Intelligent agricultural facility management method and system based on intelligent perception

Abstract

The invention relates to the technical field of agricultural facility management, in particular to an intelligent agricultural facility management method and system based on intelligent perception. The method comprises the following steps: acquiring farmland area survey information data; performing hierarchical sensor node deployment on the farmland area survey information data to generate farmland sensor node deployment data; communication network connection is carried out according to the farmland sensor node deployment data, so that a farmland sensing network is generated, and the farmland sensing network comprises a plurality of farmland sensor nodes; performing farmland state region plot division on the farmland sensing node layout planning data through a farmland sensing network to generate a normal farmland state region plot and an abnormal farmland state region plot; performing water content calculation on the abnormal farmland state area plot to obtain abnormal farmland area water content data. According to the invention, through refined farmland perception, irrigation prediction, facility adjustment and strategy optimization, the efficiency of intelligent agricultural facility management is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural facility management, and in particular to a smart agricultural facility management method and system based on intelligent perception. Background Art

[0002] Initially, traditional agriculture relied on manual management and empirical judgment, and there were problems such as delayed information acquisition and unreasonable resource allocation. With the development of automated control technology, greenhouses, irrigation systems and other facilities have gradually realized automated management, but there is still a lack of intelligent perception and real-time feedback mechanisms. After entering the 21st century, breakthroughs in intelligent perception technology have made agricultural facility management precise and intelligent. The development of sensor technology has made it possible to monitor environmental factors such as temperature, humidity, light, and soil moisture in real time, and the Internet of Things technology enables remote transmission and processing of these data. At the same time, the application of artificial intelligence algorithms in data analysis, prediction and decision support has improved the level of intelligence in agricultural facility management. In recent years, agricultural big data analysis based on cloud computing platforms has made agricultural facility management not limited to the optimization of a single facility, but can be globally scheduled and coordinated, further improving agricultural production efficiency and resource utilization. However, the current traditional farmland status monitoring has problems such as unclear regional division and inaccurate detection of farmland problems. At the same time, the lack of accurate water spread prediction and regulation often leads to low irrigation efficiency and waste of resources, which in turn leads to low efficiency in smart agricultural facility management. Summary of the invention

[0003] Based on this, it is necessary to provide a smart agricultural facility management method and system based on intelligent perception to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a smart agricultural facility management method based on intelligent perception includes the following steps:

[0005] Step S1: Acquire farmland area survey information data; perform hierarchical sensor node deployment on the farmland area survey information data to generate farmland sensor node deployment data; perform communication network connection according to the farmland sensor node deployment data to generate a farmland sensing network, wherein the farmland sensing network includes a plurality of farmland sensor nodes;

[0006] Step S2: using the farmland sensing network to divide the farmland sensing node layout planning data into farmland status area plots, generating normal farmland status area plots and abnormal farmland status area plots; calculating the moisture content of the abnormal farmland status area plots to obtain abnormal farmland area moisture content data; using the abnormal farmland area moisture content data to perform irrigation facility performance management on the abnormal farmland status area plots, generating irrigation facility performance management data;

[0007] Step S3: predicting the spread of irrigation water bodies in adjacent plots of land in the normal farmland state area to generate irrigation water body spread prediction data; adjusting the irrigation facility direction of the irrigation facilities according to the irrigation water body spread prediction data to generate irrigation facility direction management data; integrating the irrigation facility performance management data and the irrigation facility direction management data into an irrigation strategy to generate an irrigation facility irrigation strategy;

[0008] Step S4: simulate irrigation of the irrigation facility irrigation strategy to generate irrigation facility management simulation data; visualize the irrigation facility management simulation data to generate an irrigation facility management simulation report; use the irrigation facility management simulation report to optimize the irrigation facility irrigation strategy management strategy to perform smart agricultural facility management operations.

[0009] The present invention can lay the foundation for the farmland sensing network by acquiring survey information data of the farmland area and deploying hierarchical sensor nodes. The rationality of the sensor node deployment can ensure the extensiveness and accuracy of information collection, help to monitor farmland environmental changes in real time, and provide accurate data for subsequent management. The farmland sensing network is used to accurately divide the farmland status area, and it is possible to monitor and distinguish normal farmland areas from abnormal farmland areas in real time. By calculating the water content of the plots in the abnormal farmland status area and generating relevant data, irrigation problems can be discovered in time to help accurately adjust the irrigation strategy. By using the water content data of the abnormal farmland area to manage the performance of irrigation facilities, the working status and efficiency of the irrigation equipment can be comprehensively evaluated to ensure that the irrigation facilities can maintain optimal performance in different periods, thereby effectively improving the utilization rate of water resources. The spread of irrigation water bodies in adjacent plots in the normal farmland status area can accurately predict the distribution trend of irrigation water bodies and provide a scientific basis for adjusting the irrigation direction. By adjusting the direction of the irrigation facilities, it is possible to effectively avoid excessive spread or waste of water flow and ensure the rational use of irrigation water. The irrigation facility performance management data and the irrigation facility direction management data are integrated into an irrigation strategy to ensure that the irrigation operation meets the specific needs of the farmland. Through intelligent strategy integration and management, the irrigation process can be optimized, the irrigation efficiency can be improved, and the waste of resources can be reduced. By simulating the irrigation operation, the irrigation facility management simulation data can be generated to further optimize the actual management process. Data visualization and simulation reports can help managers clearly understand the working conditions of the irrigation facilities and provide an intuitive and clear basis for subsequent decision-making. By optimizing and analyzing the irrigation facility management simulation report, it can provide important support for the management strategy of smart agriculture. The optimized irrigation strategy can achieve precise water application and adapt to the dynamic changes of the farmland environment. The goal of the entire system is to achieve the optimal allocation and use of water resources through precise irrigation facility management and dynamic adjustment of irrigation strategies, thereby reducing the waste of water resources. This method helps to achieve the goal of smart agriculture, combines Internet of Things technology, sensor networks and data analysis, improves the automation and intelligence level of farmland management, and promotes the modernization of agricultural management. Therefore, the present invention improves the efficiency of smart agricultural facility management through refined farmland perception, irrigation prediction, facility adjustment and strategy optimization.

[0010] Preferably, step S1 comprises the following steps:

[0011] Step S11: Acquire farmland area survey information data; perform sensing node layout design on the farmland area survey information data to generate farmland sensing node layout planning data;

[0012] Step S12: hierarchical sensor node deployment is performed based on the farmland sensing node layout planning data to generate farmland sensor node deployment data, wherein the farmland sensor node deployment data includes soil sensing layer sensor deployment data, air and water sensing layer sensor deployment data, and microbial ecological monitoring layer sensor deployment data;

[0013] Step S13: confirm the intersection of the deployment area through the soil perception layer sensor deployment data, the air and water perception layer sensor deployment data and the microbial ecological monitoring layer sensor deployment data to obtain the deployment area intersection data; perform data fusion node deployment according to the deployment area intersection data to generate data fusion node deployment data;

[0014] Step S14: Based on the data fusion node deployment data, the farmland sensor node deployment data is connected to a communication network to generate a farmland perception network, wherein the farmland perception network includes a plurality of farmland sensor nodes.

[0015] The present invention realizes multi-dimensional perception of farmland environment through the step-by-step layout and node deployment process of steps S11 to S13, and the layout design of multi-level sensors such as soil, air, water and microbial ecology, which helps to improve the comprehensiveness of data collection and cover farmland ecological information at different levels. In step S12, the rationality of node distribution is ensured through scientific perception node layout and hierarchical deployment, effectively reducing blind spots, thereby improving data collection efficiency. And the deployment of sensors at each layer is subdivided into soil, air and water, microbial ecology, etc., which improves the precision of monitoring. In step S13, regional intersection confirmation and data fusion node deployment are deployed, which can aggregate data at the intersection of different sensor levels, help improve the accuracy and reliability of data fusion, and reduce the deviation of data collected by sensors alone. Step S14 builds a stable farmland perception network by connecting the communication network of the nodes, which helps to improve the stability and efficiency of data transmission, and ensures that the data between the nodes can be transmitted in real time, thereby forming the continuity and real-time nature of farmland monitoring. The farmland sensing network formed by combining the execution results of all steps can provide support for intelligent decision-making such as farmland management, pest warning and environmental monitoring, and improve the intelligent level of farmland management. This layered and integrated sensor layout scheme makes the deployment of sensing nodes more adaptable, and can be flexibly adjusted and optimized according to different farmland environments and needs to meet diverse agricultural monitoring needs.

[0016] Preferably, step S14 comprises the following steps:

[0017] Step S141: performing signal coverage analysis on the farmland sensor node deployment data based on the data fusion node deployment data to generate farmland node coverage data; performing communication protocol selection based on the farmland node coverage data to obtain communication protocol selection data;

[0018] Step S142: using the communication protocol selection data to perform node connection on the farmland sensor node deployment data and the data fusion node deployment data to generate an initial node connection network;

[0019] Step S143: performing node unique identifier allocation on the initial node connection network to generate a network node unique identifier; performing network stability detection on the initial node connection network based on the network node unique identifier to generate network connection stability data;

[0020] Step S144: Utilize the network connection stability data to perform network topology optimization on the initial node connection network to generate a farmland sensing network, wherein the farmland sensing network includes a number of farmland sensor nodes.

[0021] The present invention ensures that the nodes reasonably distributed in the farmland can effectively cover the monitoring area, reduce blind spots and overlapping coverage, and improve the stability and accuracy of signal transmission through signal coverage analysis and communication protocol selection. The selection of the communication protocol is combined with the coverage data of the node, so that the nodes in different areas can use the appropriate communication protocol according to the actual situation, thereby maximizing the signal transmission efficiency, reducing energy consumption and signal interference, and ensuring the efficiency of data transmission. By assigning a unique identifier to each node, a network structure that is easy to manage is formed, which helps to easily identify and track the location and status of each node in a complex farmland perception network, and is convenient for subsequent network maintenance and management. The network connection stability detection ensures the communication quality between the nodes, timely discovers potential unstable factors in the initial connection network, and optimizes them in subsequent steps, which helps to reduce the risk of communication interruption and ensure the continuity and reliability of data transmission. The structure of the farmland perception network is made more flexible and scalable through topology optimization. The optimized network topology reduces unnecessary connections, improves the overall efficiency of the network, reduces transmission delays, and makes the perception network more suitable for the distributed monitoring needs of farmland. The process design of step S14 takes into account the steps of communication protocol, node unique identifier and topology optimization, so that in the future, when the farmland environment changes or the expansion demand increases, new nodes can be easily added or existing nodes can be adjusted to achieve flexible expansion of the perception network. Through coverage analysis, stability detection and topology optimization, the farmland perception network has high reliability and durability, can adapt to long-term operation in different environments, reduces the frequency and cost of subsequent maintenance, and is conducive to the management of the farmland facility monitoring system.

[0022] Preferably, step S2 comprises the following steps:

[0023] Step S21: using the farmland sensing network to divide the farmland sensing node layout planning data into farmland monitoring states, generating normal farmland monitoring states and abnormal farmland monitoring states; based on the normal farmland monitoring states and abnormal farmland monitoring states, the farmland area survey information data is divided into regions, generating normal farmland state area plots and abnormal farmland state area plots;

[0024] Step S22: extracting soil properties of the land in the abnormal farmland state area to obtain farmland soil property data; calculating the water content of the land in the abnormal farmland state area according to the farmland soil property data to obtain the water content data of the abnormal farmland area;

[0025] Step S23: comparing the moisture content data of the abnormal farmland area with the preset standard soil moisture content threshold, when the moisture content data of the abnormal farmland area is less than the preset standard soil moisture content threshold, marking the abnormal farmland state area plot as a water-deficient plot;

[0026] Step S24: When the moisture content data of the abnormal farmland area is greater than the preset standard soil moisture content threshold, the land in the abnormal farmland status area is marked as an over-watered land; irrigation facility performance management is performed based on the water-deficient land and the over-watered land, and irrigation facility performance management data is generated.

[0027] The present invention divides the farmland monitoring status into normal and abnormal areas through the farmland sensing network, realizes the early detection and regional division of abnormal status, helps managers quickly identify and locate farmland areas that need attention, and improves monitoring efficiency. Soil properties are extracted and water content is calculated in abnormal areas, so that the monitoring system can obtain detailed soil characteristic data of abnormal plots, accurately grasp soil moisture and other important properties, and provide a scientific basis for subsequent processing and decision-making. By comparing with the standard soil moisture content threshold, the moisture state of the abnormal area is classified in real time, and the abnormal area is divided into water-deficient plots and over-waterlogged plots, which helps to improve the accuracy of water resource management and quickly respond to drought or waterlogging problems. Based on the division of water-deficient plots and over-waterlogged plots, step S24 can generate irrigation facility performance management data, help managers optimize the configuration and operation of irrigation systems, realize targeted water resource allocation, and avoid resource waste. The entire step process effectively combines the sensor network and data analysis to form an intelligent farmland status monitoring and management system, which can manage the moisture and soil properties of farmland in a refined manner and promote the refined development of farmland management.

[0028] Preferably, the dynamic management of irrigation facilities based on water-deficient plots and over-waterlogged plots includes:

[0029] Performing a first liquid filling operation on the water-deficient plot with the irrigation facility to generate first liquid filling data for the irrigation facility; periodically irrigating the water-deficient plot based on the first liquid filling data for the irrigation facility, and synchronously collecting soil data for the water-deficient plot after irrigation to obtain soil data for the water-deficient plot after irrigation;

[0030] Conduct irrigation infiltration analysis on the soil data of water-deficient plots after irrigation to generate soil irrigation infiltration data; adjust the irrigation intensity of irrigation facilities based on the soil irrigation infiltration data to generate irrigation management data for water-deficient plots;

[0031] Filling the irrigation facility with a second liquid according to the data on the activity level of microorganisms in the plot, and generating irrigation facility second liquid filling data;

[0032] Extract regional meteorological data from overwatered plots to obtain regional meteorological data for overwatered plots; perform temperature change analysis on regional meteorological data for overwatered plots to generate regional temperature change data for overwatered plots; calculate the activity level of microorganisms in overwatered plots using regional temperature change data for overwatered plots to obtain the activity level of microorganisms in the plots;

[0033] The irrigation concentration of the second liquid filling data of the irrigation facility is adjusted using the data on the activity level of microorganisms in the plot, thereby generating irrigation management data for the overwatered plot; the irrigation management data for the water-deficient plot and the overwatered plot are integrated to generate irrigation facility performance management data.

[0034] The present invention can achieve precise management of farmland water shortage problems by performing liquid filling, periodic irrigation, soil data collection and irrigation penetration analysis on water-deficient plots, ensuring uniform soil water penetration, avoiding over-irrigation or insufficient water, improving irrigation efficiency and reducing water resource waste. By adjusting the irrigation intensity based on the soil data after irrigation and guiding the irrigation liquid filling based on the microbial activity data, the liquid filling and irrigation concentration of the irrigation facilities are dynamically adjusted, thereby forming a more intelligent irrigation scheme to ensure the optimal configuration of water and nutrition. The management process can adjust the operating parameters of the irrigation facilities in real time according to the status of different plots (water shortage or over-waterlogging) and the microbial activity, improve the flexibility and adaptability of the irrigation system, and ensure that each plot is accurately irrigated according to its actual needs. For over-waterlogged plots, by extracting meteorological data and analyzing temperature changes, and combining microbial activity data to adjust the irrigation concentration, it is helpful to optimize the irrigation management of over-waterlogged areas, prevent further aggravation of waterlogging, and promote moderate drainage and recovery of the soil. The adjustment of irrigation intensity and liquid filling based on microbial activity data not only ensures the reasonable distribution of water, but also has a positive impact on soil ecology, promoting the health of soil microorganisms and the long-term sustainability of soil. By integrating irrigation management data of water-deficient and over-waterlogged plots, it is possible to provide comprehensive irrigation plans and decision-making support for farmland, promote unified optimization and performance improvement of irrigation facilities, and improve the overall efficiency of the irrigation system. The system can respond to changes in the farmland environment in real time and dynamically adjust irrigation plans based on data feedback. This flexibility and adaptability improves the management level of irrigation facilities and their ability to adapt to complex agricultural environments.

[0035] Preferably, performing irrigation infiltration analysis on the soil data of the water-deficient plot after irrigation includes:

[0036] The soil moisture content of the water-deficient plots after irrigation is calculated in time series to obtain the irrigation soil moisture content change data; the soil moisture distribution of the water-deficient plots is analyzed based on the irrigation soil moisture content change data to generate a soil moisture distribution map;

[0037] Extract the soil structure of the water-deficient plot soil data after irrigation to generate the water-deficient plot soil structure data, wherein the water-deficient plot soil structure data includes soil physical structure data and soil chemical structure data; perform soil permeability characteristic analysis based on the soil physical structure data and soil chemical structure data to generate soil permeability characteristic data;

[0038] The soil permeability characteristic data is used to detect the permeability uniformity of the soil moisture distribution map to generate soil permeability uniformity data; the soil permeability uniformity data is used to estimate the permeability depth of the soil moisture distribution map to generate soil irrigation permeability data.

[0039] The present invention calculates the soil moisture content of the soil data after irrigation in a time series and generates the irrigation soil moisture content change data, which is helpful to fully understand the change trend of soil moisture and timely identify abnormal moisture changes, thereby realizing accurate moisture management of water-deficient plots and optimizing irrigation schemes. Through soil moisture distribution analysis, a soil moisture distribution map is generated, which can clearly show the distribution of soil moisture after irrigation, help farm managers understand the penetration and distribution pattern of moisture in the soil, help to reasonably arrange the irrigation cycle, and avoid uneven moisture distribution. By extracting soil physical structure and chemical structure data and performing soil structure analysis, in-depth soil background information can be provided for irrigation permeability characteristics, ensuring targeted analysis of the permeability behavior of different soil types, thereby improving the effect of the irrigation system. Through soil permeability characteristic analysis, the permeability capacity data of the soil is obtained, and the permeability characteristics of the soil can be accurately judged. This data provides a scientific basis for the optimization of the irrigation system, making the water penetration more uniform and avoiding over-irrigation or waste of water resources due to permeability differences. Soil permeability uniformity detection helps to evaluate the permeability uniformity of soil moisture in different regions and promptly discover the problem of uneven permeability in the irrigation system. Based on this, targeted adjustments can be made to the irrigation system to ensure that water can evenly penetrate deep into the soil. By analyzing the soil penetration uniformity data and estimating the penetration depth, the penetration depth and range of water after irrigation can be predicted more accurately. This helps to optimize the control of irrigation volume, avoid shallow irrigation and over-deep irrigation, and ensure the rational use of irrigation water. The design of this process makes irrigation management more data-driven, providing a large amount of key data such as soil moisture, structure, and permeability, supporting refined farmland management decisions, enhancing the level of intelligence in the agricultural production process, and improving the scientificity and efficiency of agricultural management.

[0040] Preferably, calculating the microbial activity level of the flooded plots using the regional temperature change data of the flooded plots includes:

[0041] Extract the microbial monitoring data of the over-waterlogged plots to obtain the microbial monitoring data of the over-waterlogged plots; classify the microbial species of the microbial monitoring data of the over-waterlogged plots to generate beneficial microbial species data and harmful microbial species data; calculate the microbial density ratio of the plots for the beneficial microbial species data and the harmful microbial species data to obtain the microbial density ratio data of the plots;

[0042] Screen the overwatered plots for plots with high harmful microorganism density according to the plot microbial density ratio data to obtain plots with high harmful microorganism density; perform microbial preferred temperature analysis on plots with high harmful microorganism density to generate harmful microorganism preferred temperature range data;

[0043] The temperature change data of the flooded plots were used to calculate the activity of the microorganisms in the flooded plots, and the data of the activity of the microorganisms in the plots were obtained. The formula for calculating the activity of the microorganisms in the plots is as follows:

[0044] A=α·ΔT+β·H+γ·O+δ·M;

[0045] Where A is the microbial activity index, α is the weight coefficient of the temperature change rate, ΔT is the temperature change rate, β is the weight coefficient of the humidity, H is the soil moisture, γ is the weight coefficient of the oxygen concentration, O is the soil oxygen concentration, δ is the weight coefficient of the microbial density, and M is the microbial density coefficient.

[0046] The present invention comprehensively considers multiple factors such as temperature changes, humidity, oxygen concentration and microbial density, and the calculation formula can accurately evaluate the activity of microorganisms in the soil. The weighted influence of different factors can fully reflect the impact of actual environmental conditions on microbial activity, thereby providing more detailed data support for farmland management. Through the classification of microbial species and the calculation of density ratio, the types and densities of harmful microorganisms can be accurately identified, and high-density plots can be screened. Combined with the analysis of microbial preference temperature, it can help to timely discover potential disease risks in areas with high harmful microbial density, thereby providing a scientific basis for farmland disease prevention and control. The microbial activity index (A) can provide important information on soil health status through the comprehensive influence of temperature, humidity, oxygen concentration and microbial density. This data provides a scientific basis for optimizing irrigation decisions and adjusting soil management strategies (such as improving soil permeability and adjusting fertilizer use), which helps to improve farmland yield and health. By quantitatively calculating the microbial activity of over-waterlogged plots, it can help identify the changing trend of microbial communities in the soil and timely discover the risk of soil degradation or pollution. Improving the microbial activity of over-waterlogged plots can promote soil recovery, reduce soil degradation problems, and ensure the sustainability of agricultural production. The microbial community in the soil directly affects the structure and fertility of the soil. By monitoring the activity of microorganisms, the activity of beneficial microorganisms in the soil can be maintained and improved, the soil ecosystem can be optimized, and the soil's nutrient cycling capacity can be enhanced. This method can provide a multi-dimensional analysis of soil microbial activity by integrating multiple environmental factors (temperature, humidity, oxygen concentration, etc.). This comprehensive method can better reflect the true situation of microbial activity in a complex environment than a single factor analysis, and provide stronger data support for precise farmland management and decision-making. According to the calculation results of the activity of microorganisms, targeted management can be carried out on over-waterlogged plots, and the use of irrigation, water and nutrients can be optimized to improve resource utilization efficiency and reduce unnecessary irrigation or fertilization, thereby reducing costs and reducing negative impacts on the environment.

[0047] Preferably, step S3 comprises the following steps:

[0048] Step S31: for the normal farmland state area plot, the adjacent plot state attribute difference is judged. When the adjacent plot state is identified as the abnormal farmland state area plot, the area boundary of the normal farmland state area plot and the abnormal farmland state area plot is identified to obtain the adjacent plot area boundary data;

[0049] Step S32: predicting the spread of irrigation water for the plots in the normal farmland state area and the plots in the abnormal farmland state area according to the boundary data of the adjacent plots, and generating irrigation water spread prediction data;

[0050] Step S33: adjusting the direction of the irrigation facilities according to the irrigation water body spread prediction data, thereby generating irrigation facility direction management data;

[0051] Step S34: Integrate the irrigation facility performance management data and the irrigation facility direction management data into an irrigation strategy to generate an irrigation facility irrigation strategy.

[0052] The present invention can accurately identify the changes in farmland areas and timely discover potential abnormal situations by distinguishing the difference in state attributes of adjacent plots between normal farmland state areas and abnormal farmland state areas. This method helps to avoid waste of farmland resources caused by improper irrigation or soil problems. After identifying the difference in the states of adjacent plots, regional boundary identification is performed to clearly determine the boundaries between normal and abnormal areas. This boundary data is crucial for subsequent irrigation management and precision agriculture decision-making, ensuring that irrigation measures are highly targeted and reducing unnecessary waste of resources. Predicting the spread of irrigation water bodies based on regional boundary data can effectively estimate the flow range of water bodies and their impact on farmland. This helps to plan and adjust irrigation strategies in advance to prevent irrigation water bodies from spreading in areas where irrigation is not required, improve water resource utilization efficiency, and reduce waste. By adjusting the direction of irrigation facilities according to the prediction results of irrigation water body spread, the direction of water flow and irrigation volume can be accurately controlled. This management method helps to improve irrigation efficiency, reduce unnecessary water body spread, and ensure that the irrigation system can better serve farmland needs. Integrating irrigation facility performance management data and irrigation facility direction management data to generate irrigation strategies helps to provide a comprehensive irrigation management solution. Through this integration step, all irrigation facilities are ensured to work together, the operation of the overall irrigation system is optimized, and the utilization efficiency of water resources is maximized. By optimizing the direction of irrigation facilities and integrating irrigation strategies, water waste can be effectively avoided and the actual needs of farmland can be accurately matched. This precision management improves agricultural production efficiency and ensures that farmland maintains optimal moisture conditions. The direction adjustment of irrigation facilities and the integration of irrigation strategies effectively avoid over-irrigation of areas with abnormal farmland conditions and reduce the waste of irrigation water. This not only saves water resources, but also reduces the cost of agricultural production. Through real-time identification of farmland status differences and dynamic adjustment of irrigation water spread prediction, environmental changes and sudden farmland problems can be responded to. With changes in weather, soil moisture and other factors, irrigation strategies can be optimized and adjusted in a timely manner to maintain a continuous and stable production state of farmland. By automatically analyzing farmland status and irrigation needs, this method can improve the level of intelligent agricultural management. Combined with modern Internet of Things and sensor technology, farmland managers can make more accurate and efficient decisions with the support of real-time data, promoting the development of agriculture towards intelligence and precision.

[0053] Preferably, step S32 includes the following steps:

[0054] Step S321: classifying the boundaries of the plots in the normal farmland state area and the plots in the abnormal farmland state area according to the boundary data of the adjacent plots, and generating the permeable boundary data and the blocking boundary data;

[0055] Step S322: Calculate the land terrain slope difference of the adjacent land area boundary data through the permeable boundary data and the barrier boundary data to generate land terrain slope difference data; perform water body natural flow trend analysis on the adjacent land area boundary data based on the land terrain slope difference data to generate water body natural flow trend data;

[0056] Step S323: using the experimental measurement method to perform soil moisture diffusion analysis on the boundary data of adjacent plots to generate the soil moisture diffusion coefficient of the plots; dividing the data sets of the natural flow trend data of the water body and the soil moisture diffusion coefficient to generate a model training set and a model test set;

[0057] Step S324: Use the diffusion equation to train the infiltration model of the model training set to generate a water spread prediction pre-model; perform model optimization iteration on the water spread prediction pre-model according to the model test set to generate a water spread prediction model; import the adjacent plot area boundary data into the water spread prediction model to perform adjacent plot water spread prediction, thereby generating irrigation water spread prediction data.

[0058] The present invention can clearly distinguish which areas can naturally accept the spread of water and which areas will block the water flow by classifying the boundary data of adjacent plots into permeable boundaries and barrier boundaries. This provides clear spatial information support for subsequent irrigation water spread prediction and helps to optimize irrigation efficiency. By calculating the terrain slope differences between adjacent plots, the flow characteristics of water flow in different terrain areas can be accurately understood. This analysis provides an important basis for understanding the flow trend of water bodies between plots with different slopes, and helps to formulate irrigation strategies that meet terrain conditions. The natural flow trend analysis of water bodies based on terrain slope difference data can reveal the flow path and direction of water flow between different plots. This analysis ensures that water bodies can flow according to natural laws, avoids over-irrigation or water waste, and helps optimize irrigation areas. By analyzing soil moisture diffusion through experimental determination methods, the absorption, diffusion and permeability characteristics of soil to water bodies can be better understood. The generation of soil moisture diffusion coefficient provides accurate physical data for subsequent model training, which can effectively simulate the infiltration process of irrigation water bodies. By dividing the data set of water body natural flow trend data and soil moisture diffusion coefficient, the training set and test set are generated to ensure that the model can accurately reflect the actual situation during the training process and ensure the generalization ability of the model. Through this process, the model can adapt to the law of water body spread under different soil and terrain conditions. Using the diffusion equation to train the model training set for infiltration model training can deeply understand the physical phenomena in the process of water body spread, so as to generate a more accurate water body spread prediction model. The generation of this model provides a scientific basis for the precise control of irrigation water body spread. By optimizing and iterating the model test set, the model parameters and structure are continuously adjusted, so that the water body spread prediction model can better adapt to the actual needs of different farmlands. The iterative process ensures the accuracy and stability of the model and improves the accuracy of irrigation water body spread prediction. After the boundary data of adjacent plots are imported into the water body spread prediction model, the scope and trend of water body spread can be accurately predicted for different regions. This prediction data helps to optimize and adjust irrigation facilities, achieve more efficient irrigation management, and avoid excessive spread or insufficient coverage of water bodies. Accurate prediction of irrigation water spread can provide agricultural managers with more scientific and accurate decision-making support, ensuring resource optimization and maximum efficiency of the irrigation process.

[0059] In this specification, a smart agricultural facility management system based on intelligent perception is provided, which is used to execute the above-mentioned smart agricultural facility management method based on intelligent perception. The smart agricultural facility management system based on intelligent perception includes:

[0060] The sensor network connection module is used to obtain farmland area survey information data; hierarchical sensor node deployment is performed on the farmland area survey information data to generate farmland sensor node deployment data; communication network connection is performed according to the farmland sensor node deployment data to generate a farmland perception network, wherein the farmland perception network includes a number of farmland sensor nodes;

[0061] The irrigation performance management module is used to divide the farmland status area plots according to the farmland sensing node layout planning data through the farmland sensing network, and generate normal farmland status area plots and abnormal farmland status area plots; calculate the moisture content of the abnormal farmland status area plots to obtain the abnormal farmland area moisture content data; use the abnormal farmland area moisture content data to perform irrigation facility performance management on the abnormal farmland status area plots, and generate irrigation facility performance management data;

[0062] The irrigation direction management module is used to predict the spread of irrigation water bodies in adjacent plots of land in normal farmland areas and generate irrigation water body spread prediction data; adjust the irrigation facility direction of irrigation facilities according to the irrigation water body spread prediction data, thereby generating irrigation facility direction management data; integrate the irrigation facility performance management data and the irrigation facility direction management data into irrigation strategies, and generate irrigation facility irrigation strategies;

[0063] The irrigation management simulation module is used to simulate irrigation of irrigation facilities and generate irrigation facility management simulation data; visualize the irrigation facility management simulation data and generate irrigation facility management simulation reports; use the irrigation facility management simulation reports to optimize the irrigation facility irrigation strategy and perform smart agricultural facility management operations.

[0064] The beneficial effect of the present invention is that by deploying hierarchical sensor nodes and connecting them into a farmland sensing network, environmental information of farmland (such as soil moisture, temperature, light, etc.) can be obtained in real time, providing accurate sensing data for agricultural management. The construction of the farmland sensing network enables efficient communication between each sensor node, thereby building a sensing network covering the entire farmland, ensuring the timeliness and accuracy of information transmission, and avoiding the problem of delayed or incomplete information transmission in traditional agricultural management. By dividing the farmland status area plots through the sensing network, it is possible to accurately distinguish between normal farmland status areas and abnormal farmland status areas, which helps to find problem areas in time and take measures. The calculation of the water content in the abnormal area can accurately understand the soil moisture situation, so as to implement targeted irrigation in the abnormal area and improve the utilization efficiency of water resources. Using water content data to perform performance management on irrigation facilities, the working status of irrigation equipment can be monitored, the equipment can be adjusted or repaired in time, and the efficient operation of the irrigation system can be ensured. The irrigation water body spread prediction of adjacent plots in the normal farmland status area can effectively foresee the diffusion path of irrigation water and avoid unnecessary waste of water resources. Adjust the direction of irrigation facilities according to the water spread prediction data to ensure uniform distribution of water, improve irrigation efficiency, and reduce over-irrigation or under-irrigation. Combining irrigation facility performance management data and facility direction management data, a scientific irrigation strategy can be integrated to further optimize resource utilization and ensure that the water needs of crops throughout the growth cycle are met. By simulating the irrigation strategy of irrigation facilities, the effect of the strategy can be verified before actual implementation to avoid wrong decisions. Data visualization can enable managers to understand the irrigation effect and management status more intuitively. According to the report generated by the simulation data, the irrigation strategy can be analyzed and optimized to ensure that the management of agricultural facilities is more efficient and scientific. The optimized strategy can further improve the overall performance of the irrigation system and reduce energy consumption and water waste. Therefore, the present invention improves the efficiency of smart agricultural facility management through refined farmland perception, irrigation prediction, facility adjustment and strategy optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 A schematic diagram of the steps of a smart agricultural facility management method based on intelligent perception;

[0066] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0067] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0068] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0069] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are 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 technicians in this field without creative work are within the scope of protection of the present invention.

[0070] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0071] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0072] To achieve this, please refer to Figures 1 to 3 , a smart agricultural facility management method based on intelligent perception, the method comprising the following steps:

[0073] Step S1: Acquire farmland area survey information data; perform hierarchical sensor node deployment on the farmland area survey information data to generate farmland sensor node deployment data; perform communication network connection according to the farmland sensor node deployment data to generate a farmland sensing network, wherein the farmland sensing network includes a plurality of farmland sensor nodes;

[0074] Step S2: using the farmland sensing network to divide the farmland sensing node layout planning data into farmland status area plots, generating normal farmland status area plots and abnormal farmland status area plots; calculating the moisture content of the abnormal farmland status area plots to obtain abnormal farmland area moisture content data; using the abnormal farmland area moisture content data to perform irrigation facility performance management on the abnormal farmland status area plots, generating irrigation facility performance management data;

[0075] Step S3: predicting the spread of irrigation water bodies in adjacent plots of land in the normal farmland state area to generate irrigation water body spread prediction data; adjusting the irrigation facility direction of the irrigation facilities according to the irrigation water body spread prediction data to generate irrigation facility direction management data; integrating the irrigation facility performance management data and the irrigation facility direction management data into an irrigation strategy to generate an irrigation facility irrigation strategy;

[0076] Step S4: simulate irrigation of the irrigation facility irrigation strategy to generate irrigation facility management simulation data; visualize the irrigation facility management simulation data to generate an irrigation facility management simulation report; use the irrigation facility management simulation report to optimize the irrigation facility irrigation strategy management strategy to perform smart agricultural facility management operations.

[0077] The present invention can lay the foundation for the farmland sensing network by acquiring survey information data of the farmland area and deploying hierarchical sensor nodes. The rationality of the sensor node deployment can ensure the extensiveness and accuracy of information collection, help to monitor farmland environmental changes in real time, and provide accurate data for subsequent management. The farmland sensing network is used to accurately divide the farmland status area, and it is possible to monitor and distinguish normal farmland areas from abnormal farmland areas in real time. By calculating the water content of the plots in the abnormal farmland status area and generating relevant data, irrigation problems can be discovered in time to help accurately adjust the irrigation strategy. By using the water content data of the abnormal farmland area to manage the performance of irrigation facilities, the working status and efficiency of the irrigation equipment can be comprehensively evaluated to ensure that the irrigation facilities can maintain optimal performance in different periods, thereby effectively improving the utilization rate of water resources. The spread of irrigation water bodies in adjacent plots in the normal farmland status area can accurately predict the distribution trend of irrigation water bodies and provide a scientific basis for adjusting the irrigation direction. By adjusting the direction of the irrigation facilities, it is possible to effectively avoid excessive spread or waste of water flow and ensure the rational use of irrigation water. The irrigation facility performance management data and the irrigation facility direction management data are integrated into an irrigation strategy to ensure that the irrigation operation meets the specific needs of the farmland. Through intelligent strategy integration and management, the irrigation process can be optimized, the irrigation efficiency can be improved, and the waste of resources can be reduced. By simulating the irrigation operation, the irrigation facility management simulation data can be generated to further optimize the actual management process. Data visualization and simulation reports can help managers clearly understand the working conditions of the irrigation facilities and provide an intuitive and clear basis for subsequent decision-making. By optimizing and analyzing the irrigation facility management simulation report, it can provide important support for the management strategy of smart agriculture. The optimized irrigation strategy can achieve precise water application and adapt to the dynamic changes of the farmland environment. The goal of the entire system is to achieve the optimal allocation and use of water resources through precise irrigation facility management and dynamic adjustment of irrigation strategies, thereby reducing the waste of water resources. This method helps to achieve the goal of smart agriculture, combines Internet of Things technology, sensor networks and data analysis, improves the automation and intelligence level of farmland management, and promotes the modernization of agricultural management. Therefore, the present invention improves the efficiency of smart agricultural facility management through refined farmland perception, irrigation prediction, facility adjustment and strategy optimization.

[0078] In the embodiment of the present invention, reference Figure 1 FIG. 1 is a flow chart of a smart agricultural facility management method based on intelligent perception according to the present invention. In this example, the smart agricultural facility management method based on intelligent perception includes the following steps:

[0079] Step S1: Acquire farmland area survey information data; perform hierarchical sensor node deployment on the farmland area survey information data to generate farmland sensor node deployment data; perform communication network connection according to the farmland sensor node deployment data to generate a farmland sensing network, wherein the farmland sensing network includes a plurality of farmland sensor nodes;

[0080] In an embodiment of the present invention, a preliminary survey of the target farmland area is conducted by using technologies such as drones and satellite images to collect terrain, landforms and vegetation information. The collected raw data is cleaned, denoised and standardized to generate standardized farmland area survey information data to ensure data consistency and accuracy. According to the farmland area survey information data, sensors suitable for monitoring specific environmental parameters, such as temperature, humidity, light, soil moisture, etc., are selected. The sensor nodes are divided into multiple levels for deployment. The functions and layouts of each layer of nodes are different, for example: Basic node layer: covers each small block in the farmland area and is used to collect real-time environmental data. Relay node layer: arranged between each small block, responsible for aggregating and transmitting data from the basic node layer. Master node layer: centrally manages data transmission and is responsible for uploading data from the relay node layer to the central database. The location, type and connection relationship of each node are formed into structured data to generate farmland sensor node deployment data. According to the node deployment data, the communication network topology in the farmland area is designed, taking into account factors such as distance, signal strength, and data transmission delay. Configure wireless communication connections (such as LoRa, Zigbee, Wi-Fi, etc.) between each node to ensure that the sensor nodes can communicate stably and efficiently. Optimize the network topology to ensure the stability of data transmission and the lowest latency to generate the final farmland perception network. Test the entire farmland perception network to ensure that all nodes are in normal operation and can collect and transmit data in real time. Detect and record the fault points in the network and set up an automatic repair mechanism to ensure data continuity. Finally, generate farmland perception network data, including farmland sensor node location, hierarchical connection information, real-time data transmission status and other information.

[0081] Step S2: using the farmland sensing network to divide the farmland sensing node layout planning data into farmland status area plots, generating normal farmland status area plots and abnormal farmland status area plots; calculating the moisture content of the abnormal farmland status area plots to obtain abnormal farmland area moisture content data; using the abnormal farmland area moisture content data to perform irrigation facility performance management on the abnormal farmland status area plots, generating irrigation facility performance management data;

[0082] In an embodiment of the present invention, real-time environmental parameter data, including temperature, humidity, soil moisture content, etc., are collected from each sensor node through a farmland sensing network. The collected data is compared with the farmland state threshold to determine whether the state of each farmland plot is within the normal range. According to the data analysis results, the farmland is divided into "normal farmland state area plot" and "abnormal farmland state area plot". Among them: the normal farmland state area plot refers to a plot where all parameters are within the set range, and the abnormal farmland state area plot refers to a plot where the parameters are abnormal and requires further management. The farmland state area plot division result is output to form a data file, and the state category of each plot is marked. The data of all abnormal farmland state area plots are filtered out from the plot division data, and further analysis is concentrated. The soil moisture content of each abnormal area plot is calculated using the data of the soil moisture sensor node, and a moisture content data file is generated to record the moisture content of each abnormal plot. The moisture content of each abnormal plot is compared with the standard moisture content range to determine whether irrigation intervention is required. Based on the water content data of the abnormal area, identify the plots that need irrigation, and record the amount of water and time required for irrigation. Obtain the performance status of the irrigation facilities (such as sprinkler systems, drip irrigation systems) associated with the abnormal plots, including water pressure, flow, etc. Compare the current performance of the irrigation facilities with the set standards to ensure the effectiveness of the facilities. If the performance of the facilities is below the standard, record the facility information that needs maintenance or optimization. Summarize the irrigation demand and facility performance status corresponding to each abnormal plot, and generate an irrigation facility performance management data file as a reference for irrigation management.

[0083] Step S3: predicting the spread of irrigation water bodies in adjacent plots of land in the normal farmland state area to generate irrigation water body spread prediction data; adjusting the irrigation facility direction of the irrigation facilities according to the irrigation water body spread prediction data to generate irrigation facility direction management data; integrating the irrigation facility performance management data and the irrigation facility direction management data into an irrigation strategy to generate an irrigation facility irrigation strategy;

[0084] In the embodiment of the present invention, a water flow model for the spread of irrigation water is constructed by using data such as the topography, soil permeability, and slope of the plots in the normal farmland state area. Based on the water flow model, combined with parameters such as the irrigation amount and irrigation rate, the spread of the irrigation water of each plot is predicted to simulate the spread of water between plots. The adjacent plots affected by the spread of water are predicted to ensure that the irrigation water will not flow into the area that does not need irrigation, thereby avoiding waste of water resources or water accumulation in farmland. The irrigation water spread prediction data is output, and the water spread range of each plot and the impact of the adjacent plots are marked. The spread range and the impact of the adjacent plots in the spread prediction data are obtained to determine whether the direction of the current irrigation facility needs to be adjusted. For the plots affected by the spread, the spraying angle, nozzle direction, and water spray radius of the irrigation facility are adjusted to ensure that the water flow direction accurately covers the required area. The adjusted irrigation facilities are tested to ensure that the water spread meets the expected range. If it does not meet expectations, further optimization is performed until the best effect is achieved. The direction adjustment of the irrigation facility is recorded, and an irrigation facility direction management data file is generated to ensure that the adjusted direction data can be traced and referenced. Combine the irrigation facility performance management data with the direction management data to analyze the mutual impact of the two, such as irrigation efficiency, coverage accuracy, etc. Based on the integrated data, formulate irrigation strategies for each plot, including irrigation volume, time, frequency, facility direction, spraying angle, etc. Output irrigation facility irrigation strategy files, including integrated operation instructions, to provide a comprehensive control solution for farmland irrigation.

[0085] Step S4: simulate irrigation of the irrigation facility irrigation strategy to generate irrigation facility management simulation data; visualize the irrigation facility management simulation data to generate an irrigation facility management simulation report; use the irrigation facility management simulation report to optimize the irrigation facility irrigation strategy management strategy to perform smart agricultural facility management operations.

[0086] In the embodiment of the present invention, the formulated irrigation strategy of the irrigation facilities is input into the irrigation simulation system, including parameters such as irrigation amount, time, frequency, and spraying direction. The relevant conditions of the farmland environment (such as soil moisture, temperature, wind speed, etc.) are set in the simulation system, and are as close to the actual farmland conditions as possible to ensure the accuracy of the simulation results. The simulation is started, and each irrigation facility is simulated to perform irrigation operations according to the input strategy, and the water absorption of each plot and the water body spread range and other data are recorded. The irrigation facility management simulation data is output, including the simulated water content, irrigation coverage, and water body spread of each plot, etc., as the basic data for subsequent analysis. The irrigation facility management simulation data is sorted and key indicators (such as soil moisture, irrigation coverage, water body infiltration range, etc.) are screened out. The simulation data is converted into easy-to-understand charts using visualization tools, including but not limited to the following forms: plot status map: showing the moisture content, irrigation coverage, etc. of each plot, water body spread heat map: showing the spread distribution of irrigation water in the farmland, and irrigation coverage effect map: intuitively showing the irrigation situation of each plot. The above charts are integrated into an irrigation facility management simulation report, including data descriptions, analysis results and visualization charts, to help users fully understand the simulation results. According to the irrigation facility management simulation report, the effectiveness and shortcomings of irrigation strategies can be identified. For example, if some plots are under-covered or over-irrigated, corresponding adjustments need to be made.

[0087] Preferably, step S1 comprises the following steps:

[0088] Step S11: Acquire farmland area survey information data; perform sensing node layout design on the farmland area survey information data to generate farmland sensing node layout planning data;

[0089] Step S12: hierarchical sensor node deployment is performed based on the farmland sensing node layout planning data to generate farmland sensor node deployment data, wherein the farmland sensor node deployment data includes soil sensing layer sensor deployment data, air and water sensing layer sensor deployment data, and microbial ecological monitoring layer sensor deployment data;

[0090] Step S13: confirm the intersection of the deployment area through the soil perception layer sensor deployment data, the air and water perception layer sensor deployment data and the microbial ecological monitoring layer sensor deployment data to obtain the deployment area intersection data; perform data fusion node deployment according to the deployment area intersection data to generate data fusion node deployment data;

[0091] Step S14: Based on the data fusion node deployment data, the farmland sensor node deployment data is connected to a communication network to generate a farmland perception network, wherein the farmland perception network includes a plurality of farmland sensor nodes.

[0092] In an embodiment of the present invention, a comprehensive survey of the target farmland area is conducted to obtain basic information such as terrain, soil type, humidity, temperature, and microbial ecology. Based on the survey information of the farmland area, the farmland is functionally divided, such as areas with good soil quality, areas with sufficient water sources, and areas with active microorganisms. The monitoring needs of different areas are determined based on various survey information of the farmland, so as to efficiently and reasonably arrange the sensing nodes. The sensing nodes are reasonably arranged for different functional areas to ensure that the nodes have wide coverage, good signal strength, and can efficiently transmit information. The layout design results are organized into farmland sensing node layout planning data to provide a basis for subsequent sensor node deployment. According to the farmland sensing node layout planning data, sensors such as humidity sensors, temperature sensors, nutrient sensors, etc. are reasonably deployed in the soil layer to monitor soil moisture, temperature, fertility, etc., generate soil sensing layer sensor deployment data, and record the specific location and function of each soil sensor. Air temperature and humidity sensors, CO2 monitoring sensors, water quality sensors, etc. are deployed in the air and water layers to monitor air quality, water quality parameters, etc., and generate air and water sensing layer sensor deployment data, including the specific location and monitoring range of air and water sensors. In view of the farmland microbial ecological environment, microbial monitoring sensors are deployed on the soil surface or in the plant root area to generate sensor deployment data for the microbial ecological monitoring layer, and the specific location of the microbial ecological monitoring sensors and the types of microorganisms monitored are recorded. Based on the sensor deployment data of each perception layer (i.e., soil, air and water, and microbial ecological monitoring layer data), the intersection of the deployment area is confirmed through coordinate and coverage analysis. The confirmed intersection is recorded as the intersection data of the deployment area as the key point of data fusion. At the confirmed intersection location, a data fusion node is deployed to collect data from multiple sensors, aggregate and fuse them for unified transmission. The deployment location of the fusion node and the type of sensor connected to it are recorded for subsequent network communication design. Based on the data fusion node deployment data, each sensor node is connected in a network topology to ensure the smooth flow of data transmission channels. The network can adopt a multi-hop communication structure or a grid structure to improve network coverage and transmission efficiency. Establish communication links between various sensor nodes and fusion nodes to form a complete farmland perception network. The final farmland perception network includes sensor nodes at multiple levels such as soil, air and water, and microbial ecology, and has the ability to collect and transmit farmland data in real time.

[0093] Preferably, step S14 includes the following steps:

[0094] Step S141: performing signal coverage analysis on the farmland sensor node deployment data based on the data fusion node deployment data to generate farmland node coverage data; performing communication protocol selection based on the farmland node coverage data to obtain communication protocol selection data;

[0095] Step S142: using the communication protocol selection data to perform node connection on the farmland sensor node deployment data and the data fusion node deployment data to generate an initial node connection network;

[0096] Step S143: performing node unique identifier allocation on the initial node connection network to generate a network node unique identifier; performing network stability detection on the initial node connection network based on the network node unique identifier to generate network connection stability data;

[0097] Step S144: Utilize the network connection stability data to perform network topology optimization on the initial node connection network to generate a farmland sensing network, wherein the farmland sensing network includes a number of farmland sensor nodes.

[0098] In an embodiment of the present invention, the signal coverage of each sensor node in the farmland is analyzed based on the data fusion node deployment data, and the effective coverage distance of the sensor node, signal interference factors, etc. are considered. The signal coverage range of each node is calculated to ensure the comprehensive coverage of the farmland area and avoid repeated coverage or blind spots. Farmland node coverage data is generated according to the analysis results to provide basic data for subsequent communication protocol selection. According to the farmland node coverage data, a suitable communication protocol is selected, such as LoRa, Zigbee or NB-IoT, etc. The specific selection depends on the coverage area, node density, data transmission requirements, etc. of the farmland. The selected communication protocol is recorded as communication protocol selection data to provide a communication standard for subsequent node connection. Based on the communication protocol selection data, the farmland sensor node and the data fusion node are connected according to the topological relationship. Considering the transmission distance, signal interference and communication protocol restrictions of the node, the connection path is optimized to ensure data transmission efficiency. The node relationship after connection is recorded as the initial node connection network, so that unique identifier allocation and network stability detection can be performed on this basis. Assign a unique identifier to each node in the initial node connection network to ensure that the data source of each node can be accurately identified during data transmission, generate network node unique identifier data, and record it in the network configuration file for management and monitoring. Based on the network node unique identifier, perform stability tests on the initial node connection network, including signal strength detection, delay analysis, packet loss rate calculation, etc. Organize the test results into network connection stability data for subsequent network topology optimization to ensure the robustness of the network structure. Use the network connection stability data to identify signal weaknesses or bottlenecks in the connection and optimize the connection path. By fine-tuning the layout of data fusion nodes and sensor nodes, optimize the connection path and network topology, and make the network connection more stable and efficient. Record the optimized network structure as the farmland sensing network to ensure that it has efficient data transmission, low latency, and good signal coverage. Perform a final test on the farmland sensing network to verify its stability and coverage.

[0099] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0100] Step S21: using the farmland sensing network to divide the farmland sensing node layout planning data into farmland monitoring states, generating normal farmland monitoring states and abnormal farmland monitoring states; based on the normal farmland monitoring states and abnormal farmland monitoring states, the farmland area survey information data is divided into regions, generating normal farmland state area plots and abnormal farmland state area plots;

[0101] Step S22: extracting soil properties of the land in the abnormal farmland state area to obtain farmland soil property data; calculating the water content of the land in the abnormal farmland state area according to the farmland soil property data to obtain the water content data of the abnormal farmland area;

[0102] Step S23: comparing the moisture content data of the abnormal farmland area with the preset standard soil moisture content threshold, when the moisture content data of the abnormal farmland area is less than the preset standard soil moisture content threshold, marking the abnormal farmland state area plot as a water-deficient plot;

[0103] Step S24: When the moisture content data of the abnormal farmland area is greater than the preset standard soil moisture content threshold, the land in the abnormal farmland status area is marked as an over-watered land; irrigation facility performance management is performed based on the water-deficient land and the over-watered land, and irrigation facility performance management data is generated.

[0104] In an embodiment of the present invention, farmland sensing nodes layout planning data is obtained by utilizing a farmland sensing network, and farmland environmental data collected by each monitoring node is monitored and analyzed in real time. According to preset standards and data analysis, farmland monitoring status is identified and classified as "normal" or "abnormal". Normal farmland monitoring status and abnormal farmland monitoring status are recorded and generated to provide data support for subsequent regional division. Based on normal and abnormal farmland monitoring status, farmland regional survey information data is divided into regions, and plots with normal and abnormal states are marked. Division data of plots in normal farmland status areas and plots in abnormal farmland status areas are formed to further analyze the soil properties of abnormal areas. In the plots in the abnormal farmland status area, soil physical and chemical property data are collected by soil sensing layer sensors. Soil data is analyzed to extract key property data such as soil pH, organic matter content, and particle structure. The analysis results are recorded as farmland soil property data for subsequent accurate calculation of water content. According to the farmland soil property data, the soil moisture content of the abnormal area plot is calculated using a soil moisture sensor. Record and generate water content data of abnormal farmland areas to further determine whether there is water shortage or overwatering in the area. Preset standard soil moisture content threshold to determine whether the farmland meets the appropriate water content conditions. Compare the water content data of abnormal farmland areas with the standard threshold. If the water content of the abnormal farmland area is lower than the standard soil moisture content threshold, the plot is marked as a water shortage plot. Mark the plot information and status as a water shortage plot so that it can be given priority in irrigation management. If the water content data of the abnormal farmland area is higher than the standard soil moisture content threshold, the area is marked as an overwatered plot. Record the overwatering status of the plot and mark it as a plot that needs drainage treatment to facilitate the subsequent management of irrigation facilities. Based on the status information of the water shortage plot and the overwatered plot, detect the performance of the irrigation facilities, such as the operation of the water pump and the water flow of the drip irrigation system. According to the test results, adjust or maintain the irrigation equipment to ensure irrigation efficiency and the rational use of water resources. Record and generate irrigation facility performance management data to guide precise irrigation and water resource allocation in farmland areas.

[0105] Preferably, the dynamic management of irrigation facilities based on water-deficient plots and over-waterlogged plots includes:

[0106] Performing a first liquid filling operation on the water-deficient plot with the irrigation facility to generate first liquid filling data for the irrigation facility; periodically irrigating the water-deficient plot based on the first liquid filling data for the irrigation facility, and synchronously collecting soil data for the water-deficient plot after irrigation to obtain soil data for the water-deficient plot after irrigation;

[0107] Conduct irrigation infiltration analysis on the soil data of water-deficient plots after irrigation to generate soil irrigation infiltration data; adjust the irrigation intensity of irrigation facilities based on the soil irrigation infiltration data to generate irrigation management data for water-deficient plots;

[0108] Filling the irrigation facility with a second liquid according to the data on the activity level of microorganisms in the plot, and generating irrigation facility second liquid filling data;

[0109] Extract regional meteorological data from overwatered plots to obtain regional meteorological data for overwatered plots; perform temperature change analysis on regional meteorological data for overwatered plots to generate regional temperature change data for overwatered plots; calculate the activity level of microorganisms in overwatered plots using regional temperature change data for overwatered plots to obtain the activity level of microorganisms in the plots;

[0110] The irrigation concentration of the second liquid filling data of the irrigation facility is adjusted using the data on the activity level of microorganisms in the plot, thereby generating irrigation management data for the overwatered plot; the irrigation management data for the water-deficient plot and the overwatered plot are integrated to generate irrigation facility performance management data.

[0111] In the embodiment of the present invention, the required amount of liquid and formula are determined by evaluating the soil moisture content and nutrient data of the water-deficient plot. The formula may include water and necessary nutrients, such as nitrogen, phosphorus, potassium, etc. The required liquid is loaded into the irrigation facility to ensure that the liquid filling amount is suitable for the irrigation needs of the plot. The time of filling completion, liquid type and filling amount are recorded, and "irrigation facility first liquid filling data" is generated for subsequent use. The water-deficient plot is irrigated according to the set irrigation cycle (for example, every day, every two days). After each irrigation is completed, relevant data such as soil moisture, nutrients and infiltration rate are collected immediately. The soil state of the irrigation area is monitored in real time using sensors, including humidity sensors, soil conductivity sensors and temperature sensors, etc., to generate "soil data of water-deficient plots after irrigation" so as to analyze the irrigation effect and provide data support for subsequent adjustments. Parameters such as moisture content and infiltration rate in the "soil data of water-deficient plots after irrigation" are read. The penetration depth and diffusion range of water in the soil are calculated by an infiltration model (for example, an infiltration model based on Darcy's law). Analyze the water holding capacity of different layers of soil to generate "soil irrigation infiltration data" and use it to determine whether the irrigation has achieved the expected effect and whether the irrigation amount needs to be further adjusted. By analyzing the "soil irrigation infiltration data", determine whether the current irrigation intensity is appropriate and whether there is water waste or insufficient irrigation. If the infiltration is too fast, reduce the irrigation intensity to avoid water loss; if the infiltration is slow, the irrigation amount can be appropriately increased. Record the parameters and reasons for each adjustment to generate "irrigation management data for water-deficient plots" for long-term irrigation strategy optimization. Use microbial activity sensors to monitor the activity of microorganisms in the soil of water-deficient plots. Record the number, activity and response of microorganisms to changes in soil moisture to form "microbial activity data". According to the impact of seasonality and irrigation cycles on microbial activity, the data is used to optimize soil biological health. Analyze the "microbial activity data" to determine the liquid composition, such as adding microbial nutrients such as organic matter or amino acids. Record the type, amount and time of the second filling liquid to generate "irrigation facility second liquid filling data". Collect real-time meteorological data including temperature, humidity and precipitation through meteorological stations or sensors. Record the collected data as "meteorological data for overwatered plot areas". Analyze the temperature change trend in the "meteorological data of overwatered plots" and calculate the impact of the temperature difference between day and night on the evaporation of soil moisture. Record the analysis results as "temperature change data of overwatered plots" for subsequent judgment of microbial activity. Based on the "temperature change data of overwatered plots", combined with soil moisture and nutritional status, calculate the activity of microorganisms under current environmental conditions and generate "plot microbial activity data" to guide the adjustment of subsequent irrigation concentration. Read the "plot microbial activity data" and "irrigation facility second liquid filling data". Optimize the microbial activity in the soil by adjusting the microbial nutrient concentration in the irrigation liquid.If the microbial activity is low, the concentration of organic nutrients can be increased, and if it is too high, the concentration can be reduced. After adjustment, the "overwatered plot irrigation management data" is generated. The "irrigation management data for water-deficient plots" and "overwatered plot irrigation management data" are integrated to generate "irrigation facility performance management data", including information such as irrigation frequency, liquid type, concentration and microbial activity. The "irrigation facility performance management data" is input into the control system of the irrigation facility to optimize the use of irrigation facilities in future decisions.

[0112] Preferably, performing irrigation infiltration analysis on the soil data of the water-deficient plot after irrigation includes:

[0113] The soil moisture content of the water-deficient plots after irrigation is calculated in time series to obtain the irrigation soil moisture content change data; the soil moisture distribution of the water-deficient plots is analyzed based on the irrigation soil moisture content change data to generate a soil moisture distribution map;

[0114] Extract the soil structure of the water-deficient plot soil data after irrigation to generate the water-deficient plot soil structure data, wherein the water-deficient plot soil structure data includes soil physical structure data and soil chemical structure data; perform soil permeability characteristic analysis based on the soil physical structure data and soil chemical structure data to generate soil permeability characteristic data;

[0115] The soil permeability characteristic data is used to detect the permeability uniformity of the soil moisture distribution map to generate soil permeability uniformity data; the soil permeability uniformity data is used to estimate the permeability depth of the soil moisture distribution map to generate soil irrigation permeability data.

[0116] In an embodiment of the present invention, the soil moisture data of the water-deficient plots before and after irrigation is obtained. Data is collected by sensors (such as soil moisture sensors) or remote sensing technology (such as ground laser scanning, satellite remote sensing, etc.), covering multiple moments (such as different periods before and after irrigation). Based on the time series data, the soil moisture formula (such as the moisture content formula based on soil density) is used to calculate the soil moisture change at each moment, and the irrigation soil moisture change data is generated, which reflects the change trend of soil moisture after irrigation. According to the soil moisture change data, a spatial interpolation algorithm (such as Kriging interpolation, inverse distance weighted method, etc.) is used to perform spatial distribution analysis on the soil moisture of the water-deficient plots. This process can use the data obtained by the sensor network and combine it with the geographic information system (GIS) for spatial mapping. Based on the spatial distribution data, a soil moisture distribution map is drawn to show the moisture levels in different regions. This map can identify areas with poor irrigation effects or uneven moisture distribution. Analyze the physical properties of the soil (such as soil particle size distribution, soil porosity, soil density, etc.). Data can be obtained through laboratory analysis, field testing (such as soil permeability experiments, density tests), and other methods. Test and analyze the chemical composition of the soil (such as pH value, organic matter content, salt content, nutrient content, etc.). Obtain data through soil chemical analysis instruments (such as mass spectrometers, ion chromatographs). Combine physical structure data with chemical structure data to form complete soil structure data for water-deficient plots. Based on the physical and chemical structure data of the soil, soil permeability models (such as Kostiakov formula, Horton formula, etc.) are used to analyze the permeability characteristics of the soil. Considering the porosity, particle composition, and chemical properties of the soil (such as the effect of soil salinity on permeability), the permeability coefficient of the soil is calculated. Soil permeability characteristic data, such as permeability rate, permeability depth, etc., are obtained through permeability tests or numerical simulations. Based on the soil permeability characteristic data, statistical methods or image processing techniques are used to analyze the permeability uniformity of the soil moisture distribution map. For example, variance analysis, standard deviation, and geostatistical methods are used to detect the uniformity of irrigation water distribution. The soil infiltration uniformity index or indicator is obtained to evaluate the infiltration effect in different areas to determine whether there are areas with concentrated water or uneven water distribution. Based on the soil infiltration uniformity data, the penetration depth is estimated using a physical model or regression model (such as Darcy's law, Philip model, etc.). Combined with the actual observation data, the water penetration depth in different soil areas is inferred through simulation or theoretical calculation. Combined with the above analysis, a complete soil irrigation infiltration data is generated, which will show the penetration depth and infiltration effect in different areas and provide a reference for subsequent irrigation management and soil improvement.

[0117] Preferably, calculating the microbial activity level of the flooded plots using the regional temperature change data of the flooded plots includes:

[0118] Extract the microbial monitoring data of the over-waterlogged plots to obtain the microbial monitoring data of the over-waterlogged plots; classify the microbial species of the microbial monitoring data of the over-waterlogged plots to generate beneficial microbial species data and harmful microbial species data; calculate the microbial density ratio of the plots for the beneficial microbial species data and the harmful microbial species data to obtain the microbial density ratio data of the plots;

[0119] Screen the overwatered plots for plots with high harmful microorganism density according to the plot microbial density ratio data to obtain plots with high harmful microorganism density; perform microbial preferred temperature analysis on plots with high harmful microorganism density to generate harmful microorganism preferred temperature range data;

[0120] The temperature change data of the flooded plots were used to calculate the activity of the microorganisms in the flooded plots, and the data of the activity of the microorganisms in the plots were obtained. The formula for calculating the activity of the microorganisms in the plots is as follows:

[0121] A=α·ΔT+β·H+γ·O+δ·M;

[0122] Where A is the microbial activity index, α is the weight coefficient of the temperature change rate, ΔT is the temperature change rate, β is the weight coefficient of the humidity, H is the soil moisture, γ is the weight coefficient of the oxygen concentration, O is the soil oxygen concentration, δ is the weight coefficient of the microbial density, and M is the microbial density coefficient.

[0123] In an embodiment of the present invention, microbial data in the soil is regularly collected by using microbial monitoring equipment (such as soil microbial sensors and sampling devices) in the overwatered plots. These devices can capture the changes in the types and quantities of microorganisms and different microbial communities in the soil. The microbial monitoring data of the overwatered plots are extracted from the monitoring system, mainly including information such as microbial species, density and distribution. The monitoring data may include the classification results of microbial species and the biomass of each microbial community. The microbial species of the overwatered plots are classified, and beneficial microorganisms (such as nitrogen-fixing bacteria and microorganisms that decompose organic matter) and harmful microorganisms (such as pathogens, molds, etc.) are usually determined by methods such as microbial genome analysis, culture medium detection, PCR technology or high-throughput sequencing. Beneficial microbial species data and harmful microbial species data are divided. Each microbial species is associated with its corresponding function, density and ecological role, and detailed classification data of beneficial and harmful microorganisms are generated. According to the microbial monitoring data, the number of different microorganisms in each area is calculated (in units of individuals / unit soil volume). Based on the species data, the density of beneficial microorganisms and harmful microorganisms is calculated respectively. The density data of each species is used to calculate its proportion, that is, the proportion of beneficial microorganisms and harmful microorganisms in the total microbial density, and the microbial density proportion data of the plot is generated. Based on the microbial density proportion data of the plot, the screening criteria are set (for example, the density of harmful microorganisms above a certain threshold is considered to be a high-density plot). According to these criteria, the plots with high-degree harmful microorganism density are screened out. The areas where these high-density harmful microorganisms gather are marked to provide key areas for further monitoring or intervention. According to the growth environment data of harmful microorganisms and combined with the existing research on the temperature adaptability of microbial populations, the growth activity of various types of harmful microorganisms under different temperature conditions is analyzed. The optimal temperature range of different harmful microorganisms is obtained through literature or experimental data. For each high-density harmful microorganism, its preferred temperature range is obtained, that is, the preferred temperature range data of harmful microorganisms, which provides temperature conditions for subsequent microbial activity calculations. Using the regional temperature change data of the overwatered plot, the temperature change rate ΔT at different time points is calculated. The temperature change rate can be determined by measuring the temperature changes of the soil and the environment. Based on the soil moisture and oxygen concentration data of the overwatered plot, the soil moisture (H) and oxygen concentration (O) are calculated. These data are usually provided by humidity sensors and oxygen sensors. The microbial density coefficient M is calculated using the aforementioned microbial density ratio data. This coefficient takes into account the impact of the combined density of beneficial and harmful microorganisms on activity. The microbial activity index (A) is calculated using the following formula: A = α·ΔT+β·H+γ·O+δ·M; the microbial activity index A of each flooded plot is calculated based on the formula to generate the plot microbial activity data.

[0124] As an example of the present invention, refer to Figure 3As shown, in this example, step S3 includes:

[0125] Step S31: for the normal farmland state area plot, the adjacent plot state attribute difference is judged. When the adjacent plot state is identified as the abnormal farmland state area plot, the area boundary of the normal farmland state area plot and the abnormal farmland state area plot is identified to obtain the adjacent plot area boundary data;

[0126] Step S32: predicting the spread of irrigation water for the plots in the normal farmland state area and the plots in the abnormal farmland state area according to the boundary data of the adjacent plots, and generating irrigation water spread prediction data;

[0127] Step S33: adjusting the direction of the irrigation facilities according to the irrigation water body spread prediction data, thereby generating irrigation facility direction management data;

[0128] Step S34: Integrate the irrigation facility performance management data and the irrigation facility direction management data into an irrigation strategy to generate an irrigation facility irrigation strategy.

[0129] In an embodiment of the present invention, farmland status data of plots in the normal farmland state area and surrounding plots are collected. The farmland status data may include soil moisture, temperature, vegetation growth, crop health, irrigation conditions, etc. The farmland status attribute data of adjacent plots are obtained by remote sensing technology, geographic information system (GIS) or drone monitoring. Data analysis methods (such as machine learning classification algorithms, cluster analysis, etc.) are used to compare the state attributes of the normal farmland state area and the adjacent plots to identify whether there are abnormalities. Abnormal states include excessive soil moisture (water accumulation), crop yellowing, and the occurrence of pests and diseases. When the adjacent plot is determined to be in an abnormal farmland state, it is marked as an abnormal state area. According to the identified boundary line between normal farmland and abnormal farmland, boundary identification is performed by image processing, edge detection and other technologies to determine the boundary between the normal farmland area and the abnormal farmland area. GIS technology is used to mark the boundary data, including boundary coordinates, area area and other information. The regional boundary data of the adjacent plots is output, and the data will be used for irrigation water spread prediction in subsequent steps. Based on the boundary data of adjacent plots and factors such as soil moisture, precipitation, temperature, and irrigation water source flow, an irrigation water body spread prediction model is established. The spread of irrigation water bodies can be predicted using hydrodynamic models, machine learning algorithms, or physically-based water flow models. Combined with the state attributes of adjacent plots (such as the availability of water sources, the efficiency of irrigation systems, etc.), the spread process of irrigation water bodies in farmland is simulated. Considering the topography, soil permeability, and irrigation methods of farmland, the expansion trend of water flow in farmland is predicted. By simulating the spread of irrigation water bodies, irrigation water body spread prediction data is generated. This data includes information such as the range, speed, and direction of water body spread. Output irrigation water body spread prediction data to provide a basis for subsequent adjustments to irrigation facilities. Obtain the working status data of current irrigation facilities to understand the layout, coverage, and irrigation effect of irrigation facilities. Collect the operation data of irrigation facilities through sensors, remote sensing monitoring, or data recording devices built into irrigation equipment. Evaluate the efficiency and scope of existing irrigation facilities to determine whether there are problems such as uneven irrigation, inefficiency, or untimely irrigation. Based on the irrigation water spread prediction data, determine which areas need to be irrigated more and which areas are over-irrigated (such as irrigation water spreading excessively to abnormal farmland areas). Adjust the direction of irrigation facilities to more accurately cover the areas that need irrigation. Adjustments include nozzle direction adjustment, flow control, irrigation area division, etc. The adjusted facility direction data will be used to optimize irrigation strategies. Output management data after the irrigation facility direction is adjusted, including information such as the working direction of the irrigation equipment, coverage area, flow control, etc. These data will help managers adjust and optimize irrigation operations. Collect performance data of irrigation facilities, such as irrigation water volume, pressure, work efficiency, fault records, etc. Use these data to analyze the working status of irrigation facilities and their support for crop growth.If there are performance problems with irrigation facilities (such as nozzle blockage, unstable flow, etc.), improve facility performance through maintenance and optimization. Combine irrigation facility direction management data (i.e. adjusted irrigation facility direction and flow control data) with facility performance data to analyze the comprehensive performance of the irrigation system. Considering the irrigation water body spread prediction data, adjust the irrigation strategy to make rational use of water sources and avoid resource waste or insufficient irrigation. Develop new irrigation strategies by integrating facility performance management data and facility direction management data. These strategies will guide irrigation operations, equipment configuration, irrigation frequency, irrigation volume, etc., generate irrigation strategies for irrigation facilities, and provide specific irrigation operation plans.

[0130] Preferably, step S32 includes the following steps:

[0131] Step S321: classifying the boundaries of the plots in the normal farmland state area and the plots in the abnormal farmland state area according to the boundary data of the adjacent plots, and generating the permeable boundary data and the blocking boundary data;

[0132] Step S322: Calculate the land terrain slope difference of the adjacent land area boundary data through the permeable boundary data and the barrier boundary data to generate land terrain slope difference data; perform water body natural flow trend analysis on the adjacent land area boundary data based on the land terrain slope difference data to generate water body natural flow trend data;

[0133] Step S323: using the experimental measurement method to perform soil moisture diffusion analysis on the boundary data of adjacent plots to generate the soil moisture diffusion coefficient of the plots; dividing the data sets of the natural flow trend data of the water body and the soil moisture diffusion coefficient to generate a model training set and a model test set;

[0134] Step S324: Use the diffusion equation to train the infiltration model of the model training set to generate a water spread prediction pre-model; perform model optimization iteration on the water spread prediction pre-model according to the model test set to generate a water spread prediction model; import the adjacent plot area boundary data into the water spread prediction model to perform adjacent plot water spread prediction, thereby generating irrigation water spread prediction data.

[0135] In an embodiment of the present invention, farmland status data of adjacent plots are obtained by using remote sensing technology (such as satellite images or drone photography), and the boundaries of normal farmland status areas and abnormal farmland status areas are marked in combination with GIS technology. Based on the moisture status, soil type, terrain and other characteristics of the farmland, the farmland area is classified to clarify which areas belong to areas with good permeability (permeability boundaries) and which areas are water flow barrier areas (barrier boundaries). Permeability boundary data refers to boundary areas where factors such as soil type and irrigation system allow water to spread freely, and these areas usually have good water permeability. Barrier boundary data refers to areas where water flow is blocked due to factors such as soil density, obstacles (such as buildings, vegetation belts, etc.) or uneven distribution of water sources. According to the classification results, permeability boundary and barrier boundary data are generated, and different identifiers are assigned to different areas. Digital elevation model (DEM) data of adjacent plots are obtained for slope analysis. By analyzing the slope differences between different plots, the natural flow trend of water in different areas is evaluated. Calculate the slope difference and generate the corresponding plot terrain slope difference data, which reflects the acceleration or slowdown trend of water flow. Based on the slope difference data, soil type and water source distribution of the plot, analyze the natural flow trend of water in different areas. For example, the water flow is faster in areas with larger slopes and slower in areas with smaller slopes. Combined with the boundary data of the plot, generate the natural flow trend data of water bodies to describe how the water flow expands in the farmland and the direction of flow. Measure the water diffusion coefficient of the soil through experimental determination methods (such as field experiments or simulation experiments). Use soil samples to determine the diffusion rate of soil moisture, considering factors such as soil type, humidity, and temperature. Based on the experimental results, generate the soil moisture diffusion coefficient data for each plot. This coefficient reflects the diffusion rate of water in the soil and directly affects the speed and range of water spread. Combine the generated water body natural flow trend data and soil moisture diffusion coefficient data, and divide the training set and test set through data preprocessing (such as standardization and normalization). Usually, 70% is used for training set and 30% is used for test set to ensure the effectiveness of model training and evaluation. The mathematical model of water spread is established using the diffusion equation. Common diffusion equations include Fick's law or diffusion models based on soil moisture transport. The model is trained through the training set, and the soil moisture diffusion coefficient, natural flow trend data, etc. are used as input features to predict the speed and direction of water spread. During the training process, the model parameters are adjusted to ensure that the model can accurately reflect the water spread process. The trained water spread prediction model is evaluated using the model test set. The model parameters are optimized by comparing the error between the model prediction results and the actual observation data. Cross-validation, parameter adjustment and other methods are applied to ensure the adaptability and accuracy of the water spread prediction model in various situations. After multiple iterations and optimization, the final water spread prediction model is generated.The model can predict the spread behavior of water bodies in different plots, including the expansion speed, spread range and affected area of ​​water bodies. The boundary data of adjacent plots are imported into the water body spread prediction model to predict water body spread. The output of this step is a prediction of the irrigation water body spread process, including how the irrigation water body expands in the farmland, which areas it spreads to, and the layout of irrigation facilities that need to be adjusted. The water body spread prediction data is output to provide a scientific basis for the adjustment of irrigation strategies. The data will include information such as the time, spatial distribution, and spread speed of water body spread, helping farmland managers make timely irrigation adjustments.

[0136] In this specification, a smart agricultural facility management system based on intelligent perception is provided, which is used to execute the above-mentioned smart agricultural facility management method based on intelligent perception. The smart agricultural facility management system based on intelligent perception includes:

[0137] The sensor network connection module is used to obtain farmland area survey information data; hierarchical sensor node deployment is performed on the farmland area survey information data to generate farmland sensor node deployment data; communication network connection is performed according to the farmland sensor node deployment data to generate a farmland perception network, wherein the farmland perception network includes a number of farmland sensor nodes;

[0138] The irrigation performance management module is used to divide the farmland status area plots according to the farmland sensing node layout planning data through the farmland sensing network, and generate normal farmland status area plots and abnormal farmland status area plots; calculate the moisture content of the abnormal farmland status area plots to obtain the abnormal farmland area moisture content data; use the abnormal farmland area moisture content data to perform irrigation facility performance management on the abnormal farmland status area plots, and generate irrigation facility performance management data;

[0139] The irrigation direction management module is used to predict the spread of irrigation water bodies in adjacent plots of land in normal farmland areas and generate irrigation water body spread prediction data; adjust the irrigation facility direction of irrigation facilities according to the irrigation water body spread prediction data, thereby generating irrigation facility direction management data; integrate the irrigation facility performance management data and the irrigation facility direction management data into irrigation strategies, and generate irrigation facility irrigation strategies;

[0140] The irrigation management simulation module is used to simulate irrigation of irrigation facilities and generate irrigation facility management simulation data; visualize the irrigation facility management simulation data and generate irrigation facility management simulation reports; use the irrigation facility management simulation reports to optimize the irrigation facility irrigation strategy and perform smart agricultural facility management operations.

[0141] The beneficial effect of the present invention is that by deploying hierarchical sensor nodes and connecting them into a farmland sensing network, environmental information of farmland (such as soil moisture, temperature, light, etc.) can be obtained in real time, providing accurate sensing data for agricultural management. The construction of the farmland sensing network enables efficient communication between each sensor node, thereby building a sensing network covering the entire farmland, ensuring the timeliness and accuracy of information transmission, and avoiding the problem of delayed or incomplete information transmission in traditional agricultural management. By dividing the farmland status area plots through the sensing network, it is possible to accurately distinguish between normal farmland status areas and abnormal farmland status areas, which helps to find problem areas in time and take measures. The calculation of the water content in the abnormal area can accurately understand the soil moisture situation, so as to implement targeted irrigation in the abnormal area and improve the utilization efficiency of water resources. Using water content data to perform performance management on irrigation facilities, the working status of irrigation equipment can be monitored, the equipment can be adjusted or repaired in time, and the efficient operation of the irrigation system can be ensured. The irrigation water body spread prediction of adjacent plots in the normal farmland status area can effectively foresee the diffusion path of irrigation water and avoid unnecessary waste of water resources. Adjust the direction of irrigation facilities according to the water spread prediction data to ensure uniform distribution of water, improve irrigation efficiency, and reduce over-irrigation or under-irrigation. Combining irrigation facility performance management data and facility direction management data, a scientific irrigation strategy can be integrated to further optimize resource utilization and ensure that the water needs of crops throughout the growth cycle are met. By simulating the irrigation strategy of irrigation facilities, the effect of the strategy can be verified before actual implementation to avoid wrong decisions. Data visualization can enable managers to understand the irrigation effect and management status more intuitively. According to the report generated by the simulation data, the irrigation strategy can be analyzed and optimized to ensure that the management of agricultural facilities is more efficient and scientific. The optimized strategy can further improve the overall performance of the irrigation system and reduce energy consumption and water waste. Therefore, the present invention improves the efficiency of smart agricultural facility management through refined farmland perception, irrigation prediction, facility adjustment and strategy optimization.

[0142] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0143] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A smart agricultural facility management method based on intelligent perception, characterized in that: The following steps are involved: Step S1: Acquire farmland area survey information data; Performing hierarchical sensor node deployment on farmland area survey information data to generate farmland sensor node deployment data; performing communication network connection according to the farmland sensor node deployment data to generate a farmland sensing network, wherein the farmland sensing network includes a number of farmland sensor nodes; Step S2: using the farmland sensing network to divide the farmland sensing node layout planning data into farmland status area plots, generating normal farmland status area plots and abnormal farmland status area plots; Calculate the water content of the plots in the abnormal farmland status area to obtain the water content data of the abnormal farmland area; Use the water content data of abnormal farmland areas to manage the performance of irrigation facilities in areas with abnormal farmland status and generate irrigation facility performance management data; Step S3: For the plots in the normal farmland state area, the irrigation water body spread prediction is performed to the adjacent plots, and the irrigation water body spread prediction data is generated; Adjust the direction of irrigation facilities according to the irrigation water spread prediction data, thereby generating irrigation facility direction management data; integrate the irrigation facility performance management data and the irrigation facility direction management data into irrigation strategies, thereby generating irrigation facility irrigation strategies; Step S4: simulate irrigation of the irrigation facility irrigation strategy to generate irrigation facility management simulation data; visualize the irrigation facility management simulation data to generate an irrigation facility management simulation report; use the irrigation facility management simulation report to optimize the irrigation facility irrigation strategy management strategy to perform smart agricultural facility management operations.

2. The intelligent agricultural facility management method based on intelligent perception according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: Acquire farmland area survey information data; perform sensing node layout design on the farmland area survey information data to generate farmland sensing node layout planning data; Step S12: hierarchical sensor node deployment is performed based on the farmland sensing node layout planning data to generate farmland sensor node deployment data, wherein the farmland sensor node deployment data includes soil sensing layer sensor deployment data, air and water sensing layer sensor deployment data, and microbial ecological monitoring layer sensor deployment data; Step S13: confirm the intersection of the deployment area through the soil perception layer sensor deployment data, the air and water perception layer sensor deployment data and the microbial ecological monitoring layer sensor deployment data to obtain the deployment area intersection data; perform data fusion node deployment according to the deployment area intersection data to generate data fusion node deployment data; Step S14: Based on the data fusion node deployment data, the farmland sensor node deployment data is connected to a communication network to generate a farmland perception network, wherein the farmland perception network includes a plurality of farmland sensor nodes.

3. The intelligent agricultural facility management method based on intelligent perception according to claim 2 is characterized in that: Step S14 includes the following steps: Step S141: performing signal coverage analysis on the farmland sensor node deployment data based on the data fusion node deployment data to generate farmland node coverage data; performing communication protocol selection based on the farmland node coverage data to obtain communication protocol selection data; Step S142: using the communication protocol selection data to perform node connection on the farmland sensor node deployment data and the data fusion node deployment data to generate an initial node connection network; Step S143: performing node unique identifier allocation on the initial node connection network to generate a network node unique identifier; performing network stability detection on the initial node connection network based on the network node unique identifier to generate network connection stability data; Step S144: Utilize the network connection stability data to perform network topology optimization on the initial node connection network to generate a farmland sensing network, wherein the farmland sensing network includes a number of farmland sensor nodes.

4. The intelligent agricultural facility management method based on intelligent perception according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: using the farmland sensing network to divide the farmland sensing node layout planning data into farmland monitoring states, generating normal farmland monitoring states and abnormal farmland monitoring states; based on the normal farmland monitoring states and abnormal farmland monitoring states, the farmland area survey information data is divided into regions, generating normal farmland state area plots and abnormal farmland state area plots; Step S22: extracting soil properties of the land in the abnormal farmland state area to obtain farmland soil property data; calculating the water content of the land in the abnormal farmland state area according to the farmland soil property data to obtain the water content data of the abnormal farmland area; Step S23: comparing the moisture content data of the abnormal farmland area with the preset standard soil moisture content threshold, when the moisture content data of the abnormal farmland area is less than the preset standard soil moisture content threshold, marking the abnormal farmland state area plot as a water-deficient plot; Step S24: When the moisture content data of the abnormal farmland area is greater than the preset standard soil moisture content threshold, the land in the abnormal farmland status area is marked as an over-watered land; irrigation facility performance management is performed based on the water-deficient land and the over-watered land, and irrigation facility performance management data is generated.

5. The intelligent agricultural facility management method based on intelligent perception according to claim 4 is characterized in that: Dynamic management of irrigation facilities based on water-deficient and overwatered plots includes: Performing a first liquid filling operation on the water-deficient plot with the irrigation facility to generate first liquid filling data for the irrigation facility; periodically irrigating the water-deficient plot based on the first liquid filling data for the irrigation facility, and synchronously collecting soil data for the water-deficient plot after irrigation to obtain soil data for the water-deficient plot after irrigation; Conduct irrigation infiltration analysis on the soil data of water-deficient plots after irrigation to generate soil irrigation infiltration data; adjust the irrigation intensity of irrigation facilities based on the soil irrigation infiltration data to generate irrigation management data for water-deficient plots; Filling the irrigation facility with a second liquid according to the data on the activity level of microorganisms in the plot, and generating irrigation facility second liquid filling data; Extract regional meteorological data from overwatered plots to obtain regional meteorological data for overwatered plots; perform temperature change analysis on regional meteorological data for overwatered plots to generate regional temperature change data for overwatered plots; calculate the activity level of microorganisms in overwatered plots using regional temperature change data for overwatered plots to obtain the activity level of microorganisms in the plots; The irrigation concentration of the second liquid filling data of the irrigation facility is adjusted using the data on the activity level of microorganisms in the plot, thereby generating irrigation management data for the overwatered plot; the irrigation management data for the water-deficient plot and the overwatered plot are integrated to generate irrigation facility performance management data.

6. The intelligent agricultural facility management method based on intelligent perception according to claim 5 is characterized in that: Irrigation infiltration analysis of soil data of water-deficient plots after irrigation includes: The soil moisture content of the water-deficient plots after irrigation is calculated in time series to obtain the irrigation soil moisture content change data; the soil moisture distribution of the water-deficient plots is analyzed based on the irrigation soil moisture content change data to generate a soil moisture distribution map; Extract the soil structure of the water-deficient plot soil data after irrigation to generate the water-deficient plot soil structure data, wherein the water-deficient plot soil structure data includes soil physical structure data and soil chemical structure data; perform soil permeability characteristic analysis based on the soil physical structure data and soil chemical structure data to generate soil permeability characteristic data; The soil permeability characteristic data is used to detect the permeability uniformity of the soil moisture distribution map to generate soil permeability uniformity data; the soil permeability uniformity data is used to estimate the permeability depth of the soil moisture distribution map to generate soil irrigation permeability data.

7. The intelligent agricultural facility management method based on intelligent perception according to claim 5 is characterized in that: The calculation of the microbial activity level of the flooded plots through the temperature change data of the flooded plots includes: Extract the microbial monitoring data of the over-waterlogged plots to obtain the microbial monitoring data of the over-waterlogged plots; classify the microbial species of the microbial monitoring data of the over-waterlogged plots to generate beneficial microbial species data and harmful microbial species data; calculate the microbial density ratio of the plots for the beneficial microbial species data and the harmful microbial species data to obtain the microbial density ratio data of the plots; Screen the overwatered plots for plots with high harmful microorganism density according to the plot microbial density ratio data to obtain plots with high harmful microorganism density; perform microbial preferred temperature analysis on plots with high harmful microorganism density to generate harmful microorganism preferred temperature range data; The temperature change data of the flooded plots were used to calculate the activity of the microorganisms in the flooded plots, and the data of the activity of the microorganisms in the plots were obtained. The formula for calculating the activity of the microorganisms in the plots is as follows: A=α·ΔT+β·H+γ·O+δ·M; Where A is the microbial activity index, α is the weight coefficient of the temperature change rate, ΔT is the temperature change rate, β is the weight coefficient of the humidity, H is the soil moisture, γ is the weight coefficient of the oxygen concentration, O is the soil oxygen concentration, δ is the weight coefficient of the microbial density, and M is the microbial density coefficient.

8. The intelligent agricultural facility management method based on intelligent perception according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: for the normal farmland state area plot, the adjacent plot state attribute difference is judged. When the adjacent plot state is identified as the abnormal farmland state area plot, the area boundary of the normal farmland state area plot and the abnormal farmland state area plot is identified to obtain the adjacent plot area boundary data; Step S32: predicting the spread of irrigation water bodies for the plots in the normal farmland state area and the plots in the abnormal farmland state area according to the boundary data of the adjacent plots, and generating irrigation water body spread prediction data; Step S33: adjusting the direction of the irrigation facilities according to the irrigation water body spread prediction data, thereby generating irrigation facility direction management data; Step S34: Integrate the irrigation facility performance management data and the irrigation facility direction management data into an irrigation strategy to generate an irrigation facility irrigation strategy.

9. The intelligent agricultural facility management method based on intelligent perception according to claim 8 is characterized in that: Step S32 includes the following steps: Step S321: classifying the boundaries of the plots in the normal farmland state area and the plots in the abnormal farmland state area according to the boundary data of the adjacent plots, and generating the permeable boundary data and the blocking boundary data; Step S322: Calculate the land terrain slope difference of the adjacent land area boundary data through the permeable boundary data and the barrier boundary data to generate land terrain slope difference data; perform water body natural flow trend analysis on the adjacent land area boundary data based on the land terrain slope difference data to generate water body natural flow trend data; Step S323: using the experimental measurement method to perform soil moisture diffusion analysis on the boundary data of adjacent plots to generate the soil moisture diffusion coefficient of the plots; dividing the data sets of the natural flow trend data of the water body and the soil moisture diffusion coefficient to generate a model training set and a model test set; Step S324: Use the diffusion equation to train the infiltration model of the model training set to generate a water spread prediction pre-model; perform model optimization iteration on the water spread prediction pre-model according to the model test set to generate a water spread prediction model; import the adjacent plot area boundary data into the water spread prediction model to perform adjacent plot water spread prediction, thereby generating irrigation water spread prediction data.

10. A smart agricultural facility management system based on intelligent perception, characterized in that: Used to execute the intelligent agricultural facility management method based on intelligent perception as claimed in claim 1, the intelligent agricultural facility management system based on intelligent perception includes: The sensor network connection module is used to obtain farmland area survey information data; hierarchical sensor node deployment is performed on the farmland area survey information data to generate farmland sensor node deployment data; communication network connection is performed according to the farmland sensor node deployment data to generate a farmland perception network, wherein the farmland perception network includes a number of farmland sensor nodes; The irrigation performance management module is used to divide the farmland status area plots according to the farmland sensing node layout planning data through the farmland sensing network, and generate normal farmland status area plots and abnormal farmland status area plots; calculate the moisture content of the abnormal farmland status area plots to obtain the abnormal farmland area moisture content data; use the abnormal farmland area moisture content data to perform irrigation facility performance management on the abnormal farmland status area plots, and generate irrigation facility performance management data; The irrigation direction management module is used to predict the spread of irrigation water bodies in adjacent plots of land in normal farmland areas and generate irrigation water body spread prediction data; adjust the irrigation facility direction of irrigation facilities according to the irrigation water body spread prediction data, thereby generating irrigation facility direction management data; integrate the irrigation facility performance management data and the irrigation facility direction management data into irrigation strategies, and generate irrigation facility irrigation strategies; The irrigation management simulation module is used to simulate the irrigation of irrigation facilities and generate irrigation facility management simulation data; visualize the irrigation facility management simulation data and generate an irrigation facility management simulation report; and use the irrigation facility management simulation report to optimize the irrigation facility irrigation strategy to perform smart agricultural facility management operations.

Images