model; and subsequently uses the optimized machine learning model as the prediction model. The present application uses a target parameter adjustment strategy selected from a plurality of preset parameter adjustment strategies, and uses the target parameter adjustment strategy to optimize the machine learning model to obtain an optimized prediction model, which can effectively reduce the overfitting probability of the generated prediction model, and thus can help improve the prediction accuracy of the loss assessment model constructed after the prediction model is subsequently trained using sample data.
[0134] In some optional implementations of this embodiment, the use of the sample data to perform model construction processing on the prediction model to obtain a loss assessment model that meets the preset construction requirements includes the following steps:
[0135] The sample data is divided into a training data set and a test data set based on a preset division value.
[0136] In this embodiment, there is no specific limitation on the numerical selection of the above-mentioned division value, which can be set according to actual business usage requirements, for example, it can be set to 7:3.
[0137] The prediction model is trained using the training data set to obtain a trained prediction model.
[0138] In this embodiment, the prediction model can be trained by using the training data set so that the prediction model learns the correspondence between the historical forest remote sensing image data in the sample data and the loss degree labels corresponding to the forest remote sensing image data, thereby training a prediction model with the function of predicting the possibility and degree of different loss categories.
[0139] The trained prediction model is tested using the test data set, and a model evaluation index value corresponding to the trained prediction model is calculated.
[0140] In this embodiment, the above-mentioned model evaluation index value may specifically be a prediction accuracy rate corresponding to the trained prediction model generated after the trained prediction model is tested by the test data set.
[0141] Determine whether the model evaluation index value is greater than a preset index threshold.
[0142] In this embodiment, there is no specific limitation on the selection of the numerical value of the above indicator threshold value, which can be set according to actual usage requirements.
[0143] If the model evaluation index value is greater than the index threshold, the trained prediction model is used as the loss assessment model.
[0144] The present application divides the sample data into a training data set and a test data set based on a preset partition value; then trains the prediction model through the training data set to obtain a trained prediction model; then tests the trained prediction model through the test data set to calculate the model evaluation index value corresponding to the trained prediction model; subsequently determines whether the model evaluation index value is greater than a preset index threshold; if the model evaluation index value is greater than the index threshold, the trained prediction model is used as the loss assessment model. The present application divides the sample data into a training data set and a test data set based on a preset partition value, and then uses the training data set and the test data set to train and test the prediction model to obtain the loss assessment model whose model evaluation index value meets the preset index threshold, thereby completing the model construction process of the loss assessment model, effectively ensuring the model effect and prediction accuracy of the obtained loss assessment model, and improving the construction efficiency of the loss assessment model.
[0145] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.
[0146] It should be emphasized that in order to further ensure the privacy and security of the above-mentioned loss assessment results, the above-mentioned loss assessment results can also be stored in a node of a blockchain.
[0147] 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.
[0148] 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.
[0149] 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.
[0150] 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).
[0151] 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.
[0152] 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 data evaluation device, and the device embodiment is Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.
[0153] like Figure 3 As shown, the data evaluation device 300 described in this embodiment includes: a judgment module 301, a first acquisition module 302, an extraction module 303, an evaluation module 304 and a display module 305. Among them:
[0154] The judgment module 301 is used to judge whether a forestry insurance assessment request triggered by a user is received; wherein the forestry insurance assessment request carries forest land information of the target forest land;
[0155] A first acquisition module 302 is used to acquire forest remote sensing image data corresponding to the forest information from a preset remote sensing satellite;
[0156] An extraction module 303 is used to extract target features from the forest remote sensing image data based on a preset image processing algorithm;
[0157] An evaluation module 304 is used to evaluate the target feature based on a preset loss evaluation model to generate a loss evaluation result corresponding to the target forest land;
[0158] The display module 305 is used to display the loss assessment result.
[0159] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the data evaluation method in the aforementioned implementation mode, and are not described in detail here.
[0160] In some optional implementations of this embodiment, the extraction module 303 includes:
[0161] An extraction submodule, used for performing feature extraction on the forest remote sensing image data based on the image processing algorithm to obtain corresponding initial features;
[0162] The first acquisition submodule is used to acquire a preset specified feature type;
[0163] A first screening submodule, configured to screen out specified features corresponding to the specified feature type from the initial features;
[0164] The first determination submodule is used as a submodule, and is used to use the specified feature as the target feature.
[0165] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the data evaluation method in the aforementioned implementation mode, and are not described in detail here.
[0166] In some optional implementations of this embodiment, the display module 305 includes:
[0167] The second acquisition submodule is used to acquire a preset map;
[0168] A first processing submodule is used to present the loss assessment result on the map in a visual manner based on geographic information system technology;
[0169] The display submodule is used to display the map in a preset interactive interface.
[0170] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the data evaluation method in the aforementioned implementation mode, and will not be described in detail here.
[0171] In some optional implementations of this embodiment, the data evaluation device further includes:
[0172] The second acquisition module is used to obtain the historical forest loss data collected in advance;
[0173] A preprocessing module, used for preprocessing the historical forest land loss data to obtain corresponding target forest land loss data, and constructing sample data based on the target forest land loss data;
[0174] The calling module is used to call the preset machine learning model;
[0175] An optimization module, used to optimize the machine learning model based on a preset parameter adjustment strategy to obtain a corresponding prediction model;
[0176] A construction module is used to use the sample data to perform model construction processing on the prediction model to obtain a loss assessment model that meets preset construction requirements.
[0177] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the data evaluation method in the aforementioned implementation mode, and are not described in detail here.
[0178] In some optional implementations of this embodiment, the preprocessing module includes:
[0179] A second processing submodule is used to perform data cleaning processing on the historical forest loss data to obtain corresponding first loss data;
[0180] A third processing submodule is used to perform data supplementation processing on the first loss data to obtain corresponding second loss data;
[0181] a fourth processing submodule, configured to perform standardization processing on the second loss data to obtain corresponding third loss data;
[0182] The second determination submodule is used to use the third loss data as the target forest land loss data.
[0183] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the data evaluation method in the aforementioned implementation mode, and are not described in detail here.
[0184] In some optional implementations of this embodiment, the optimization module includes:
[0185] The third acquisition submodule is used to obtain preset multiple parameter adjustment strategies;
[0186] A second screening submodule, used to screen out a target parameter adjustment strategy from the multiple parameter adjustment strategies;
[0187] An optimization submodule, used to perform model optimization processing on the machine learning model based on the target parameter adjustment strategy to obtain an optimized machine learning model;
[0188] The third determination submodule is used to use the optimized machine learning model as the prediction model.
[0189] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the data evaluation method in the aforementioned implementation mode, and are not described in detail here.
[0190] In some optional implementations of this embodiment, the building blocks include:
[0191] A division submodule, used for dividing the sample data into a training data set and a test data set based on a preset division value;
[0192] A training submodule, used to train the prediction model using the training data set to obtain a trained prediction model;
[0193] A testing submodule, used to test the trained prediction model using the test data set and calculate a model evaluation index value corresponding to the trained prediction model;
[0194] A judgment submodule is used to judge whether the value of the model evaluation index is greater than a preset index threshold;
[0195] The fourth determination submodule is used to use the trained prediction model as the loss assessment model if the model evaluation index value is greater than the index threshold.
[0196] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the data evaluation method in the aforementioned implementation mode, and are not described in detail here.
[0197] 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.
[0198] 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.
[0199] 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.
[0200] 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 data evaluation 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.
[0201] 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 the computer-readable instructions stored in the memory 41 or process data, such as computer-readable instructions for running the data evaluation method.
[0202] 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.
[0203] Compared with the prior art, the embodiments of the present application have the following beneficial effects:
[0204] In the embodiment of the present application, firstly, it is determined whether a forestry risk assessment request triggered by a user is received; if so, forest remote sensing image data corresponding to the forest information is obtained from a preset remote sensing satellite; then, based on a preset image processing algorithm, target features are extracted from the forest remote sensing image data; subsequently, the target features are evaluated and processed based on a preset loss assessment model to generate a loss assessment result corresponding to the target forest; finally, the loss assessment result is displayed and processed. After receiving a forestry risk assessment request triggered by a user, the embodiment of the present application uses remote sensing satellite technology to quickly obtain forest remote sensing image data corresponding to the forest information, and based on the use of an image processing algorithm, target features are extracted from the forest remote sensing image data, and then the target features are evaluated and processed based on a loss assessment model to generate a loss assessment result corresponding to the target forest, thereby realizing an automated and accurate assessment of the loss of the target forest. Compared with traditional manual survey and sample survey methods, it can save a lot of manpower and material costs, reduce the influence of subjective factors on the assessment results, effectively improve the assessment efficiency and accuracy of the loss of the target forest, and ensure the accuracy of the generated loss assessment results.
[0205] 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 data evaluation method as described above.
[0206] Compared with the prior art, the embodiments of the present application have the following beneficial effects:
[0207] In the embodiment of the present application, firstly, it is determined whether a forestry risk assessment request triggered by a user is received; if so, forest remote sensing image data corresponding to the forest information is obtained from a preset remote sensing satellite; then, based on a preset image processing algorithm, target features are extracted from the forest remote sensing image data; subsequently, the target features are evaluated and processed based on a preset loss assessment model to generate a loss assessment result corresponding to the target forest; finally, the loss assessment result is displayed and processed. After receiving a forestry risk assessment request triggered by a user, the embodiment of the present application uses remote sensing satellite technology to quickly obtain forest remote sensing image data corresponding to the forest information, and based on the use of an image processing algorithm, target features are extracted from the forest remote sensing image data, and then the target features are evaluated and processed based on a loss assessment model to generate a loss assessment result corresponding to the target forest, thereby realizing an automated and accurate assessment of the loss of the target forest. Compared with traditional manual survey and sample survey methods, it can save a lot of manpower and material costs, reduce the influence of subjective factors on the assessment results, effectively improve the assessment efficiency and accuracy of the loss of the target forest, and ensure the accuracy of the generated loss assessment results.
[0208] 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.
[0209] 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 data evaluation method, characterized in that: The steps include: Determine whether a forestry insurance assessment request triggered by a user is received; wherein the forestry insurance assessment request carries forest land information of the target forest land; If so, obtaining forest remote sensing image data corresponding to the forest information from a preset remote sensing satellite; Based on a preset image processing algorithm, extracting target features from the forest remote sensing image data; The target characteristics are evaluated based on a preset loss assessment model to generate a loss assessment result corresponding to the target forest land; The loss assessment results are displayed.
2. The data evaluation method according to claim 1, characterized in that: The step of extracting target features from the forest remote sensing image data based on a preset image processing algorithm specifically includes: Extracting features from the forest remote sensing image data based on the image processing algorithm to obtain corresponding initial features; Get the preset specified feature type; Filtering out designated features corresponding to the designated feature type from the initial features; The designated feature is used as the target feature.
3. The data evaluation method according to claim 1, characterized in that: The step of displaying the loss assessment result specifically includes: Get the preset map; Based on geographic information system technology, the loss assessment results are presented on the map in a visual manner; The map is displayed in a preset interactive interface.
4. The data evaluation method according to claim 1, characterized in that: Before the step of evaluating the target feature based on the preset loss assessment model to generate a loss assessment result corresponding to the target forest land, the method further includes: Access to pre-collected historical forestland loss data; Preprocessing the historical forestland loss data to obtain corresponding target forestland loss data, and constructing sample data based on the target forestland loss data; Call the preset machine learning model; Optimizing the machine learning model based on a preset parameter adjustment strategy to obtain a corresponding prediction model; The prediction model is processed by model construction using the sample data to obtain a loss assessment model that meets preset construction requirements.
5. The data evaluation method according to claim 4, characterized in that: The step of preprocessing the historical forest land loss data to obtain corresponding target forest land loss data specifically includes: Performing data cleaning on the historical forest land loss data to obtain corresponding first loss data; Performing data supplementation processing on the first loss data to obtain corresponding second loss data; performing standardization processing on the second loss data to obtain corresponding third loss data; The third loss data is used as the target loss forest land data.
6. The data evaluation method according to claim 4, characterized in that: The step of optimizing the machine learning model based on a preset parameter adjustment strategy to obtain a corresponding prediction model specifically includes: Get preset multiple parameter adjustment strategies; Selecting a target parameter adjustment strategy from the plurality of parameter adjustment strategies; Performing model optimization processing on the machine learning model based on the target parameter adjustment strategy to obtain an optimized machine learning model; The optimized machine learning model is used as the prediction model.
7. The data evaluation method according to claim 4, characterized in that: The step of using the sample data to perform model construction processing on the prediction model to obtain a loss assessment model that meets the preset construction requirements specifically includes: Dividing the sample data into a training data set and a test data set based on a preset division value; Training the prediction model using the training data set to obtain a trained prediction model; Testing the trained prediction model using the test data set, and calculating a model evaluation index value corresponding to the trained prediction model; Determine whether the model evaluation index value is greater than a preset index threshold; If the model evaluation index value is greater than the index threshold, the trained prediction model is used as the loss assessment model.
8. A data evaluation device, characterized in that: include: A judgment module, used to judge whether a forestry insurance assessment request triggered by a user is received; wherein the forestry insurance assessment request carries forest land information of the target forest land; A first acquisition module is used to acquire forest remote sensing image data corresponding to the forest information from a preset remote sensing satellite; An extraction module, used for extracting target features from the forest remote sensing image data based on a preset image processing algorithm; An assessment module, used to assess the target features based on a preset loss assessment model and generate a loss assessment result corresponding to the target forest land; A display module is used to display the loss assessment results.
9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the data evaluation method according to any one of claims 1 to 7 when executing the computer-readable instructions.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the data evaluation method according to any one of claims 1 to 7.