An agricultural data interaction method and platform based on multi-source information

Abstract

The present invention relates to an agricultural data interaction method and platform based on multi-source information, belonging to the technical field of agricultural data processing. The method includes the following steps: processing the collected data through corresponding edge computing modules to generate dynamic tags; analyzing and processing agricultural information data to obtain supervision tags and corresponding supervision data; importing all tags and corresponding data into a geographic information system, and matching them according to the corresponding regions and their respective tags, and at the same time, identifying and updating the monitoring tags through the cloud platform computing center. The present invention processes and fuses real-time data through edge computing modules and sends it to the cloud computing platform, generates interaction prompts through association with supervision data, thereby improving the real-time performance and efficiency of data processing. At the same time, through interaction prompts, the monitoring data and supervision data are associated, improving the interactivity of visual display.

Description

Technical Field

[0001] The present invention belongs to the technical field of agricultural data processing, and particularly relates to an agricultural data interaction method and platform based on multi-source information. Background Art

[0002] With the development of agricultural modernization and information technology, a large amount of multi-source data has been generated in agricultural production, including meteorological data, soil data, crop growth data, pest and disease monitoring data, agricultural production management data, etc. These data come from a wide range of sources and have different formats, bringing great challenges to the integration and utilization of agricultural data. Traditional agricultural data management systems often cannot effectively collect information from different sources, and lack real-time and intelligent data analysis and early warning capabilities, unable to provide sufficient data support for agricultural production decision-making.

[0003] At the same time, the visualization of agricultural data is relatively single, only considering the direct data of agricultural production, and not associating and visualizing data such as decision-making data of regulatory departments, social and economic data, and science and technology and innovation data, unable to highlight the interactivity of data between different functional departments. Summary of the Invention

[0004] To solve the above problems existing in the prior art, the present invention provides an agricultural data interaction method and platform based on multi-source information. The real-time data is fused and processed by an edge computing module and sent to a cloud computing platform, and an interaction prompt is generated through association with regulatory data, thereby improving the real-time and efficiency of data processing. At the same time, through the interaction prompt, the monitoring data and regulatory data are associated, improving the interactivity of visual display.

[0005] The object of the present invention can be achieved by the following technical solutions:

[0006] The first aspect of the present disclosure provides an agricultural data interaction method based on multi-source information, including the following steps:

[0007] Regional agricultural data processing: Divide the agricultural supervision target area, set real-time data collection devices for each area, and process the collected data through the corresponding edge computing module to generate dynamic tags;

[0008] Agricultural-related information processing: Collect relevant information of smart agriculture by accessing a third-party platform, analyze and process the information data to obtain supervision tags and corresponding supervision data;

[0009] Global data visualization: Import all tags and corresponding data into a geographic information system, match them according to the corresponding area and their respective tags, and at the same time identify and update the monitoring tags through the cloud platform computing center;

[0010] The global data visualization includes the following steps:

[0011] Data matching and display: The dynamic labels are displayed flowing at the corresponding positions on the map according to the coordinate system of the data acquisition device, and interactive prompts are given by calculating the correlation between the dynamic labels and the supervision labels;

[0012] Deepening of interactive prompts: According to the dynamic labels where interactive prompts occur, the trend prediction model is called, and the monitoring data corresponding to the dynamic labels is subjected to feature engineering processing and then input into the trend prediction model to obtain the trend changes of the dynamic labels. At the same time, early warning prompts are given for the monitoring data based on the supervision data.

[0013] Furthermore, the regional agricultural data processing includes the following steps:

[0014] Agricultural region division: Set data acquisition devices according to data application requirements, set edge computing modules according to the expansion status of data acquisition, and divide agricultural supervision regions based on the edge computing modules;

[0015] Collect monitoring data: Through the set data acquisition devices, each edge computing module obtains real-time data by setting the acquisition frequency;

[0016] Dynamic label generation: After the edge computing module preprocesses the real-time data, dynamic labels are generated for the preprocessed data through an association rule engine;

[0017] Upload of monitoring data: Integrate the data with assigned dynamic labels and the data without assigned dynamic labels into corresponding data packets respectively, perform encryption processing, and then upload them to the cloud computing center.

[0018] Furthermore, the dynamic label generation further includes the following steps:

[0019] Align and normalize the status data and dynamic labels based on time periods for the agricultural historical data, merge the status data according to the dynamic labels, and establish a dynamic label transaction database;

[0020] Use the association rule mining algorithm to mine the frequent item sets corresponding to each dynamic label from the dynamic label transaction database, generate association rules from the frequent item sets, and calculate the support and confidence of the rules;

[0021] Screen the association rules by setting the minimum support threshold and confidence threshold to generate a series of association rules for the dynamic labels.

[0022] Furthermore, the processing of agricultural-related information includes the following steps:

[0023] Collect relevant information: Obtain the decision-making data, social and economic data, and science and technology and innovation data of the supervision department through a third-party platform;

[0024] Generate regulatory labels: Use a multi-modal large model to process relevant information data, fuse data from different modalities, and generate corresponding regulatory labels;

[0025] Extract regulatory data: Obtain the range thresholds of the corresponding data types according to the generated regulatory labels. For the regulatory labels that cannot be directly obtained from the relevant information, infer and supplement the reference values through the multi-modal large model;

[0026] Monitor data annotation: For the monitoring data uploaded to the cloud computing center, label the monitoring data by data type and calculating the similarity between the monitoring data and the range thresholds or reference values of the regulatory data.

[0027] Furthermore, the visualization of the global data further includes the following steps:

[0028] Import multi-source data: Uniformly convert all associated data of the target agricultural area into a format supported by the geographic information system, add descriptive metadata to the data, store it in the cloud computing center, and import the preprocessed data into the GIS for visual display;

[0029] Association rule update: The cloud computing center collects monitoring data, adds it to the dynamic label transaction database after establishing a complete data format through label annotation of the monitoring data, and updates the association rules through association mining and distributes them to the edge computing module.

[0030] Furthermore, the deepening of the interactive prompt includes the following steps:

[0031] Integrate the monitoring data used for dynamic label generation into a data set, and perform feature engineering on the integrated data set, including feature extraction, feature selection, and feature construction;

[0032] Select a machine learning model as the basis of the trend prediction model, and use the existing historical data to train the selected model, with the fusion result of the multi-source data as the input feature and the trend change of the dynamic label as the output;

[0033] Compare the data corresponding to the dynamic label and the regulatory label according to the interactive prompt, and give a warning prompt when the monitoring data exceeds the range threshold or reference value of the regulatory data.

[0034] The second aspect of the present disclosure provides an agricultural data interaction platform based on multi-source information, which is used to implement an agricultural data interaction method based on multi-source information as described above, including a data collection and fusion module, a data storage and management module, a data analysis and mining module, an intelligent decision-making and warning module, and a data sharing and interaction module;

[0035] The data acquisition and fusion module, data storage and management module, data analysis and mining module, intelligent decision-making and early warning module, and data sharing and interaction module are sequentially communicatively connected;

[0036] The data acquisition and fusion module is used to collect multi-source agricultural data and perform preprocessing, and then fuse and associate heterogeneous data from different data sources;

[0037] Among them, the fusion and association include the following steps:

[0038] Data acquisition: Using intelligent sensing technology through the set data acquisition devices, each edge computing module obtains real-time data through the set acquisition frequency, including meteorological sensors, soil sensors, cameras, drones, and satellite remote sensing;

[0039] Data preprocessing: Thoroughly clean the collected raw data, remove invalid, incorrect, or incomplete records, perform data standardization processing, and convert data with different dimensions and scales into a unified data format that can be used for analysis by the association rule engine;

[0040] Data fusion: Input the preprocessed data into the association rule engine to generate dynamic labels, complete the fusion of multi-source data, and perform subsequent prediction and visualization.

[0041] As a preferred technical solution of the present invention, the data storage and management module is used to store the collected and gathered data in a database, and select a cloud computing center to achieve parallel storage and access of data.

[0042] As a preferred technical solution of the present invention, the data analysis and mining module is used to analyze and process all data through a cloud computing center, including:

[0043] Mining a series of rules engines for dynamic labels from agricultural historical data and corresponding states through an association rule mining algorithm;

[0044] Analyzing decision-making data, socio-economic data, and science and technology and innovation data of regulatory departments through a multi-modal large model to generate regulatory labels and regulatory data;

[0045] Training a machine learning model through existing historical data to establish a trend prediction model, and inputting the monitoring data of dynamic labels into the model for trend change prediction.

[0046] As a preferred technical solution of the present invention, the intelligent decision-making and early warning module is used to calculate the correlation based on the generated dynamic tags and regulatory tags, give an interactive prompt for the dynamic tags that reach the design threshold, and at the same time compare the data corresponding to the dynamic tags and regulatory tags according to the interactive prompt, and give an early warning prompt when the monitored data exceeds the range threshold or reference value of the regulatory data;

[0047] The data sharing and interaction module is used to integrate the target agricultural area, dynamic tags and real-time data into a geographic information system for visual display, where the dynamic tags also include interactive prompts, trend predictions and early warning prompts.

[0048] The beneficial effects of the present invention are as follows:

[0049] First, the present invention generates dynamic tags for the direct data of agricultural production through the edge computing modules in different regions through an association rule engine, and completes data collection and fusion through distributed processing, reducing the difficulty of fusing massive data and improving the processing efficiency of real-time data; at the same time, other information data related to smart agriculture are integrated through a multi-modal large model to extract regulatory tags and regulatory data, guiding the data annotation of monitored data, and improving the consistency and relevance of data tag annotation; finally, interactive prompts are given through the correlation calculation of dynamic tags and regulatory tags, thereby associating the monitored data and regulatory data, and visual display is performed based on GIS, improving the interactivity of agricultural data management.

[0050] In the visual display of the present invention, a dynamic map of the target agricultural area is established based on GIS, which includes an agricultural area map, dynamic tags and real-time data. The dynamic tags include interactive prompts, trend predictions and early warning prompts. The interactive prompts provide the association status between the current monitored data and the regulatory data for users. At the same time, trend change predictions and early warning prompts are made for the dynamic tags with interactive prompts, improving the visual effect, helping users understand complex data and analysis results in an intuitive and concise manner, and enhancing the real-time response ability through early warning prompts and improving the decision-making efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] For the convenience of those skilled in the art to understand, the present invention will be further described below with reference to the accompanying drawings.

[0052] Figure 1 It is a schematic flowchart of a method for agricultural data interaction based on multi-source information provided by an embodiment of the present invention;

[0053] Figure 2 It is a schematic flowchart of regional agricultural data processing provided by an embodiment of the present invention;

[0054] Figure 3A schematic flow chart of agricultural-related information processing provided by an embodiment of the present invention;

[0055] Figure 4 A schematic flow chart of global data visualization provided by an embodiment of the present invention;

[0056] Figure 5 A schematic structural diagram of an agricultural data interaction platform based on multi-source information provided by an embodiment of the present invention. Detailed implementation manners

[0057] To further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation manners, structures, features, and their effects according to the present invention as follows.

[0058] The present invention provides an agricultural data interaction method and platform based on multi-source information, which is used to realize the integration and visualization of multi-source data in agricultural production. By using a geographic information system to visualize all data and monitor and prompt, early warning information is timely provided to agricultural producers and decision-makers, thereby improving the interaction ability of different functional departments with respect to agricultural data and providing a more efficient processing method for smart agriculture. Specifically, the agricultural data interaction method and platform based on multi-source information of the present invention are detailed as follows:

[0059] This embodiment provides an agricultural data interaction method based on multi-source information, as Figure 1 shown, including the following steps:

[0060] S1. Regional agricultural data processing: Divide the agricultural supervision target area, set real-time data collection devices for each area, and process the collected data through the corresponding edge computing module to generate dynamic tags, as Figure 2 shown, including the following steps:

[0061] S11. Agricultural area division: Set data collection devices according to data application requirements, set edge computing modules according to the expansion status of data collection, and divide the agricultural supervision area based on the edge computing module;

[0062] It can be understood that the data collection devices include meteorological sensors, soil sensors, cameras, unmanned aerial vehicles, and satellite remote sensing, etc., covering all aspects from environmental monitoring to crop growth, soil quality, irrigation management, etc., providing more comprehensive basic data for smart agriculture.

[0063] It should be noted that for agricultural supervision data, acquisition devices with different types and quantities need to be set according to different supervision objectives. However, due to the rapid expansion of agricultural data, it is impossible to complete the processing and analysis of real-time data within a certain period of time, resulting in poor data management and analysis decision-making effects. Therefore, an edge computing module is set to perform real-time processing of the acquired data in a cloud-edge collaborative manner to improve the real-time performance and efficiency of data processing.

[0064] S12. Collect monitoring data: Through the set data acquisition devices, each edge computing module obtains real-time data by setting the acquisition frequency;

[0065] S13. Generate dynamic labels: After the edge computing module preprocesses the real-time data, it generates dynamic labels for the preprocessed data through an association rule engine;

[0066] It should be noted that the association rule engine includes a series of association rules, among which the association rules are mined from agricultural historical data and corresponding states through a cloud computing center, including the following steps:

[0067] S131. Align and normalize the status data and dynamic labels of agricultural historical data based on time periods, merge the status data according to the dynamic labels, and establish a dynamic label transaction database;

[0068] S132. Use association rule mining algorithms (such as Apriori, FP-Growth, etc.) to mine the frequent item sets corresponding to each dynamic label from the dynamic label transaction database, generate association rules from the frequent item sets, and calculate the support and confidence of the rules;

[0069] S133. Screen the association rules by setting minimum support thresholds and confidence thresholds to generate a series of association rules for dynamic labels.

[0070] It should be noted that dynamic labels are used to reflect some situations associated with the current status data, such as pest conditions, spores, meteorology, soil moisture, irrigation, seedling conditions, disaster conditions, video monitoring, production, traceability, etc. in the agricultural production area. The generated association rules are such as "If the soil humidity is high and the temperature is moderate, then the pest condition is high", etc.

[0071] S14. Upload monitoring data: Integrate the data with assigned dynamic labels and the data without assigned dynamic labels into corresponding data packets respectively, encrypt them, and then upload them to the cloud computing center.

[0072] It is understandable that the data with dynamic tags is integrated into data packets based on the dynamic tags, and the data without dynamic tags is integrated into data packets with unknown tags. Among them, the data with dynamic tags can be understood as the conditional data to which the dynamic tags generated by the association rule engine are applied, and the other remaining data is the data without dynamic tags.

[0073] It should be noted that in this step, the data is divided and uploaded, which is convenient for subsequent trend prediction based on the data corresponding to the dynamic tags. At the same time, all the data is uploaded for the cloud computing center to update the association rules. The updates here include enriching the dynamic tags and adjusting the association rule screening thresholds, so as to improve the comprehensiveness of the dynamic tags and the flexibility of the association rules.

[0074] S2. Processing of agricultural-related information: Collect relevant information of smart agriculture through accessing third-party platforms, analyze and process the information data to obtain supervision tags and corresponding supervision data, such as Figure 3 shown, including the following steps:

[0075] S21. Collect relevant information: Obtain decision-making data, socio-economic data, and science and technology and innovation data of the supervision department through third-party platforms;

[0076] It is understandable that in the process of realizing smart agriculture, it not only includes agricultural production data, but also includes decision-making data of the supervision department, socio-economic data, and science and technology and innovation data, etc. Among them, agricultural production data involves direct data in the agricultural production process, including crop planting, farmland management, climate conditions, etc.; decision-making data is the relevant data formulated by the supervision department based on national or regional policies, regulations, and plans, and these data help to make decisions and supervise agricultural activities; socio-economic data reflects the impact of socio-economic factors on agricultural production and helps the supervision department evaluate the agricultural economic situation and risks; science and technology and innovation data involves data in the fields of agricultural technology, innovation, education, etc., and provides technical support for agricultural production and supervision.

[0077] It should be noted that in the above process, it is necessary to encrypt and license the acquired data to prevent data leakage problems and improve data security.

[0078] S22. Generate supervision tags: Use a multi-modal large model to process relevant information data, fuse data from different modalities (such as text, images, etc.), and generate corresponding supervision tags, specifically including the steps:

[0079] S221. Data preprocessing: Include preprocessing of text data and image data:

[0080] Text data preprocessing: Use regular expressions to clean HTML tags, special characters, and extra spaces in the text; use Jieba word segmentation to segment Chinese text and break each sentence into meaningful words; remove stop words (such as "的", "和") or do part-of-speech tagging according to task requirements.

[0081] Image data preprocessing: Use OpenCV to scale, rotate, and crop the image to ensure that the input image size is consistent (such as 224x224); normalize the image and scale the pixel value range from [0, 255] to [0, 1]; use image enhancement methods (such as flipping, rotation, color change) to increase data diversity.

[0082] S222. Modal feature extraction: including text modal feature extraction and image modal feature extraction:

[0083] Text modality feature extraction: Load a pre-trained BERT model (such as the model provided by Hugging Face), input text data into the BERT model for encoding, obtain the context-related word vectors of the text, and extract the hidden state of the last layer as the feature representation of the text.

[0084] Image modality feature extraction: Load the ResNet model (usually ResNet-50 or ResNet-101), input the preprocessed image into ResNet, and use its residual connection to extract image features; extract the features of the penultimate layer (the layer before the fully connected layer) as the image representation.

[0085] S223, Multimodal Fusion: Extract feature vectors from text and image modalities respectively, such as BERT text features and ResNet image features, concatenate the text features and image features to obtain a larger feature vector, and standardize the concatenated feature vector to ensure consistent feature scale.

[0086] S224, Model training: Build a multimodal Transformer model and input text and image features into the model through multiple encoders (processing text and image modalities respectively);

[0087] Establish connections between multiple modalities through the self-attention mechanism and learn the associations between different modalities;

[0088] Use the Cross-Entropy Loss function for classification task training, or use other suitable loss functions.

[0089] S225. Generate regulatory labels: Input new multimodal data, perform inference using the trained multimodal Transformer model, and output a feature vector.

[0090] Pass the feature vector to the adaptive Softmax. This classifier uses a hierarchical calculation method and calculates layer by layer according to the frequency of categories. The model outputs a probability distribution representing the probabilities of different regulatory labels, and selects the label with the highest probability as the final regulatory label.

[0091] S23. Extract regulatory data: Obtain the range thresholds of the corresponding data types according to the generated regulatory labels. For the regulatory labels that cannot be directly obtained from the relevant information, use the multimodal large model to infer and supplement the reference values.

[0092] It can be understood that the regulatory data is the defined range or reference value of each data type corresponding to the regulatory label.

[0093] S24. Monitor data annotation: For the monitoring data uploaded to the cloud computing center, label the monitoring data by data type and calculating the similarity between the monitoring data and the range thresholds or reference values of the regulatory data.

[0094] It can be understood that the monitoring data annotation label is the dynamic label of the data used for subsequent association rule updates.

[0095] It should be noted that the multimodal large model is a deep learning model that can simultaneously process and understand multiple types of data (modalities), usually including various data forms such as text, images, sounds, and time series. In this embodiment, by using the multimodal large model, the generation of regulatory labels, the extraction of range thresholds of regulatory data, and the generation of reference values for the decision-making data of the regulatory department, social and economic data, and science and technology and innovation data are completed, making the regulatory labels more accurate and the data thresholds more perfect. At the same time, the above-generated results are used to label the latest monitoring data, facilitating the update of subsequent association rules and improving the consistency and relevance of data label annotation.

[0096] S3. Visualize all-region data: Import all labels and corresponding data into the Geographic Information System, match them according to the corresponding regions and their respective labels, and at the same time, the cloud platform computing center identifies and updates the monitoring labels, as Figure 4 shown, including the following steps:

[0097] S31. Import multi-source data: Uniformly convert all associated data of the target agricultural region into a format supported by the Geographic Information System (GIS), add descriptive metadata to the data, store it in the cloud computing center, and import the preprocessed data into the GIS for visual display.

[0098] Among them, the associated data includes remote sensing data, monitoring data, supervision data, and public data, etc., and the descriptive metadata such as acquisition time, data source, and coordinate system. It is understandable that for data import, the GIS platform (such as ArcGIS or QGIS) is used to load raster and vector data; data is directly imported from the database to the WebGIS platform through the API; the vector layer of the farmland boundary is superimposed on the NDVI remote sensing image layer, and the real-time data of the weather station is displayed in the form of a heat map; different crop types are distinguished by means of color, transparency, etc., and the real-time meteorological changes are dynamically rendered.

[0099] It should be noted that in this embodiment, a geographic information system is established for the target agricultural area, and then the monitoring data and supervision data are respectively loaded into the GIS in the form of dynamic labels and supervision labels, so as to efficiently display a large amount of data and improve the interactivity of the data at the same time.

[0100] S32. Data matching and display: The dynamic labels are displayed flowing at the corresponding positions on the map according to the coordinate system of the data acquisition device, and interactive prompts are made by calculating the correlation between the dynamic labels and the supervision labels.

[0101] It should be noted that the calculation of the correlation between the dynamic labels and the supervision labels is to obtain the correlation between the two by using the Pearson correlation coefficient method and other correlation calculation methods according to the respective data types and data values of the labels. The correlation is defined by setting a threshold to complete the association between the dynamic labels and the supervision labels for interactive prompts, and the colors can be rendered and displayed on the map.

[0102] S33. Deepening of interactive prompts: According to the dynamic labels that generate interactive prompts, the trend prediction model is called. After the monitoring data corresponding to the dynamic labels is subjected to feature engineering processing, it is input into the trend prediction model to obtain the trend changes of the dynamic labels. At the same time, early warning prompts are made for the monitoring data based on the supervision data, which specifically includes the following steps:

[0103] S331. Integrate the monitoring data used for generating dynamic labels into a data set, and perform feature engineering on the integrated data set, including feature extraction, feature selection, and feature construction;

[0104] S332. Select a machine learning model as the basis of the trend prediction model, and use the existing historical data to train the selected model, with the fusion result of multi-source data as the input feature and the trend change of the dynamic label as the output;

[0105] S333. Compare the data corresponding to the dynamic labels and the supervision labels according to the interactive prompts, and make early warning prompts when the monitoring data exceeds the range threshold or reference value of the supervision data.

[0106] It should be noted that in the process of trend prediction, the machine learning model is not limited. Using the monitoring data corresponding to the dynamic tags as the input is equivalent to the conditional data of the association rules here, that is, the input features of the trend prediction model have been screened, improving the prediction accuracy of the dynamic tags. At the same time, based on the interactive prompt, the monitoring data is compared with the regulatory data. When it exceeds the range, a warning prompt is given to process the current state in a timely manner. In this process, the matching of the data types for comparison is completed through the interactive prompt. Therefore, through the above-mentioned trend prediction and warning prompt, the overall state of the dynamic tags is grasped and visually displayed. The above processing process is based on the interactive prompt. Therefore, both prediction and warning are completed by screening data, improving the relevance and efficiency of visualization.

[0107] In this embodiment, the display granularity of the interactive prompt is displayed according to the degree of data visualization. By adjusting the minimum support threshold and confidence threshold in the association rule mining process, the number of generated dynamic tags is adjusted, so as to achieve the adjustment of the number of visual interactive prompts. The dynamic tags for interactive prompts have a corresponding relevance to the regulatory decision. The platform completes the interaction between the directly collected data and the regulatory decision data through the interactive method mentioned in this embodiment. After obtaining the dynamic tags of the interactive prompt, trend prediction is carried out, providing associated display and trend prediction for the visualization of agricultural data, improving the data integration efficiency and display pertinence, and at the same time providing a reference for decision support.

[0108] S34. Association rule update: The cloud computing center collects the monitoring data, and after establishing a perfect data format by labeling the monitoring data, it is added to the dynamic tag transaction database, and the association rules are updated through association mining and sent to the edge computing module.

[0109] This embodiment also provides an agricultural data interaction platform based on multi-source information, as Figure 5 shown, including a data collection and fusion module, a data storage and management module, a data analysis and mining module, an intelligent decision-making and warning module, and a data sharing and interaction module; the data collection and fusion module, the data storage and management module, the data analysis and mining module, the intelligent decision-making and warning module, and the data sharing and interaction module are sequentially connected for communication.

[0110] The data collection and fusion module is used to collect multi-source agricultural data and perform preprocessing, and then fuse and associate the heterogeneous data from different data sources.

[0111] Among them, the fusion and association include the following steps:

[0112] A11. Data collection: Through the set data collection devices using intelligent sensing technology, each edge computing module obtains real-time data by setting the collection frequency, including meteorological sensors, soil sensors, cameras, drones, and satellite remote sensing.

[0113] A12. Data preprocessing: Thoroughly clean the collected raw data, removing invalid, incorrect, or incomplete records to eliminate noise and outliers in the data;

[0114] Perform data standardization processing to convert data with different dimensions and scales into a unified data format that can be used for analysis by the association rule engine.

[0115] A13. Data fusion: Input the preprocessed data into the association rule engine to generate dynamic labels, complete the fusion of multi-source data, and perform subsequent prediction and visualization.

[0116] The data storage and management module is used to store the collected and gathered data in the database, and select a cloud computing center to achieve parallel storage and access of the data.

[0117] It should be noted that when the data storage and management module realizes its functions, it includes: standardizing the format, removing duplicates, and correcting errors of all data; designing the database schema according to the data characteristics and query requirements; selecting a suitable distributed storage system (such as HDFS, HBase); designing a data partitioning strategy (such as partitioning by time, by region, business line, etc. according to logic) to optimize parallel storage and access; loading data through an ETL tool or a distributed data import tool (such as Sqoop, Kafka); introducing Redis (Remote Dictionary Server) to accelerate hot data query; setting permissions and security policies to protect the data.

[0118] The data analysis and mining module is used to analyze and process all data through the cloud computing center, including:

[0119] Mining a series of rules for dynamic labels from agricultural historical data and corresponding states through an association rule mining algorithm;

[0120] Analyzing decision-making data, socio-economic data, and science and technology and innovation data of regulatory departments through a multi-modal large model to generate regulatory labels and regulatory data;

[0121] Training a machine learning model through existing historical data to establish a trend prediction model, and inputting the monitoring data of dynamic labels into the model for trend change prediction.

[0122] The intelligent decision-making and early warning module is used to calculate the correlation based on the generated dynamic tags and regulatory tags. For the dynamic tags that reach the design threshold, interactive prompts are given. At the same time, according to the interactive prompts, the data corresponding to the dynamic tags and regulatory tags are compared, and early warning prompts are given when the monitored data exceeds the range threshold or reference value of the regulatory data.

[0123] The data sharing and interaction module is used to integrate the target agricultural area, dynamic tags and real-time data into a geographic information system for visual display, where the dynamic tags also include interactive prompts, trend predictions and early warning prompts.

[0124] It should be noted that the interactive prompt means that the direct data collected in agricultural production completes data interaction with the decision-making data, social and economic data, and science and technology and innovation data of the regulatory department in the form of matching dynamic tags and regulatory tags, thus realizing the correlation visualization of the regulatory data of different functional departments, and displaying the data on the sharing platform in an efficient, real-time and accurate state, providing a convenient data query method for agricultural producers and decision-makers.

[0125] The present invention first generates dynamic tags for the direct data of agricultural production through the edge computing modules in different regions by means of an association rule engine, and completes data collection and fusion through distributed processing, reducing the difficulty of fusing massive data and improving the processing efficiency of real-time data; at the same time, integrating other information data related to smart agriculture through a multimodal large model to extract regulatory tags and regulatory data, guiding the data annotation of monitored data, and improving the consistency and relevance of data tag annotation; finally, through the correlation calculation of dynamic tags and regulatory tags for interactive prompts, the monitored data and regulatory data are associated, and visual display is carried out based on GIS, improving the interactivity of agricultural data management.

[0126] In the visual display of the present invention, a dynamic map of the target agricultural area is established based on GIS, which includes an agricultural area map, dynamic tags and real-time data. The dynamic tags include interactive prompts, trend predictions and early warning prompts. The interactive prompts provide the association status between the current monitored data and the regulatory data for users. At the same time, trend change predictions and early warning prompts are made for the dynamic tags with interactive prompts, improving the visual effect, helping users understand complex data and analysis results in an intuitive and concise manner, and enhancing the real-time response ability through early warning prompts and improving the decision-making efficiency.

[0127] The above are only the preferred embodiments of the present invention, and do not impose any form of limitation on the present invention. Although the present invention has been disclosed above with the preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some changes or modifications to equivalent embodiments by using the above-disclosed technical content without departing from the technical solution of the present invention. However, as long as it does not depart from the technical solution content of the present invention, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. An agricultural data interaction method based on multi-source information, characterized in that: The following steps are involved: Regional agricultural data processing: Divide the target areas for agricultural supervision, set up real-time data collection equipment for each area, process the collected data through the corresponding edge computing module, and generate dynamic labels; Processing of agriculture-related information: Collect relevant information about smart agriculture through access to third-party platforms, analyze and process the information data, and obtain regulatory labels and corresponding regulatory data; Global data visualization: import all tags and corresponding data into the geographic information system, match them according to the corresponding areas and their respective tags, and identify and update the monitoring tags through the cloud platform computing center; The global data visualization includes the following steps: Data matching display: Dynamic tags are displayed in a mobile manner at corresponding locations on the map according to the coordinate system of the data collection device, and interactive prompts are provided by calculating the correlation between dynamic tags and regulatory tags. The interactive prompts include matching direct data collected from agricultural production with decision-making data, social and economic data, and science and technology and innovation data of regulatory departments through dynamic tags and regulatory tags to complete data interaction. Deepening interactive prompts: Call the trend prediction model based on the dynamic tags of interactive prompts, perform feature engineering on the monitoring data corresponding to the dynamic tags, and input them into the trend prediction model to obtain the trend changes of the dynamic tags. At the same time, the monitoring data will be used for early warning prompts based on the regulatory data. The regional agricultural data processing comprises the following steps: Agricultural area division: set up data collection equipment according to data application requirements, set up edge computing modules according to the expansion of data collection, and divide agricultural supervision areas based on edge computing modules; Collect monitoring data: Through the set data collection equipment, each edge computing module obtains real-time data by setting the collection frequency; Dynamic label generation: After the edge computing module pre-processes the real-time data, it generates dynamic labels for the pre-processed data through the association rule engine; Monitoring data upload: The data with dynamic tags and the data without dynamic tags are integrated into corresponding data packets and encrypted before uploading to the cloud computing center; The dynamic tag generation further includes the following steps: Align and normalize the state data and dynamic tags of agricultural historical data based on time periods, merge the state data based on dynamic tags, and establish a dynamic tag transaction database; The association rule mining algorithm is used to mine the frequent item sets corresponding to each dynamic tag from the dynamic tag transaction database, generate association rules from the frequent item sets, and calculate the support and confidence of the rules; The association rules are screened by setting the minimum support threshold and the confidence threshold to generate a series of association rules for dynamic tags.

2. The agricultural data interaction method based on multi-source information according to claim 1 is characterized in that: The processing of the agricultural related information comprises the following steps: Collect relevant information: obtain decision-making data, socio-economic data, and science and technology and innovation data from regulatory authorities through third-party platforms; Generate regulatory labels: Use a multimodal large model to process relevant information data, fuse data from different modalities, and generate corresponding regulatory labels; Extract regulatory data: Obtain the range threshold of the corresponding data type based on the generated regulatory labels. For regulatory labels that cannot be directly obtained from relevant information, use a multimodal large model to infer and supplement reference values; Monitoring data labeling: For monitoring data uploaded to the cloud computing center, labels are annotated by data type and by calculating the similarity between the range threshold or reference value of the monitoring data and the regulatory data.

3. The agricultural data interaction method based on multi-source information according to claim 1 is characterized in that: The global data visualization further includes the following steps: Import multi-source data: All relevant data of the target agricultural area are uniformly converted into a format supported by the geographic information system, and descriptive metadata is added to the data and stored in the cloud computing center. The pre-processed data is imported into the GIS for visualization; Association rule update: The cloud computing center collects monitoring data, and adds it to the dynamic label transaction database after establishing a complete data format by labeling the monitoring data. It updates the association rules through association mining and sends them to the edge computing module.

4. The agricultural data interaction method based on multi-source information according to claim 1 is characterized in that: The interactive prompt deepening includes the following steps: Integrate the monitoring data used for dynamic label generation into a dataset, and perform feature engineering on the integrated dataset, including feature extraction, feature selection, and feature construction; Select a machine learning model as the basis of the trend prediction model, use the existing historical data to train the selected model, use the fusion results of multi-source data as input features, and use the trend changes of dynamic labels as output; The data corresponding to the dynamic label and the regulatory label are compared based on the interactive prompts, and an early warning prompt is issued when the monitoring data exceeds the range threshold or reference value of the regulatory data.

5. An agricultural data interaction platform based on multi-source information, used to implement an agricultural data interaction method based on multi-source information as claimed in any one of claims 1 to 4, characterized in that: It includes data collection and fusion module, data storage and management module, data analysis and mining module, intelligent decision-making and early warning module and data sharing and interaction module; The data collection and fusion module, the data storage and management module, the data analysis and mining module, the intelligent decision-making and early warning module and the data sharing and interaction module are sequentially connected in communication; The data collection and fusion module is used to collect and pre-process multi-source agricultural data, and then fuse and associate heterogeneous data from different data sources; The fusion and association include the following steps: Data collection: Using intelligent sensing technology through the set data collection equipment, each edge computing module obtains real-time data by setting the collection frequency, including meteorological sensors, soil sensors, cameras, drones and satellite remote sensing; Data preprocessing: Thoroughly clean the collected raw data, remove invalid, erroneous or incomplete records, perform data standardization, and convert data of different dimensions and scales into a unified data format that can be used for association rule engine analysis; Data fusion: The pre-processed data is input into the association rule engine to generate dynamic labels, complete the fusion of multi-source data, and perform subsequent prediction and visualization.

6. The agricultural data interactive platform based on multi-source information according to claim 5, characterized in that: The data storage and management module is used to store the collected and collected data in a database and select a cloud computing center to realize parallel storage and access of data.

7. The agricultural data interactive platform based on multi-source information according to claim 5, characterized in that: The data analysis and mining module is used to analyze and process all data through the cloud computing center, including: A rule engine that mines agricultural historical data and corresponding status through association rule mining algorithms to obtain a series of dynamic labels; Analyze the decision-making data, socio-economic data, and science and innovation data of regulatory authorities through multimodal big models to generate regulatory labels and regulatory data; The machine learning model is trained with existing historical data to establish a trend prediction model, and the monitoring data of dynamic tags is input into the model to predict trend changes.

8. The agricultural data interactive platform based on multi-source information according to claim 5, characterized in that: The intelligent decision-making and early warning module is used to calculate the correlation based on the generated dynamic tags and regulatory tags, to interactively prompt the dynamic tags whose correlation values ​​reach the designed threshold, and to compare the data corresponding to the dynamic tags and regulatory tags based on the interactive prompts, and to issue early warning prompts when the monitoring data exceeds the range threshold or reference value of the regulatory data; wherein the interactive prompts include completing data interaction between the direct data collected from agricultural production and the decision-making data, social and economic data, and science and innovation data of the regulatory department by matching dynamic tags and regulatory tags; The data sharing and interaction module is used to integrate the target agricultural area, dynamic tags and real-time data into the geographic information system for visual display, wherein the dynamic tags include interactive prompt information, trend prediction information and early warning prompt information.

Images