Intelligent agricultural information management platform based on cloud computing
Through a smart agricultural information management platform based on cloud computing, using sensors and Internet of Things technology to collect data in real time, and combining machine learning and deep learning models for analysis, it solves the problems of data storage and processing, sharing, updating and security in traditional systems. It has improved agricultural production efficiency and benefits and promoted the modernization of agriculture.
Patent Information
- Application Number
- CN202411026789.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-30
- Publication Date
- 2024-11-15
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional agricultural information management systems have limited data storage and processing capabilities, difficulty in data sharing and collaboration, insufficient real-time data updates, lack of intelligent analysis and decision support, as well as security and reliability problems, which limit the efficiency and decision-making quality of agricultural production.
Adopt a smart agricultural information management platform based on cloud computing, including data acquisition and monitoring modules, data storage and processing modules, decision support and optimization modules, remote monitoring and management modules, and agricultural farm management modules. Use sensors and Internet of Things technology to collect data in real time , combine machine learning and deep learning models for data analysis and prediction, provide intelligent decision-making support for farmers and agricultural managers, and realize data sharing and collaborative work through cloud platforms.
Effectively integrate agricultural data, improve agricultural production efficiency, reduce production costs, and improve agricultural efficiency. It solves the problems of data storage and processing capabilities, sharing and collaboration, real-time updates and monitoring, intelligent analysis and security of traditional systems, and promotes the modernization of agriculture. develop.
Smart Images

Figure CN118967351A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of smart agriculture, and in particular to a smart agriculture information management platform based on cloud computing. Background Art
[0002] The agricultural system is a large-scale multi-level production system, and the rapid development of Internet of Things technology has also provided support for the development of modern smart agriculture, which is conducive to large-scale agricultural production, reducing planting costs and improving planting efficiency. It is the current development trend of agriculture.
[0003] Traditional agricultural information management systems have the following problems:
[0004] Limited data storage and processing capabilities: Traditional systems usually rely on local servers or personal computers for data storage and processing, which are limited by hardware resources and storage capacity. This limits the system's ability to process and analyze large-scale agricultural data, especially when faced with complex data analysis requirements.
[0005] Difficulties in data sharing and collaboration: Traditional systems usually lack effective data sharing and collaboration mechanisms, making it difficult for different departments or farmers to share data and work together. This limits the flow of information and the overall efficiency of agricultural decision-making.
[0006] Insufficient real-time data updating and monitoring: Traditional systems are usually unable to obtain and update agricultural data in real time, resulting in untimely and inaccurate monitoring of key information such as crop growth and climate change, which may affect the decision-making and management of agricultural production.
[0007] Lack of intelligent analysis and decision support: Traditional systems often lack intelligent analysis and decision support functions, and cannot use advanced technologies such as machine learning and data mining to discover potential patterns, trends and laws. This limits agricultural managers' in-depth understanding of agricultural production and markets, which may lead to inefficiency and waste of resources.
[0008] Security and reliability issues: Data storage and transmission in traditional systems often have security and reliability risks. Data may be vulnerable to viruses, hacker attacks, or hardware failures, leading to the risk of data loss or leakage.
[0009] Therefore, there is an urgent need in this field for an agricultural information management platform that can solve the above problems.
[0010] The information disclosed in this background technology section is only intended to enhance the understanding of the overall background of the invention and should not be regarded as an acknowledgment 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
[0011] The purpose of the present invention is to provide a smart agricultural information management platform with strong comprehensive capabilities.
[0012] To achieve the above object, the present invention provides the following solutions:
[0013] A cloud computing-based smart agriculture information management platform, comprising:
[0014] Data collection and monitoring module, which is used to collect agricultural data in real time through sensors and IoT technology, and upload it to the cloud platform for storage and analysis;
[0015] The data storage and processing module is used to store, process and analyze agricultural data using the storage and computing resources provided by cloud computing. This includes using statistical methods and visualization tools to explore the distribution, trends and correlations of data to guide subsequent analysis steps. It also includes establishing a time prediction model to predict crop yields and market demand, establishing image processing and computer vision models to analyze remote sensing images and detect crop health. It also includes establishing a deep learning model to process time series data and predict the impact of future meteorological conditions on crop growth. It also includes establishing an integrated learning model to combine multiple data sources for comprehensive prediction. The integrated learning algorithm is as follows:
[0016] Initialize a model single decision tree T0, and get the initial prediction by fitting the training set D
[0017] For the tth iteration, t≥1, calculate the residual in is the prediction result of the previous t-1 round;
[0018] Train a new base model T t To fit the residual r t ;
[0019] Update the prediction results of the ensemble model:
[0020]
[0021] Where η is the learning rate, which controls the contribution of each iteration;
[0022] For a new input sample X new , the final prediction value is obtained by accumulating the prediction results of each tree:
[0023]
[0024] Where T is the total number of iterations;
[0025] Decision support and optimization module, which is used to intelligently analyze and predict agricultural data based on the data analysis and machine learning capabilities provided by the cloud platform, and provide decision support and optimization suggestions for farmers and agricultural managers;
[0026] The remote monitoring and management module is used to monitor the farmland conditions in real time through the cloud platform and adjust agricultural production strategies in a timely manner. The production strategies include:
[0027] Crop selection and variety optimization: select suitable crop varieties according to local climate, soil conditions and market demand;
[0028] Optimizing variety selection for adaptation to climate change and resistance to pests and diseases;
[0029] Soil management and health, implementing scientific soil testing and analysis to ensure soil nutrient balance and health; applying organic fertilizers and soil conditioners to improve soil quality and structure;
[0030] water resource management, implementing water-saving irrigation techniques, including drip irrigation and rainwater harvesting;
[0031] Monitor soil moisture and crop water requirements for precise irrigation;
[0032] Pest control, implementing integrated pest monitoring and control measures, including biological control and the use of environmentally friendly pesticides;
[0033] Promoting pest-resistant varieties and balanced management of agro-ecosystems;
[0034] Mechanization and technology application, using modern agricultural machinery and technology, including automated harvesters and precision seeding equipment, to improve production efficiency;
[0035] Apply information technology to optimize decision-making and management;
[0036] Market orientation and quality control, analyzing market demand and price trends, and adjusting crop planting structure;
[0037] Implement quality control measures to ensure products meet market standards and consumer expectations;
[0038] Sustainable development and environmental protection, adopting sustainable agricultural practices, reducing the use of pesticides and fertilizers, and protecting soil and water resources;
[0039] Support biodiversity and ecosystem services and protect the natural ecological balance;
[0040] Providing farmer training and technical support to help them master the latest agricultural technologies and best practices;
[0041] Promote agricultural cooperatives and technical cooperation, and promote information sharing and resource integration;
[0042] Providing market access opportunities and financial support to promote the healthy development of the agricultural industry chain;
[0043] Agricultural information sharing and collaboration module, which is used to enable different farms and agricultural-related stakeholders to share agricultural information and experience through cloud computing platforms, and promote collaborative work and knowledge sharing in agricultural production;
[0044] Agricultural farming management module, used to manage agricultural farming processes, including:
[0045] A soil resource information collection unit, used for collecting soil resource information;
[0046] A farming machinery and equipment information sensing unit, used to sense various information of the farming machinery and equipment;
[0047] Soil moisture analysis unit, used to establish a relationship model between meteorological factors and water demand and to establish an intelligent water control unit in combination with Internet of Things technology to predict and remotely control soil moisture;
[0048] The soil cutting simulation unit is used to perform neural network modeling on soil and agricultural tillage machinery and equipment and simulate and predict the soil cutting process to obtain the influence of the forward speed of tillage machinery and equipment, tillage depth, and soil physical and chemical properties on the tillage effect;
[0049] A statistical module for analyzing spatial changes in crop soils, used to monitor soil variation structure;
[0050] The farming process planning unit is used to plan the farming process by combining farming requirements, farming objectives, farming effects, farming rules and farming costs with neural network technology to establish a neural network model;
[0051] The demand research module includes field research, demand analysis, production needs and user needs.
[0052] Optionally, the sensors include: soil sensors, meteorological sensors, plant sensors, camera sensors and GPS sensors;
[0053] The soil sensors include: soil moisture sensor, soil temperature sensor, soil humidity sensor, soil conductivity sensor, soil pH sensor and soil nutrient sensor;
[0054] The meteorological sensors include: temperature sensor, humidity sensor, rainfall sensor, light sensor, wind speed and wind direction sensor;
[0055] The plant sensors include: a leaf area index sensor, a plant height sensor, a chlorophyll content sensor and a leaf area sensor.
[0056] Optionally, the various pieces of information of the mechanical equipment include:
[0057] Specific make and model of agricultural machinery;
[0058] The power output of the engine or electric motor;
[0059] Dimensions and overall weight of agricultural machinery;
[0060] Maximum operating speed;
[0061] The operating functions of different machines, including tilling, sowing, fertilizing, spraying, and harvesting;
[0062] The efficiency of completing tasks per unit time;
[0063] Whether it has automated control functions, including autonomous driving technology and intelligent operation control;
[0064] How to use, how the farmer or operator should use the equipment properly;
[0065] Safety precautions, safety precautions and operating procedures that need to be paid attention to during operation;
[0066] Maintenance cycles and methods, daily maintenance requirements of equipment, such as lubrication, cleaning, and parts replacement;
[0067] Powertrain, including type of engine or electric motor, fuel consumption rate;
[0068] Transmission system, including gearbox type and transmission mode;
[0069] Control system: whether it is equipped with electronic control system and monitoring system;
[0070] Investment cost, the cost of purchasing the machinery and equipment;
[0071] Cost of use: the cost of daily use and maintenance, including fuel costs and parts replacement costs;
[0072] Life expectancy and depreciation analysis, the expected useful life and depreciation of the equipment, and how to plan for replacement;
[0073] Applicable crops or operation types, which types of crops or specific agricultural operations the equipment is suitable for;
[0074] The competitiveness of the equipment in the market and user evaluation;
[0075] Whether the equipment complies with environmental regulations and standards;
[0076] Resource efficiency of equipment use, including energy consumption and water use;
[0077] After-sales service and technical support provided;
[0078] The warranty period and specific terms of the equipment.
[0079] Optionally, the algorithm formula of the relationship model between meteorological factors and water demand is specifically:
[0080]
[0081] Among them, N(h) is the number of sampling points, Z is the meteorological parameters and water volume parameters of the sampling points, and x i is the spatial position of the sampling point.
[0082] Optionally, the neural network modeling of soil and agricultural farming machinery and equipment and the simulation prediction of the soil cutting process include:
[0083] Collect soil moisture, density, structure type, organic matter content, and clay content;
[0084] Collect data on power output, tillage depth, rotary wheel diameter, fertilization device configuration, and operating parameters of tillage machinery and equipment;
[0085] Use sensors to record data such as force, displacement, temperature, vibration, etc. during the farming process in real time;
[0086] Standardize the collected data to remove noise and outliers;
[0087] Extract the combined features of soil and mechanical parameters, including the ratio of soil moisture to clay content, the product of tillage depth and rotary wheel diameter, and use principal component analysis to reduce multidimensional data to a lower-dimensional feature space to improve model training efficiency;
[0088] Choose appropriate deep learning frameworks and network structures, including convolutional neural networks for feature extraction, recurrent neural networks for processing time series data, or hybrid network structures;
[0089] Divide the processed data into training set, validation set and test set;
[0090] Use the training set to train the neural network model and use cross-validation technology to select the optimal hyperparameters;
[0091] Use the validation set to evaluate the performance of the model and perform model tuning;
[0092] Use the test set to finally evaluate the generalization ability of the model;
[0093] Use the trained model to predict new combinations of soil and machine parameters and simulate the soil cutting process under different conditions;
[0094] Analyze the prediction results and compare them with the measured data to verify the accuracy and reliability of the model.
[0095] Optionally, the step of combining farming requirements, farming objectives, farming effects, farming rules and farming costs with neural network technology to establish a neural network model to plan the farming process includes:
[0096] Data collection and preprocessing;
[0097] Farming demand data include crop types, planting area, soil type, climate conditions, and pest and disease conditions;
[0098] Farming target data include yield target, quality target, and economic benefit target;
[0099] Farming performance data include historical yields, quality indicators, pest and disease incidence, fertilizer usage, and irrigation water usage;
[0100] Farming law data include crop growth models, soil fertility models, and pest and disease occurrence models;
[0101] Farming cost data include seed cost, fertilizer cost, pesticide cost, labor cost, machinery cost, and water cost;
[0102] Clean, normalize and extract features of the original data;
[0103] Depending on the data type, choose the appropriate feature engineering method, including:
[0104] The time series data uses sliding window and difference methods to extract features;
[0105] The image data uses convolutional neural networks to extract features;
[0106] The text data uses word embedding and topic model methods to extract features;
[0107] Neural network model design;
[0108] The model structure selects the recurrent neural network model;
[0109] Use the preprocessed data as the input of the model;
[0110] Model output, the output of the model includes:
[0111] Farming process planning, including planting time, fertilization time, irrigation time, and pest and disease control time;
[0112] Optimal farming parameters, including optimal fertilizer application, optimal irrigation, and optimal pest and disease control programs;
[0113] Yield forecasting, predicting yields under different farming scenarios;
[0114] Cost forecasting, predicting the cost under different farming schemes;
[0115] Model training and evaluation;
[0116] Training data uses historical data to train the model;
[0117] Evaluation Metrics Use appropriate evaluation metrics to evaluate model performance, including:
[0118] Accuracy, the degree of agreement between the predicted results and the actual results;
[0119] Recall rate, how many true results are included in the predicted results;
[0120] F1-score, a comprehensive indicator of precision and recall;
[0121] Cost-effectiveness, comparison of costs and benefits of different farming options;
[0122] Model deployment and optimization;
[0123] Model deployment: deploying the trained model to the actual production environment;
[0124] Model optimization: continuously collect new data, optimize the model, and improve model performance.
[0125] Compared with the prior art, the present invention has the following beneficial effects:
[0126] The present invention provides a smart agricultural information management platform based on cloud computing, including a data acquisition and monitoring module, a data storage and processing module, a decision support and optimization module, a remote monitoring and management module, an agricultural cultivation management module and a crop soil spatial change analysis and statistics module, which solves the problems of limited data storage and processing capabilities, difficulty in data sharing and collaboration, insufficient real-time data updating and monitoring, lack of intelligent analysis and decision support, and insufficient security and reliability in traditional agricultural information management systems. The smart agricultural information management platform based on cloud computing provided by the present invention can effectively integrate agricultural data, improve agricultural production efficiency, reduce production costs, enhance agricultural benefits, and promote agricultural development, and is an important means to promote agricultural modernization. BRIEF DESCRIPTION OF THE DRAWINGS
[0127] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0128] Figure 1 A schematic diagram of the structure of a cloud computing-based smart agriculture information management platform provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0129] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in 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 creative work are within the scope of protection of the present invention.
[0130] The purpose of the present invention is to provide a smart agricultural information management platform with strong comprehensive capabilities.
[0131] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.
[0132] Embodiment 1:
[0133] This embodiment provides a smart agriculture information management platform based on cloud computing, including:
[0134] Data collection and monitoring module, which is used to collect agricultural data in real time through sensors and IoT technology, and upload it to the cloud platform for storage and analysis;
[0135] The data storage and processing module is used to store, process and analyze agricultural data using the storage and computing resources provided by cloud computing. This includes using statistical methods and visualization tools to explore the distribution, trends and correlations of data to guide subsequent analysis steps. It also includes establishing a time prediction model to predict crop yields and market demand, establishing image processing and computer vision models to analyze remote sensing images and detect crop health. It also includes establishing a deep learning model to process time series data and predict the impact of future meteorological conditions on crop growth. It also includes establishing an integrated learning model to combine multiple data sources for comprehensive prediction. The integrated learning algorithm is as follows:
[0136] Initialize a model single decision tree T0, and get the initial prediction by fitting the training set D
[0137] For the tth iteration, t≥1, calculate the residual in is the prediction result of the previous t-1 round;
[0138] Train a new base model T t To fit the residual r t ;
[0139] Update the prediction results of the ensemble model:
[0140]
[0141] Where η is the learning rate, which controls the contribution of each iteration;
[0142] For a new input sample X new , the final prediction value is obtained by accumulating the prediction results of each tree:
[0143]
[0144] Where T is the total number of iterations;
[0145] Decision support and optimization module, which is used to intelligently analyze and predict agricultural data based on the data analysis and machine learning capabilities provided by the cloud platform, and provide decision support and optimization suggestions for farmers and agricultural managers;
[0146] The remote monitoring and management module is used to monitor the farmland conditions in real time through the cloud platform and adjust agricultural production strategies in a timely manner. The production strategies include:
[0147] Crop selection and variety optimization: select suitable crop varieties according to local climate, soil conditions and market demand;
[0148] Optimizing variety selection for adaptation to climate change and resistance to pests and diseases;
[0149] Soil management and health, implementing scientific soil testing and analysis to ensure soil nutrient balance and health; applying organic fertilizers and soil conditioners to improve soil quality and structure;
[0150] water resource management, implementing water-saving irrigation techniques, including drip irrigation and rainwater harvesting;
[0151] Monitor soil moisture and crop water requirements for precise irrigation;
[0152] Pest control, implementing integrated pest monitoring and control measures, including biological control and the use of environmentally friendly pesticides;
[0153] Promoting pest-resistant varieties and balanced management of agro-ecosystems;
[0154] Mechanization and technology application, using modern agricultural machinery and technology, including automated harvesters and precision seeding equipment, to improve production efficiency;
[0155] Apply information technology to optimize decision-making and management;
[0156] Market orientation and quality control, analyzing market demand and price trends, and adjusting crop planting structure;
[0157] Implement quality control measures to ensure products meet market standards and consumer expectations;
[0158] Sustainable development and environmental protection, adopting sustainable agricultural practices, reducing the use of pesticides and fertilizers, and protecting soil and water resources;
[0159] Support biodiversity and ecosystem services and protect the natural ecological balance;
[0160] Providing farmer training and technical support to help them master the latest agricultural technologies and best practices;
[0161] Promote agricultural cooperatives and technical cooperation, and promote information sharing and resource integration;
[0162] Providing market access opportunities and financial support to promote the healthy development of the agricultural industry chain;
[0163] Agricultural information sharing and collaboration module, which is used to enable different farms and agricultural-related stakeholders to share agricultural information and experience through cloud computing platforms, and promote collaborative work and knowledge sharing in agricultural production;
[0164] Agricultural farming management module, used to manage agricultural farming processes, including:
[0165] A soil resource information collection unit, used for collecting soil resource information;
[0166] A farming machinery and equipment information sensing unit, used to sense various information of the farming machinery and equipment;
[0167] Soil moisture analysis unit, used to establish a relationship model between meteorological factors and water demand and to establish an intelligent water control unit in combination with Internet of Things technology to predict and remotely control soil moisture;
[0168] The soil cutting simulation unit is used to perform neural network modeling on soil and agricultural tillage machinery and equipment and simulate and predict the soil cutting process to obtain the influence of the forward speed of tillage machinery and equipment, tillage depth, and soil physical and chemical properties on the tillage effect;
[0169] A statistical module for analyzing spatial changes in crop soils, used to monitor soil variation structure;
[0170] The farming process planning unit is used to plan the farming process by combining farming requirements, farming objectives, farming effects, farming rules and farming costs with neural network technology to establish a neural network model;
[0171] The demand research module includes field research, demand analysis, production needs and user needs.
[0172] Further, the sensors include: soil sensors, meteorological sensors, plant sensors, camera sensors and GPS sensors;
[0173] The soil sensors include: soil moisture sensor, soil temperature sensor, soil humidity sensor, soil conductivity sensor, soil pH sensor and soil nutrient sensor;
[0174] The meteorological sensors include: temperature sensor, humidity sensor, rainfall sensor, light sensor, wind speed and wind direction sensor;
[0175] The plant sensors include: a leaf area index sensor, a plant height sensor, a chlorophyll content sensor and a leaf area sensor.
[0176] Furthermore, the various information of the mechanical equipment includes:
[0177] Specific make and model of agricultural machinery;
[0178] The power output of the engine or electric motor;
[0179] Dimensions and overall weight of agricultural machinery;
[0180] Maximum operating speed;
[0181] The operating functions of different machines, including tilling, sowing, fertilizing, spraying, and harvesting;
[0182] The efficiency of completing tasks per unit time;
[0183] Whether it has automated control functions, including autonomous driving technology and intelligent operation control;
[0184] How to use, how the farmer or operator should use the equipment properly;
[0185] Safety precautions, safety precautions and operating procedures that need to be paid attention to during operation;
[0186] Maintenance cycles and methods, daily maintenance requirements of equipment, such as lubrication, cleaning, and parts replacement;
[0187] Powertrain, including type of engine or electric motor, fuel consumption rate;
[0188] Transmission system, including gearbox type and transmission mode;
[0189] Control system: whether it is equipped with electronic control system and monitoring system;
[0190] Investment cost, the cost of purchasing the machinery and equipment;
[0191] Cost of use: the cost of daily use and maintenance, including fuel costs and parts replacement costs;
[0192] Life expectancy and depreciation analysis, the expected useful life and depreciation of the equipment, and how to plan for replacement;
[0193] Applicable crops or operation types, which types of crops or specific agricultural operations the equipment is suitable for;
[0194] The competitiveness of the equipment in the market and user evaluation;
[0195] Whether the equipment complies with environmental regulations and standards;
[0196] Resource efficiency of equipment use, including energy consumption and water use;
[0197] After-sales service and technical support provided;
[0198] The warranty period and specific terms of the equipment.
[0199] Furthermore, the algorithm formula of the relationship model between meteorological factors and water demand is specifically as follows:
[0200]
[0201] Among them, N(h) is the number of sampling points, Z is the meteorological parameters and water volume parameters of the sampling points, and x i is the spatial position of the sampling point.
[0202] Furthermore, the neural network modeling of soil and agricultural farming machinery and equipment and the simulation prediction of the soil cutting process include:
[0203] Collect soil moisture, density, structure type, organic matter content, and clay content;
[0204] Collect data on power output, tillage depth, rotary wheel diameter, fertilization device configuration, and operating parameters of tillage machinery and equipment;
[0205] Use sensors to record data such as force, displacement, temperature, vibration, etc. during the farming process in real time;
[0206] Standardize the collected data to remove noise and outliers;
[0207] Extract the combined features of soil and mechanical parameters, including the ratio of soil moisture to clay content, the product of tillage depth and rotary wheel diameter, and use principal component analysis to reduce multidimensional data to a lower-dimensional feature space to improve model training efficiency;
[0208] Choose appropriate deep learning frameworks and network structures, including convolutional neural networks for feature extraction, recurrent neural networks for processing time series data, or hybrid network structures;
[0209] Divide the processed data into training set, validation set and test set;
[0210] Use the training set to train the neural network model and use cross-validation techniques to select the optimal hyperparameters;
[0211] Use the validation set to evaluate the performance of the model and perform model tuning;
[0212] Use the test set to finally evaluate the generalization ability of the model;
[0213] Use the trained model to predict new combinations of soil and machine parameters and simulate the soil cutting process under different conditions;
[0214] Analyze the prediction results and compare them with the measured data to verify the accuracy and reliability of the model.
[0215] Furthermore, the method of combining farming requirements, farming objectives, farming effects, farming rules and farming costs with neural network technology to establish a neural network model to plan the farming process includes:
[0216] Data collection and preprocessing;
[0217] Farming demand data include crop types, planting area, soil type, climate conditions, and pest and disease conditions;
[0218] Farming target data include yield target, quality target, and economic benefit target;
[0219] Farming performance data include historical yields, quality indicators, pest and disease incidence, fertilizer usage, and irrigation water usage;
[0220] Farming law data include crop growth models, soil fertility models, and pest and disease occurrence models;
[0221] Farming cost data include seed cost, fertilizer cost, pesticide cost, labor cost, machinery cost, and water cost;
[0222] Clean, normalize and extract features of the original data;
[0223] Depending on the data type, choose the appropriate feature engineering method, including:
[0224] The time series data uses sliding window and difference methods to extract features;
[0225] The image data uses convolutional neural networks to extract features;
[0226] The text data uses word embedding and topic model methods to extract features;
[0227] Neural network model design;
[0228] The model structure selects the recurrent neural network model;
[0229] Use the preprocessed data as the input of the model;
[0230] Model output, the output of the model includes:
[0231] Farming process planning, including planting time, fertilization time, irrigation time, and pest and disease control time;
[0232] Optimal farming parameters, including optimal fertilizer application, optimal irrigation, and optimal pest and disease control programs;
[0233] Yield forecasting, predicting yields under different farming scenarios;
[0234] Cost forecasting, predicting the cost under different farming schemes;
[0235] Model training and evaluation;
[0236] Training data uses historical data to train the model;
[0237] Evaluation Metrics Use appropriate evaluation metrics to evaluate model performance, including:
[0238] Accuracy, the degree of agreement between the predicted results and the actual results;
[0239] Recall rate, how many true results are included in the predicted results;
[0240] F1-score, a comprehensive indicator of precision and recall;
[0241] Cost-effectiveness, comparison of costs and benefits of different farming options;
[0242] Model deployment and optimization;
[0243] Model deployment: deploying the trained model to the actual production environment;
[0244] Model optimization: continuously collect new data, optimize the model, and improve model performance.
[0245] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.
[0246] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of the present invention. At the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.
Claims
1. A cloud computing-based smart agriculture information management platform, characterized in that: include: Data collection and monitoring module, which is used to collect agricultural data in real time through sensors and IoT technology, and upload it to the cloud platform for storage and analysis; The data storage and processing module is used to store, process and analyze agricultural data using the storage and computing resources provided by cloud computing. This includes using statistical methods and visualization tools to explore the distribution, trends and correlations of data to guide subsequent analysis steps. It also includes establishing a time prediction model to predict crop yields and market demand, establishing image processing and computer vision models to analyze remote sensing images and detect crop health. It also includes establishing a deep learning model to process time series data and predict the impact of future meteorological conditions on crop growth. It also includes establishing an integrated learning model to combine multiple data sources for comprehensive prediction. The integrated learning algorithm is as follows: Initialize a model single decision tree T0, and get the initial prediction by fitting the training set D For the tth iteration, t≥1, calculate the residual in is the prediction result of the previous t-1 round; Train a new base model T t To fit the residual r t ; Update the prediction results of the ensemble model: Where η is the learning rate, which controls the contribution of each iteration; For a new input sample X new , the final prediction value is obtained by accumulating the prediction results of each tree: Where T is the total number of iterations; Decision support and optimization module, which is used to intelligently analyze and predict agricultural data based on the data analysis and machine learning capabilities provided by the cloud platform, and provide decision support and optimization suggestions for farmers and agricultural managers; The remote monitoring and management module is used to monitor the farmland conditions in real time through the cloud platform and adjust agricultural production strategies in a timely manner. The production strategies include: Crop selection and variety optimization: select suitable crop varieties according to local climate, soil conditions and market demand; Optimizing variety selection for adaptation to climate change and resistance to pests and diseases; Soil management and health, implementing scientific soil testing and analysis to ensure soil nutrient balance and health; applying organic fertilizers and soil conditioners to improve soil quality and structure; water resource management, implementing water-saving irrigation techniques, including drip irrigation and rainwater harvesting; Monitor soil moisture and crop water requirements for precise irrigation; Pest control, implementing integrated pest monitoring and control measures, including biological control and the use of environmentally friendly pesticides; Promoting pest-resistant varieties and balanced management of agro-ecosystems; Mechanization and technology application, using modern agricultural machinery and technology, including automated harvesters and precision seeding equipment, to improve production efficiency; Apply information technology to optimize decision-making and management; Market orientation and quality control, analyzing market demand and price trends, and adjusting crop planting structure; Implement quality control measures to ensure products meet market standards and consumer expectations; Sustainable development and environmental protection, adopting sustainable agricultural practices, reducing the use of pesticides and fertilizers, and protecting soil and water resources; Support biodiversity and ecosystem services and protect the natural ecological balance; Providing farmer training and technical support to help them master the latest agricultural technologies and best practices; Promote agricultural cooperatives and technical cooperation, and promote information sharing and resource integration; Providing market access opportunities and financial support to promote the healthy development of the agricultural industry chain; Agricultural information sharing and collaboration module, which is used to enable different farms and agricultural-related stakeholders to share agricultural information and experience through cloud computing platforms, and promote collaborative work and knowledge sharing in agricultural production; Agricultural farming management module, used to manage agricultural farming processes, including: A soil resource information collection unit, used for collecting soil resource information; A farming machinery and equipment information sensing unit, used to sense various information of the farming machinery and equipment; Soil moisture analysis unit, used to establish a relationship model between meteorological factors and water demand and to establish an intelligent water control unit in combination with Internet of Things technology to predict and remotely control soil moisture; The soil cutting simulation unit is used to perform neural network modeling on soil and agricultural tillage machinery and equipment and simulate and predict the soil cutting process to obtain the influence of the forward speed of tillage machinery and equipment, tillage depth, and soil physical and chemical properties on the tillage effect; A statistical module for analyzing spatial changes in crop soils, used to monitor soil variation structure; The farming process planning unit is used to plan the farming process by combining farming requirements, farming objectives, farming effects, farming rules and farming costs with neural network technology to establish a neural network model; The demand research module includes field research, demand analysis, production needs and user needs.
2. The cloud computing-based smart agriculture information management platform according to claim 1, characterized in that: The sensors include: soil sensors, meteorological sensors, plant sensors, camera sensors and GPS sensors; The soil sensors include: soil moisture sensor, soil temperature sensor, soil humidity sensor, soil conductivity sensor, soil pH sensor and soil nutrient sensor; The meteorological sensors include: temperature sensor, humidity sensor, rainfall sensor, light sensor, wind speed and wind direction sensor; The plant sensors include: a leaf area index sensor, a plant height sensor, a chlorophyll content sensor and a leaf area sensor.
3. The cloud computing-based smart agriculture information management platform according to claim 1, characterized in that: The various information of the mechanical equipment includes: Specific make and model of agricultural machinery; The power output of the engine or electric motor; Dimensions and overall weight of agricultural machinery; Maximum operating speed; The operating functions of different machines, including tilling, sowing, fertilizing, spraying, and harvesting; The efficiency of completing tasks per unit time; Whether it has automated control functions, including autonomous driving technology and intelligent operation control; How to use, how the farmer or operator should use the equipment properly; Safety precautions, safety precautions and operating procedures that need to be paid attention to during operation; Maintenance cycles and methods, daily maintenance requirements of equipment, such as lubrication, cleaning, and parts replacement; Powertrain, including type of engine or electric motor, fuel consumption rate; Transmission system, including gearbox type and transmission mode; Control system: whether it is equipped with electronic control system and monitoring system; Investment cost, the cost of purchasing the machinery and equipment; Cost of use: the cost of daily use and maintenance, including fuel costs and parts replacement costs; Life expectancy and depreciation analysis, the expected useful life and depreciation of the equipment, and how to plan for replacement; Applicable crops or operation types, which types of crops or specific agricultural operations the equipment is suitable for; The competitiveness of the equipment in the market and user evaluation; Whether the equipment complies with environmental regulations and standards; Resource efficiency of equipment use, including energy consumption and water use; After-sales service and technical support provided; The warranty period and specific terms of the equipment.
4. The cloud computing-based smart agriculture information management platform according to claim 1, characterized in that: The algorithm formula of the relationship model between meteorological factors and water demand is specifically: Among them, N(h) is the number of sampling points, Z is the meteorological parameters and water volume parameters of the sampling points, and x i is the spatial position of the sampling point.
5. The cloud computing-based smart agriculture information management platform according to claim 1, characterized in that: The neural network modeling of soil and agricultural farming machinery and equipment and the simulation prediction of the soil cutting process include: Collect soil moisture, density, structure type, organic matter content, and clay content; Collect data on power output, tillage depth, rotary wheel diameter, fertilization device configuration, and operating parameters of tillage machinery and equipment; Use sensors to record data such as force, displacement, temperature, vibration, etc. during the farming process in real time; Standardize the collected data to remove noise and outliers; Extract the combined features of soil and mechanical parameters, including the ratio of soil moisture to clay content, the product of tillage depth and rotary wheel diameter, and use principal component analysis to reduce multidimensional data to a lower-dimensional feature space to improve model training efficiency; Choose appropriate deep learning frameworks and network structures, including convolutional neural networks for feature extraction, recurrent neural networks for processing time series data, or hybrid network structures; Divide the processed data into training set, validation set and test set; Use the training set to train the neural network model and use cross-validation technology to select the optimal hyperparameters; Use the validation set to evaluate the performance of the model and perform model tuning; Use the test set to finally evaluate the generalization ability of the model; Use the trained model to predict new combinations of soil and machine parameters and simulate the soil cutting process under different conditions; Analyze the prediction results and compare them with the measured data to verify the accuracy and reliability of the model.
6. The cloud computing-based smart agriculture information management platform according to claim 1, characterized in that: The method of combining farming requirements, farming objectives, farming effects, farming rules and farming costs with neural network technology to establish a neural network model to plan the farming process includes: Data collection and preprocessing; Farming demand data include crop types, planting area, soil type, climate conditions, and pest and disease conditions; Farming target data include yield target, quality target, and economic benefit target; Farming performance data include historical yields, quality indicators, pest and disease incidence, fertilizer usage, and irrigation water usage; Farming law data include crop growth models, soil fertility models, and pest and disease occurrence models; Farming cost data include seed cost, fertilizer cost, pesticide cost, labor cost, machinery cost, and water cost; Clean, normalize and extract features of the original data; Depending on the data type, choose the appropriate feature engineering method, including: The time series data uses sliding window and difference methods to extract features; The image data uses convolutional neural networks to extract features; The text data uses word embedding and topic model methods to extract features; Neural network model design; The model structure selects the recurrent neural network model; Use the preprocessed data as the input of the model; Model output, the output of the model includes: Farming process planning, including planting time, fertilization time, irrigation time, and pest and disease control time; Optimal farming parameters, including optimal fertilizer application, optimal irrigation, and optimal pest and disease control programs; Yield forecasting, predicting yields under different farming scenarios; Cost forecasting, predicting the cost under different farming schemes; Model training and evaluation; Training data uses historical data to train the model; Evaluation Metrics Use appropriate evaluation metrics to evaluate model performance, including: Accuracy, the degree of agreement between the predicted results and the actual results; Recall rate, how many true results are included in the predicted results; F1-score, a comprehensive indicator of precision and recall; Cost-effectiveness, comparison of costs and benefits of different farming options; Model deployment and optimization; Model deployment: deploying the trained model to the actual production environment; Model optimization: continuously collect new data, optimize the model, and improve model performance.
Citation Information
Patent Citations
Pro / E based simulation optimization method for cutting soil by cutter suction dredger reamer
CN103761352A
Fall detection method and system based on integrated decision tree
CN110222708A
Soil subsoiling simulation method based on DEM-FEM bidirectional coupling
CN116432479A
Intelligent agricultural management system based on data processing
CN117575169A
AI intelligent agricultural harvesting management system based on Internet of Things and application thereof
CN117893346A
Cited By
Intelligent agriculture big data cloud service supervision platform fusing aerial remote sensing and spatial distance measurement information
CN119783992A
Farming machinery holographic sensing intelligent module based on multi-source fusion
CN121359680A
