Agricultural digital management system and method

Abstract

The invention provides an agricultural digital management system and method, and the system comprises a field management module which is used for managing field archives, monitoring soil, and monitoring climate; the planting management module is used for executing plantology management, four-condition monitoring, yield prediction and agricultural machinery operation; the grain purchasing module is used for executing weighing management, purchasing standard management, purchasing application management, contract management, payment management and supplier management; the grain sales module is used for managing agricultural products, orders, after-sales, transportation, storage and customers; the digital management system covering the whole process of agricultural production is constructed through deep integration of the field management module, the planting management module, the grain purchasing module, the grain selling module and the data service module, and the system realizes refinement, intellectualization and transparency of agricultural production by using the Internet of Things, big data, artificial intelligence and remote sensing technologies. The agricultural production efficiency and the economic benefit are obviously improved.

Description

Technical Field

[0001] This invention relates to the field of agricultural management, and more particularly to an agricultural digital management system and method. Background Technology

[0002] With the development of agricultural parks and the popularization of digital agriculture and 5G + With the development of technologies such as agriculture, the management of agricultural parks is becoming increasingly digital and intelligent, and various agricultural management platforms have emerged. These platforms range from planting platforms responsible for planting management to sales platforms responsible for marketing, as well as traceability platforms that allow for one-code access. The use of these platforms has enabled digital management of the pre-production, pre-production, and post-production stages of agriculture, greatly improving agricultural efficiency and saving labor and resource costs.

[0003] However, existing agricultural management systems store meteorological, soil, and crop data independently, making it impossible to analyze them in a coordinated manner; they rely on human experience for judgment and cannot respond to environmental changes in real time; and irrigation equipment lacks an intelligent scheduling mechanism. Therefore, an agricultural digital management system and method are proposed to solve the above problems. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to overcome the defects of the existing technology. The present invention proposes an agricultural digital management system.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, the present invention provides an agricultural digital management system, comprising: The field management module is used to manage field records, soil monitoring, and climate monitoring. The planting management module is used to perform planting management, monitoring of four conditions (planting, soil, and water conditions), yield forecasting, and agricultural machinery operation. The grain procurement module is used for weighing management, procurement standard management, purchase application management, contract management, payment management, and supplier management. The grain sales module is used to manage agricultural products, orders, after-sales service, transportation, warehousing, and customers. The data service module is used to provide meteorological and environmental data, soil data, drone management, and satellite remote sensing data; Through the field management module, planting management module, grain purchase module, grain sales module, and data service module, the entire process from grain planting to sales can be controlled.

[0006] Preferably, the field management module also includes growth monitoring, which uses the drone management of the data service module to monitor crops and obtain information on crop growth.

[0007] Preferably, the grain sales module also includes agricultural product traceability, obtaining complete information about the agricultural products composed of the field management module, planting management module, grain purchase module, and grain sales module.

[0008] Preferably, the planting management module also includes a four-condition early warning and prediction system, which constructs a four-condition prediction model using data from soil monitoring, climate monitoring, agronomic management, and four-condition monitoring.

[0009] Preferably, the planting management module also includes irrigation management, which constructs an irrigation model using data from field records, soil monitoring, climate monitoring, and agronomic management to determine irrigation methods, irrigation time, irrigation volume, and irrigation frequency.

[0010] Preferably, the crop management determines the crop and planting time through field records, soil monitoring, and climate monitoring.

[0011] Preferably, the field management module also includes field enclosure, which adds individual farmers' fields to the field file, and guides individual farmers in cultivating the land, planting crops, fertilizing, aerating and irrigating through the field file, soil monitoring, climate monitoring and planting season management.

[0012] Secondly, the present invention provides an agricultural digital management method, including an agricultural digital management system, comprising: Acquire satellite remote sensing data to construct field profiles; Acquire meteorological and environmental data to build a climate monitoring system; Soil data is acquired through soil sensors to build a soil monitoring system; Select crops and planting times based on data from field records, climate monitoring, and soil monitoring. Using drones to obtain information on crop growth and predict crop yield; Obtain crop procurement information, transport crops for sale, and complete the entire process control from crop planting to sales.

[0013] Thirdly, the present invention provides an electronic device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions, which, when executed by the processor, implement the steps of the agricultural digital management system.

[0014] Fourthly, the present invention provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the agricultural digital management system.

[0015] Compared with existing technologies, the beneficial effects of this invention include: by deeply integrating five major modules—field management, planting management, grain purchase, grain sales, and data services—a digital management system covering the entire agricultural production process is constructed. The system utilizes the Internet of Things, big data, artificial intelligence, and remote sensing technologies to achieve refined, intelligent, and transparent agricultural production, significantly improving agricultural production efficiency and economic benefits. Attached Figure Description

[0016] The disclosure of this invention is illustrated with reference to the accompanying drawings. It should be understood that the drawings are for illustrative purposes only and are not intended to limit the scope of protection of this invention. In the drawings, the same reference numerals are used to refer to the same parts. Wherein: Figure 1 A flowchart of an agricultural digital management system according to one embodiment of the present invention is shown schematically. Detailed Implementation

[0017] It is readily understood that, based on the technical solution of this invention, those skilled in the art can propose various interchangeable structural methods and implementations without altering the essential spirit of the invention. Therefore, the following detailed embodiments and accompanying drawings are merely illustrative examples of the technical solution of this invention and should not be considered as the entirety of the invention or as limitations or restrictions on the technical solution of this invention.

[0018] Example 1, referring to Figure 1 As an embodiment of the present invention, an agricultural digital management system and method are provided, comprising: S100: Field Management Module. The Field Management Module is the foundation of the system. It is responsible for managing basic information about farmland, soil and climate data, and providing data support for other modules.

[0019] S101: Field Records Data acquisition: The geographical location, boundaries, area and topography of the fields are obtained through high-resolution satellite remote sensing images. GIS technology is used to draw electronic maps of the fields and mark the field number, the farmer to which it belongs, the soil type and historical planting records.

[0020] Data storage: Field records are stored in a cloud database in both structured and unstructured data formats, supporting multi-dimensional queries and visualization.

[0021] Dynamic updates: The system updates field files in real time based on changes in the planting season and land transfer. For example, when field boundaries change due to land consolidation, the system automatically redraws the field map using satellite remote sensing data.

[0022] S102: Soil Monitoring Sensor deployment: Deploy IoT soil sensors in the field to monitor parameters such as soil moisture, temperature, pH value, nitrogen, phosphorus and potassium content. Sensor data is transmitted to the cloud via LoRaWAN or NB-IoT network.

[0023] Data analysis: Utilizing machine learning algorithms to analyze soil data and generate soil quality assessment reports. For example, cluster analysis can be used to divide fields into high, medium, and low fertility zones, providing a basis for precision fertilization.

[0024] Early warning function: When the soil pH value is abnormal or the nutrients are unbalanced, the system will automatically send early warning information to farmers and prompt them to take improvement measures.

[0025] S103: Climate Monitoring Data sources: integrating meteorological station data, satellite remote sensing data and third-party meteorological services to obtain climate parameters such as precipitation, temperature, humidity, wind speed, and sunshine duration.

[0026] Microclimate modeling: By combining field topography and vegetation cover data, microclimate models are constructed to predict climate change trends at the field level. For example, for valley topography, the system can predict the probability and extent of frost.

[0027] Disaster early warning: By using historical climate data and real-time monitoring data, identify the risks of disasters such as drought, floods, and hail, and issue early warnings in advance.

[0028] S104: Growth Monitoring Drone inspection: Multispectral drones are used to inspect fields weekly to obtain vegetation indices (such as NDVI and EVI) and monitor crop growth.

[0029] Growth assessment: Using deep learning models to analyze drone images, the system identifies symptoms such as crop diseases, pests, and nutrient deficiencies. For example, when the NDVI index is below the threshold, the system marks the area as "abnormal growth".

[0030] Visualization: Crop growth is displayed on the electronic map of the field in the form of a heat map, with green indicating healthy areas and red indicating abnormal areas.

[0031] S105: Enclosure Management Consolidation of scattered farmland plots is a fundamental step in farmland management. It aims to digitize fragmented farmland using high-tech methods to create unified plot archives. The system automatically identifies plot boundaries using satellite remote sensing data and manages spatial data using a Geographic Information System (GIS). The plot archives not only include boundary information but also integrate attributes such as plot area, topography, and historical planting records, providing data support for subsequent planting guidance and benefit analysis. This process improves the accuracy and efficiency of farmland management and reduces the cost and errors of manual surveying.

[0032] Using satellite remote sensing data sources, field images are acquired regularly to ensure that the data update frequency matches the crop growth cycle.

[0033] Preprocessing of remote sensing images, including radiometric correction, atmospheric correction, and geometric correction, is performed to eliminate environmental interference and improve the accuracy of boundary identification.

[0034] Integrate auxiliary data, such as drone aerial photography or ground survey data, to verify and supplement satellite data, especially in areas with complex terrain.

[0035] Image segmentation algorithms (such as semantic segmentation models based on deep learning) are applied to automatically extract field boundaries and identify the shape, size, and location of fields. The algorithms need to be trained on diverse farmland datasets to adapt to different crops and landforms.

[0036] The identified boundary data is imported into the field archive database. The database is designed with a cloud storage structure, supports multi-user access and real-time updates, and the archive fields include: field ID, location coordinates, area, soil type, historical crop rotation records, etc.

[0037] Establish a data quality control mechanism, regularly check the accuracy of boundaries through manual sampling, keep the error rate within 5%, and ensure the reliability of the archives.

[0038] Planting guidance is the core of farmland management. Through multi-source data fusion and intelligent analysis, it provides farmers with personalized agricultural operation suggestions throughout the entire cycle. Based on field records, real-time soil monitoring (such as humidity, pH value, and nutrient content) and climate monitoring (such as rainfall, temperature, and humidity), the system uses machine learning models to generate dynamic planting plans. The plans cover all stages from tillage to harvest and automatically trigger early warnings and response measures based on real-time environmental changes (such as severe weather) to help farmers optimize resource utilization and reduce losses. This not only increases crop yields but also promotes sustainable agricultural practices.

[0039] Collect historical data (such as crop rotation patterns), soil monitoring data (real-time collection of soil moisture, nitrogen, phosphorus and potassium content, etc. through IoT sensor networks), and climate monitoring data (obtaining rainfall, temperature, wind speed, etc. from weather stations or satellites) from field records.

[0040] A personalized recommendation model is constructed, employing decision tree or random forest algorithms and incorporating local farmer knowledge (such as traditional planting habits) to output planting plans. The model training process considers the experience of regional agricultural experts to ensure the scientific validity of the recommendations.

[0041] The plan includes: Timing of tillage: Based on soil moisture and climate forecasts, the optimal tillage window is recommended to avoid soil that is too wet or too dry, which would make mechanical operations difficult.

[0042] Crop varieties: Based on the soil characteristics, historical yields and market demand, recommend adaptable crop varieties, such as drought-resistant varieties in arid regions.

[0043] Fertilizer application rate: Based on soil nutrient test results, the precise fertilizer application rate is calculated, and variable fertilization technology is adopted to reduce fertilizer waste and environmental pollution.

[0044] Irrigation plan: Develop a water-saving irrigation schedule based on evaporation and crop water requirements, and recommend drip irrigation or sprinkler irrigation methods.

[0045] Severe Weather Response Mechanism: The system monitors climate data in real time and sets threshold triggers (such as continuous rainfall exceeding 50mm or soil moisture below 30%). When severe weather is detected, the system automatically notifies farmers via SMS, APP push, or voice call.

[0046] When soil moisture is sufficient, cover the soil on rainy days: The system recommends using waterproof cloth or straw mulch to reduce additional moisture absorption. Strategies include the selection of mulch materials, the timing of mulching (implemented 1-2 hours before rainfall), and post-mulching inspections to avoid the mulch affecting soil aeration.

[0047] When the land is dry, watering is notified: Based on soil moisture sensor data, when the moisture level is below the crop's tolerance threshold, a watering reminder is sent, and the amount of irrigation and the best time (such as early morning or evening to reduce evaporation) are suggested.

[0048] When nutrients are deficient, fertilizer application is notified: Through soil nutrient monitoring, when key elements (such as nitrogen and phosphorus) are below the standard value, a fertilizer application notification is triggered, recommending the type, amount, and application method of organic or chemical fertilizer.

[0049] When there is excessive moisture, notify the soil to be aerated: In cases of standing water or high humidity, it is recommended to use a soil aerator or manually to create holes 10-15 cm deep and spaced 1-2 meters apart to enhance aeration and moisture evaporation. Simultaneously, incorporate drainage ditches to prevent waterlogging.

[0050] When the soil moisture sensor maintains a consistently high reading (e.g., >45%), or when the weather station detects heavy rainfall and the field camera observes significant water accumulation, individual farmers are notified to aerate their land. For large areas of farmland: It is recommended to use a self-propelled or tractor-mounted soil aerator with a hole diameter of 2-3 cm and a hole depth strictly controlled at 10-15 cm to avoid damaging the main root system.

[0051] For small plots or orchards: use a handheld soil aerator or manually with a steel rod.

[0052] Drill holes using either a rectangular grid method or a quincunx pattern: Drill holes at 1.5m x 1.5m intervals in the water-filled area. For the quincunx pattern, the interval is 1-2 meters; this method provides more even ventilation.

[0053] Timing for drilling: Drilling should be done after the rain has stopped, when there is no obvious standing water on the ground but the soil is still saturated. At this time, drilling can effectively drain water and will not clog the holes due to the sticky soil.

[0054] When soil moisture is greater than 70% of field capacity and the weather forecast predicts moderate to heavy rain in the next 6-12 hours, individual farmers should be notified to cover their land to reduce soil water absorption.

[0055] Based on farmers' preset inventory and cost preferences, the system automatically recommends covering materials.

[0056] Waterproof cloth: Suitable for short-term heavy rainfall, with excellent waterproof effect, but it should be removed in time after the rain to prevent high temperature scorching of crops and soil hypoxia.

[0057] Straw / rice straw: Environmentally friendly, it can increase soil organic matter, but the initial cost may be high. The thickness of the layer should be 5-10 cm to ensure even coverage without any bare spots.

[0058] After the rainfall ends, individual farmers are reminded that the rain has stopped. Please check whether the covering has been blown away by the wind and decide whether to remove the waterproof cloth to maintain soil aeration based on the soil moisture.

[0059] Precision irrigation solutions: Triggering condition: Soil moisture < specific threshold for crop growth stage (e.g., the threshold is set to 30% during flowering and 25% during fruiting).

[0060] Irrigation Decision Support: Irrigation calculation: The system calculates the amount of water that needs to be replenished based on the soil field water holding capacity, current soil moisture, and crop water requirements. For example, if the target moisture content is 35%, the current moisture content is 25%, and the soil depth is 40cm, then approximately XX cubic meters of water are needed per acre.

[0061] Recommended irrigation time: It is strongly recommended to irrigate in the early morning (5-8 am) or late afternoon (5-7 pm) when evaporation is minimal and water utilization is highest. This recommendation will be explicitly written into the notification.

[0062] System Integration (Advanced Function): Can be integrated with smart irrigation valves to achieve fully automated irrigation. After receiving the notification, farmers can click "One-Click Execution" on the APP, and the system will immediately start the water pump and solenoid valve for irrigation according to the preset plan.

[0063] Precision fertilization program: Soil nutrient data is directly acquired through NPK sensors, and combined with soil test results and leaf nutrient diagnosis results, which are then manually entered into the system by agricultural technicians.

[0064] The system generates a prescription by calling the fertilization model based on the missing elements and their degree, combined with the target yield.

[0065] Example of a notification: "Alert! Nitrogen content in field D4 is low (currently 120 mg / kg, standard value >150 mg / kg). We recommend applying XX kg / acre of urea or YY kg / acre of ammonium nitrate. We suggest using furrow or hole application methods, and immediately cover with soil and water after application." Organic fertilizer recommendations: The system database contains the nutrient content of common organic fertilizers (such as livestock and poultry manure and oilseed cake), and can provide equivalent organic fertilizer application plans.

[0066] 3. Benefit Analysis Extended description: Benefit analysis is a closed-loop component of field management. By quantitatively analyzing the return on investment (ROI) of each field, it assesses the economic viability and sustainability of planting strategies. The system automatically collects input data (such as seed, fertilizer, and labor costs) and output data (such as crop yield and sales revenue) during the production process and calculates the ROI. Combining historical data and comparative analysis, the system provides visualized reports and optimization suggestions to help farmers identify efficient practices, adjust planting plans, and ultimately improve overall profitability and resource efficiency.

[0067] Detailed strategy: Data collection and computation: Input data: This includes direct costs (seeds, fertilizers, pesticides, irrigation water fees) and indirect costs (labor, machinery rental) that are manually entered by farmers or automatically collected (e.g., by IoT devices recording fertilizer usage).

[0068] Output data: Integrate field yield monitoring (such as harvester sensor data) and market sales data (obtained from local markets or e-commerce platforms) to calculate total revenue.

[0069] ROI calculation formula: ROI = (Total Revenue - Total Investment) / Total Investment × 100%. The system updates data monthly to ensure timeliness.

[0070] Analysis and optimization suggestions: Use data analysis tools (such as regression analysis or time series models) to identify key factors affecting ROI, such as excessive fertilization leading to increased costs, or crop varieties being unsuitable leading to low yields.

[0071] Generate personalized optimization reports, including suggestions to reduce unnecessary inputs, adjust crop structure, or improve irrigation methods. For example, if the ROI of a field is below average, the system may recommend switching to high-value crops or adopting precision agriculture technologies.

[0072] It provides a visual dashboard, allowing farmers to view historical trends and peer comparisons through charts, enhancing the transparency of decision-making.

[0073] S200: Planting Management Module The planting management module, based on data from the field management module, enables functions such as planting decisions, growth monitoring, yield prediction, and agricultural machinery scheduling.

[0074] S201: Plant Management Crop selection: By analyzing soil type, pH value, and historical yield data from field records, as well as accumulated temperature and precipitation patterns from climate monitoring, the most suitable crop varieties are recommended. For example, potatoes are recommended for planting in fields with a slightly acidic pH.

[0075] Planting time planning: Using climate prediction models, the optimal planting window is determined. For example, the system combines the probability of precipitation and temperature trends for the next 15 days to suggest that farmers plant spring corn between March 10 and March 20.

[0076] Planting plan generation: Based on the crop growth cycle and field conditions, a detailed planting plan is generated, including sowing density, row spacing and depth.

[0077] S202: Monitoring of Four Conditions Monitoring content: The four conditions include seedling condition, insect condition, disease condition and disaster condition.

[0078] Crop emergence rate and uniformity were analyzed using multispectral images from drones.

[0079] Insect infestation: Deploy smart insect monitoring lights in the fields to automatically identify the types and quantities of pests.

[0080] Disease status: Use hyperspectral remote sensing technology to monitor crop canopy temperature and stomatal conductance to identify diseases at an early stage.

[0081] Disaster Situation: Based on climate monitoring data, assess the impact of disasters such as drought and floods on crops in real time.

[0082] Data integration: The data on the four conditions are linked with field records, soil monitoring and climate monitoring data to form a panoramic view of crop growth.

[0083] S203: Four-Situation Early Warning and Forecast Prediction Model: Based on historical data on the four elements, soil data, and climate data, a time series prediction model (such as ARIMA or LSTM) is trained to predict the probability of insect infestation and the trend of disease spread in the next 7 days.

[0084] Warning rules: The system presets warning thresholds. For example, when the pest index exceeds 0.8, a pest warning will be automatically issued.

[0085] Prevention and control recommendations: Based on the early warning results, specific prevention and control measures are recommended, such as the type and dosage of pesticides to be sprayed.

[0086] S204: Production Forecast Multi-source data fusion: Integrating drone growth monitoring data, satellite remote sensing vegetation index, and climate data to construct a yield prediction model.

[0087] Machine learning algorithms: Random forest or gradient boosting tree algorithms are used to combine historical yield data with real-time growth data to predict yield per unit area and total yield. For example, the model input includes NDVI index, soil nitrogen content, and precipitation, and the output is an estimated yield per acre.

[0088] Prediction accuracy optimization: By using ensemble learning techniques, the prediction results of multiple models are combined to improve accuracy.

[0089] S205: Agricultural Machinery Operations Vehicle-mounted positioning and communication terminal: integrates an RTK positioning module (which can access BeiDou / GNSS differential services), an inertial measurement unit (IMU), and a 4G / 5G communication module. It is fixedly installed on agricultural machinery to collect and upload high-precision three-dimensional position, speed, heading, and time information (PVT data) of the agricultural machinery in real time.

[0090] Cloud data processing server: Deployed with a work area calculation engine, spatial database (storing field electronic fences, historical trajectories, etc.) and business logic module.

[0091] User interaction terminals, such as web management backends or mobile apps, are used for field management, task assignment, result viewing, and export.

[0092] Step 1: Data Preparation and Preprocessing Field electronic fence management: The polygonal electronic fences of each field are pre-entered into the system or drawn using map tools. The boundary coordinates adopt a coordinate system consistent with RTK positioning (such as WGS-84, and are transformed to planar coordinates such as UTM through projection).

[0093] Agricultural machinery operation trajectory data collection: When agricultural machinery is operating in the field, the on-board terminal continuously collects RTK positioning data at a frequency of 1-5Hz (accuracy up to centimeter level), forming an ordered sequence of trajectory points {P1, P2, ..., Pn}, each point containing information such as latitude and longitude, elevation, timestamp, and speed. The data is uploaded to the cloud server in real time or near real time.

[0094] Trajectory preprocessing: The server filters and smooths the original trajectory, removes obvious jump point noise, and interpolates according to the time series to ensure the continuity of trajectory points.

[0095] Not all trajectory points represent valid tasks. The system determines valid task segments in both spatial and temporal dimensions using the following rules: Spatial attribution determination: Using the fast ray method where points lie within polygons, all trajectory points located within the electronic fence polygon of the target field are filtered out.

[0096] Operation status determination: Combining the preset operating speed range of the agricultural machinery (e.g., 3-8 km / h for seeders, 2-6 km / h for harvesters) and the status signals of the agricultural implements (e.g., rotary tiller blade speed, seeder metering signal, etc., which can be obtained via CAN bus), the trajectory points in a valid operating state are determined. Only when a trajectory point simultaneously meets both conditions of "within the field" and "in operating state" is it marked as a valid operating point.

[0097] Track segmentation: A continuous series of effective work points constitutes an effective work segment. When the field turns, the agricultural machinery temporarily leaves the field, or work is paused, the effective work segment is interrupted.

[0098] To resolve the contradiction between the insufficient accuracy of pure polygon methods and the high computational cost of pure raster methods, this invention employs a two-stage fusion calculation method: Phase 1: Polygon Pre-screening and Coarse Calculation The minimum convex hull or AlphaShape shape (which can better adapt to curved work rows) of all valid work points within a work segment is generated according to their spatial distribution, and this polygon is called the work coverage polygon.

[0099] Calculate the intersection polygon of the coverage polygon and the target field's electronic fence polygon. This step quickly eliminates invalid areas outside the field.

[0100] Calculate the area Area_poly of the intersection polygon as a preliminary area estimate for this work segment.

[0101] Phase Two: Rasterization Refinement Calculation Set a fine raster resolution (e.g., 0.5m x 0.5m, which can be adjusted according to the working width) and rasterize the geographical area covered by the above intersecting polygons.

[0102] For each rasterized grid cell, determine whether its center point is "covered" by the original, unapplied, valid work trajectory points. The coverage determination rule is: take the center point of the grid cell as the center, and half the width of the agricultural machinery operation area as the radius (or set an effective influence radius R according to the type of agricultural implement). If there is at least one valid work point within this radius, the grid cell is marked as "operated".

[0103] Count the number N of all raster cells marked as "worked".

[0104] Calculate the precise working area of ​​this work segment: Area_final=N*(Grid_Width*Grid_Height), where Grid_Width and Grid_Height are the dimensions of the grid cells.

[0105] The advantages of this fusion method are: the polygon stage quickly removes a large number of obviously irrelevant areas, greatly reducing the number of grids that need to be judged in detail; the rasterization stage accurately describes the coverage of the area by the proximity relationship between points and grids, avoiding the edge error and internal hole neglect problems caused by simple polygon calculation.

[0106] When multiple agricultural machines (M1, M2, ..., Mk) are operating in the same field, and their operating trajectories overlap in time or space, deduplication calculations are required to obtain the total effective operating area of ​​the field. The system employs a spatiotemporal fusion grid-based attribution determination method. The entire target field is rasterized at a uniform high resolution (e.g., 0.5 meters).

[0107] Maintain a status label and an associated list of timestamps for each grid cell.

[0108] Iterate through all valid operational trajectory points of all agricultural machinery. For each operational point P, find all grid cells covered within its effective influence radius R.

[0109] For each covered raster cell: If the current status of the grid is "not in operation", then mark its status as "operated" and record the agricultural machinery ID and timestamp of the current operation point P.

[0110] If the grid is already in the "worked" state, check the timestamp of the current work point P against the previously recorded timestamps. The system can be configured with a deduplication strategy: Strategy A (Strict Deduplication): Regardless of the time sequence, the area of ​​the same grid cell is only counted when it is covered by the first operation. Suitable for scenarios such as tillage and sowing where repeated operations are not advisable.

[0111] Strategy B (Time Window Deduplication): The second operation on the same grid cell is only counted in the area calculation if the time interval between two operations exceeds a set threshold (e.g., 24 hours). Suitable for scenarios such as plant protection and fertilization that may require multiple operations.

[0112] Strategy C (Agricultural Machinery Priority): Set priorities for different agricultural machinery or operation types. High-priority operations can cover the grid usage of low-priority operations.

[0113] After all agricultural machinery trajectories have been processed, count the total number of grid cells with the status "already worked" in the entire grid, N_total.

[0114] Calculate the total effective working area of ​​the field: Total_Area=N_total*(Grid_Width*Grid_Height).

[0115] This method solves the problem of repetitive calculations caused by trajectory intersections, overlaps, and repetitive operations at the bottom-level grid, ensuring the uniqueness and accuracy of the area calculation results.

[0116] The system automatically generates a work area calculation report, including: Map showing the independent operating area and operating trajectory of each agricultural machine within a designated field.

[0117] The total effective working area of ​​the field after deduplication.

[0118] Visualization layer: Overlays field boundaries, agricultural machinery tracks (distinguished by different colors), and a rasterized "operation density" map represented by color shades on the electronic map to intuitively show operation coverage and overlapping areas.

[0119] The data can be integrated with settlement systems, work statistics reports, etc.

[0120] Taking two wheat combine harvesters (M1, 4 meters wide; M2, 4 meters wide) harvesting wheat together in the same rectangular wheat field (approximately 200 mu) as an example: Data acquisition: The onboard RTK terminals of the two harvesters record the entire operation trajectory.

[0121] Valid segment determination: The system filters out sections of road that turn at the edge of the field (due to excessive speed) and sections of road that enter or exit the field.

[0122] Single-machine calculation: The effective operation trajectories of M1 and M2 were calculated using the polygon-grid fusion method, and the preliminary operation area of ​​M1 was 85 mu and the operation area of ​​M2 was 92 mu (simply added together to 177 mu).

[0123] Multi-machine deduplication: The system will grid the fields (0.5-meter grid).

[0124] Process all work points M1 and M2, with the radius of influence for each point set to 2 meters (half the width of the work area).

[0125] It was discovered that the work tracks of the two machines overlapped in an area of ​​about 15 acres in the middle of the field (either taking over or supplementing the harvest).

[0126] A strict deduplication strategy is adopted, and a grid in the intersection area is counted only once when it is covered by the earliest working locomotive point.

[0127] Output results: The system calculated the total effective harvested area of ​​the field to be 165 mu (approximately 10 hectares), and clearly marked the respective operating areas of M1 and M2, as well as the 15 mu (approximately 1 hectare) overlapping area, on the map. This result accurately reflects the actual harvested area, providing a precise basis for the settlement of machine harvesting service fees.

[0128] S206: Irrigation Management Irrigation model: A dynamic irrigation model is constructed based on soil moisture sensor data, soil type data in field records, and evaporation data from climate monitoring.

[0129] Decision support: The model outputs irrigation time, irrigation amount, and irrigation frequency. For example, when soil moisture is below 60% of field capacity, the system prompts for irrigation and recommends 30 cubic meters per acre.

[0130] Intelligent control: It integrates with intelligent irrigation systems to automatically start and stop water pumps and valves.

[0131] S300: Grain Procurement Module The grain procurement module is responsible for managing the entire grain procurement process, including weighing, quality inspection, contracts, and payments.

[0132] S301: Weighing Management Automatic weighing: IoT weighbridges are installed at collection points, and the weight of vehicles is automatically recorded and photos of the vehicles are captured when they pass through the weighbridge.

[0133] Data Linkage: Weighing data is automatically linked with purchase orders and supplier information to avoid human error.

[0134] S302: Acquisition Standards Management Standards Library: The system includes built-in national standards, industry standards, and enterprise internal standards, including indicators such as moisture content, impurities, and breakage rate.

[0135] Dynamic adjustment: The procurement standards are dynamically adjusted based on market conditions and inventory levels. For example, the moisture content requirement is increased when inventory is sufficient.

[0136] S303: Procurement Requisition Management Application process: Internal departments of the enterprise submit purchase requests through the system, specifying the type, quantity and purpose.

[0137] Approval workflow: The application goes through multiple levels of approval, including department manager and financial director, and the system automatically records the approval comments.

[0138] S304: Contract Management Template Library: The system provides standard contract templates and supports custom clauses.

[0139] Electronic signature: Both parties to the contract sign it online using digital certificates, and the contract is automatically archived.

[0140] S305: Payment Management Automatic reconciliation: The system automatically generates settlement statements based on weighing data and contract unit prices.

[0141] Payment Integration: Connects with bank payment systems to support online payments.

[0142] S306: Supplier Management Supplier profile: Records supplier qualifications, historical transaction records, and credit rating.

[0143] Performance evaluation: Suppliers are comprehensively evaluated based on indicators such as on-time delivery rate and quality pass rate.

[0144] S400: Grain Sales Module The grain sales module covers functions such as listing agricultural products, order processing, logistics tracking, and customer service.

[0145] S401: Agricultural Product Management Product Database: The system maintains basic information about agricultural products, including variety, origin, specifications, and price.

[0146] Traceability information: Each agricultural product is associated with field files, planting records, acquisition and quality inspection reports, etc., forming a traceability file.

[0147] S402: Order Management Multi-channel orders: Supports order access from multiple channels such as online stores and wholesale markets.

[0148] Intelligent pricing: Dynamically adjust sales prices based on market supply and demand, inventory costs, and competitor prices.

[0149] S403: After-sales Management Complaint handling: Customers can submit complaints through the system, and customer service personnel can quickly locate the problem based on the traceability information.

[0150] Return process: The system automatically processes return requests and updates inventory.

[0151] S404: Transportation Management Route planning: Based on the order address and traffic conditions, plan the optimal route for logistics vehicles.

[0152] Real-time tracking: Customers can track the location of goods via GPS and check the logistics status in real time.

[0153] S405: Warehouse Management Inventory monitoring: Utilize RFID technology to monitor inventory quantity and quality in real time.

[0154] Intelligent early warning: When inventory falls below the safety threshold, the system automatically generates replenishment suggestions.

[0155] S406: Customer Management Customer profiling: Based on transaction records and behavioral data, customer profiles are built to identify high-value customers.

[0156] Targeted marketing: Recommending relevant products to target customers through SMS, app push notifications, and other means.

[0157] S407: Agricultural Product Traceability Traceability chain: From field records to sales orders, the system records data on the entire life cycle of agricultural products.

[0158] QR code traceability: A unique QR code is generated for each agricultural product, and consumers can scan the code to view the place of origin, planting process and quality inspection report.

[0159] S500: Data Service Module The data service module provides data support for other modules, including meteorological, soil, drone, and satellite remote sensing data.

[0160] S501: Meteorological and Environmental Data Data acquisition: Meteorological data is acquired through weather stations, satellite remote sensing, and third-party APIs.

[0161] Data cleaning: Filling in missing values ​​and removing outliers from the raw data to ensure data quality.

[0162] S502: Soil Data Sensor network: Soil sensors collect data every 30 minutes and upload it to the cloud via an IoT gateway.

[0163] Data fusion: Combining laboratory soil test data to improve monitoring accuracy.

[0164] S503: Drone Management Flight platform: A drone equipped with a multispectral camera, RTK positioning module, data transmission radio and autonomous flight control system.

[0165] Ground control station: An intelligent terminal or server equipped with mission planning and data processing software.

[0166] Cloud-based data processing platform: used for remote sensing image processing, model calculation, and report generation.

[0167] Users select target fields via ground control stations (or the system automatically triggers the process based on the agricultural calendar) and choose the purpose of the field inspection, including but not limited to: routine growth surveys, early diagnosis of pests and diseases, assessment of nutrient / water deficiencies, and maturity prediction. The system reads the pre-stored electronic fence coordinates (formats such as KML, Shapefile, or latitude and longitude sequence) of the field and obtains the field attribute information: crop type (rice, corn, wheat, etc.), current growth stage, soil type, and historical farming records.

[0168] Based on the geofence coordinates, the system first calculates the minimum bounding rectangle of the field and then uses a zigzag flight path to cover the entire field. The flight path generation algorithm is dynamically adjusted based on the following factors: Flight altitude: Automatically calculated based on the purpose of the field survey and the required ground resolution (GSD). For example: Routine survey: At an altitude of 60-80 meters, the ground depth (GSD) is approximately 4-5 centimeters. Detailed inspection of the disease: at a height of 30-40 meters, the GSD is approximately 2-3 centimeters. Heading and waypoint spacing: Optimize by taking into account wind direction, lighting angle (to avoid shadows) and terrain undulation (in conjunction with DEM data) to ensure image stitching quality.

[0169] Overlap rate settings: The forward overlap rate should be no less than 75%, and the lateral overlap rate should be no less than 65%, to meet the needs of subsequent stitching and 3D modeling.

[0170] Special area enhancement: If historical data or user annotations show that a problem has occurred in a certain area, the flight path density can be automatically increased or the flight altitude can be reduced in that area.

[0171] After the flight path is generated, the system automatically performs conflict detection (such as avoiding known obstacles like high-voltage lines and tall trees) and simulates flight time and battery consumption to ensure the mission can be completed safely.

[0172] The ground control station transmits the flight path and mission instructions to the UAV via a data radio. The UAV automatically takes off upon receiving the commands, flies along the planned route, and automatically triggers its multispectral camera to acquire images (typically including blue, green, red, red-edge, and near-infrared bands) at each waypoint. During flight, the UAV transmits real-time status information (position, altitude, battery level, and image preview). In case of strong winds, low battery, or communication interruption, the UAV automatically executes preset emergency strategies (such as returning to base or hovering).

[0173] After completing the mission, the drone automatically returns and lands. The acquired multispectral images are automatically uploaded to a cloud data processing platform via wireless network. The platform performs the following automated processing: Image alignment and stitching: Using POS data and feature point matching, orthophoto mosaics of fields are generated.

[0174] Radiation correction: Convert DN values ​​to reflectance and perform atmospheric correction (if required).

[0175] Index Calculation: Automatically calculates a series of vegetation indices, including but not limited to: NDVI (Normalized Difference Vegetation Index), NDRE (Normalized Difference Red Edge Index), GNDVI (Normalized Difference Vegetation Index for Green Light), and LAI (Leaf Area Index, retrieved through model inversion). Based on the processed multispectral data and vegetation indices, the system calls upon the built-in crop growth model and knowledge base to automatically generate a structured analysis report. The report content includes: (1) Remote sensing thematic map of crop growth The spatial distribution of indices such as NDVI across the entire field is visually displayed using a color gradient map.

[0176] The system automatically divides fields into multiple grade zones, such as excellent, good, medium, and poor growth, and calculates the area percentage of each grade.

[0177] (2) Recommendations for agricultural management Fertilization recommendations: If NDVI is below the threshold for this growth period and the spatial distribution shows a specific pattern (such as patchy low values), it indicates possible nitrogen deficiency. Topdressing is recommended and the amount should be estimated.

[0178] Irrigation recommendations: Identify drought-stressed areas by combining thermal infrared data (if available) or moisture index, and prioritize irrigation accordingly.

[0179] Disease, pest and weed early warning: Identify potential stresses by combining red-edge bands with specific indices (such as PSRI). If abnormal textures or spectral features are found, it indicates that there may be a risk of disease or pests, and on-site verification is recommended.

[0180] Maturity prediction: For crops such as corn and wheat, growth period models and exponential curves are used to predict the optimal harvest time window.

[0181] (3) Recommendations for subsequent field inspections Based on the severity of the problem areas discovered this time, the recommended time for the next field inspection (e.g., to re-inspect the development of the disease in 3-5 days) and key areas (e.g., to conduct a detailed lower-altitude inspection of areas with poor growth).

[0182] The system automatically updates the task calendar for this field.

[0183] The generated report (including charts and text summaries) is automatically pushed to the user's terminal (mobile app or computer). All data and reports are archived to establish a historical record for the field, providing trend comparisons for subsequent analysis. The system also has a self-learning function, which can continuously optimize the accuracy of model parameters and recommendations as data on the same crop and the same region accumulates.

[0184] Taking rice field inspection during the tillering stage in the middle and lower reaches of the Yangtze River as an example: Input: Select the target paddy field, and the purpose of the field inspection is "routine growth survey and nutrient deficiency assessment".

[0185] Flight route generation: The system automatically plans the flight route based on the rectangular field (approximately 100 acres), with the flight altitude set at 70 meters and the heading overlap rate at 80%.

[0186] Data Acquisition: The drone flew automatically for about 25 minutes, acquiring 5-band multispectral images.

[0187] Analysis revealed that the NDVI index value in the northern part of the field was significantly lower than that in the southern part. Based on the fertilizer requirements during the tillering stage, the system determined that nitrogen deficiency might exist in the northern part.

[0188] Generate report: Growth map: shows the spatial distribution of NDVI and marks the northern 15 acres as a "weak growth area".

[0189] Agricultural advice: It is recommended to add about 5-8 kg / acre of urea to the northern area and provide a variable fertilizer prescription map (if the drone has variable fertilizer function).

[0190] Field inspection recommendation: It is recommended to re-inspect the northern area in 7-10 days to observe the effect of fertilization.

[0191] S504: Satellite Remote Sensing Data Multi-source data: Integrating optical remote sensing (such as Landsat-8) and radar remote sensing (such as Sentinel-1) data to achieve all-weather monitoring.

[0192] Change detection: By comparing multiple remote sensing images, changes in field boundaries and crop types can be identified.

[0193] System Workflow The following example, using the entire process from wheat planting to sales, illustrates the system's workflow: Field preparation stage: The system uses satellite remote sensing to create electronic maps of fields and deploys soil sensors.

[0194] Based on soil monitoring data and climate forecasts, it is recommended to plant "strong gluten wheat" varieties, with sowing time from October 15th to 25th.

[0195] Planting and management stage: The drone conducts weekly inspections to monitor wheat growth. When the NDVI index decreases, the system prompts for the application of nitrogen fertilizer.

[0196] The four-situation early warning model predicted a high risk of aphid outbreaks and recommended spraying imidacloprid for prevention.

[0197] Yield forecast and harvest: Based on the NDVI index during the flowering period and the precipitation during the grain-filling period, the yield prediction model estimates the yield per mu to be 500 kg.

[0198] The system scheduled the harvesters to start work on June 10 and planned the optimal route.

[0199] Grain procurement stage: After the wheat was harvested, it was transported to the collection point, where the IoT-enabled weighbridge automatically recorded the weight as 50 tons.

[0200] The quality inspection system detected a moisture content of 13.5%, which meets the purchase standards.

[0201] The system generates an electronic contract, which is signed online by both parties. The finance department then completes the payment through integrated payment.

[0202] Grain sales stages: After wheat is processed into flour and put on the shelves for sale, the system generates a traceability QR code.

[0203] Consumers can scan a QR code to view the location of the field, climate data during the planting period, and quality inspection reports.

[0204] Based on inventory data, the system automatically adjusts promotional strategies to improve turnover.

[0205] Technical effect Full-process digitalization: Through the collaborative work of five major modules, the entire process from field to sales is fully controllable and traceable.

[0206] Scientific decision-making: Based on big data and artificial intelligence models, it replaces traditional experience-based decision-making and improves resource utilization efficiency.

[0207] Operational automation: Reduce human intervention and lower production costs through the Internet of Things and smart equipment.

[0208] Information transparency: The traceability system enhances consumer trust and increases brand value.

[0209] Example 2: Precision Irrigation of Rice Background: A rice planting base used to rely on manual judgment of irrigation timing, which led to water waste.

[0210] Implementation process: Soil moisture sensors are deployed in the fields to monitor soil moisture in real time.

[0211] The irrigation model generates irrigation plans based on soil data, soil types in field records, and evaporation rates from climate monitoring.

[0212] The system automatically starts the drip irrigation system when the soil moisture is below 65%, irrigating 20 cubic meters per acre each time.

[0213] Results: 30% water saving and 5% increase in rice yield.

[0214] Example 3: Early warning of corn pests A corn-growing area has been plagued by corn borers for many years, and the failure to control them in time has led to reduced yields.

[0215] Insect infestations are monitored using multispectral images from drones and insect monitoring lamps.

[0216] The four-situation early warning model, combining historical insect infestation data and climate data, predicts that the peak period for corn borer infestation will be from July 10th to 15th.

[0217] The system sends an early warning to farmers three days in advance and recommends the use of chlorantraniliprole for prevention and control.

[0218] Results: Pest damage rate decreased from 15% to 5%.

[0219] Example 4: Wheat traceability sales An agricultural company hopes to enhance its brand value through a traceability system.

[0220] The system records field files for wheat, fertilization and pesticide application records during the planting process, and quality inspection reports upon purchase.

[0221] A traceability QR code is affixed to the packaging of processed wheat flour.

[0222] Consumers can scan the code to view the entire lifecycle information.

[0223] By deeply integrating five modules—field management, planting management, grain procurement, grain sales, and data services—a digital management system covering the entire agricultural production process has been constructed. The system utilizes the Internet of Things, big data, artificial intelligence, and remote sensing technologies to achieve refined, intelligent, and transparent agricultural production, significantly improving agricultural production efficiency and economic benefits.

[0224] Example 5 illustrates an agricultural digital management system. It should be noted that the technical solution of this agricultural digital management method belongs to the same concept as the technical solution of the aforementioned agricultural digital management system. Details not described in detail in this example can be found in the description of the technical solution of the aforementioned agricultural digital management system.

[0225] This embodiment also provides an agricultural digital management method, including: Acquire satellite remote sensing data to construct field profiles; Acquire meteorological and environmental data to build a climate monitoring system; Soil data is acquired through soil sensors to build a soil monitoring system; Select crops and planting times based on data from field records, climate monitoring, and soil monitoring. Using drones to obtain information on crop growth and predict crop yield; Obtain crop procurement information, transport crops for sale, and complete the entire process control from crop planting to sales.

[0226] This embodiment also provides an electronic device, including: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions, which, when executed by the processor, implement the steps of the agricultural digital management system.

[0227] This embodiment also provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of an agricultural digital management system.

[0228] The storage medium proposed in this embodiment and the implementation of the agricultural digital management system proposed in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0229] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0230] The technical scope of this invention is not limited to the content described above. Those skilled in the art can make various modifications and variations to the above embodiments without departing from the technical concept of this invention, and all such modifications and variations should fall within the protection scope of this invention.

Claims

1. An agricultural digital management system, characterized in that, include: The field management module is used to manage field records, soil monitoring, and climate monitoring. The planting management module is used to perform planting management, monitoring of four conditions (planting, soil, and water conditions), yield forecasting, and agricultural machinery operation. The grain procurement module is used for weighing management, procurement standard management, purchase application management, contract management, payment management, and supplier management. The grain sales module is used to manage agricultural products, orders, after-sales service, transportation, warehousing, and customers. The data service module is used to provide meteorological and environmental data, soil data, drone management, and satellite remote sensing data; Through the field management module, planting management module, grain purchase module, grain sales module, and data service module, the entire process from grain planting to sales can be controlled.

2. The agricultural digital management system according to claim 1, characterized in that, The field management module also includes growth monitoring, which uses the drone management of the data service module to monitor crops and obtain information on crop growth.

3. An agricultural digital management system according to claim 1, characterized in that, The grain sales module also includes agricultural product traceability, which obtains complete information about agricultural products from the field management module, planting management module, grain purchase module, and grain sales module.

4. An agricultural digital management system according to claim 1, characterized in that, The planting management module also includes early warning and prediction of four conditions, which uses data from soil monitoring, climate monitoring, agronomic management and monitoring of the four conditions to build a prediction model for the four conditions.

5. An agricultural digital management system according to claim 1, characterized in that, The planting management module also includes irrigation management, which uses data from field records, soil monitoring, climate monitoring, and crop management to build an irrigation model and determine irrigation methods, irrigation time, irrigation volume, and irrigation frequency.

6. An agricultural digital management system according to claim 1, characterized in that, The crop management system determines the crops and planting times through field records, soil monitoring, and climate monitoring.

7. An agricultural digital management system according to claim 1, characterized in that, The field management module also includes field enclosure, which adds individual farmers' fields to the field file. Through the field file, soil monitoring, climate monitoring and planting season management, it guides individual farmers in cultivating land, planting crops, fertilizing, aerating and irrigating.

8. An agricultural digital management method, comprising the agricultural digital management system according to any one of claims 1-7, characterized in that, include: Acquire satellite remote sensing data to construct field profiles; Acquire meteorological and environmental data to build a climate monitoring system; Soil data is acquired through soil sensors to build a soil monitoring system; Select crops and planting times based on data from field records, climate monitoring, and soil monitoring. Using drones to obtain information on crop growth and predict crop yield; Obtain crop procurement information, transport crops for sale, and complete the entire process control from crop planting to sales.

9. An electronic device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions, which, when executed by the processor, implement the steps of the agricultural digital management system according to any one of claims 1 to 7.

10. A computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of an agricultural digital management system according to any one of claims 1 to 7.

Images