Crop monitoring method and related equipment

Abstract

The embodiment of the invention belongs to the field of artificial intelligence, is applied to the field of smart agriculture, and relates to a crop monitoring method, which comprises the following steps: acquiring images and growth environment data of crops in a target area according to preset time nodes to obtain crop images and growth environment data corresponding to each time node; respectively carrying out standardization processing on the crop images to obtain standardized crop images; inputting the crop standardized image into a preset convolutional neural network model for image processing, and generating crop growth state information; performing feature construction on the crop growth state information and the growth environment data by a sliding window method to obtain a time sequence feature set; inputting the time sequence feature set into a preset crop growth prediction model to generate growth prediction information of crops in the target area; and generating visual information according to the time sequence feature set and the growth prediction information, and feeding back the visual information to the user terminal. The crop monitoring efficiency can be improved, and the growth state can be predicted.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a crop monitoring method, device, computer equipment and computer-readable storage medium. Background Art

[0002] With the development of science and technology, the gradual development of traditional agriculture towards intelligent agriculture has become a development trend.

[0003] In the existing technology, manual field surveys are mainly used to observe the growth status of crops. This is highly dependent on manual experience, easily affected by subjective factors, and cannot accurately identify the growth status of crops. Even if the relevant information is fed back to agricultural experts, due to the long information collection cycle and time lag, agricultural experts cannot follow up in time. If pests and diseases occur, it will cause great economic losses to crop planting. Therefore, the current crop monitoring has the technical problem of low efficiency. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose a crop monitoring method, device, computer equipment and computer-readable storage medium, the main purpose of which is to automatically identify the growth status of crops during crop monitoring, timely predict the growth status of crops, and improve the efficiency of crop monitoring.

[0005] In order to solve the above technical problems, the present application provides a crop monitoring method, which adopts the following technical solutions:

[0006] Collect images and growth environment data of crops in the target area according to preset time nodes, and obtain crop images and growth environment data corresponding to each time node;

[0007] Performing standardization processing on the crop images corresponding to each time node to obtain a standardized crop image corresponding to each time node;

[0008] Inputting the standardized crop images corresponding to each time node into a preset convolutional neural network model for image processing to generate crop growth status information corresponding to each time node;

[0009] The crop growth status information and growth environment data corresponding to each time node are subjected to a sliding window method to construct features to obtain a time series feature set;

[0010] Inputting the time series feature set into a preset crop growth prediction model based on a time series algorithm to generate growth prediction information of crops in the target area;

[0011] Visualization information is generated according to the time series feature set and the growth prediction information, and the visualization information is fed back to a user terminal.

[0012] In order to solve the above technical problems, the embodiment of the present application further provides a crop monitoring device, which adopts the following technical solution, and the crop monitoring device includes:

[0013] The acquisition module is used to acquire images and growth environment data of crops in the target area according to preset time nodes, and obtain crop images and growth environment data corresponding to each time node;

[0014] A processing module, used for performing standardization processing on the crop images corresponding to each time node to obtain a standardized crop image corresponding to each time node;

[0015] A calculation module, used for inputting the standardized images of crops corresponding to each time node into a preset convolutional neural network model for image processing to generate crop growth status information corresponding to each time node;

[0016] A construction module, used to construct features using a sliding window method for the crop growth status information and growth environment data corresponding to each time node to obtain a time series feature set;

[0017] A prediction module, used for inputting the time series feature set into a preset crop growth prediction model based on a time series algorithm to generate growth prediction information of crops in the target area;

[0018] A feedback module generates visualization information according to the time series characteristics and the crop growth prediction information, and feeds back the visualization information to a user terminal.

[0019] 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:

[0020] The computer device comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the above-mentioned crop monitoring method when executing the computer-readable instructions.

[0021] 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:

[0022] The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps of the above-mentioned crop monitoring method are implemented.

[0023] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0024] By regularly collecting images and growth environment data of crops in the target area, the crop images are first standardized to ensure the accuracy of the subsequent generation of crop growth status information using the convolutional neural network model. Then, the crop growth status information and growth environment data of each time node are constructed using the sliding window method to obtain time series features. The time series features are input into the crop growth prediction model based on the time series algorithm, which can accurately generate growth prediction information of crops in the target area. After that, the perfect time series features and future crop growth prediction information can be conveniently used to generate visualization information and send it to the user terminal, so as to timely display the current crop monitoring information and future crop growth prediction information to the user, thereby improving the efficiency and accuracy of crop monitoring. In this way, users can not only accurately grasp the current crop growth status and environmental data, but also intervene in advance according to the future crop growth prediction information to avoid abnormal growth status of crops in the future. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] 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.

[0026] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0027] Figure 2 is a flow chart of an embodiment of a crop monitoring method according to the present application;

[0028] Figure 3 is a flow chart of another embodiment of the crop monitoring method according to the present application;

[0029] Figure 4 is a flow chart of another embodiment of the crop monitoring method according to the present application;

[0030] Figure 5 is a schematic structural diagram of an embodiment of a crop monitoring device according to the present application;

[0031] Figure 6 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0032] 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.

[0033] 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.

[0034] 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.

[0035] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a sensor device set 104, a network 105, and a server 106. The network 105 is used to provide a medium for communication links between the terminal devices 101, 102, 103, the sensor device set 104, and the server 106. The sensor device set 104 may include but is not limited to temperature sensors, humidity sensors, camera devices, soil component detection sensors, location sensors, data registration devices, etc. The network 105 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0036] The server 106 can issue data collection commands to the sensor device set 104 through the network 105 according to the preset time node strategy, and the sensor device set 104 can transmit the collected crop growth images and growth environment data to the server 106 through the network 105. Users can use terminal devices 101, 102, and 103 to interact with the sensor device set 104 and the server 106 through the network 105 to receive or send messages or commands, etc. Various communication client applications can be installed on the terminal devices 101, 102, and 103, such as web browser applications, search applications, instant messaging tools, email clients, social platform software, etc., for receiving and displaying the visual information of crop monitoring generated and sent by the server 106.

[0037] The terminal devices 101, 102, and 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, etc.

[0038] The server 106 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 .

[0039] It should be noted that the crop monitoring method provided in the embodiment of the present application is generally executed by a server, and accordingly, the crop monitoring device is generally disposed in the server.

[0040] It should be understood that Figure 1 The number of terminal devices, sensor device sets, networks and servers in the embodiment is only for illustration. Any number of terminal devices, sensor device sets, networks and servers may be provided according to implementation requirements.

[0041] Continue to refer Figure 2 , shows a flow chart of an embodiment of a crop monitoring method according to the present application. The crop monitoring method comprises the following steps:

[0042] Step S201, collecting images and growth environment data of crops in a target area according to preset time nodes, and obtaining crop images and growth environment data corresponding to each time node.

[0043] In this embodiment, the crop monitoring method is executed on an electronic device (eg Figure 1 The server / sensor device set / terminal device shown in the figure can be connected via a wired connection or a wireless connection, receive the command request of the server, and collect the image and growth environment data of the crops in the target area according to the preset time interval. It should be noted that the above wireless connection method can 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.

[0044] The preset time nodes may be time nodes within a preset time range, and the preset time range may be from the sowing date to the current date, or from a historical date with a preset time from the current date to the current date. The preset time nodes for collecting crop images and growth environment data may be the same or different, and may be: daily nodes, one or more fixed time points or time periods every day, such as 9 am, 12 pm and 4 pm every day; or a fixed time point or time period on one or more days of each week. When the time nodes for collecting images and growth environment data are different, the alignment rules for images and growth environment data are preset.

[0045] The acquisition equipment can be a variety of sensor devices based on IoT technology, including but not limited to: fixed-position cameras or patrol vehicles with cameras, drones, etc., for collecting crop images; temperature sensors for measuring ambient temperature; light sensors for measuring light intensity; location sensors for measuring the coordinate range of the current area in the data format of longitude and latitude; other sensors, such as recording and registration equipment for recording sowing dates, crop types, manual operations, etc. Each of the above sensors can be single or multiple.

[0046] The target area can be a limited farmland or greenhouse area. When the target area is large, it can also be divided into several sub-areas and numbered, and then sensors with corresponding numbers are placed in the corresponding sub-areas. In this way, the collected images and growth environment data carry the sub-area number information, which is convenient for subsequent monitoring in sub-areas.

[0047] The collected data include crop images and growth environment data of the target area corresponding to each time node. The crop images corresponding to the time node can be a single image or multiple images. The growth environment data include but are not limited to the temperature, humidity, light intensity, wind intensity, rainfall in the weather, etc. at the corresponding time node. If the corresponding time node is a time period, the average value of the above parameters in the time period needs to be calculated later.

[0048] Furthermore, to ensure image quality, the collected crop images are taken during the day as much as possible.

[0049] Furthermore, the collected crop images should contain at least one complete plant of the crop in the target area as much as possible, and the images should be taken under the same camera setting parameters, for example, the same image size, resolution, depth of field, shooting distance, etc.

[0050] Specifically, as an implementation method, various sets of sensor devices based on the Internet of Things network can be controlled to collect crop images and growth environment data of the target area according to preset time nodes, and send them to the server, or the server can control the sending and storage to the cloud or blockchain nodes.

[0051] It should be noted that the growth environment data also includes information such as crop sowing date and crop type, longitude and latitude location information, etc. After this information has been collected and stored on the server, it does not need to be collected at every time node.

[0052] As an implementation manner, before the step of collecting images and growth environment data of crops in the target area according to preset time nodes to obtain crop images and growth environment data corresponding to each time node, the method further includes:

[0053] A sensor network system based on Internet of Things technology is established in the target area to collect images and growth environment data of crops in the target area, wherein the growth environment data includes but is not limited to: soil nutrient information, temperature, humidity, light, geographic information, and weather information of the target area.

[0054] Among them, the Internet of Things (IoT) technology refers to connecting various devices, sensors and systems through the Internet to realize data collection, transmission and processing, thereby realizing intelligent management and control. Based on the Internet of Things technology, various sensor devices are deployed in the target area to obtain a sensor device set 104, and various authorized information, such as weather information, etc., are collected through the server 106 to form a sensor network system. The sensor device set 104 includes but is not limited to various sensors for collecting images, soil nutrient information, temperature, humidity, light, and geographic information of the target area. After the arrangement of each sensor is completed, each sensor can be connected to the Internet through various network protocols (such as WiFi, Bluetooth, Zigbee, LoRa, etc.) to realize data transmission and communication with the server 106. The server 106 processes the collected data to obtain images and growth environment data of crops in the target area.

[0055] As a result, real-time collection of crop images and growth environment data is achieved, the collection efficiency and stability are improved, and the real-time analysis of crop images and growth environment data is facilitated, thereby improving the analysis efficiency.

[0056] Step S202 , performing standardization processing on the crop images corresponding to the respective time nodes to obtain standardized crop images corresponding to the respective time nodes.

[0057] In this embodiment, the standard processing of the crop image may be a series of standard processing such as image preprocessing, color standardization, image enhancement, noise removal and image normalization to obtain a standardized crop image of uniform specifications and quality. These standardized images can be used for subsequent analysis and processing, which helps to improve the accuracy of subsequent extraction of crop growth characteristics and growth status classification.

[0058] As an implementation manner, the step of performing standardization processing on the crop images corresponding to the respective time nodes to obtain the standardized crop images corresponding to the respective time nodes specifically includes:

[0059] Performing size, shape and pixel standardization preprocessing on the crop images at each time node to obtain a preprocessed crop image corresponding to each time node;

[0060] De-noising the pre-processed crop images corresponding to each time node by using a bilateral filtering algorithm to obtain a smoothed crop image corresponding to each time node;

[0061] Performing color correction processing on the smoothed crop images corresponding to each time node by using a white balance algorithm to obtain a corrected crop image corresponding to each time node;

[0062] The processed crop images corresponding to the time nodes are respectively marked with growth period marks to obtain standardized crop images corresponding to the time nodes.

[0063] Specifically, according to the preset image standard value, the size, shape and pixel of the crop image corresponding to each time node are adjusted / modified respectively, so that the specifications of each crop image are the same, and the pre-processed crop image corresponding to each time node is obtained. Then, the denoising process is performed by the bilateral filtering algorithm to obtain the smoothed crop image corresponding to each time node after denoising, thereby improving the accuracy of image recognition. The smoothed crop image corresponding to each time node can also be color corrected by the white balance algorithm, so that the crop image is closer to its actual growth color, thereby improving the accuracy of image recognition.

[0064] It should be noted that when standardizing crop images, the crop images can also be labeled with the growth period. The growth period is the difference between the image acquisition date and the crop planting date. Because crop growth characteristics such as plant height, stem thickness, flower number, size, color characteristics, and leaf number, size, shape and color are closely related to the number of growing days, labeling the growth period will help improve the accuracy of subsequent extraction of crop growth characteristics and growth status classification.

[0065] Therefore, the present application can reduce redundant information of crop images, reduce computational complexity, and speed up processing through standardized processing; moreover, it can make the details in crop images clearer, make crop images from different sources have consistent scale and distribution, improve the robustness of subsequent image processing algorithms, and make them more stable when facing different types of images.

[0066] Step S203, inputting the standardized crop images corresponding to each time node into a preset convolutional neural network model for image processing to generate crop growth status information corresponding to each time node.

[0067] In this embodiment, the preset convolutional neural network model can classify crop images through data training to obtain corresponding crop growth status information. The training data set includes images corresponding to each growth state of the crop, and the convolutional neural network model can be accurately classified through training. The growth status information may include growth stages and status values, wherein the growth stages may include "seedling stage", "mature stage", etc., and the status values ​​may include: "normal" and "abnormal".

[0068] As an implementation mode, the step of inputting the standardized crop images corresponding to each time node into a preset convolutional neural network model for image processing to generate the crop growth status information corresponding to each time node specifically includes:

[0069] Obtaining crop types according to crop images corresponding to each time node, and determining a convolutional neural network model corresponding to the crop type;

[0070] The standardized images corresponding to the time nodes are respectively input into the convolutional neural network model for processing to obtain the crop growth status information corresponding to the time nodes, wherein the crop growth status information includes the growth characteristic information and growth status classification information of the crop.

[0071] Furthermore, the preset convolutional neural network model corresponding to the target crop species and target geographical area can be selected according to the geographical location information in the collected growth environment data. Because even for the same species, different geographical locations have a huge impact on the growth status information of the target species. For example, rice in Northeast China, Central China, South China and Hainan has huge differences in planting time, growth cycle and growth status information due to geographical differences. Selecting the preset convolutional neural network model corresponding to the target crop species and target geographical area can focus more on the growth status information of the target crop in the specified geographical area, and improve the accuracy of the growth status information generated by the target crop.

[0072] Then, the standardized images corresponding to each time node are respectively input into the convolutional neural network model for processing to obtain the crop growth status information corresponding to each time node. The crop growth status information generated by the preset convolutional neural network model may include: crop growth characteristic information and growth status classification information.

[0073] Among them, the growth characteristic information can include different growth characteristics according to the crop type and geographical region, such as plant height, leaf area, leaf color, leaf shape, stem diameter and verticality, number of flowers, flower color, number of fruits, fruit color, fruit size and growth stage, etc. The growth status classification information can also include different growth status classification information according to different crop types and geographical regions, and can be expressed in the format of "growth stage-status value", where the status value can include: "normal", "abnormal: disease", "abnormal: insect pest", "abnormal: growth retardation", "abnormal: lodging", etc. For example, when the growth features extracted from the crop image are reproductive period features and there are no abnormalities, and the growth days are also verified to be the reproductive period, the growth status classification information output by the preset convolutional neural network model is "reproductive period-normal"; if the leaves and flowers in the above-extracted growth features have insect pest or disease features that exceed the hidden threshold, the growth status classification information output by the preset convolutional neural network model is "reproductive period-abnormal: disease" or "reproductive period-abnormal: insect pest"; if the extracted growth features are seedling period features, and the growth days are verified to be the reproductive period, the growth status classification information output by the preset convolutional neural network model is "seedling period-abnormal: slow growth".

[0074] In this embodiment, since the type of crop has a huge impact on the crop growth status information, in order to focus more on accurately generating the growth status information of the target crop, a convolutional neural network model corresponding to the crop type can be selected according to the crop type. This can reduce the model training time and training amount, while improving the accuracy of generating the growth status information of the target crop.

[0075] Step S204, constructing features using a sliding window method for the crop growth status information and growth environment data corresponding to each time node to obtain a time series feature set.

[0076] In this embodiment, the crop growth status information and growth environment data of each time node are standardized to obtain the crop growth status information and growth environment data in a sequence format, and then the crop growth status information and growth environment data in a sequence format are interpolated and aligned according to the time node, and the window features of each sliding window are calculated using the defined window size and window sliding step size, and finally all the window features are merged to form a new time series feature data set.

[0077] As an implementation mode, the step of constructing features using a sliding window method for the crop growth status information and growth environment data corresponding to each time node to obtain time series features specifically includes:

[0078] Cleaning, formatting and serializing the growth state information and growth environment data corresponding to each time node to obtain a growth state window sequence and a growth environment window sequence;

[0079] The growth state window sequence and the growth environment window sequence are combined to construct a time series feature set.

[0080] Specifically, the crop growth status information and growth environment data of each time node are standardized, including data cleaning, data formatting and data serialization. Among them, data cleaning can be specifically selected to first delete records with missing values, or fill missing values ​​with methods such as mean, median, interpolation, etc., and then use statistical methods (such as standard deviation) or machine learning methods (such as isolation forest) to identify and remove outliers in the data, and finally use methods such as moving average or exponential smoothing to reduce noise in the data. Data formatting, specifically, first format the time node by timestamp formatting to ensure that all time nodes are in the same format, usually using ISO 8601 format (such as YYYY-MM-DD HH:MM:SS), and then standardize the crop growth status information and environmental data features, and scale the feature values ​​to the same range. Commonly used methods include normalization (scaling the values ​​to the [0,1] range) and standardization (converting the values ​​to a distribution with a mean of 0 and a standard deviation of 1). Data serialization, the growth status information and growth environment data that have undergone data cleaning and data formatting are converted into their respective time series to obtain growth status window series and growth environment window series.

[0081] Specifically, when constructing the sliding window feature, the window is initialized first, that is, starting from the starting point of the crop growth status information and the growth environment data respectively, the first set of data is taken according to the window size, the corresponding features are calculated, and the features of the first window in the window sequence are obtained. Among them, the window size can be a preset time period, including one time node or multiple time nodes. The calculation method of the window feature can include calculating the average value, maximum value, minimum value, standard deviation, etc. For example, the growth features in the growth status information are calculated: the average height of the plant in the window, the maximum leaf area index, the average number of fruits, etc.; the growth environment features are calculated: for example, the average temperature in the window, the total rainfall, the average light intensity, etc. The sliding window reselects the data of the window size according to the step size moving window, and repeats the above calculation steps until the entire growth status information is traversed, and the features of all windows are obtained to form a growth status window sequence. Similarly, the environmental features are calculated according to the growth environment data to generate a growth environment window sequence. Then, according to each time node, each window feature corresponding to the growth state window sequence and the growth environment window sequence is merged to form a new time series feature set.

[0082] In this embodiment, the growth status information and growth environment data corresponding to each time node are cleaned, formatted and serialized to obtain a growth status window sequence and a growth environment window sequence, which improves data accuracy and obtains an ordered window sequence that characterizes the growth status and the growth environment; then, the growth status window sequence and the growth environment window sequence are merged according to the time node to construct a time series feature set that records the growth status and the growth environment in time order. The serialized data set records a larger amount of information, which can improve the stability and accuracy of subsequent model processing.

[0083] Step S205: input the time series feature set into a preset crop growth prediction model based on a time series algorithm to generate growth prediction information of the crops in the target area.

[0084] In this embodiment, the crop growth prediction model can be a long short-term memory (LSTM) neural network model based on a time series algorithm. Specifically, the LSTM model can predict future growth characteristics and states by inputting historical crop growth data (such as environmental factors such as temperature, humidity, light intensity, and plant growth status data). For example, the growth rate, number of leaves, flowering time, etc. of crops in the future window period can be predicted. In addition, the LSTM model can also perform state classification, for example, classifying crops into different states such as health, water shortage, and disease according to the input growth data, and judging whether the predicted growth state of the crop is abnormal.

[0085] Among them, the growth prediction information includes the growth characteristics and state classification of crops in a single or multiple time windows in the future.

[0086] Furthermore, future weather information is extracted from the weather information to generate partial known environmental characteristic information of the future, and a long short-term memory (LSTM) neural network model based on multivariate time series prediction is used to generate crop growth prediction information. This is because it not only uses past time series data, but also combines known future characteristics to improve the accuracy of the prediction.

[0087] Step S206: generating visualization information according to the time series feature set and the growth prediction information, and feeding back the visualization information to the user terminal.

[0088] In this embodiment, the time series characteristics and crop growth prediction information are converted into corresponding charts to generate visualization information, such as a crop growth characteristic curve with a time series. Different growth characteristics can be in the same chart or in different charts. The growth characteristic curve can include growth characteristics corresponding to each time node and predicted future growth characteristics. The visualization information can also include a chart corresponding to the growth state, such as drawing a corresponding crop prediction picture based on the predicted future growth characteristics, so as to more clearly and intuitively display the crop growth prediction information, and the predicted future growth characteristics can also be marked in the crop prediction picture.

[0089] Then, the visualized information is pushed to the user terminal, such as a server, terminal computer, mobile phone, tablet computer, etc., so that the user can view the relevant information in time.

[0090] Therefore, in this embodiment, by regularly collecting images and growth environment data of crops in the target area, the crop images are first standardized to ensure the accuracy of the subsequent generation of crop growth status information using the convolutional neural network model, and then the crop growth status information and growth environment data of each time node are constructed using a sliding window method to obtain time series features. The time series features are input into a crop growth prediction model based on a time series algorithm, which can accurately generate growth prediction information of crops in the target area. After that, the perfect time series features and future crop growth prediction information can be conveniently used to generate visualization information and send it to the user terminal, so as to timely display the current crop monitoring information and future crop growth prediction information to the user, thereby improving the crop monitoring efficiency and accuracy. In this way, the user can not only accurately grasp the current crop growth status and environmental data, but also intervene in advance according to the future crop growth prediction information to avoid abnormal growth status of crops in the future.

[0091] In some optional implementations of this embodiment, after step S205, the electronic device may further perform the following steps:

[0092] Step S207, judging whether the current growth state and the predicted growth state of the crop are abnormal according to the time series feature set and the growth prediction information.

[0093] Specifically, if the time series feature set and growth status information include negative information such as insect pests, the current growth status and predicted growth status of the crop can be judged to be abnormal; if the time series feature set and growth status information include positive information such as health, the current growth status and predicted growth status of the crop can be judged to be normal.

[0094] Step S208: If the current growth state and / or predicted growth state is abnormal, corresponding abnormal visual warning information is generated.

[0095] Specifically, the abnormal visualization warning information may be an abnormality mark, an image containing negative information, and the like.

[0096] Step S209, feeding back the abnormal visual warning to the user terminal, and / or, searching the corresponding target form in the preset insurance policy data according to the target area, obtaining the corresponding administrator account from the target form, and pushing the abnormal visual warning information to the administrator account.

[0097] Specifically, the abnormal visual warning information can be fed back to the user terminal, and the corresponding insurance policy can be retrieved from the preset database according to the target area as the target form, and then the corresponding administrator information recorded in the target insurance policy can be obtained to obtain the administrator account, so as to push the abnormal visual warning information to the administrator account.

[0098] In this embodiment, abnormal alarms are promptly fed back to the user terminal and / or the administrator account of the insurance policy, so that the user and / or administrator can be notified in time and adjust the crop growth environment in response to the abnormal information, such as eliminating diseases, reducing sunlight, etc. The administrator of the insurance policy can also make compensation predictions based on the abnormal visualization information in time, and notify the target area to adjust the crop growth environment in time to reduce losses.

[0099] In some optional implementations of this embodiment, after step S207, the electronic device may further perform the following steps:

[0100] Step S210, if the current growth state is abnormal, according to a preset abnormality handling strategy, control the preset agricultural machinery and equipment to perform abnormality handling operations, adjust the growth environment so that the crops return to a normal growth state; and / or,

[0101] Step S211, if the predicted growth state is abnormal, according to a preset abnormality prevention strategy, the preset agricultural machinery and equipment are controlled to perform abnormality prevention processing operations, and the growth environment is adjusted to keep the crops in a normal growth state.

[0102] Specifically, if the current growth state of the target area is abnormal, negative information, such as insect pests, drought, etc., is determined based on the growth characteristics of the current time node in the time series feature set. Then, the corresponding abnormality handling strategy, such as insecticide strategy, irrigation strategy, etc., is matched in the preset abnormality handling strategy database according to the negative information. After obtaining the abnormality handling strategy, the preset agricultural machinery and equipment, such as drones for spraying pesticides and irrigation equipment, are controlled to perform abnormality handling operations and adjust the growth environment to restore the crops to a normal growth state.

[0103] If the predicted growth state of the target area is abnormal, negative information is determined based on the growth state in the growth prediction information, such as lack of light, drought, etc. Then, the corresponding abnormality prevention strategy is matched in the preset abnormality prevention strategy database based on the negative information, such as enhanced light strategy, irrigation strategy, etc. After obtaining the abnormality prevention strategy, the preset agricultural machinery and equipment, such as artificial irradiation equipment, irrigation equipment, etc., are controlled to perform abnormality prevention processing operations and adjust the growth environment to keep the crops in a normal growth state.

[0104] Among them, the preset agricultural machinery and equipment can be connected to the server 106, and the server 106 can control the agricultural machinery and equipment to perform automatic operations.

[0105] The present application determines a response strategy when the current growth state and / or predicted growth state are abnormal, and automatically adjusts the growth environment so that crops can grow in a suitable and healthy environment, reducing or avoiding losses. In addition, the automatic adjustment of the growth environment reduces labor costs and time costs.

[0106] 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.

[0107] The basic technologies of artificial intelligence generally include sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics and other technologies. Artificial intelligence software technology mainly includes computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning. This application can be applied to the field of smart crop growth prediction, thereby promoting the construction of smart cities.

[0108] 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).

[0109] 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.

[0110] Further references Figure 4 , 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 crop monitoring device. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0111] like Figure 4 As shown, the crop monitoring device 300 described in this embodiment includes: a collection module 301, a processing module 302, a calculation module 303, a construction module 304, a prediction module 305 and a feedback module 406. Among them:

[0112] The acquisition module 301 is used to acquire images and growth environment data of crops in the target area according to preset time nodes, and obtain crop images and growth environment data corresponding to each time node;

[0113] A processing module 302 is used to perform standardization processing on the crop images corresponding to each time node to obtain a standardized crop image corresponding to each time node;

[0114] The calculation module 303 is used to input the standardized crop images corresponding to each time node into a preset convolutional neural network model for image processing to generate crop growth status information corresponding to each time node;

[0115] A construction module 304 is used to construct features using a sliding window method for the crop growth status information and growth environment data corresponding to each time node to obtain a time series feature set;

[0116] A prediction module 305 is used to input the time series feature set into a preset crop growth prediction model based on a time series algorithm to generate growth prediction information of crops in the target area;

[0117] The feedback module 306 generates visualization information according to the time series characteristics and the crop growth prediction information, and feeds back the visualization information to the user terminal.

[0118] The specific implementation of the crop monitoring device 300 of the present application is the same as that of the above embodiment, and will not be repeated here.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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 D intelligent crop growth prediction 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 Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of the crop monitoring 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.

[0123] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run computer-readable instructions stored in the memory 41 or process data, such as computer-readable instructions for running the crop monitoring method.

[0124] 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.

[0125] The specific implementation of the computer device of the present application is the same as that of the above embodiment and will not be repeated here.

[0126] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the crop monitoring method as described above.

[0127] The specific implementation of the computer-readable storage medium of the present application is the same as the above embodiment and will not be repeated here.

[0128] The non-Company software tools or components appearing in the embodiments of this application are merely examples and do not represent actual use.

[0129] 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.

[0130] 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 crop monitoring method, characterized in that: The steps include: Collect images and growth environment data of crops in the target area according to preset time nodes, and obtain crop images and growth environment data corresponding to each time node; Performing standardization processing on the crop images corresponding to each time node to obtain a standardized crop image corresponding to each time node; Inputting the standardized crop images corresponding to each time node into a preset convolutional neural network model for image processing to generate crop growth status information corresponding to each time node; The crop growth status information and growth environment data corresponding to each time node are subjected to a sliding window method to construct features to obtain a time series feature set; Inputting the time series feature set into a preset crop growth prediction model based on a time series algorithm to generate growth prediction information of crops in the target area; Visualization information is generated according to the time series feature set and the growth prediction information, and the visualization information is fed back to a user terminal.

2. The crop monitoring method according to claim 1, characterized in that: Before the step of collecting images and growth environment data of crops in the target area according to preset time nodes to obtain crop images and growth environment data corresponding to each time node, the method further includes: A sensor network system based on Internet of Things technology is established in the target area to collect images and growth environment data of crops in the target area.

3. The crop monitoring method according to claim 1, characterized in that: The step of respectively performing standardization processing on the crop images corresponding to the respective time nodes to obtain the standardized crop images corresponding to the respective time nodes specifically includes: Performing size, shape and pixel standardization preprocessing on the crop images corresponding to each time node to obtain a preprocessed crop image corresponding to each time node; De-noising the pre-processed crop images corresponding to each time node by using a bilateral filtering algorithm to obtain a smoothed crop image corresponding to each time node; Performing color correction processing on the adjusted crop images corresponding to each time node by using a white balance algorithm to obtain a corrected crop image corresponding to each time node; The growth period of the corrected crop images corresponding to each time node is marked respectively to obtain a standardized crop image corresponding to each time node.

4. The crop monitoring method according to claim 1, characterized in that: The step of inputting the standardized crop images corresponding to each time node into a preset convolutional neural network model for image processing to generate crop growth status information corresponding to each time node specifically includes: Obtaining crop types according to crop images corresponding to each time node, and determining a convolutional neural network model corresponding to the crop type; The standardized images corresponding to the time nodes are respectively input into the convolutional neural network model for processing to obtain the crop growth status information corresponding to the time nodes, wherein the crop growth status information includes the growth characteristic information and growth status classification information of the crop.

5. The crop monitoring method according to claim 1, characterized in that: The step of constructing features using a sliding window method for the crop growth status information and growth environment data corresponding to each time node to obtain a time series feature set specifically includes: Cleaning, formatting and serializing the growth state information and growth environment data corresponding to each time node to obtain a growth state window sequence and a growth environment window sequence; The growth state window sequence and the growth environment window sequence are combined to construct a time series feature set.

6. The crop monitoring method according to claim 1, characterized in that: After the step of inputting the time series feature set into a preset crop growth prediction model based on a time series algorithm to generate growth prediction information of the crops in the target area, the method further includes: Determining whether the current growth state and the predicted growth state of the target area are abnormal according to the time series feature set and the growth prediction information; If the current growth state and / or predicted growth state is abnormal, generating corresponding abnormal visual warning information; Feedback the abnormal visual warning to the user terminal, and / or retrieve the corresponding target form in the preset insurance policy data according to the target area, obtain the corresponding administrator account from the target form, and push the abnormal visual warning information to the administrator account.

7. The crop monitoring method according to claim 6, characterized in that: After the step of judging whether the current growth state and the predicted growth state of the target area are abnormal according to the time series feature set and the growth prediction information, the method further includes: If the current growth state is abnormal, according to a preset abnormality handling strategy, the preset agricultural machinery and equipment are controlled to perform abnormality handling operations, and the growth environment is adjusted to restore the crop to a normal growth state; and / or, If the predicted growth state is abnormal, the preset agricultural machinery and equipment are controlled to perform abnormal prevention processing operations according to the preset abnormality prevention strategy, and the growth environment is adjusted to keep the crops in a normal growth state.

8. A crop monitoring device, characterized in that: include: The acquisition module is used to acquire images and growth environment data of crops in the target area according to preset time nodes, and obtain crop images and growth environment data corresponding to each time node; A processing module, used for performing standardization processing on the crop images corresponding to each time node to obtain a standardized crop image corresponding to each time node; A calculation module, used for inputting the standardized images of crops corresponding to each time node into a preset convolutional neural network model for image processing to generate crop growth status information corresponding to each time node; A construction module, used to construct features using a sliding window method for the crop growth status information and growth environment data corresponding to each time node to obtain a time series feature set; A prediction module, used for inputting the time series feature set into a preset crop growth prediction model based on a time series algorithm to generate growth prediction information of crops in the target area; A feedback module generates visualization information according to the time series characteristics and the crop growth prediction information, and feeds back the visualization information to a user terminal.

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 crop monitoring 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 crop monitoring method according to any one of claims 1 to 7 are implemented.

Images