Agricultural big data management platform information acquisition system and method

Abstract

The invention discloses an agricultural big data management platform information acquisition system and method, and the method comprises the steps: obtaining a farmland image, and dividing the image into different planting regions according to plants; based on the images of different planting areas, dividing the images into a plurality of sub-areas, obtaining soil samples in each sub-area, and analyzing the samples to obtain soil fertility in the sub-areas; based on the land fertility of different time nodes in each sub-region, obtaining a land fertility change condition; and comprehensively evaluating and analyzing the soil fertility change condition of the planting area based on the soil fertility change condition in each sub-area. The farmland soil fertility monitoring system has the advantages that accurate monitoring and dynamic tracking of farmland soil fertility are realized through image analysis and soil sample collection, and scientific decision support is provided for agricultural production. Through analysis of the soil fertility change trend, optimization of a fertilization scheme is facilitated, the land utilization efficiency is improved, and sustainable agricultural development is promoted.

Description

Technical Field

[0001] The present invention relates to agricultural data collection, and in particular to an agricultural big data management platform information collection system and method. Background Art

[0002] An agricultural big data management platform information collection system and method, which collects image data and environmental data from various areas of farmland and preprocesses them. The features of the image data are extracted to identify the type of crops and their growth status, and further analysis is performed in combination with machine learning technology to accurately determine the status of the crops. Then, the system determines the environmental anomaly threshold range of each area according to the crop type and growth status through a preset mapping table. Based on these thresholds, the system performs an anomaly analysis on the environmental data and identifies potential environmental problems. Finally, based on the results of the environmental anomaly analysis, corresponding control strategies are generated to guide farmland management and decision-making, thereby improving agricultural production efficiency and sustainable development. This system effectively combines big data, image processing and machine learning technologies to provide intelligent decision-making support for precision agriculture.

[0003] The current agricultural information collection methods on the market mainly include sensors, drones, the Internet of Things, and other technologies. Sensors monitor soil moisture, temperature and other environmental data in real time; drones are equipped with multispectral sensors for crop health monitoring and help identify pests and diseases; the Internet of Things technology enables intelligent interconnection of equipment and sensors and provides real-time data. Overall, the combination of these technologies improves the accuracy and efficiency of agricultural production. Summary of the invention

[0004] In order to improve the existing agricultural management platform information collection method, an agricultural big data management platform information collection system and method are provided. The method collects farmland images and environmental data, uses machine learning to identify crop types and growth status, and analyzes environmental anomalies. According to the analysis results, a control strategy is generated to optimize farmland management and agricultural production efficiency.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] An agricultural big data management platform information collection method, characterized by comprising:

[0007] Collect image data and environmental data of each monitoring area in the farmland and perform data preprocessing;

[0008] Extract features based on image data to obtain crop characteristics in each monitoring area;

[0009] Through machine learning, identify the crop types and crop growth status corresponding to different crop characteristics;

[0010] Based on the preset mapping table, determine the environmental anomaly threshold range of each monitoring area according to the crop type and crop growth status;

[0011] Perform an anomaly analysis on the environmental data information of each monitoring area according to the environmental anomaly threshold range of each monitoring area to obtain the environmental analysis results of each monitoring area;

[0012] The environmental analysis results of the monitoring area are environmental anomalies, and control strategies are generated.

[0013] Preferably, the feature extraction based on the image data to obtain the crop features in each monitoring area specifically includes:

[0014] The image is segmented into multiple super-pixel regions based on the image data, and the pixels in each super-pixel region have similar features;

[0015] Based on extracting multispectral features in each superpixel region, the texture features in each superpixel region are calculated through the gray-level co-occurrence matrix to extract the morphological features of each superpixel region;

[0016] Combine multispectral features, texture features and morphological features into a feature vector;

[0017] Based on the feature selection method, a key feature subset is selected from the feature vector as crop features.

[0018] Preferably, the identifying the crop types and crop growth states corresponding to different crop characteristics through machine learning specifically includes:

[0019] Based on the acquired crop features, the features are input into a pre-trained crop recognition model to obtain the crop type and crop growth status corresponding to the crop features;

[0020] The crop recognition model is obtained through iterative training based on multiple sample images and pre-labeled crop type labels and crop growth status labels.

[0021] Preferably, the acquired crop features are input into a pre-trained crop recognition model to obtain the crop type and crop growth status corresponding to the crop features, specifically including:

[0022] The crop recognition model training step specifically includes:

[0023] Acquire an image dataset and perform image preprocessing, wherein the sample image dataset includes multiple sample images and pre-labeled crop type labels and crop growth status labels;

[0024] Perform feature extraction on the sample image data set to obtain sample crop features, and divide the sample crop features into a training set, a validation set, and a test set;

[0025] The training set is input into a pre-built convolutional neural network for initial training. The convolutional neural network includes a convolutional layer, a pooling layer, a fully connected layer, and an output layer. The output layer is used to output the predicted probability of each crop type and crop growth status.

[0026] Based on the validation set and test set, the initially trained convolutional neural network is verified and model parameters are optimized to obtain a trained crop recognition model.

[0027] Preferably, the verifying and optimizing the model parameters of the initially trained convolutional neural network based on the verification set and the test set to obtain the trained crop recognition model specifically includes:

[0028] Input the training set into a pre-built convolutional neural network for iterative training, optimize the model parameters and calculate the cross entropy loss function of the model until the cross entropy loss function meets the preset conditions, thereby obtaining a trained convolutional neural network;

[0029] Validating the convolutional neural network based on the validation set, evaluating the performance of the convolutional neural network and adjusting the hyperparameters of the model according to the validation results;

[0030] The prediction ability of the adjusted convolutional neural network is tested based on the test set.

[0031] Preferably, performing abnormal analysis on the environmental data information of each monitoring area according to the environmental abnormality threshold range of each monitoring area to obtain the environmental analysis results of each monitoring area specifically includes:

[0032] Determine whether the environmental data information of each monitoring area exceeds the corresponding environmental abnormality threshold range, and if so, determine that the environmental data information of the monitoring area is abnormal;

[0033] Determine whether the duration of abnormality in the environmental data information of the monitoring area exceeds a preset duration threshold;

[0034] If it exceeds, the environmental analysis result of the monitoring area is output as an environmental abnormality result, and the corresponding abnormality type and abnormality degree are determined according to the abnormal environmental data information;

[0035] If it does not exceed, the environmental analysis result of the monitoring area is output as a normal environmental result.

[0036] Preferably, the environmental analysis result based on the monitoring area is an environmental abnormality result, and generating a control strategy specifically includes:

[0037] Determine the corresponding abnormality type and abnormality degree based on the environmental abnormality result;

[0038] Based on the preset rule relationship, the corresponding environmental parameter adjustment type and environmental parameter adjustment index are determined according to the abnormality type and abnormality degree;

[0039] Based on the environmental parameter adjustment type and the environmental parameter adjustment index, the target environmental parameters of the monitoring area are adjusted and the corresponding control strategy is generated.

[0040] Furthermore, an agricultural big data management platform information collection system is characterized by comprising:

[0041] A data acquisition module, which is mainly used to collect image data and environmental data of each monitoring area in the farmland;

[0042] A preprocessing module, wherein the preprocessing module is mainly used to perform data preprocessing on image data and environmental data;

[0043] A feature extraction module, which is mainly used to extract features from image data to obtain crop features in each monitoring area;

[0044] An identification module, wherein the identification module is mainly used to identify the crop type and crop growth status corresponding to the crop characteristics based on a machine learning algorithm;

[0045] An abnormal threshold range determination module, the abnormal threshold range determination module is mainly used to determine the environmental abnormal threshold range of each monitoring area according to the crop type and crop growth status;

[0046] An abnormality analysis module, which is mainly used to perform abnormality analysis on the environmental data information of each monitoring area according to the environmental abnormality threshold range of each monitoring area, and obtain the environmental analysis result of each monitoring area;

[0047] A control strategy generation module is mainly used to generate a control strategy according to the abnormal environment result in response to the environmental analysis result of the monitoring area being an abnormal environment result.

[0048] Compared with the prior art, the advantages of the present invention are:

[0049] The present invention can accurately identify the growth status of crops and changes in their surrounding environment through real-time collection and analysis of multi-dimensional data. By extracting features from image data, the system can accurately identify the types and health conditions of different crops. Based on the machine learning model, the system can automatically learn and optimize the relationship between crop growth characteristics and environmental data. It can not only monitor the farmland environment in real time and detect potential environmental anomalies in a timely manner, but also generate personalized control strategies based on the results of abnormal analysis, avoid blindness and errors in manual operations, and improve agricultural management efficiency. In addition, based on preset thresholds and dynamic adjustments, the system can also flexibly respond to the needs of different regions and different crops, providing strong technical support for precision agriculture. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A schematic diagram of agricultural data collection of the system and method proposed in the present invention;

[0051] Figure 2 A schematic diagram of crop feature extraction of the system and method proposed in the present invention;

[0052] Figure 3 A schematic diagram of crop identification of the system and method proposed in the present invention;

[0053] Figure 4 A schematic diagram of crop characteristics acquisition of the system and method proposed by the present invention;

[0054] Figure 5 A schematic diagram of obtaining a crop identification model of the system and method proposed in the present invention;

[0055] Figure 6 A schematic diagram of the environmental analysis results of the system and method proposed by the present invention;

[0056] Figure 7 Generate a schematic diagram of the control strategy of the system and method proposed by the present invention;

[0057] Figure 8 An architecture diagram of an electronic device of the system and method proposed by the present invention;

[0058] Fig. 9 A schematic diagram of the computer-readable storage medium structure of the system and method proposed in the present invention. DETAILED DESCRIPTION

[0059] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0060] An agricultural big data management platform information collection system, comprising:

[0061] A data acquisition module, which is mainly used to collect image data and environmental data of each monitoring area in the farmland;

[0062] A preprocessing module, wherein the preprocessing module is mainly used to perform data preprocessing on image data and environmental data;

[0063] A feature extraction module, which is mainly used to extract features from image data to obtain crop features in each monitoring area;

[0064] An identification module, wherein the identification module is mainly used to identify the crop type and crop growth status corresponding to the crop characteristics based on a machine learning algorithm;

[0065] An abnormal threshold range determination module, the abnormal threshold range determination module is mainly used to determine the environmental abnormal threshold range of each monitoring area according to the crop type and crop growth status;

[0066] An abnormality analysis module, which is mainly used to perform abnormality analysis on the environmental data information of each monitoring area according to the environmental abnormality threshold range of each monitoring area, and obtain the environmental analysis result of each monitoring area;

[0067] A control strategy generation module is mainly used to generate a control strategy according to the abnormal environment result in response to the environmental analysis result of the monitoring area being an abnormal environment result.

[0068] See also Figure 1 As shown, a method for collecting information on an agricultural big data management platform includes:

[0069] Step 1: Collect image data and environmental data of each monitoring area in the farmland and perform data preprocessing;

[0070] Step 2: Extract features based on image data to obtain crop features in each monitoring area;

[0071] Step 3: Identify the crop types and crop growth status corresponding to different crop characteristics through machine learning;

[0072] Step 4: Based on the preset mapping table, determine the environmental abnormality threshold range of each monitoring area according to the crop type and crop growth status;

[0073] Step 5: Perform an abnormal analysis on the environmental data information of each monitoring area according to the environmental abnormality threshold range of each monitoring area to obtain the environmental analysis results of each monitoring area;

[0074] Step 6: Generate a control strategy based on the environmental analysis results of the monitoring area as environmental anomaly results.

[0075] See also Figure 2 As shown, feature extraction is performed based on image data to obtain crop features in each monitoring area, specifically including:

[0076] The image is segmented into multiple super-pixel regions based on the image data, and the pixels in each super-pixel region have similar features;

[0077] Based on extracting multispectral features in each superpixel region, the texture features in each superpixel region are calculated through the gray-level co-occurrence matrix to extract the morphological features of each superpixel region;

[0078] Combine multispectral features, texture features and morphological features into a feature vector;

[0079] Based on the feature selection method, a key feature subset is selected from the feature vector as crop features.

[0080] Specifically, the SLIC algorithm is an efficient image segmentation method that can divide an image into multiple regions based on the color similarity and spatial position of the image. These regions are called superpixels. The size and shape of superpixels can be adjusted according to specific needs to adapt to the characteristics and monitoring requirements of different crops. Through superpixel segmentation, the image can be simplified into a group of regions with similar attributes, which is very helpful for subsequent feature extraction and crop classification. This method can not only reduce the computational complexity, but also improve the efficiency of image processing.

[0081] GLCM is one of the commonly used texture analysis methods. It extracts image texture features such as contrast, homogeneity, energy, etc. by calculating the frequency of occurrence between adjacent pixel gray levels. Different crop types and growth stages usually present unique texture features, which reflect the structural information of local areas in the image. By analyzing these texture features, the texture of the crop surface can be effectively identified, thus playing an important role in the identification of crop types.

[0082] See also Figure 3 As shown in the figure, through machine learning, the crop types and crop growth states corresponding to different crop characteristics are identified, including:

[0083] Based on the acquired crop features, the features are input into a pre-trained crop recognition model to obtain the crop type and crop growth status corresponding to the crop features;

[0084] The crop recognition model is obtained through iterative training based on multiple sample images and pre-labeled crop type labels and crop growth status labels.

[0085] See also Figure 4As shown, based on the acquired crop features, they are input into a pre-trained crop recognition model to obtain the crop type and crop growth status corresponding to the crop features, including:

[0086] The crop recognition model training step specifically includes:

[0087] Acquire an image dataset and perform image preprocessing, wherein the sample image dataset includes multiple sample images and pre-labeled crop type labels and crop growth status labels;

[0088] Perform feature extraction on the sample image data set to obtain sample crop features, and divide the sample crop features into a training set, a validation set, and a test set;

[0089] The training set is input into a pre-built convolutional neural network for initial training. The convolutional neural network includes a convolutional layer, a pooling layer, a fully connected layer, and an output layer. The output layer is used to output the predicted probability of each crop type and crop growth status.

[0090] Based on the validation set and test set, the initially trained convolutional neural network is verified and model parameters are optimized to obtain a trained crop recognition model.

[0091] Specifically, the feature extraction step includes segmenting the sample image into multiple superpixel regions using a superpixel segmentation algorithm, extracting multispectral features from each superpixel region, calculating the texture features within each superpixel region based on the gray-level co-occurrence matrix, extracting the morphological features of each superpixel region, combining these features into a feature vector, and using a feature selection method to select a subset of key features from the feature vector as sample crop features.

[0092] The extracted sample crop features are randomly divided into three parts: training set, validation set and test set. The training set is used to train the model, the validation set is used to adjust the model parameters, and the test set is used to evaluate the final performance of the model. By dividing the data set, the effectiveness of model training can be ensured and the generalization ability of the model can be objectively evaluated. The existence of the validation set and the test set helps prevent the model from overfitting and ensures that the model can perform well on unknown data.

[0093] See also Figure 5 As shown in the figure, the convolutional neural network after initial training is verified and the model parameters are optimized based on the verification set and the test set, and the trained crop recognition model is obtained, which specifically includes:

[0094] Input the training set into a pre-built convolutional neural network for iterative training, optimize the model parameters and calculate the cross entropy loss function of the model until the cross entropy loss function meets the preset conditions, thereby obtaining a trained convolutional neural network;

[0095] Validating the convolutional neural network based on the validation set, evaluating the performance of the convolutional neural network and adjusting the hyperparameters of the model according to the validation results;

[0096] The prediction ability of the adjusted convolutional neural network is tested based on the test set.

[0097] Specifically, the pre-built convolutional neural network is iteratively trained using training set data. In each iteration, the convolutional neural network receives a batch of training samples as input and calculates prediction results through forward propagation. Based on the difference between the prediction results and the actual labels, for example, using the cross entropy loss function as a measure, the weights and biases of the network are adjusted through the back propagation algorithm to minimize the loss function, and the training is iterative until the loss function converges.

[0098] Use the validation set data to validate the trained convolutional neural network, evaluate the performance indicators such as the loss and accuracy of the model on the validation set, and adjust the model's hyperparameters such as learning rate, batch size, regularization coefficient, etc. according to the validation results. In addition, an early stopping strategy can be used, that is, the training is terminated early when the performance on the validation set no longer improves.

[0099] See also Figure 6 , perform abnormal analysis on the environmental data information of each monitoring area according to the environmental abnormality threshold range of each monitoring area, and obtain the environmental analysis results of each monitoring area, including:

[0100] Determine whether the environmental data information of each monitoring area exceeds the corresponding environmental abnormality threshold range, and if so, determine that the environmental data information of the monitoring area is abnormal;

[0101] Determine whether the duration of abnormality in the environmental data information of the monitoring area exceeds a preset duration threshold;

[0102] If it exceeds, the environmental analysis result of the monitoring area is output as an environmental abnormality result, and the corresponding abnormality type and abnormality degree are determined according to the abnormal environmental data information;

[0103] If it does not exceed, the environmental analysis result of the monitoring area is output as a normal environmental result.

[0104] See also Figure 7 As shown, the environmental analysis results based on the monitoring area are environmental abnormality results, and the control strategy generated specifically includes:

[0105] Determine the corresponding abnormality type and abnormality degree based on the environmental abnormality result;

[0106] Based on the preset rule relationship, the corresponding environmental parameter adjustment type and environmental parameter adjustment index are determined according to the abnormality type and abnormality degree;

[0107] Based on the environmental parameter adjustment type and the environmental parameter adjustment index, the target environmental parameters of the monitoring area are adjusted and the corresponding control strategy is generated.

[0108] Furthermore, the method according to the embodiment of the present application can also be performed by Figure 8 The electronic device architecture shown in FIG. Figure 8 As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, a read-only memory (ROM) 503, a random access memory (RAM) 504, a communication port 505 connected to a network, an input / output component 506, a hard disk 507, etc. The storage device in the electronic device 500, such as ROM 503 or hard disk 507, may store an agricultural big data management platform information collection system and method provided by the present application. The electronic device 500 may also include a terminal interface 508. Of course, Figure 8 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 8 One or more components of an electronic device are shown.

[0109] Fig. 9 Schematic diagram of a computer-readable storage medium structure provided by an embodiment of the present application. Fig. 9 As shown, a computer-readable storage medium 600 according to an embodiment of the present application is shown. Computer-readable instructions are stored on the computer-readable storage medium 600. When the computer-readable instructions are executed by the processor, an agricultural big data management platform information collection system and method according to an embodiment of the present application described with reference to the above figures can be executed. The storage medium 600 includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0110] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The above is a description of a specific embodiment of this specification. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0111] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0112] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for collecting information on an agricultural big data management platform, characterized in that: include: Collect image data and environmental data of each monitoring area in the farmland and perform data preprocessing; Extract features based on image data to obtain crop characteristics in each monitoring area; Through machine learning, identify the crop types and crop growth status corresponding to different crop characteristics; Based on the preset mapping table, determine the environmental anomaly threshold range of each monitoring area according to the crop type and crop growth status; Perform an abnormal analysis on the environmental data information of each monitoring area according to the environmental abnormality threshold range of each monitoring area to obtain the environmental analysis results of each monitoring area; The environmental analysis results of the monitoring area are environmental anomalies, and control strategies are generated.

2. The information collection method of an agricultural big data management platform according to claim 1, characterized in that: The feature extraction based on the image data to obtain the crop features in each monitoring area specifically includes: The image is segmented into multiple super-pixel regions based on the image data, and the pixels in each super-pixel region have similar features; Based on extracting multispectral features in each superpixel region, the texture features in each superpixel region are calculated through the gray-level co-occurrence matrix to extract the morphological features of each superpixel region; Combine multispectral features, texture features and morphological features into a feature vector; Based on the feature selection method, a key feature subset is selected from the feature vector as crop features.

3. The information collection method of an agricultural big data management platform according to claim 1 is characterized in that: The method of identifying the crop types and crop growth states corresponding to different crop characteristics through machine learning specifically includes: Based on the acquired crop features, the features are input into a pre-trained crop recognition model to obtain the crop type and crop growth status corresponding to the crop features; The crop recognition model is obtained through iterative training based on multiple sample images and pre-labeled crop type labels and crop growth status labels.

4. The information collection method of an agricultural big data management platform according to claim 3 is characterized in that: The crop characteristics acquired are input into a pre-trained crop recognition model to obtain the crop type and crop growth status corresponding to the crop characteristics, specifically including: The crop recognition model training step specifically includes: Acquire an image dataset and perform image preprocessing, wherein the sample image dataset includes multiple sample images and pre-labeled crop type labels and crop growth status labels; Perform feature extraction on the sample image data set to obtain sample crop features, and divide the sample crop features into a training set, a validation set, and a test set; The training set is input into a pre-built convolutional neural network for initial training. The convolutional neural network includes a convolutional layer, a pooling layer, a fully connected layer, and an output layer. The output layer is used to output the predicted probability of each crop type and crop growth status. Based on the validation set and test set, the initially trained convolutional neural network is verified and model parameters are optimized to obtain a trained crop recognition model.

5. The information collection method of an agricultural big data management platform according to claim 4 is characterized in that: The verification and model parameter optimization of the initially trained convolutional neural network based on the verification set and the test set to obtain the trained crop recognition model specifically includes: Input the training set into a pre-built convolutional neural network for iterative training, optimize the model parameters and calculate the cross entropy loss function of the model until the cross entropy loss function meets the preset conditions, thereby obtaining a trained convolutional neural network; Validating the convolutional neural network based on the validation set, evaluating the performance of the convolutional neural network and adjusting the hyperparameters of the model according to the validation results; The prediction ability of the adjusted convolutional neural network is tested based on the test set.

6. The information collection method of an agricultural big data management platform according to claim 1, characterized in that: The abnormal analysis of the environmental data information of each monitoring area is performed according to the environmental abnormality threshold range of each monitoring area to obtain the environmental analysis results of each monitoring area, which specifically includes: Determine whether the environmental data information of each monitoring area exceeds the corresponding environmental abnormality threshold range, and if so, determine that the environmental data information of the monitoring area is abnormal; Determine whether the duration of abnormality in the environmental data information of the monitoring area exceeds a preset duration threshold; If it exceeds, the environmental analysis result of the monitoring area is output as an environmental abnormality result, and the corresponding abnormality type and abnormality degree are determined according to the abnormal environmental data information; If it does not exceed, the environmental analysis result of the monitoring area is output as a normal environmental result.

7. The information collection method of an agricultural big data management platform according to claim 1, characterized in that: The environmental analysis result based on the monitoring area is an environmental abnormality result, and generating a control strategy specifically includes: Determine the corresponding abnormality type and abnormality degree based on the environmental abnormality result; Based on the preset rule relationship, the corresponding environmental parameter adjustment type and environmental parameter adjustment index are determined according to the abnormality type and abnormality degree; Based on the environmental parameter adjustment type and the environmental parameter adjustment index, the target environmental parameters of the monitoring area are adjusted and the corresponding control strategy is generated.

8. Combined with an agricultural big data management platform information collection method, it is used to implement an agricultural big data management platform information collection system as described in any one of claims 1 to 7, characterized in that: include: A data acquisition module, which is mainly used to collect image data and environmental data of each monitoring area in the farmland; A preprocessing module, wherein the preprocessing module is mainly used to perform data preprocessing on image data and environmental data; A feature extraction module, which is mainly used to extract features from image data to obtain crop features in each monitoring area; An identification module, wherein the identification module is mainly used to identify the crop type and crop growth status corresponding to the crop characteristics based on a machine learning algorithm; An abnormal threshold range determination module, the abnormal threshold range determination module is mainly used to determine the environmental abnormal threshold range of each monitoring area according to the crop type and crop growth status; An abnormality analysis module, which is mainly used to perform abnormality analysis on the environmental data information of each monitoring area according to the environmental abnormality threshold range of each monitoring area, and obtain the environmental analysis result of each monitoring area; A control strategy generation module is mainly used to generate a control strategy according to the abnormal environment result in response to the environmental analysis result of the monitoring area being an abnormal environment result.

9. An electronic device, characterized in that: include: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute an agricultural big data management platform information collection method as described in any one of claims 1-7.

10. A computer-readable storage medium storing computer-readable instructions, characterized in that: When the computer-readable instructions are executed by a processor, an agricultural big data management platform information collection method described in any one of claims 1-7 is implemented.

Images