Intelligent digital agricultural platform integrated management system and method

Abstract

The invention discloses a comprehensive management system and method for an intelligent digital agricultural platform, and belongs to the technical field of agricultural management. The comprehensive management system for the agricultural platform comprises a sensing layer, an edge computing layer, a cloud decision-making layer, an execution layer and an interaction layer; the sensing layer part comprises multispectral imaging equipment, a soil layered moisture sensor, a meteorological monitoring station and an unmanned aerial vehicle cruising device which are arranged in a farmland. According to the invention, through multi-source data fusion and an edge calculation layer, second-level response to emergencies such as plant diseases and insect pests and freeze injury is realized, and the disaster prevention and control efficiency is greatly improved; a plot-level accurate strategy is generated based on the dynamic knowledge graph and the prediction model, so that the utilization rate of the fertilizer is increased while the irrigation water is effectively reduced; equipment access to a heterogeneous control bus is supported, mainstream agricultural equipment is compatible, and the intelligent transformation cost is reduced; through collaborative decision making of the mobile terminal and the cloud terminal, the farming operation time consumption is greatly shortened; therefore, the agricultural management efficiency and the resource utilization rate are remarkably improved.

Description

Technical Field

[0001] The present invention belongs to the field of agricultural management technology, and specifically relates to a smart digital agricultural platform integrated management system and method. Background Art

[0002] With the development of agricultural parks, the popularization of digital agriculture, and the advancement of technologies like 5G+, agricultural park management is becoming increasingly digital and intelligent. Various agricultural management platforms have emerged, ranging from planting platforms responsible for plantation management to sales platforms responsible for marketing, and traceability platforms that enable one-code access. These platforms enable digital management of agricultural processes, including pre-production, production, and post-production, significantly improving agricultural efficiency and saving labor and resource costs.

[0003] The existing agricultural management system has the following problems:

[0004] 1. Data fragmentation: Meteorological, soil, and crop data are stored independently and cannot be analyzed in a coordinated manner;

[0005] 2. Decision lag: Relying on manual experience and judgment, it cannot respond to environmental changes in real time;

[0006] 3. Inefficient execution: Irrigation and fertilization equipment lack an intelligent scheduling mechanism.

[0007] The information disclosed in this background technology section is only intended to enhance understanding of the overall background of the invention and should not be regarded as an admission or any form of suggestion that the information constitutes the prior art already known to a person skilled in the art. Summary of the Invention

[0008] The purpose of the present invention is to provide a smart digital agricultural platform integrated management system and method, which can solve the problems of data fragmentation, decision lag and inefficient execution in existing agricultural management systems.

[0009] In order to achieve the above object, a specific embodiment of the present invention provides the following technical solutions:

[0010] A comprehensive management system for a smart digital agricultural platform, including:

[0011] Perception layer: Multispectral imaging equipment, soil stratification moisture sensors, meteorological monitoring stations, and drone cruise devices deployed in farmland; the perception layer is the overall framework of the system, and its function is to build a closed-loop management chain from data collection to execution.

[0012] Edge computing layer: On-site processing terminal, used to integrate perception layer data in real time and generate early warning signals; its function is to achieve millisecond-level disaster response.

[0013] Cloud-based decision-making layer: includes a crop growth model library, an environmental prediction engine, and an equipment control strategy generator; its function is to generate optimized decision-making strategies.

[0014] Execution layer: connects irrigation systems, greenhouse control equipment and fertilization machinery through industrial buses;

[0015] Interaction layer: supports the operation interface of computers, mobile phones and touch screen terminals.

[0016] In one or more embodiments of the present invention, the edge computing layer is configured as follows:

[0017] The system integrates satellite imagery, drone aerial imagery, and ground sensor data. The resolution of the fused satellite imagery is ≥10 meters, while the resolution of the drone aerial imagery is ≤5 centimeters. Satellite imagery provides large-scale vegetation coverage at a higher resolution, while drone aerial imagery uses a finer resolution to identify individual crop anomalies. The high-definition drone imagery is mapped to the satellite image grid through geographic coordinate alignment.

[0018] The response time to emergencies such as pests and diseases, equipment failures, etc. does not exceed 0.1 seconds, and a lightweight CNN model is used to continuously analyze sensor data streams; emergency plans are cached in the field, such as directly starting sprinkler irrigation when frost damage occurs, without the need for cloud interaction.

[0019] In one or more embodiments of the present invention, the cloud-based decision layer includes:

[0020] Dynamic crop knowledge base, linking variety characteristics, pest and disease characteristics and agronomic operation rules;

[0021] Weather forecast module, outputs the probability distribution of rainfall and temperature in the next 7 days;

[0022] Principle of weather forecast: Access the Meteorological Bureau API to obtain numerical forecasts, and combine them with historical field microclimate data for correction. For example, the actual humidity in the greenhouse is 15% higher than that outside.

[0023] The decision-making optimization unit automatically adjusts irrigation and fertilization recipes. The initial strategy is based on a crop model library, such as 4.5 mm of water per day for grapes during veraison. Dynamic adjustments are made, such as automatically reducing irrigation by 30% when the predicted probability of rainfall in the next 48 hours is greater than 70%.

[0024] A comprehensive management method for a smart digital agricultural platform, comprising the following steps:

[0025] Step 1: Collect soil depth profile moisture data and crop canopy temperature data;

[0026] Step 2: Calculate the crop water requirement index;

[0027] Step 3: Generate a zone irrigation instruction table based on rainfall forecast.

[0028] The above steps can realize field-level variable irrigation.

[0029] In one or more embodiments of the present invention, step 2 is implemented by:

[0030] Establish a soil-crop-atmosphere water movement model;

[0031] Analysis of crop transpiration status based on thermal infrared images.

[0032] In one or more embodiments of the present invention, the partition irrigation instruction table of step 3 includes:

[0033] Plot number, current soil moisture content, recommended irrigation amount, and implementation time window;

[0034] Priority identification, graded according to the degree of crop water shortage.

[0035] In one or more embodiments of the present invention, the integrated management method also includes pest and disease control, which is used to achieve precise plant protection. The process is as follows:

[0036] The characteristics of crop disease spots are detected through image recognition models. Specifically, the mobile terminal takes pictures of leaves, compresses and transmits them to the edge layer. The edge CNN model extracts the characteristics of the disease spots, including color, shape, and texture.

[0037] Matching prevention and control plans in the knowledge base;

[0038] Output the type of pesticide, spraying concentration and operation time. When spraying, the drone's flight altitude needs to be recommended based on wind speed data. When the wind speed is greater than level 3, the flight altitude should be ≤2m.

[0039] In one or more embodiments of the present invention, the comprehensive management method further includes a resource optimization method. The resource optimization method is used to reduce production costs. The resource optimization method includes:

[0040] The goal is to minimize water and fertilizer costs, under the constraint of ensuring expected yields;

[0041] Generate a calendar of farm operations with cost estimates.

[0042] In one or more embodiments of the present invention, the execution layer control is used to achieve heterogeneous device collaboration. The execution layer control logic is as follows:

[0043] Convert irrigation instructions into valve opening control signals;

[0044] Synchronously adjust greenhouse ventilation, shading and carbon dioxide concentration through the bus;

[0045] Remotely dispatch plant protection drones to perform spraying tasks.

[0046] A computer-readable storage medium stores a computer program, which implements the steps of the above method when executed by a processor.

[0047] Compared with the existing technology, the present invention achieves second-level response to emergencies such as pests and diseases, frost damage, etc. through multi-source data fusion and edge computing layer, greatly improving the efficiency of disaster prevention and control; generates plot-level precise strategies based on dynamic knowledge graphs and prediction models, effectively reducing irrigation water while improving fertilizer utilization; supports equipment access to heterogeneous control buses, is compatible with mainstream agricultural equipment, and reduces the cost of intelligent transformation; through collaborative decision-making between mobile terminals and the cloud, it greatly shortens the time spent on agricultural operations, thereby significantly improving agricultural management efficiency and resource utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0049] Figure 1 This is a system diagram of a smart digital agriculture platform integrated management system in one embodiment of the present invention;

[0050] Figure 2 This is a flow chart of a smart digital agriculture platform integrated management system in one embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to enable those skilled in the art to better understand the technical solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0052] like Figure 1 and Figure 2 As shown, a smart digital agriculture platform integrated management system in one embodiment of the present invention includes a perception layer, an edge computing layer, a cloud decision layer, an execution layer and an interaction layer.

[0053] Perception layer: Multispectral imaging equipment, soil stratification moisture sensors, meteorological monitoring stations, and drone cruise devices deployed in farmland; the perception layer is the overall framework of the system, and its function is to build a closed-loop management chain from data collection to execution.

[0054] Edge computing layer: On-site processing terminal, used to integrate perception layer data in real time and generate early warning signals; its function is to achieve millisecond-level disaster response.

[0055] Specifically, the edge computing layer is configured as follows:

[0056] The system integrates satellite imagery, drone aerial imagery, and ground sensor data. The resolution of the fused satellite imagery is ≥10 meters, while the resolution of the drone aerial imagery is ≤5 centimeters. Satellite imagery provides large-scale vegetation coverage at a higher resolution, while drone aerial imagery uses a finer resolution to identify individual crop anomalies. The high-definition drone imagery is mapped to the satellite image grid through geographic coordinate alignment.

[0057] The response time to emergencies such as pests and diseases, equipment failures, etc. does not exceed 0.1 seconds, and a lightweight CNN model is used to continuously analyze sensor data streams; emergency plans are cached in the field, such as directly starting sprinkler irrigation when frost damage occurs, without the need for cloud interaction.

[0058] Cloud-based decision-making layer: includes a crop growth model library, an environmental prediction engine, and an equipment control strategy generator; its function is to generate optimized decision-making strategies.

[0059] Specifically, the cloud decision-making layer includes:

[0060] Dynamic crop knowledge base, linking variety characteristics, pest and disease characteristics and agronomic operation rules;

[0061] Weather forecast module, outputs the probability distribution of rainfall and temperature in the next 7 days;

[0062] Principle of weather forecast: Access the Meteorological Bureau API to obtain numerical forecasts, and combine them with historical field microclimate data for correction. For example, the actual humidity in the greenhouse is 15% higher than that outside.

[0063] The decision-making optimization unit automatically adjusts irrigation and fertilization recipes. The initial strategy is based on a crop model library, such as 4.5 mm of water per day for grapes during veraison. Dynamic adjustments are made, such as automatically reducing irrigation by 30% when the predicted probability of rainfall in the next 48 hours is greater than 70%.

[0064] Execution layer: connects irrigation systems, greenhouse control equipment and fertilization machinery through industrial buses;

[0065] Interaction layer: supports the operation interface of computers, mobile phones and touch screen terminals.

[0066] A comprehensive management method for a smart digital agricultural platform includes the following steps:

[0067] Step 1: Collect soil depth profile moisture data and crop canopy temperature data;

[0068] Step 2: Calculate the crop water requirement index;

[0069] Step 3: Generate a zone irrigation instruction table based on rainfall forecast.

[0070] The above steps can realize field-level variable irrigation.

[0071] Specifically, step 2 is implemented in the following way:

[0072] Establish a soil-crop-atmosphere water movement model;

[0073] Analysis of crop transpiration status based on thermal infrared images.

[0074] Specifically, the partition irrigation instruction table in step 3 includes:

[0075] Plot number, current soil moisture content, recommended irrigation amount, and implementation time window;

[0076] Priority identification, graded according to the degree of crop water shortage.

[0077] Preferably, the integrated management approach also includes pest and disease control, which is used to achieve precise plant protection. The process is as follows:

[0078] The characteristics of crop disease spots are detected through image recognition models. Specifically, the mobile terminal takes pictures of leaves, compresses and transmits them to the edge layer. The edge CNN model extracts the characteristics of the disease spots, including color, shape, and texture.

[0079] Matching prevention and control plans in the knowledge base;

[0080] Output the type of pesticide, spraying concentration and operation time. When spraying, the drone's flight altitude needs to be recommended based on wind speed data. When the wind speed is greater than level 3, the flight altitude should be ≤2m.

[0081] Preferably, the comprehensive management method also includes a resource optimization method, which is used to reduce production costs. The resource optimization method includes:

[0082] The goal is to minimize water and fertilizer costs, under the constraint of ensuring expected yields;

[0083] Generate a calendar of farm operations with cost estimates.

[0084] Preferably, the function of the execution layer control is to achieve heterogeneous device collaboration, and the execution layer control logic is:

[0085] Convert irrigation instructions into valve opening control signals;

[0086] Synchronously adjust greenhouse ventilation, shading and carbon dioxide concentration through the bus;

[0087] Remotely dispatch plant protection drones to perform spraying tasks.

[0088] A computer-readable storage medium stores a computer program, which implements the steps of the above method when executed by a processor.

[0089] Through multi-source data fusion and edge computing layer, the present invention can achieve second-level response to emergencies such as pests and diseases, frost damage, etc., greatly improving the efficiency of disaster prevention and control; based on dynamic knowledge graphs and prediction models, it generates precise plot-level strategies, effectively reducing irrigation water consumption while improving fertilizer utilization; supports equipment access to heterogeneous control buses, is compatible with mainstream agricultural equipment, and reduces the cost of intelligent transformation; through collaborative decision-making between mobile terminals and the cloud, it greatly shortens the time spent on agricultural operations, thereby significantly improving agricultural management efficiency and resource utilization.

[0090] This application solves the three long-standing pain points of delayed response, extensive resources, and closed systems in agricultural management through three technological breakthroughs: edge intelligent real-time response + cloud-based knowledge graph decision-making + collaborative control of heterogeneous equipment, and realizes a modern agricultural digital closed loop of "second-level warning, minute-level decision-making, and zero-transformation access."

[0091] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

[0092] In addition, it should be understood that although this specification is described in terms of implementation methods, not every implementation method contains only one independent technical solution. This narrative method of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment can also be appropriately combined to form other implementation methods that can be understood by those skilled in the art.

Claims

1. A smart digital agricultural platform integrated management system, characterized by: include: Perception layer: multispectral imaging equipment, soil stratification moisture sensors, meteorological monitoring stations, and drone patrol devices deployed in farmland; Edge computing layer: On-site processing terminal, used to integrate perception layer data in real time and generate early warning signals; Cloud-based decision-making layer: includes a crop growth model library, an environmental prediction engine, and an equipment control strategy generator; Execution layer: connects irrigation systems, greenhouse control equipment and fertilization machinery through industrial buses; Interaction layer: supports the operation interface of computers, mobile phones and touch screen terminals.

2. A smart digital agricultural platform integrated management system according to claim 1, characterized in that: The edge computing layer is configured as follows: Fusion of satellite imagery, drone aerial imagery, and ground sensor data; where the resolution of fused satellite imagery is ≥10 meters, and the resolution of drone aerial imagery is ≤5 centimeters; The response time to emergencies such as pests and diseases, equipment failures, etc. does not exceed 0.1 seconds.

3. The intelligent digital agricultural platform integrated management system according to claim 1, characterized in that: The cloud-based decision-making layer includes: Dynamic crop knowledge base, linking variety characteristics, pest and disease characteristics and agronomic operation rules; Weather forecast module, outputs the probability distribution of rainfall and temperature in the next 7 days; Decision optimization unit automatically adjusts irrigation amount and fertilization formula.

4. A smart digital agricultural platform integrated management method, used in a smart digital agricultural platform integrated management system as claimed in any one of claims 1 to 3, characterized in that: The comprehensive management method comprises the following steps: Step 1: Collect soil depth profile moisture data and crop canopy temperature data; Step 2: Calculate the crop water requirement index; Step 3: Generate a zone irrigation instruction table based on rainfall forecast.

5. A comprehensive management method for a smart digital agricultural platform according to claim 4, characterized in that: Step 2 is achieved by: Establish a soil-crop-atmosphere water movement model; Analysis of crop transpiration status based on thermal infrared images.

6. A comprehensive management method for a smart digital agricultural platform according to claim 4, characterized in that: The partition irrigation instruction table in step 3 includes: Plot number, current soil moisture content, recommended irrigation amount, and implementation time window; Priority identification, graded according to the degree of crop water shortage.

7. A comprehensive management method for a smart digital agricultural platform according to claim 4, characterized in that: The integrated management approach also includes pest and disease control processes: Detect crop disease spot characteristics through image recognition models; Matching prevention and control plans in the knowledge base; Output the type of pesticide, spraying concentration and operation time.

8. A comprehensive management method for a smart digital agricultural platform according to claim 4, characterized in that: The comprehensive management method also includes a resource optimization method, which includes: The goal is to minimize water and fertilizer costs, under the constraint of ensuring expected yields; Generate a calendar of farm operations with cost estimates.

9. A comprehensive management method for a smart digital agricultural platform according to claim 4, characterized in that: The execution layer control logic is: Convert irrigation instructions into valve opening control signals; Synchronously adjust greenhouse ventilation, shading and carbon dioxide concentration through the bus; Remotely dispatch plant protection drones to perform spraying tasks.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When executed, all steps of the method according to any one of claims 4 to 8 are realized.

Images