Risk analysis method and device, computer equipment and storage medium

Abstract

The embodiment of the invention belongs to the field of financial science and technology, and relates to a risk analysis method and device, computer equipment and a storage medium, and the method comprises the following steps: obtaining growth time sequence multi-dimensional information, meteorological time sequence image information and growth environment parameter information, carrying out the preprocessing, and carrying out the space-time registration, feature extraction and data fusion; obtaining a crop growth monitoring data set; performing crop growth condition evaluation based on the crop growth monitoring data set to obtain a crop growth condition evaluation result; determining a key influence factor according to the crop growth condition evaluation result, and performing growth condition prediction according to the key influence factor and the crop growth condition evaluation result to obtain a growth trend prediction result; and performing crop growth risk analysis according to the crop growth condition evaluation result and the growth trend prediction result to obtain risk early warning information. According to the invention, the risk of crop growth can be accurately and effectively analyzed, so that risk early warning information can be generated in real time for early warning.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, specifically to the field of financial technology, and in particular to a risk analysis method, device, computer equipment and storage medium. Background Art

[0002] In the field of modern agricultural planting, precise management and risk control of crop growth cycles have become key factors affecting agricultural production efficiency and economic benefits. Traditional agriculture relies on the gift of natural conditions, but unpredictable weather, such as drought, floods, extreme temperature fluctuations and other unfavorable factors, often directly affect the crop growth cycle, resulting in slower growth, reduced quality and even crop failure. In addition, micro-environmental differences such as insufficient or excessive light, uneven soil moisture and nutrient distribution, have further exacerbated the uncertainty of crop growth.

[0003] At the same time, the outbreak of pests and diseases is a major concern in agricultural production. These biological factors not only affect the health of crops, but can also spread rapidly, causing large-scale yield reductions. Without a timely and effective monitoring and early warning mechanism, farmers can only respond passively, and by the time they take remedial measures, they have missed the best time, thus suffering significant economic losses.

[0004] In this context, modern agricultural technology is gradually transforming towards intelligence and precision. By integrating advanced technologies such as the Internet of Things, big data, and artificial intelligence, real-time monitoring and data analysis of farmland environments can be achieved, and potential growth risks, such as extreme weather and outbreaks of pests and diseases, can be predicted and identified in advance, providing farmers with scientific planting decision support. This data-driven agricultural management model not only helps optimize crop growth cycles, improve yields and quality, but also effectively reduces economic losses caused by natural disasters and pests and diseases, and promotes the sustainable development of the agricultural economy. Summary of the invention

[0005] The purpose of the embodiments of the present application is to propose a risk analysis method, device, computer equipment and storage medium to solve the problem of being unable to accurately and effectively identify and warn of risks in the crop planting process.

[0006] In order to solve the above technical problems, the present application embodiment provides a risk analysis method, which adopts the following technical solution:

[0007] Obtaining multi-dimensional information of growth time series, meteorological time series image information, and growth environment parameter information;

[0008] Preprocessing the growth time series multi-dimensional information, the meteorological time series image information, and the growth environment parameter information to obtain a first growth information data set, a second growth information data set, and a third growth information data set;

[0009] Performing spatiotemporal registration, feature extraction, and data fusion on the first growth information dataset, the second growth information dataset, and the third growth information dataset to obtain a crop growth monitoring dataset;

[0010] Performing crop growth status assessment based on the crop growth monitoring data set to obtain a crop growth status assessment result;

[0011] Determining key influencing factors according to the crop growth status assessment results, and predicting the growth status according to the key influencing factors and the crop growth status assessment results to obtain a growth trend prediction result;

[0012] Crop growth risk analysis is performed based on the crop growth status assessment results and the growth trend prediction results to obtain risk warning information.

[0013] Furthermore, the step of obtaining the multi-dimensional information of growth time series, the meteorological time series image information, and the growth environment parameter information specifically includes:

[0014] Acquire crop growth image data collected by a drone, and extract the growth time series multi-dimensional information from the crop growth image data;

[0015] Acquire satellite remote sensing image data, and extract the meteorological time-series image information from the satellite remote sensing image data;

[0016] A sensor data set collected by a sensor is acquired, and the growth environment parameter information is extracted from the sensor data set.

[0017] Furthermore, the step of preprocessing the growth time series multidimensional information, the meteorological time series image information, and the growth environment parameter information to obtain a first growth information data set, a second growth information data set, and a third growth information data set specifically includes:

[0018] Marking outliers and noise data on the growth time series multi-dimensional information, and removing the marked outliers and noise data to obtain the first growth information data set;

[0019] Performing atmospheric correction and geometric correction on the meteorological time series image information to obtain the second growth information data set;

[0020] The growth environment parameter information is subjected to data cleaning, denoising and standardization processing to obtain the third growth information data set.

[0021] Furthermore, the step of performing spatiotemporal registration, feature extraction, and data fusion on the first growth information dataset, the second growth information dataset, and the third growth information dataset to obtain a crop growth monitoring dataset specifically includes:

[0022] Determining whether the spatiotemporal reference systems of the first growth information dataset, the second growth information dataset, and the third growth information dataset are consistent;

[0023] If the spatiotemporal reference systems of the first growth information dataset, the second growth information dataset, and the third growth information dataset are inconsistent, converting the first growth information dataset, the second growth information dataset, and the third growth information dataset to a unified spatiotemporal reference system to obtain a first registration growth information dataset, a second registration growth information dataset, and a third registration growth information dataset;

[0024] Performing feature extraction on the first registered growth information dataset, the second registered growth information dataset, and the third registered growth information dataset to obtain a crop growth feature dataset;

[0025] The crop growth characteristic data set is fused according to a preset data fusion algorithm to obtain the crop growth monitoring data set.

[0026] Furthermore, the step of performing crop growth status assessment based on the crop growth monitoring data set to obtain a crop growth status assessment result specifically includes:

[0027] Preprocessing the crop growth monitoring data set to obtain an effective crop growth monitoring data set;

[0028] Acquire a model extraction identifier, and extract a crop growth status assessment model from a database according to the model extraction identifier;

[0029] The effective crop growth monitoring data set is input into the crop growth status assessment model to obtain the crop growth status assessment result.

[0030] Furthermore, the step of determining key influencing factors according to the crop growth status assessment result, and predicting the growth status according to the key influencing factors and the crop growth status assessment result to obtain the growth trend prediction result specifically includes:

[0031] Calculating the degree of influence of the characteristics of the crop growth monitoring data set on the crop growth status assessment result according to a preset characteristic importance analysis method;

[0032] Extracting a preset influence degree threshold, and determining whether the influence degree of the feature is greater than or equal to the influence degree threshold;

[0033] If the feature impact value is greater than or equal to the impact threshold, the feature corresponding to the feature impact value is used as the key impact factor;

[0034] Screening the crop growth monitoring data set according to the key influencing factors to obtain a key influencing data set;

[0035] constructing a key time series dataset based on the key impact dataset;

[0036] Extracting features from the key time series data set according to a time series analysis method to obtain a growth trend feature vector;

[0037] The growth trend feature vector and the crop growth status assessment result are input into a pre-trained key growth assessment model to obtain the growth trend prediction result.

[0038] Furthermore, the step of performing crop growth risk analysis based on the crop growth status assessment result and the growth trend prediction result to obtain risk warning information specifically includes:

[0039] Obtain environmental information for risk analysis;

[0040] Perform risk status judgment based on the risk analysis environment information, the crop growth status assessment result, and the growth trend prediction result to obtain the risk status type;

[0041] Extracting a corresponding risk warning model from a database according to the risk status type;

[0042] The risk analysis environment information, the crop growth status assessment results, and the growth trend prediction results are input into the risk warning model to obtain the risk warning information.

[0043] In order to solve the above technical problems, the embodiment of the present application further provides a risk analysis device, which adopts the following technical solution:

[0044] An information acquisition module is used to obtain multi-dimensional growth time series information, meteorological time series image information, and growth environment parameter information;

[0045] An information processing module, used for preprocessing the growth time series multi-dimensional information, the meteorological time series image information, and the growth environment parameter information to obtain a first growth information data set, a second growth information data set, and a third growth information data set;

[0046] a data set processing module, used for performing spatiotemporal registration, feature extraction, and data fusion on the first growth information data set, the second growth information data set, and the third growth information data set to obtain a crop growth monitoring data set;

[0047] A data evaluation module, used to evaluate the crop growth status based on the crop growth monitoring data set to obtain a crop growth status evaluation result;

[0048] A result prediction module is used to determine key influencing factors according to the crop growth status evaluation results, and to predict the growth status according to the key influencing factors and the crop growth status evaluation results to obtain a growth trend prediction result;

[0049] The risk analysis module is used to perform crop growth risk analysis based on the crop growth status assessment results and the growth trend prediction results to obtain risk warning information.

[0050] 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:

[0051] A computer device comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the risk analysis method as described in any one of the above items when executing the computer-readable instructions.

[0052] 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:

[0053] A computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the risk analysis method described in any one of the above items are implemented.

[0054] Compared with the prior art, the embodiment of the present application has the following beneficial effects: the embodiment obtains growth time series multidimensional information, meteorological time series image information, and growth environment parameter information; pre-processes the growth time series multidimensional information, the meteorological time series image information, and the growth environment parameter information to obtain a first growth information data set, a second growth information data set, and a third growth information data set; performs spatiotemporal registration, feature extraction, and data fusion on the first growth information data set, the second growth information data set, and the third growth information data set to obtain a crop growth monitoring data set; performs crop growth status assessment based on the crop growth monitoring data set to obtain a crop growth status assessment result; determines key influencing factors based on the crop growth status assessment result, and predicts growth status based on the key influencing factors and the crop growth status assessment result to obtain a growth trend prediction result; performs crop growth risk analysis based on the crop growth status assessment result and the growth trend prediction result to obtain risk warning information. Thus, accurate and effective analysis of crop growth risks is achieved, so that risk warning information is generated in real time for warning, thereby avoiding risks and effectively reducing economic losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] 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.

[0056] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0057] Figure 2 A flow chart of an embodiment of a risk analysis method according to the present application;

[0058] Figure 3 yes Figure 2 A flowchart of a specific implementation of step S30;

[0059] Figure 4 yes Figure 2 A flowchart of a specific implementation of step S40;

[0060] Figure 5 yes Figure 2 A flowchart of a specific implementation of step S50;

[0061] Figure 6 yes Figure 2 A flowchart of a specific implementation of step S60;

[0062] Figure 7 is a schematic structural diagram of an embodiment of a risk analysis device according to the present application;

[0063] Figure 8 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0064] 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.

[0065] 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 does it refer to non-related or alternative embodiments that are 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.

[0066] 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.

[0067] like Figure 1 As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0068] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0069] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to a laptop computer 1011, a tablet computer 1012 or a mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0070] The server 103 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal device 101 .

[0071] It should be noted that the risk analysis method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the risk analysis device is generally arranged in the server / terminal device.

[0072] It should be understood that Figure 1The 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.

[0073] Continue to refer Figure 2 , shows a flow chart of an embodiment of a risk analysis method according to the present application. The risk analysis method comprises the following steps:

[0074] Step S10, obtaining growth time series multi-dimensional information, meteorological time series image information, and growth environment parameter information;

[0075] In this embodiment, the multidimensional information of growth time series refers to a data set recorded over time during the growth of crops, and the key growth parameters include leaf area index, chlorophyll content, plant height and canopy coverage, among which the leaf area index is the ratio of the total area of ​​plant leaves per unit land area to the land area, the chlorophyll content is the key pigment content value of the crop, the plant height is the growth height of the crop, and the canopy coverage is the ratio of the projected area of ​​the crop canopy on the ground to the total land area. Meteorological time series image information is satellite remote sensing image data recorded in a region that changes over time. Meteorological time series image information includes time series data, multispectral information, spatial resolution information, etc., among which time series data refers to satellite remote sensing image data obtained regularly (such as daily, weekly or monthly) within a certain time range, multispectral information is information containing multiple spectral bands, such as visible light, infrared, microwave, etc., and spatial resolution information is the resolution information of the size of the smallest surface feature. Growth environment parameter information refers to useful parameter information collected in the crop growth environment. The growth environment parameter information includes soil temperature, soil moisture, light intensity, etc., among which soil temperature refers to the temperature conditions on the soil surface or at a certain depth, soil moisture refers to the water content in the soil or the saturation level of soil moisture, and light intensity refers to the light flux received per unit area.

[0076] Step S20, preprocessing the growth time series multi-dimensional information, the meteorological time series image information, and the growth environment parameter information to obtain a first growth information data set, a second growth information data set, and a third growth information data set;

[0077] In this embodiment, different preprocessing operations are performed according to the different information properties of growth time series multidimensional information, meteorological time series image information, and growth environment parameter information, wherein the preprocessing of growth time series multidimensional information includes the removal of outliers and noise data, the preprocessing of meteorological time series image information includes atmospheric correction and geometric correction, and the preprocessing of growth environment parameter information includes data cleaning, denoising, and standardization.

[0078] Step S30, performing spatiotemporal registration, feature extraction, and data fusion on the first growth information dataset, the second growth information dataset, and the third growth information dataset to obtain a crop growth monitoring dataset;

[0079] In this embodiment, spatiotemporal registration is a data processing operation that converts data at different times and different spatial locations into a unified spatiotemporal framework. Spatiotemporal registration includes time registration and space registration. Time registration is to eliminate the time error caused by the data being out of sync in time through an algorithm or asynchronous fusion method. Space registration is a data processing operation that converts data into a unified coordinate system and compensates for the measurement deviation during data collection. Feature extraction is a method of transforming a certain data to highlight the representative features of the data. Data fusion is a process of combining, correlating and combining data and information from multiple information sources.

[0080] Step S40, performing crop growth status assessment based on the crop growth monitoring data set to obtain a crop growth status assessment result;

[0081] In this embodiment, the crop growth status assessment is achieved by performing model assessment based on a pre-trained crop growth status assessment model. The crop growth status assessment model can adopt a random forest model. The training steps of the crop growth status assessment model include: obtaining a sample crop growth monitoring data set containing environmental parameters and physiological indicator data at various stages of crop growth, preprocessing the sample crop growth monitoring data set to obtain a training data set and a test data set suitable for a machine learning algorithm; constructing a crop growth status assessment model according to the goal of the sample crop growth status assessment, and training and optimizing the crop growth status assessment model using a cross-validation method; using the trained crop growth status assessment model to predict the test data set to obtain a performance indicator of the crop growth status assessment model on the test data set; and checking whether the performance indicator meets a preset indicator threshold. If so, using the current crop growth status assessment model as a pre-trained crop growth status assessment model.

[0082] Step S50, determining key influencing factors according to the crop growth status evaluation result, and performing growth status prediction according to the key influencing factors and the crop growth status evaluation result to obtain a growth trend prediction result;

[0083] In this embodiment, the key influencing factor refers to data information that has a significant impact on the evaluation process of the crop growth status evaluation result. The growth status prediction is achieved by predicting the growth trend of the crop based on the pre-trained key growth evaluation model. The training steps of the key growth evaluation model include: obtaining the first key factor data that affects the crop growth, constructing a time series data set for each first key factor data, and obtaining the key factor time series data set; using the time series analysis method to extract features from the key factor time series data set to obtain a crop growth trend feature vector; training a preset crop growth trend prediction model according to the crop growth trend feature vector, and the preset crop growth trend prediction model can use time series prediction algorithms such as ARIMA and LSTM; using the trained crop growth trend prediction model, combined with the second key factor data, to predict the crop growth status in the future; calculating the loss value between the predicted crop growth status and the real-time acquired crop growth status, and optimizing the model according to the loss value to obtain the key growth evaluation model; continuously collecting various monitoring data during the crop growth process for dynamically updating the key factor time series data set, and regularly retraining the model to obtain an effective key growth evaluation model.

[0084] Step S60, performing crop growth risk analysis based on the crop growth status assessment result and the growth trend prediction result to obtain risk warning information.

[0085] In this embodiment, the crop growth risk analysis is achieved by analyzing the crop growth status assessment results and the growth trend prediction results based on the risk warning model. The training steps of the risk warning model include: obtaining the sample crop growth status assessment results and the sample growth trend prediction results as the basic data for crop growth risk warning; obtaining agricultural meteorological data and pest and disease monitoring data as auxiliary data for crop growth risk warning; based on the sample crop growth status assessment results and the sample growth trend prediction results, combined with the agricultural meteorological data and the pest and disease monitoring data, using the threshold method to perform crop growth risk warning to determine whether the crops are in an adversity stress risk state; if the crops are in an adversity stress risk state, then based on the warning results of the threshold method, combined with the agricultural meteorological data and the pest and disease monitoring data, a cluster analysis method is used to determine the specific adversity stress risk type faced by the crops; based on the results of the cluster analysis, combined with the agricultural meteorological data and the pest and disease monitoring data, a machine learning algorithm is used to establish and train a risk warning model for crop growth.

[0086] This embodiment obtains growth time series multidimensional information, meteorological time series image information, and growth environment parameter information; pre-processes the growth time series multidimensional information, the meteorological time series image information, and the growth environment parameter information to obtain a first growth information data set, a second growth information data set, and a third growth information data set; performs spatiotemporal registration, feature extraction, and data fusion on the first growth information data set, the second growth information data set, and the third growth information data set to obtain a crop growth monitoring data set; performs crop growth status assessment based on the crop growth monitoring data set to obtain a crop growth status assessment result; determines key influencing factors based on the crop growth status assessment result, and predicts the growth status based on the key influencing factors and the crop growth status assessment result to obtain a growth trend prediction result; performs crop growth risk analysis based on the crop growth status assessment result and the growth trend prediction result to obtain risk warning information. This enables accurate and effective analysis of crop growth risks, generates risk warning information in real time for warning, and then avoids risks, effectively reducing economic losses.

[0087] This embodiment can be applied to crop planting risk warning. By generating risk warning information for real-time warning, the risks of crop planting can be effectively compared to reduce the economic losses of crop planting.

[0088] In some optional implementations of this embodiment, the acquisition of growth time series multi-dimensional information, meteorological time series image information, and growth environment parameter information includes the following steps:

[0089] Acquire crop growth image data collected by a drone, and extract the growth time series multi-dimensional information from the crop growth image data;

[0090] In this embodiment, the data collection of the drone includes determining the flight plan: according to the growth cycle and regional distribution of the crops, the flight plan of the drone is formulated, including flight time, route planning, altitude setting, etc., to ensure that the entire growth cycle and key growth stages of the crops in the coverage area are covered. Execution of flight missions: Using the high-definition camera or multispectral / hyperspectral camera carried by the drone, the crop field is imaged according to the flight plan to ensure that there are corresponding image records at different growth stages of the crops (such as sowing, emergence, growth, flowering, fruiting, maturity, etc.). Data transmission and storage: The image data captured by the drone is transmitted in real time to the ground station or storage device for subsequent processing and analysis.

[0091] Acquire satellite remote sensing image data, and extract the meteorological time-series image information from the satellite remote sensing image data;

[0092] In this embodiment, the acquisition of satellite remote sensing image data includes selecting a data source: selecting a suitable satellite data source according to the requirements, including MODIS, Landsat, Sentinel, etc., which provide image data of different resolutions and bands. Determining the time range: determining the time range for collecting image data to ensure that the changing trend of meteorological factors over time can be captured. Downloading image data: downloading satellite remote sensing image data within the required time range through the official website of the satellite data provider or a third-party data platform.

[0093] A sensor data set collected by a sensor is acquired, and the growth environment parameter information is extracted from the sensor data set.

[0094] In this embodiment, the step of collecting data by sensors includes deploying a sensor network: deploying various types of sensors in fields or greenhouses and other environments, such as temperature and humidity sensors, soil moisture sensors, light intensity sensors, carbon dioxide concentration sensors, etc., according to the monitoring needs of the research area and the crop growth environment, to monitor and record the required environmental parameters in real time. Set the sampling frequency: Set the sampling frequency of the sensor according to the research needs and data analysis accuracy requirements, where the selection of the sampling frequency should balance the relationship between data accuracy and storage / processing costs. Data collection and storage: The data collected by the sensor is transmitted to the data collection system (such as a data collector, data center, etc.) in real time by wired or wireless means, and stored to ensure the security and integrity of the data during transmission and storage.

[0095] This embodiment obtains crop growth image data collected by drones, and extracts the growth time series multidimensional information from the crop growth image data; obtains satellite remote sensing image data, and extracts the meteorological time series image information from the satellite remote sensing image data; obtains sensor data sets collected by sensors, and extracts the growth environment parameter information from the sensor data sets. Thus, the corresponding growth time series multidimensional information, meteorological time series image information, and growth environment parameter information are effectively obtained from different data sources to ensure the validity of the information and provide reliable data support for subsequent preprocessing steps.

[0096] In some optional implementations of this embodiment, the preprocessing of the growth time series multidimensional information, the meteorological time series image information, and the growth environment parameter information to obtain a first growth information data set, a second growth information data set, and a third growth information data set includes the following steps:

[0097] Marking outliers and noise data on the growth time series multi-dimensional information, and removing the marked outliers and noise data to obtain the first growth information data set;

[0098] In this embodiment, the identification of outliers and noise data can be implemented based on a threshold method or a standard deviation method, wherein the threshold method is to set a threshold value according to a reasonable range of growth environment parameters, and data beyond the range is regarded as an outlier, and the standard deviation method is to calculate the mean value and standard deviation of each growth environment parameter, and data far from the mean value (usually more than a certain multiple of the standard deviation) is regarded as an outlier. When outliers and noise data are identified, they are marked, and the data points corresponding to the marked outliers and noise data are deleted from the data set of the growth time series multidimensional information to obtain a first growth information data set.

[0099] Performing atmospheric correction and geometric correction on the meteorological time series image information to obtain the second growth information data set;

[0100] In this embodiment, atmospheric correction is used to eliminate the influence of factors such as atmosphere and illumination on the reflection of objects, and obtain real physical model parameters such as object reflectivity, radiation, and surface temperature. Atmospheric correction includes absolute atmospheric correction method and relative atmospheric correction method. In this embodiment, the atmospheric correction of meteorological time series image information adopts relative atmospheric correction method. The relative atmospheric correction method is based on statistical invariant target method, histogram matching method, etc., and performs correction through the statistical relationship between the image inside or different images corresponding to the meteorological time series image information. Geometric correction is to correct and eliminate the geometric deformation caused by various factors during remote sensing image imaging through a series of mathematical models. Geometric correction includes rough geometric correction and fine geometric correction. In this embodiment, geometric correction of meteorological time series image information adopts fine geometric correction. Fine geometric correction is a geometric correction performed using control points. The geometric distortion process of remote sensing images is described by mathematical models, and the corresponding points between the distorted remote sensing images and the standard map (i.e., control point data pairs) are used to obtain the geometric distortion model, and then the geometric distortion is corrected using this model.

[0101] The growth environment parameter information is subjected to data cleaning, denoising and standardization processing to obtain the third growth information data set.

[0102] In this embodiment, the purpose of data cleaning is to remove noise, errors and inconsistencies in the data to make the data set more accurate, reliable and complete. Data cleaning includes missing value processing, outlier processing and duplicate value processing. The purpose of denoising is to reduce random errors and noise in the data and improve the signal-to-noise ratio of the data. Denoising of data includes smoothing the data using techniques such as moving average and exponential smoothing to reduce the impact of random fluctuations, or filtering methods such as low-pass filters, high-pass filters or band-pass filters can be used to remove noise.

[0103] This embodiment obtains the first growth information data set by marking the outliers and noise data of the growth time series multidimensional information and removing the marked outliers and noise data; obtains the second growth information data set by performing atmospheric correction and geometric correction on the meteorological time series image information; obtains the third growth information data set by performing data cleaning, denoising and standardization on the growth environment parameter information. This effectively realizes different ways of processing different information to obtain standard and effective first growth information data set, second growth information data set and third growth information data set, which facilitates the subsequent generation of data sets based on the first growth information data set, the second growth information data set and the third growth information data set.

[0104] refer to Figure 3 In some optional implementations of this embodiment, step S30 includes the following steps:

[0105] Step S301, determining whether the spatiotemporal reference systems of the first growth information dataset, the second growth information dataset, and the third growth information dataset are consistent;

[0106] In this embodiment, the spatiotemporal reference system includes a time reference system and a space reference system. The consistency of the time reference system can be determined by checking the timestamp format of the data set and the time zone information of the data set. The consistency of the space reference system can be determined by checking the coordinate system of the data set, checking the projection parameters of the data set, and checking the spatial resolution of the data set.

[0107] Step S302: if the spatiotemporal reference systems of the first growth information dataset, the second growth information dataset, and the third growth information dataset are inconsistent, the first growth information dataset, the second growth information dataset, and the third growth information dataset are converted to a unified spatiotemporal reference system to obtain a first registration growth information dataset, a second registration growth information dataset, and a third registration growth information dataset;

[0108] In this embodiment, the step of converting the data set to a unified time reference system includes: selecting a common time starting point and time unit to ensure that the timestamps of all data sets can be converted to this reference system; determining the difference between the time reference system of each data set and the unified time reference system, including time zone difference, time format difference, etc.; according to the identified difference, converting the timestamp of each data set to match the unified time reference system. The step of converting the data set to a unified spatial reference system includes: selecting a geographic coordinate system (such as WGS84) or a projection coordinate system (such as UTM projection), and ensuring that all data sets can be converted to this coordinate system; for each data set, determining its current spatial reference system (including coordinate system and projection parameters) and the parameters required for conversion to the unified spatial reference system; using the reprojection function in GIS software (such as ArcGIS, QGIS) or programming library (such as GDAL, Proj4) to convert the spatial information of each data set to a unified spatial reference system.

[0109] Step S303: if the spatiotemporal reference systems of the first growth information dataset, the second growth information dataset, and the third growth information dataset are consistent, then the first growth information dataset, the second growth information dataset, and the third growth information dataset are saved as the first registration growth information dataset, the second registration growth information dataset, and the third registration growth information dataset;

[0110] In this embodiment, the first registration growth information dataset, the second registration growth information dataset, and the third registration growth information dataset are saved in a dataset folder created by the database. By saving the first registration growth information dataset, the second registration growth information dataset, and the third registration growth information dataset, data loss is avoided and the security of the system is improved.

[0111] Step S304, performing feature extraction on the first registered growth information dataset, the second registered growth information dataset, and the third registered growth information dataset to obtain a crop growth feature dataset;

[0112] In this embodiment, the crop growth feature data set includes spectral features, texture features, and shape features, wherein the spectral features are the reflected or emitted light intensity of the crop at different wavelengths, which are used to reflect the crop's physiological state, health, moisture content, chlorophyll content and other information, and the spectral features can be obtained by extracting the spectral information in the data set; the texture features are pixel distribution patterns that describe local areas in an image, and are usually related to crop properties such as surface roughness, leaf density, and canopy structure, and the texture features of the image can be extracted through gray-level co-occurrence matrix (GLCM), local binary pattern (LBP), and the like; the shape features refer to the geometric shapes of the crop in the image, such as the outline of the leaf, the shape of the fruit, and the shape features of the crop can be extracted through image processing techniques such as edge detection and shape analysis.

[0113] Step S305 , fusing the crop growth characteristic data set according to a preset data fusion algorithm to obtain the crop growth monitoring data set.

[0114] In this embodiment, the preset data fusion algorithm can adopt data-level fusion or feature-level fusion, and the crop growth monitoring data set includes spectral features: multispectral or hyperspectral image data; image data: high-resolution RGB images or infrared images; sensor data: real-time monitoring data of environmental parameters such as soil temperature and humidity, pH value, nutrient content, light intensity, wind speed and direction; biological data: indicator data directly reflecting the growth status of crops, such as crop growth rate, number of leaves, fruit size, and yield; meteorological data: meteorological element data such as rainfall, evaporation, temperature, humidity, and solar radiation; macro-scale information: information reflecting the macro-level such as crop distribution, planting area, and planting structure; meso-scale information: meso-level information such as crop canopy structure, leaf density, and growth density; micro-scale information: micro-level information such as morphological characteristics, color changes, and texture characteristics of organs such as leaves and fruits.

[0115] This embodiment determines whether the spatiotemporal reference systems of the first growth information dataset, the second growth information dataset, and the third growth information dataset are consistent; if the spatiotemporal reference systems of the first growth information dataset, the second growth information dataset, and the third growth information dataset are inconsistent, the first growth information dataset, the second growth information dataset, and the third growth information dataset are converted to a unified spatiotemporal reference system to obtain a first registered growth information dataset, a second registered growth information dataset, and a third registered growth information dataset; feature extraction is performed on the first registered growth information dataset, the second registered growth information dataset, and the third registered growth information dataset to obtain a crop growth feature dataset; the crop growth feature datasets are fused according to a preset data fusion algorithm, thereby effectively obtaining a crop growth monitoring dataset that fuses the features of each dataset, so as to facilitate subsequent evaluation of crop growth conditions.

[0116] Continue to refer Figure 4 In some optional implementations of this embodiment, step S40 includes the following steps:

[0117] Step S401, preprocessing the crop growth monitoring data set to obtain an effective crop growth monitoring data set;

[0118] In this embodiment, preprocessing includes data cleaning: removing data noise and filling missing values; data standardization and normalization: data standardization processing and data normalization processing. By preprocessing the crop growth monitoring data set, a standard, easy-to-process effective crop growth monitoring data set is obtained.

[0119] Step S402, obtaining a model extraction identifier, and extracting a crop growth status assessment model from a database according to the model extraction identifier;

[0120] In this embodiment, the model extraction identifier is a unique data identifier corresponding to the crop growth condition assessment model, and the unique data identifier can be an ID or a UUID. A matching query is performed in the database using the model extraction identifier to match the corresponding crop growth condition assessment model and perform extraction.

[0121] Step S403: input the effective crop growth monitoring data set into the crop growth status assessment model to obtain the crop growth status assessment result.

[0122] In this embodiment, the crop growth status assessment results include growth stage division: according to the growth characteristics and physiological indicators of the crop, the crop growth cycle is divided into different stages, such as sowing period, emergence period, tillering period, jointing period, heading period, filling period, maturity period, etc.; growth rate assessment: the growth amount of the crop in a certain period of time (such as plant height, leaf area, dry weight, etc.) is used to evaluate the growth rate of the crop; health status assessment: based on the characteristic information of the crop such as diseases, insect pests, and nutritional deficiencies, the health status of the crop is assessed; nutrient utilization efficiency assessment: by analyzing the absorption and utilization of soil nutrients by crops, the nutrient utilization efficiency of crops is assessed; yield prediction: based on the growth status of the crop and environmental conditions (such as climate, soil, etc.), the future yield of the crop is predicted.

[0123] This embodiment obtains an effective crop growth monitoring data set by preprocessing the crop growth monitoring data set; obtains a model extraction identifier, and extracts a crop growth status assessment model from a database according to the model extraction identifier; inputs the effective crop growth monitoring data set into the crop growth status assessment model, thereby effectively obtaining a crop growth status assessment result based on an accurate model prediction, so as to facilitate subsequent growth status prediction.

[0124] Continue to refer Figure 5 In some optional implementations of this embodiment, step S50 includes the following steps:

[0125] Step S501, calculating the degree of influence of the characteristics of the crop growth monitoring data set on the crop growth status assessment result according to a preset characteristic importance analysis method;

[0126] In this embodiment, the preset feature importance analysis method can adopt a decision tree-based feature importance evaluation. The decision tree-based feature importance evaluation works by recursively splitting the data set into smaller subsets, each subset is more homogeneous than the parent set (that is, the value of the target variable is more consistent), and then evaluating the importance of the feature based on the frequency of segmentation or the degree of improvement in the purity of the subset after segmentation.

[0127] Step S502, extracting a preset influence degree threshold, and determining whether the influence degree of the feature is greater than or equal to the influence degree threshold;

[0128] In this embodiment, the impact degree threshold is used to distinguish which feature impact degrees are significant and which are not significant, and the impact degree threshold can be preset based on experience, business requirements, etc. In this embodiment, before performing comparative judgment, it is necessary to first quantify the feature impact degree so as to convert the feature impact degree and the impact degree threshold into the same numerical unit, such as a decimal or a percentage, so as to achieve comparative judgment of the feature impact degree and the impact degree threshold.

[0129] Step S503: if the feature influence degree value is greater than or equal to the influence degree threshold, the feature corresponding to the feature influence degree value is used as the key influence factor;

[0130] In this embodiment, the key influencing factors refer to data information that has a significant impact on the evaluation process of the crop growth status evaluation results.

[0131] Step S504: if the feature influence degree value is less than the influence degree threshold, the feature corresponding to the feature influence degree value is used as a non-critical influence factor;

[0132] In this embodiment, the non-critical influencing factors refer to data information that has a non-significant impact on the evaluation process of the crop growth status evaluation results.

[0133] Step S505, screening the crop growth monitoring data set according to the key influencing factors to obtain a key influencing data set;

[0134] In this embodiment, the corresponding fields can be screened out from the effective crop growth monitoring data set according to the name or index of the key influencing factor, and the screened fields can be combined to obtain the key influencing data set.

[0135] Step S506, constructing a key time series data set according to the key impact data set;

[0136] In this embodiment, Pandas can be selected to construct the key time series data set. Pandas is a library for data analysis and processing in Python. It provides two data structures, DataFrame and Series, to store time series data. DataFrame is a two-dimensional label data structure that can store tabular data, one of which can be set as a time index. Series is a one-dimensional array that can also be set with a time index.

[0137] Step S507, extracting features from the key time series data set according to a time series analysis method to obtain a growth trend feature vector;

[0138] In this embodiment, the growth trend feature vector is a mathematical representation used to describe and quantify the growth trend of data in time series analysis, including long-term trends, growth rates, seasonal changes, cyclical fluctuations, etc. Time series analysis is to arrange the values ​​of statistical indicators in chronological order, find out the law of change of economic indicators through statistical analysis or the establishment of mathematical models, and perform trend extension and extrapolation based on this law to predict future development trends. Feature extraction includes trend feature extraction, seasonal feature extraction, and cyclical feature extraction, among which trend feature extraction includes linear trend: using a linear regression model to fit time series data, and extracting the slope as a measure of the linear trend. The slope represents the long-term trend of data changing over time; nonlinear trend: using polynomial regression, exponential smoothing or trend decomposition and other methods to fit, and extracting the corresponding trend parameters as features; sliding average / moving average: smoothing the data by calculating the average value of the data within a certain window to reduce the impact of random fluctuations on the trend, and the result of the moving average can be used as an approximate representation of the trend. Seasonal feature extraction: seasonal decomposition (such as STL decomposition) is used to extract seasonal components. Seasonal decomposition decomposes the time series into three parts: trend, seasonality, and residual. Periodic feature extraction: Extract periodic features using Fourier transform, autocorrelation function or spectrum analysis methods. Periodic features are usually manifested as peaks in the spectrum or periodic fluctuations in the autocorrelation function.

[0139] Step S508, inputting the growth trend feature vector and the crop growth status assessment result into a pre-trained key growth assessment model to obtain the growth trend prediction result.

[0140] In this embodiment, the growth trend prediction results include growth rate prediction: the growth rate of crops in a certain time period in the future, that is, the change in crop growth per unit time; growth amount prediction: the growth amount of crops at a certain point in the future, such as plant height, leaf area, biomass, etc.; growth stage division: predicting the current growth stage of the crop and the stage it may enter in the future, where the growth stage includes seedling stage, growth stage, maturity stage, etc.; growth environment adaptability assessment: assessing the adaptability of crops to the growth environment at different growth stages to predict the growth performance of crops in different environments.

[0141] This embodiment calculates the degree of influence of the characteristics of the crop growth monitoring data set on the crop growth status assessment result according to a preset feature importance analysis method; extracts a preset influence degree threshold to determine whether the characteristic influence degree is greater than or equal to the influence degree threshold; if the characteristic influence degree value is greater than or equal to the influence degree threshold, the characteristic corresponding to the characteristic influence degree value is used as the key influence factor; if the characteristic influence degree value is less than the influence degree threshold, the characteristic corresponding to the characteristic influence degree value is used as a non-key influence factor; the crop growth monitoring data set is screened according to the key influence factors to obtain a key influence data set; a key time series data set is constructed according to the key influence data set; the key time series data set is feature extracted according to the time series analysis method to obtain a growth trend feature vector; the growth trend feature vector and the crop growth status assessment result are input into a pre-trained key growth assessment model, thereby effectively obtaining a growth trend prediction result that accurately predicts crop growth, so as to facilitate subsequent crop growth risk analysis.

[0142] Continue to refer Figure 6 In some optional implementations of this embodiment, step S60 includes the following steps:

[0143] Step S601, obtaining risk analysis environment information;

[0144] In this embodiment, the risk analysis environmental information includes agricultural meteorological data and pest monitoring data, wherein agricultural meteorological data refers to data of various meteorological elements closely related to agricultural production, including but not limited to temperature, humidity, precipitation, wind speed, wind direction, light intensity, evaporation, etc. Pest monitoring data refers to data on the occurrence, development and spread of pests and diseases obtained through various monitoring means (such as real-time pest monitoring system, agricultural meteorological station, etc.).

[0145] Step S602, judging the risk status according to the risk analysis environment information, the crop growth status assessment result, and the growth trend prediction result, and obtaining the risk status type;

[0146] In this embodiment, the risk state includes a low-risk state, a medium-risk state, and a high-risk state, wherein the low-risk state refers to when the agricultural meteorological conditions are suitable for crop growth, the probability of occurrence of pests and diseases is low and controllable, and the growth of crops is in good condition, and the growth trend forecast also shows a stable growth trend. The medium-risk state refers to the existence of some potential adverse factors, such as meteorological fluctuations in local areas, and slight signs of occurrence of pests and diseases, etc.; or the crop growth status assessment results show that some indicators deviate from the normal range, but have not yet reached the level of seriously affecting growth; or the growth trend forecast shows that there may be certain uncertainties in the future. The high-risk state refers to when the agricultural meteorological conditions are bad, such as encountering extreme weather events (drought, floods, frost, etc.), or when pests and diseases are serious and difficult to control; at the same time, the crop growth status assessment results also show obvious signs of growth stunting or damage; the growth trend forecast predicts that crop growth will be seriously affected in the future.

[0147] Step S603, extracting a corresponding risk warning model from a database according to the risk status type;

[0148] In this embodiment, a matching query is performed in a database using the risk status type as query information, and the queried risk warning model is extracted to obtain a risk warning model corresponding to the risk status type.

[0149] Step S604: input the risk analysis environment information, the crop growth status assessment result, and the growth trend prediction result into the risk warning model to obtain the risk warning information.

[0150] In this embodiment, the risk warning information includes risk score, risk source, warning area and time range, warning suggestions or measures, risk assessment report, etc. The risk warning model can adopt a random forest model, and the preset random forest model is trained with basic data including sample crop growth status assessment results and sample growth trend prediction results, and auxiliary data including agricultural meteorological data and pest monitoring data to obtain a risk warning model for effective risk warning.

[0151] This embodiment obtains risk analysis environmental information; determines the risk status based on the risk analysis environmental information, the crop growth status assessment results, and the growth trend prediction results to obtain the risk status type; extracts the corresponding risk warning model from the database based on the risk status type; inputs the risk analysis environmental information, the crop growth status assessment results, and the growth trend prediction results into the risk warning model, thereby effectively obtaining risk warning information for accurate risk analysis based on the crop growth status assessment results and the growth trend prediction results, so as to facilitate risk avoidance based on the risk warning information.

[0152] 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).

[0153] 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.

[0154] Further references Figure 7 , as a response to the above Figure 1 In order to realize the method shown in the figure, the present application provides an embodiment of a risk analysis device, and the device embodiment is Figure 1 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0155] like Figure 7 As shown, the risk analysis device 700 described in this embodiment includes: an information acquisition module 701, an information processing module 702, a data set processing module 703, a data evaluation module 704, a result prediction module 705, and a risk analysis module 706. Among them:

[0156] Information acquisition module 701, used to acquire growth time series multi-dimensional information, meteorological time series image information, and growth environment parameter information;

[0157] An information processing module 702 is used to pre-process the growth time series multi-dimensional information, the meteorological time series image information, and the growth environment parameter information to obtain a first growth information data set, a second growth information data set, and a third growth information data set;

[0158] The data set processing module 703 is used to perform spatiotemporal registration, feature extraction, and data fusion on the first growth information data set, the second growth information data set, and the third growth information data set to obtain a crop growth monitoring data set;

[0159] A data evaluation module 704 is used to evaluate the crop growth status based on the crop growth monitoring data set to obtain a crop growth status evaluation result;

[0160] A result prediction module 705 is used to determine key influencing factors according to the crop growth status evaluation results, and to predict the growth status according to the key influencing factors and the crop growth status evaluation results to obtain a growth trend prediction result;

[0161] The risk analysis module 706 is used to perform crop growth risk analysis based on the crop growth status assessment result and the growth trend prediction result to obtain risk warning information.

[0162] By adopting the above-mentioned risk analysis device, this embodiment can obtain growth time series multidimensional information, meteorological time series image information, and growth environment parameter information; pre-process the growth time series multidimensional information, the meteorological time series image information, and the growth environment parameter information to obtain a first growth information data set, a second growth information data set, and a third growth information data set; perform spatiotemporal registration, feature extraction, and data fusion on the first growth information data set, the second growth information data set, and the third growth information data set to obtain a crop growth monitoring data set; evaluate the crop growth status based on the crop growth monitoring data set to obtain a crop growth status evaluation result; determine key influencing factors based on the crop growth status evaluation result, and predict the growth status based on the key influencing factors and the crop growth status evaluation result to obtain a growth trend prediction result; perform crop growth risk analysis based on the crop growth status evaluation result and the growth trend prediction result to obtain risk warning information. In this way, accurate and effective analysis of the risk of crop growth can be achieved, so that risk warning information can be generated in real time for warning, thereby avoiding risks and effectively reducing economic losses.

[0163] To solve the above technical problems, the present application also provides a computer device. Figure 8 , Figure 8 This is a basic structural block diagram of the computer device in this embodiment.

[0164] The computer device 8 includes a memory 81, a processor 82, and a network interface 83 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 8 with components 81-83, 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 (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0165] 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.

[0166] The memory 81 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 81 can be an internal storage unit of the computer device 8, such as a hard disk or memory of the computer device 8. In other embodiments, the memory 81 can also be an external storage device of the computer device 8, 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 8. Of course, the memory 81 can also include both the internal storage unit of the computer device 8 and its external storage device. In this embodiment, the memory 81 is generally used to store the operating system and various application software installed on the computer device 8, such as computer-readable instructions of the risk analysis method, etc. In addition, the memory 81 can also be used to temporarily store various types of data that have been output or are to be output.

[0167] The processor 82 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 82 is generally used to control the overall operation of the computer device 8. In this embodiment, the processor 82 is used to run computer-readable instructions stored in the memory 81 or process data, such as computer-readable instructions for running the risk analysis method.

[0168] The network interface 83 may include a wireless network interface or a wired network interface. The network interface 83 is generally used to establish a communication connection between the computer device 8 and other electronic devices.

[0169] By adopting the above-mentioned computer equipment, this embodiment can obtain growth time series multidimensional information, meteorological time series image information, and growth environment parameter information; pre-process the growth time series multidimensional information, the meteorological time series image information, and the growth environment parameter information to obtain a first growth information data set, a second growth information data set, and a third growth information data set; perform spatiotemporal registration, feature extraction, and data fusion on the first growth information data set, the second growth information data set, and the third growth information data set to obtain a crop growth monitoring data set; evaluate the crop growth status based on the crop growth monitoring data set to obtain a crop growth status evaluation result; determine key influencing factors based on the crop growth status evaluation result, and predict the growth status based on the key influencing factors and the crop growth status evaluation result to obtain a growth trend prediction result; perform crop growth risk analysis based on the crop growth status evaluation result and the growth trend prediction result to obtain risk warning information. In this way, accurate and effective analysis of the risk of crop growth can be achieved, so that risk warning information can be generated in real time for warning, thereby avoiding risks and effectively reducing economic losses.

[0170] 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 risk analysis method as described above.

[0171] By adopting the above-mentioned computer-readable storage medium, this embodiment can obtain growth time series multidimensional information, meteorological time series image information, and growth environment parameter information; pre-process the growth time series multidimensional information, the meteorological time series image information, and the growth environment parameter information to obtain a first growth information data set, a second growth information data set, and a third growth information data set; perform spatiotemporal registration, feature extraction, and data fusion on the first growth information data set, the second growth information data set, and the third growth information data set to obtain a crop growth monitoring data set; evaluate the crop growth status based on the crop growth monitoring data set to obtain a crop growth status evaluation result; determine key influencing factors based on the crop growth status evaluation result, and predict the growth status based on the key influencing factors and the crop growth status evaluation result to obtain a growth trend prediction result; perform crop growth risk analysis based on the crop growth status evaluation result and the growth trend prediction result to obtain risk warning information. In this way, accurate and effective analysis of the risk of crop growth can be achieved, so that risk warning information can be generated in real time for warning, thereby avoiding risks and effectively reducing economic losses.

[0172] 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.

[0173] 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 risk analysis method, characterized in that: The steps include: Obtaining multi-dimensional information of growth time series, meteorological time series image information, and growth environment parameter information; Preprocessing the growth time series multi-dimensional information, the meteorological time series image information, and the growth environment parameter information to obtain a first growth information data set, a second growth information data set, and a third growth information data set; Performing spatiotemporal registration, feature extraction, and data fusion on the first growth information dataset, the second growth information dataset, and the third growth information dataset to obtain a crop growth monitoring dataset; Performing crop growth status assessment based on the crop growth monitoring data set to obtain a crop growth status assessment result; Determining key influencing factors according to the crop growth status assessment results, and predicting the growth status according to the key influencing factors and the crop growth status assessment results to obtain a growth trend prediction result; Crop growth risk analysis is performed based on the crop growth status assessment results and the growth trend prediction results to obtain risk warning information.

2. The risk analysis method according to claim 1, characterized in that: The step of obtaining the growth time series multi-dimensional information, the meteorological time series image information, and the growth environment parameter information specifically includes: Acquire crop growth image data collected by a drone, and extract the growth time series multi-dimensional information from the crop growth image data; Acquire satellite remote sensing image data, and extract the meteorological time-series image information from the satellite remote sensing image data; A sensor data set collected by a sensor is acquired, and the growth environment parameter information is extracted from the sensor data set.

3. The risk analysis method according to claim 1, characterized in that: The step of preprocessing the growth time series multi-dimensional information, the meteorological time series image information, and the growth environment parameter information to obtain a first growth information data set, a second growth information data set, and a third growth information data set specifically includes: Marking outliers and noise data on the growth time series multi-dimensional information, and removing the marked outliers and noise data to obtain the first growth information data set; Performing atmospheric correction and geometric correction on the meteorological time series image information to obtain the second growth information data set; The growth environment parameter information is subjected to data cleaning, denoising and standardization processing to obtain the third growth information data set.

4. The risk analysis method according to claim 1, characterized in that: The step of performing spatiotemporal registration, feature extraction, and data fusion on the first growth information dataset, the second growth information dataset, and the third growth information dataset to obtain a crop growth monitoring dataset specifically includes: Determining whether the spatiotemporal reference systems of the first growth information dataset, the second growth information dataset, and the third growth information dataset are consistent; If the spatiotemporal reference systems of the first growth information dataset, the second growth information dataset, and the third growth information dataset are inconsistent, converting the first growth information dataset, the second growth information dataset, and the third growth information dataset to a unified spatiotemporal reference system to obtain a first registration growth information dataset, a second registration growth information dataset, and a third registration growth information dataset; Performing feature extraction on the first registered growth information dataset, the second registered growth information dataset, and the third registered growth information dataset to obtain a crop growth feature dataset; The crop growth characteristic data set is fused according to a preset data fusion algorithm to obtain the crop growth monitoring data set.

5. The risk analysis method according to claim 1, characterized in that: The step of evaluating the crop growth status based on the crop growth monitoring data set to obtain the crop growth status evaluation result specifically includes: Preprocessing the crop growth monitoring data set to obtain an effective crop growth monitoring data set; Acquire a model extraction identifier, and extract a crop growth status assessment model from a database according to the model extraction identifier; The effective crop growth monitoring data set is input into the crop growth status assessment model to obtain the crop growth status assessment result.

6. The risk analysis method according to claim 1, characterized in that: The step of determining key influencing factors according to the crop growth status evaluation results, and predicting the growth status according to the key influencing factors and the crop growth status evaluation results to obtain the growth trend prediction results specifically includes: Calculating the degree of influence of the characteristics of the crop growth monitoring data set on the crop growth status assessment result according to a preset characteristic importance analysis method; Extracting a preset influence degree threshold, and determining whether the influence degree of the feature is greater than or equal to the influence degree threshold; If the feature impact value is greater than or equal to the impact threshold, the feature corresponding to the feature impact value is used as the key impact factor; Screening the crop growth monitoring data set according to the key influencing factors to obtain a key influencing data set; constructing a key time series dataset based on the key impact dataset; Extracting features from the key time series data set according to a time series analysis method to obtain a growth trend feature vector; The growth trend feature vector and the crop growth status assessment result are input into a pre-trained key growth assessment model to obtain the growth trend prediction result.

7. The risk analysis method according to claim 1, characterized in that: The step of performing crop growth risk analysis based on the crop growth status assessment result and the growth trend prediction result to obtain risk warning information specifically includes: Obtain environmental information for risk analysis; Perform risk status judgment based on the risk analysis environment information, the crop growth status assessment result, and the growth trend prediction result to obtain the risk status type; Extracting a corresponding risk warning model from a database according to the risk status type; The risk analysis environment information, the crop growth status assessment results, and the growth trend prediction results are input into the risk warning model to obtain the risk warning information.

8. A risk analysis device, characterized in that: include: An information acquisition module is used to obtain multi-dimensional growth time series information, meteorological time series image information, and growth environment parameter information; An information processing module, used for preprocessing the growth time series multi-dimensional information, the meteorological time series image information, and the growth environment parameter information to obtain a first growth information data set, a second growth information data set, and a third growth information data set; a data set processing module, used for performing spatiotemporal registration, feature extraction, and data fusion on the first growth information data set, the second growth information data set, and the third growth information data set to obtain a crop growth monitoring data set; A data evaluation module, used to evaluate the crop growth status based on the crop growth monitoring data set to obtain a crop growth status evaluation result; A result prediction module is used to determine key influencing factors according to the crop growth status evaluation results, and to predict the growth status according to the key influencing factors and the crop growth status evaluation results to obtain a growth trend prediction result; The risk analysis module is used to perform crop growth risk analysis based on the crop growth status assessment results and the growth trend prediction results to obtain risk warning information.

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 risk analysis 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, and when the computer-readable instructions are executed by a processor, the steps of the risk analysis method according to any one of claims 1 to 7 are implemented.

Images