Digital agricultural intelligent management system and method based on Internet of Things

Abstract

The invention belongs to the technical field of digital agricultural management, and particularly relates to a digital agricultural intelligent management system and method based on the Internet of Things. Through real-time data acquisition and multi-dimensional information processing, various strategies can accurately match actual production requirements, waste of resources such as water, fertilizer and pesticide is effectively reduced, the purpose of saving cost is achieved, fertilization and prevention and control schemes are adjusted in time according to real-time crop growth states and environment changes, and therefore the influence of diseases and pests is reduced, and the crop quality is improved. Healthy growth of crops is promoted, the yield and quality are improved, stable operation of various Internet of Things devices is guaranteed through device health monitoring, management interruption or data loss caused by device faults is reduced, efficient operation of the whole intelligent agricultural system is guaranteed, and the intelligent agricultural system is safe and reliable. Spatial data integration enables a management strategy to be optimally configured according to geographical and environmental conditions of different regions, and precise agricultural management according to local conditions is realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of digital agricultural management, and particularly relates to a digital agricultural intelligent management system and method based on the Internet of Things. Background Art

[0002] Currently, agricultural production is facing multiple challenges such as resource waste, increasing environmental pressure, climate change, and frequent occurrence of pests and diseases. Traditional agricultural management methods mainly rely on experience and manual labor or use Internet of Things devices for monitoring, lacking real-time collection and comprehensive analysis of multi-dimensional data such as the environment, crops, and equipment, resulting in low utilization efficiency of water resources, fertilizers, and pesticides. At the same time, it is difficult to respond promptly to sudden environmental or equipment anomalies during the agricultural production process. In addition, traditional methods lack targeted management for regional differences and are difficult to meet the requirements of modern agriculture for precise, intelligent, and efficient management.

[0003] With the rapid development of technologies such as the Internet of Things, big data, cloud computing, and artificial intelligence, digital agriculture has gradually become an important direction for agricultural modernization. The application of Internet of Things technology enables real-time and comprehensive collection of environmental data, crop growth data, spatial data, and equipment operation data within the agricultural production area, providing a large amount of accurate data basis for agricultural management.

[0004] In the prior art, through the analysis of single or partial data, although partial automation and intelligent management have been achieved, there are still deficiencies. The prior art often fails to achieve multi-source and full-dimensional real-time monitoring of environmental, crop, spatial, and equipment operation data throughout the agricultural production process, resulting in insufficient decision-making data and unable to fully reflect the actual production situation. It usually focuses on a single link (such as only optimizing irrigation, fertilization, or pest control), lacking comprehensive consideration of multiple links such as water, fertilizer, pesticide, and equipment operation, and is difficult to coordinate the mutual influence between links, thereby reducing the overall management effect. The utilization of spatial information is insufficient, resulting in the inability to achieve precise management according to local conditions. Resource allocation and measure implementation often fail to fully adapt to different needs within the region. Summary of the Invention

[0005] The purpose of the present invention is to provide a digital agricultural intelligent management system and method based on the Internet of Things, which can achieve comprehensive collection and intelligent analysis of environmental, crop, spatial, and equipment data, thereby improving agricultural production efficiency, reducing resource waste, and promoting sustainable agricultural development.

[0006] The technical solutions adopted by the present invention are specifically as follows:

[0007] A digital agricultural intelligent management method based on the Internet of Things, comprising:

[0008] Obtain multi-dimensional data sources for agricultural production areas, where the multi-dimensional data sources include environmental data, crop data, spatial data, and equipment operation data;

[0009] Analyze the environmental data to extract soil information and meteorological information, and generate an irrigation strategy based on the soil information and meteorology;

[0010] Analyze the crop data to extract crop growth information and pest and disease information, generate a fertilization strategy based on the crop growth information and meteorological information, generate pest and disease spread path information according to the pest and disease information, generate a pesticide application strategy by combining the pest and disease spread path information and meteorological information, and fuse the fertilization strategy and the pesticide application strategy to generate a fertilization and pest control strategy;

[0011] Analyze the spatial data to extract spatial image information and geographical information, and calculate spatial weights based on the spatial image information and geographical information;

[0012] Analyze the equipment operation data to extract equipment health status information, and generate an equipment operation strategy based on the equipment health status information;

[0013] Combine the irrigation strategy, the fertilization and pest control strategy, the equipment operation strategy, and the spatial weights to generate a management strategy, and perform agricultural management operations according to the management strategy;

[0014] Construct a feedback period according to the management strategy, collect the multi-dimensional data sources within the feedback period as the updated multi-dimensional data sources, and loop through the steps of performing agricultural management operations.

[0015] In a preferred solution, the step of analyzing the environmental data to extract soil information and meteorological information and generating an irrigation strategy based on the soil information and meteorology includes:

[0016] Obtain soil information and meteorological information from the environmental data;

[0017] Construct a soil matrix according to the soil information, and extract a soil water content distribution feature matrix with a single row and multiple columns from the soil matrix;

[0018] Construct a meteorological matrix according to the meteorological information, and extract a meteorological water volume feature matrix with multiple rows and a single column from the meteorological matrix;

[0019] Obtain the soil moisture trend value according to the soil water content distribution feature matrix and the meteorological water volume feature matrix;

[0020] Obtain an irrigation trend table, where the irrigation trend table includes multiple soil moisture trend intervals and the corresponding irrigation strategies for each soil moisture trend interval;

[0021] Obtain the corresponding irrigation strategy from the irrigation trend table according to the soil moisture trend interval where the soil moisture trend value is located.

[0022] In a preferred embodiment, the steps of analyzing crop data to extract crop growth information and pest and disease information, generating a fertilization strategy based on the crop growth information and meteorological information, generating pest and disease spread path information according to the pest and disease information, generating a pesticide application strategy by combining the pest and disease spread path information and meteorological information, and integrating the fertilization strategy and the pesticide application strategy to generate a fertilization and pest control strategy include:

[0023] Obtain crop growth information and pest and disease information from the crop data;

[0024] Construct a crop growth matrix based on the crop growth information and a meteorological matrix based on the meteorological information;

[0025] Obtain crop fertilization information based on the crop growth matrix and the meteorological matrix, and obtain the corresponding fertilization strategy according to the crop fertilization information;

[0026] Obtain the corresponding pest and disease matrix according to the pest and disease information, extract the pest and disease spread distribution range from the pest and disease matrix, and obtain the pest and disease spread path according to the pest and disease spread distribution range;

[0027] Obtain the corresponding pest and disease spread vector according to the pest and disease spread path, and obtain the corresponding meteorological vector according to the meteorological information;

[0028] Obtain the pest and disease killing value according to the pest and disease spread vector and the meteorological vector;

[0029] Obtain a pesticide application table, where the pesticide application table includes multiple pest and disease killing intervals and the corresponding pesticide application strategies for each pest and disease killing interval;

[0030] Obtain the corresponding pesticide application strategy from the pesticide application table according to the pest and disease killing interval corresponding to the pest and disease killing value;

[0031] Obtain a fertilization and pest control strategy according to the fertilization strategy and the pesticide application strategy.

[0032] In a preferred embodiment, the steps of obtaining a fertilization and pest control strategy according to the fertilization strategy and the pesticide application strategy include:

[0033] Obtain the corresponding fertilization matrix according to the fertilization strategy, and extract the fertilization vector from the fertilization matrix;

[0034] Obtain the corresponding pesticide application matrix according to the pesticide application strategy, and extract the pesticide application vector from the pesticide application matrix;

[0035] Obtain the fertilization and pest control value according to the fertilization vector and the pesticide application vector;

[0036] Obtain a fertilization and pest control table, where the fertilization and pest control table includes multiple fertilization and pest control intervals and the corresponding fertilization and pest control strategies for each fertilization and pest control interval;

[0037] Obtain the corresponding fertilization and pest control strategy from the fertilization and pest control table according to the fertilization and pest control interval corresponding to the fertilization and pest control value.

[0038] In a preferred embodiment, the steps of parsing spatial data to extract spatial image information and geographic information and calculating spatial weights based on the spatial image information and geographic information include:

[0039] Obtain spatial image information and geographic information according to the spatial data;

[0040] Obtain the crop distribution image according to the spatial image information;

[0041] Construct a plane rectangular coordinate system in the crop distribution image;

[0042] Obtain the coordinates of multiple inflection points of the crop distribution contour according to the plane rectangular coordinate system;

[0043] Obtain the crop distribution value according to the coordinates of multiple inflection points of the crop distribution contour;

[0044] Obtain the corresponding geographic matrix according to the geographic information, and obtain the corresponding geographic weight according to the geographic matrix;

[0045] Obtain the spatial weight according to the crop distribution value and the geographic weight.

[0046] In a preferred embodiment, the steps of parsing device operation data to extract device health status information and generating a device operation strategy based on the device health status information include:

[0047] Obtain the device health status information according to the device operation data;

[0048] Obtain the corresponding device health status matrix according to the device health status information;

[0049] Obtain the device health status value according to the device health status matrix;

[0050] Obtain the device operation table, where the device operation table includes multiple device health status intervals and the corresponding device operation strategies for each device health status interval;

[0051] Obtain the corresponding device operation strategy from the device operation table according to the device health status interval corresponding to the device health status value.

[0052] In a preferred embodiment, the steps of generating a management strategy by combining an irrigation strategy, a fertilization and pest control strategy, a device operation strategy, and a spatial weight and performing agricultural management operations according to the management strategy include:

[0053] Obtain the corresponding irrigation vector, fertilization and pest control vector, and device operation vector according to the irrigation strategy, fertilization and pest control strategy, and device operation strategy respectively;

[0054] Obtain a comprehensive management value based on the irrigation vector, the fertilization and pest control vector, the equipment operation vector, and the spatial weight;

[0055] Obtain a management table, where the management table includes multiple comprehensive management intervals and the management strategies corresponding to each comprehensive management interval;

[0056] Obtain the corresponding management strategy from the management table according to the comprehensive management interval corresponding to the comprehensive management value;

[0057] Execute agricultural management operations according to the management strategy.

[0058] In a preferred solution, construct a feedback period according to the management strategy, collect multi-dimensional data sources within the feedback period as updated multi-dimensional data sources, and loop through the steps of executing agricultural management operations, including:

[0059] Obtain the corresponding management matrix according to the management strategy;

[0060] Obtain multiple time period management vectors according to the management matrix;

[0061] Obtain a time period value according to multiple time period management vectors;

[0062] Obtain a duration table, where the duration table includes multiple time period intervals and the feedback durations corresponding to each time period interval;

[0063] Obtain the corresponding feedback duration from the duration table according to the time period interval corresponding to the time period value;

[0064] Obtain the time node for executing agricultural management operations according to the management strategy and mark it as the start time of the feedback duration;

[0065] Obtain the end time according to the start time of the feedback duration and the feedback duration, and construct a feedback period;

[0066] Obtain the multi-dimensional data source within the feedback period and return it as a new multi-dimensional data source to the step of obtaining the multi-dimensional data source of the agricultural production area.

[0067] The present invention also provides a digital agricultural intelligent management system based on the Internet of Things for the above-mentioned digital agricultural intelligent management method based on the Internet of Things, including:

[0068] A multi-source module for obtaining the multi-dimensional data source of the agricultural production area, where the multi-dimensional data source includes environmental data, crop data, spatial data, and equipment operation data;

[0069] An irrigation module for parsing environmental data to extract soil information and meteorological information, and generating an irrigation strategy based on the soil information and meteorology;

[0070] A fertilization and pest control module, which is used to analyze crop data to extract crop growth information and pest and disease information, generate a fertilization strategy based on the crop growth information and meteorological information, generate pest and disease diffusion path information according to the pest and disease information, generate a pesticide application strategy by combining the pest and disease diffusion path information and meteorological information, and generate a fertilization and pest control strategy by integrating the fertilization strategy and the pesticide application strategy;

[0071] A space module, which is used to analyze space data to extract space image information and geographical information, and calculate space weights based on the space image information and geographical information;

[0072] An equipment operation module, which is used to analyze equipment operation data to extract equipment health status information, and generate an equipment operation strategy based on the equipment health status information;

[0073] A management module, which is used to generate a management strategy by combining an irrigation strategy, a fertilization and pest control strategy, an equipment operation strategy and space weights, and perform agricultural management operations according to the management strategy;

[0074] A feedback module, which is used to construct a feedback period according to the management strategy, obtain multi-dimensional data sources within the feedback period, and return them as new multi-dimensional data sources to the multi-source module.

[0075] And, an Internet of Things-based digital agriculture intelligent management terminal, including:

[0076] One or more processors;

[0077] A storage device, on which one or more programs are stored;

[0078] When one or more programs are executed by one or more processors, the one or more processors implement an Internet of Things-based digital agriculture intelligent management method.

[0079] The technical effects achieved by the present invention are:

[0080] In the present invention, through real-time data collection and multi-dimensional information processing, each strategy can accurately match the actual production requirements, effectively reduce the waste of resources such as water, fertilizer, and pesticides, achieve the purpose of cost savings, timely adjust the fertilization and prevention and control plans according to the real-time crop growth status and environmental changes, thereby reducing the impact of pests and diseases, promoting the healthy growth of crops, improving the yield and quality, the equipment health monitoring ensures the stable operation of various Internet of Things devices, reduces management interruptions or data loss caused by equipment failures, and guarantees the efficient operation of the entire intelligent agriculture system. The integration of space data enables the management strategy to be optimally configured according to the geographical and environmental conditions of different regions, realizing precise agriculture management adapted to local conditions. Description of the Drawings

[0081] Figure 1 is the method flow chart provided by the present invention;

[0082] Figure 2 It is a system module diagram provided by the present invention. DETAILED DESCRIPTION

[0083] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0084] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0085] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure or characteristic that may be included in at least one implementation of the present invention. The phrase "in a preferred embodiment" that appears in different places in this specification does not refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0086] Secondly, the present invention is described in detail in conjunction with schematic diagrams. When describing the embodiments of the present invention in detail, for the convenience of explanation, the schematic diagrams are only examples and should not limit the scope of protection of the present invention.

[0087] Please see attached Figure 1 As shown, a digital agriculture intelligent management method based on the Internet of Things is provided, including:

[0088] S1. Acquire a multidimensional data source of an agricultural production area, wherein the multidimensional data source includes environmental data, crop data, spatial data, and equipment operation data;

[0089] S2, parsing environmental data to extract soil information and meteorological information, and generating irrigation strategies based on the soil information and meteorological information;

[0090] S3. Analyze crop data to extract crop growth information and pest and disease information, generate fertilization strategies based on crop growth information and meteorological information, generate pest and disease diffusion path information based on pest and disease information, generate pesticide application strategies based on pest and disease diffusion path information and meteorological information, and integrate fertilization strategies and pesticide application strategies to generate fertilization and pest control strategies;

[0091] S4, parsing the spatial data to extract spatial image information and geographic information, and calculating spatial weights based on the spatial image information and geographic information;

[0092] S5. parse the device operation data to extract device health status information, and generate a device operation strategy based on the device health status information;

[0093] S6. Combine the irrigation strategy, fertilization and pest control strategy, equipment operation strategy and spatial weight to generate a management strategy, and execute agricultural management operations according to the management strategy;

[0094] S7. Construct a feedback period according to the management strategy, collect multi-dimensional data sources within the feedback period as the updated multi-dimensional data sources, and loop through the steps of executing agricultural management operations.

[0095] In the above steps S1 to S7, various sensors and monitoring devices are deployed in the agricultural production area using Internet of Things technology to collect environmental data, crop growth data, spatial information and equipment operation data in real time. According to the collected environmental data, soil and meteorological information are extracted, and these information are used to evaluate parameters such as soil humidity, temperature, rainfall, etc., so as to formulate a precise irrigation strategy, which not only avoids waste of water resources but also ensures sufficient water supply for crops. Obtain the current growth state of the crop according to the crop growth data, and at the same time monitor the pest and disease situation. Use the crop growth and meteorological information to determine the fertilization requirements. Through pests and diseases Harm expansion Scatter paths and meteorological information, plan the pesticide application plan, integrate the fertilization and pesticide application strategies to form an overall fertilization and pest control strategy. Combine the spatial image information and geographical information to evaluate factors such as terrain and vegetation coverage in different regions, and obtain spatial weights, which enables the management strategy to better adapt to regional differences and achieve local management. Detect the working status of the equipment through the equipment operation data, discover faults or anomalies in time, and formulate an equipment operation strategy to ensure the continuous and stable operation of various Internet of Things devices. Integrate the irrigation, fertilization and pest control, equipment operation strategies and spatial weights to formulate an overall agricultural management strategy and execute it. Use the feedback data after the execution of the management strategy to form a new multi-dimensional data source and return to the initial data collection link, so as to continuously correct and optimize various strategies, realize dynamic and adaptive intelligent management. Through real-time data collection and multi-dimensional information processing, each strategy can accurately match the actual production needs, effectively reduce the waste of resources such as water, fertilizer, and pesticides, and achieve the purpose of cost savings. According to the real-time crop growth status and environmental changes, timely adjust the fertilization and prevention and control plans, so as to reduce the impact of pests and diseases, promote the healthy growth of crops, improve the yield and quality. Equipment health monitoring ensures the stable operation of various Internet of Things devices, reduces management interruptions or data loss caused by equipment failures, and ensures the efficient operation of the entire intelligent agriculture system. Spatial data integration enables the management strategy to be optimally configured according to the geographical and environmental conditions of different regions, and realizes precise agricultural management adapted to local conditions.

[0096] In a preferred embodiment, the steps of parsing environmental data to extract soil information and meteorological information and generating an irrigation strategy based on the soil information and meteorology include:

[0097] S201. Obtain soil information and meteorological information from environmental data;

[0098] S202. Construct a soil matrix based on the soil information, and extract a soil water content distribution feature matrix with a single row and multiple columns from the soil matrix;

[0099] S203. Construct a meteorological matrix based on the meteorological information, and extract a meteorological water volume feature matrix with multiple rows and a single column from the meteorological matrix;

[0100] S204. Obtain the soil moisture trend value according to the soil water content distribution feature matrix and the meteorological water volume feature matrix;

[0101] S205. Obtain an irrigation trend table, where the irrigation trend table includes multiple soil moisture trend intervals and the corresponding irrigation strategies for each soil moisture trend interval;

[0102] S206. Obtain the corresponding irrigation strategy from the irrigation trend table according to the soil moisture trend interval where the soil moisture trend value is located.

[0103] In the above steps S201 to S206, soil information and meteorological information are extracted from environmental data. A soil matrix is constructed using the soil information, and a "soil water content distribution feature matrix" is extracted from the soil matrix. This matrix is a single-row and multi-column matrix that can reflect the water content distribution of each area of the soil. A meteorological matrix is constructed using the meteorological information, and a "meteorological water volume feature matrix" is extracted from the meteorological matrix. This matrix is a multi-row and single-column matrix used to reflect the water status under the current meteorological conditions (such as rainfall, humidity, etc.). The two feature matrices extracted from the soil and meteorological data are subjected to data fusion and processing to calculate the soil moisture trend value. The calculation formula for the soil moisture trend value is Q = T * S, where Q represents the soil moisture trend value, T represents the soil water content distribution feature matrix, and S represents the meteorological water volume feature matrix. An irrigation trend table containing multiple soil moisture trend intervals is constructed, and each interval corresponds to a preset irrigation strategy. This table is equivalent to a decision rule library, which matches corresponding irrigation measures according to different soil moisture conditions. According to the calculated soil moisture trend value, determine the trend interval to which it belongs, and thus find the corresponding irrigation strategy in the irrigation trend table. By constructing the soil and meteorological feature matrices, the soil water content and meteorological water volume can be quantified, ensuring that the irrigation strategy is based on scientific data analysis, thereby achieving precise irrigation and avoiding blind or excessive irrigation. Reasonable water management helps to maintain the balance of soil moisture, provides a suitable growth environment for crop growth, and thus improves the health level and overall yield of crops.

[0104] In a preferred embodiment, the steps of parsing crop data to extract crop growth information and pest and disease information, generating a fertilization strategy based on the crop growth information and meteorological information, generating pest and disease spread path information according to the pest and disease information, generating a pesticide application strategy by combining the pest and disease spread path information and meteorological information, and integrating the fertilization strategy and the pesticide application strategy to generate a fertilization and pest control strategy include:

[0105] S301. Obtain crop growth information and pest and disease information from the crop data;

[0106] S302. Construct a crop growth matrix according to the crop growth information and construct a meteorological matrix according to the meteorological information;

[0107] S303. Obtain crop fertilization information according to the crop growth matrix and the meteorological matrix, and obtain the corresponding fertilization strategy according to the crop fertilization information;

[0108] S304. Obtain the corresponding pest and disease matrix according to the pest and disease information, extract the pest and disease spread distribution range according to the pest and disease matrix, and obtain the pest and disease spread path according to the pest and disease spread distribution range;

[0109] S305. Obtain the corresponding pest and disease spread vector according to the pest and disease spread path and obtain the corresponding meteorological vector according to the meteorological information;

[0110] S306. Obtain the pest and disease killing value according to the pest and disease spread vector and the meteorological vector;

[0111] S307. Obtain a pesticide application table, where the pesticide application table includes multiple pest and disease killing intervals and the corresponding pesticide application strategies for each pest and disease killing interval;

[0112] S308. Obtain the corresponding pesticide application strategy from the pesticide application table according to the pest and disease killing interval corresponding to the pest and disease killing value;

[0113] S309. Obtain a fertilization and pest control strategy according to the fertilization strategy and the pesticide application strategy.

[0114] In the above steps S301 to S309, a crop monitoring device or sensor is used to obtain crop growth status and pest and disease information. A crop growth matrix is constructed from the crop growth information to quantify the growth data of the crop, reflecting information such as growth trends and development stages. At the same time, a meteorological matrix is constructed based on meteorological information to standardize environmental factor data such as rainfall, temperature, and humidity, facilitating integration with crop data. Using the crop growth matrix and the meteorological matrix, key indicators are extracted to evaluate the nutrient requirements of the crop, generating crop fertilization information, and then matching and formulating corresponding fertilization strategies to achieve precise fertilizer supply. A pest and disease matrix is constructed based on pest and disease information to quantify and analyze the distribution and spread range of pests and diseases, extract the spread range of pests and diseases, and further obtain the pest and disease spread path. The pest and disease spread path is converted into a pest and disease spread vector, and a meteorological vector is extracted in combination with meteorological information. Based on these two vectors, a pest and disease killing value is calculated to reflect the threat degree of pest and disease spread under the current environmental conditions. The calculation formula for the pest and disease killing value is M = K * L, where M represents the pest and disease killing value, K represents the pest and disease spread vector, and L represents the meteorological vector. A pesticide application table is constructed, setting multiple pest and disease killing intervals, each interval corresponding to a preset pesticide application strategy. According to the calculated pest and disease killing value, determine the interval it belongs to and match the corresponding pesticide application strategy to ensure that the prevention and control plan is targeted and effective. The fertilization strategy and the pesticide application strategy are organically combined to form a comprehensive fertilization and pest control strategy, so as to effectively inhibit the spread of pests and diseases while meeting the nutrient requirements of the crop, ensuring the healthy growth of the crop. By converting crop growth and pest and disease data into matrix form and then integrating them with meteorological data, data-driven precise decision-making is realized, reducing human judgment errors and improving management efficiency. Adjusting the fertilization and pesticide application plans based on real-time meteorological data ensures that the management strategy can quickly respond to environmental changes, effectively deal with sudden pests and diseases or climate anomalies, and ensure agricultural production safety. Through precise fertilizer supply and scientific pest control, overuse of chemical fertilizers and pesticides can be avoided, production costs can be reduced, and at the same time, the adverse impact on the environment can be reduced, realizing the sustainable utilization of resources.

[0115] In a preferred embodiment, the steps of obtaining a fertilization and pest control strategy according to the fertilization strategy and the pesticide application strategy include:

[0116] S3091. Obtain the corresponding fertilization matrix according to the fertilization strategy, and extract a fertilization vector from the fertilization matrix;

[0117] S3092. Obtain the corresponding pesticide application matrix according to the pesticide application strategy, and extract a pesticide application vector from the pesticide application matrix;

[0118] S3093. Obtain a fertilization and pest control value according to the fertilization vector and the pesticide application vector;

[0119] S3094. Obtain a fertilization and pest control table, where the fertilization and pest control table includes multiple fertilization and pest control intervals and the corresponding fertilization and pest control strategies for each fertilization and pest control interval;

[0120] S3095. Obtain the corresponding fertilization and pest control strategy from the fertilization and pest control table according to the fertilization and pest control interval corresponding to the fertilization and pest control value.

[0121] In the above steps S3091 to S3095, obtain the corresponding fertilization matrix from the fertilization strategy and extract the fertilization vector. The fertilization matrix contains various key fertilization indicators and is converted into data in vector form. Similarly, obtain the corresponding pesticide application matrix from the pesticide application strategy and extract the pesticide application vector. Combine and calculate the fertilization vector and the pesticide application vector to obtain a fertilization and pest control value, which reflects the comprehensive balance degree between nutrient supply and pest control in the crop growth environment under the current fertilization and pesticide application strategies. The calculation formula for the fertilization and pest control value is In the formula, P represents the fertilization and pest control value, J represents the fertilization vector, and H represents the pesticide application vector. Construct a fertilization and pest control table, which is divided into multiple fertilization and pest control intervals, and each interval corresponds to a preset comprehensive fertilization and pest control strategy. Based on the calculated fertilization and pest control value, determine the pest control interval to which it belongs, and extract the corresponding strategy from the fertilization and pest control table as the final fertilization and pest control decision. By integrating the data of the two separate strategies of fertilization and pesticide application, the synergistic effect between the two can be scientifically evaluated, avoiding the imbalance situation that may be caused by a single strategy, ensuring that the crop can obtain sufficient nutrients while effectively controlling pests and diseases. Using the mathematical processing methods of matrices and vectors, the entire decision-making process is automated, reducing manual intervention and improving the scientificity and real-time nature of the decision-making, so as to quickly respond to environmental changes.

[0122] In a preferred embodiment, the steps of parsing spatial data to extract spatial image information and geographic information and calculating the spatial weight based on the spatial image information and geographic information include:

[0123] S401. Obtain the spatial image information and geographic information according to the spatial data;

[0124] S402. Obtain the crop distribution image according to the spatial image information;

[0125] S403. Construct a plane rectangular coordinate system in the crop distribution image;

[0126] S404. Obtain the coordinates of multiple inflection points of the crop distribution contour according to the plane rectangular coordinate system;

[0127] S405. Obtain the crop distribution value according to the coordinates of multiple inflection points of the crop distribution contour;

[0128] S406. Obtain the corresponding geographical matrix according to the geographical information, and obtain the corresponding geographical weight according to the geographical matrix;

[0129] S407. Obtain the spatial weight according to the crop distribution value and the geographical weight.

[0130] As in the above steps S401 to S407, extract spatial image information and geographical information from the spatial data. These information can come from multi-source data such as satellite remote sensing and drone shooting. Use the spatial image information to generate a crop distribution image, and identify the crop coverage in the agricultural area through image processing technology. Construct a plane rectangular coordinate system in the crop distribution image. Based on this coordinate system, extract the coordinates of multiple inflection points on the crop distribution contour. These inflection points reflect the boundary and morphological characteristics of the crop distribution. Use these inflection point coordinates to calculate the crop distribution value. The calculation formula of the crop distribution value is where F represents the crop distribution value, h represents the number of the inflection point coordinates of the crop distribution contour, h = 1, 2, 3... t, X h represents the x-axis coordinate point of the h-th inflection point of the crop distribution contour, X h+1 represents the x-axis coordinate point of the (h + 1)-th inflection point of the crop distribution contour, Y h represents the y-axis coordinate point of the h-th inflection point of the crop distribution contour, Y h+1 represents the y-axis coordinate point of the (h + 1)-th inflection point of the crop distribution contour. When h takes the value of t, t + 1 represents 1. Construct a geographical matrix according to the obtained geographical information, and extract the geographical weight from it. The geographical weight may involve factors such as regional terrain, soil type, slope, etc., reflecting the potential impact of the geographical environment on crop growth. Combine the crop distribution value with the geographical weight to calculate the final spatial weight. The calculation formula of the spatial weight is k = F * d. In the formula, k represents the spatial weight, F represents the crop distribution value, and d represents the geographical weight. Through the quantitative crop distribution value and geographical weight, the agricultural production status of different regions can be distinguished, which helps to formulate management strategies more in line with regional characteristics and achieve precise agricultural management according to local conditions. The calculation of the spatial weight provides a basis for the optimal allocation of agricultural resources (such as irrigation, fertilization, pest control, etc.), enabling resources to be more scientifically allocated to regions with higher crop demand or better geographical conditions, thereby improving the overall efficiency.

[0131] In a preferred embodiment, the steps of analyzing the device operation data to extract the device health status information and generating the device operation strategy based on the device health status information include:

[0132] S501. Obtain the device health status information according to the device operation data;

[0133] S502. Obtain the corresponding device health status matrix according to the device health status information;

[0134] S503. Obtain the device health status value according to the device health status matrix;

[0135] S504. Obtain the device operation table, where the device operation table includes multiple device health status intervals and the corresponding device operation strategies for each device health status interval;

[0136] S505. Obtain the corresponding device operation strategy from the device operation table according to the device health status interval corresponding to the device health status value.

[0137] In the above steps S501 to S505, collect various key parameters from the device operation data, such as temperature, vibration, energy consumption, error logs, etc., comprehensively judge the current health status of the device, generate health status information, organize and convert the collected device health status information into a standardized device health status matrix, which can uniformly represent different device status indicators, process the device health status matrix, extract or calculate a comprehensive device health status value, which is usually an overall score calculated by weighting multiple indicators, reflecting the overall health level of the device, pre-construct a device operation table, which is divided according to different device health status intervals, and preset corresponding device operation strategies (such as normal operation, early warning maintenance, emergency repair, etc.) for each interval, according to the device health status value, judge the health status interval it belongs to, and match the corresponding device operation strategy from the device operation table, providing a scientific maintenance and control plan for the subsequent operation of the device. By real-time monitoring the device health status and automatically matching the maintenance strategy, potential faults can be discovered in time, measures can be taken in advance, the risk of sudden device failures can be reduced, and the service life of the device can be extended.

[0138] In a preferred embodiment, the steps of generating a management strategy by combining the irrigation strategy, fertilization and pest control strategy, device operation strategy and spatial weight, and performing agricultural management operations according to the management strategy include:

[0139] S601. Obtain the corresponding irrigation vector, fertilization and pest control vector, and device operation vector according to the irrigation strategy, fertilization and pest control strategy, and device operation strategy respectively;

[0140] S602. Obtain the comprehensive management value according to the irrigation vector, fertilization and pest control vector, device operation vector and spatial weight;

[0141] S603. Obtain the management table, where the management table includes multiple comprehensive management intervals and the corresponding management strategies for each comprehensive management interval;

[0142] S604. Obtain the corresponding management strategy from the management table according to the comprehensive management interval corresponding to the comprehensive management value;

[0143] S605. Perform agricultural management operations according to management strategies.

[0144] In the above steps S601 to S605, the irrigation vector extracts key data reflecting water supply regulation from existing irrigation strategies, the fertilization and pest control vector extracts numerical expressions of crop nutrients and pest control from fertilization and pest control strategies, and the equipment operation vector extracts data on equipment status and maintenance regulation from equipment operation strategies. These vectors transform each strategy into standardized and numerical information, facilitating subsequent integration and comparison. By combining the above three vectors with spatial weights, through a mathematical model or weighted calculation method, a comprehensive management value is obtained. This value reflects the overall status and requirements of agricultural production management under existing strategies and regional characteristics. The calculation formula for the comprehensive management value is Z = G * C * B * k, where Z represents the comprehensive management value, G represents the irrigation vector, C represents the fertilization and pest control vector, B represents the equipment operation vector, and k represents the spatial weight. A management table is preset, which divides the comprehensive management value into several intervals, and each interval corresponds to specific management strategies, covering various measures such as optimized irrigation, precision fertilization, and equipment maintenance. According to the calculated comprehensive management value, determine the interval it belongs to, and match the corresponding management strategy from the management table to ensure that the decision-making is targeted and real-time. According to the matched management strategy, automatically or semi-automatically regulate the agricultural production process, including water resource allocation, nutrient supply, pest control, and equipment operation and maintenance, so as to realize the intelligence and precision of overall agricultural management. By integrating multiple strategy data, ensure the coordination of water, fertilizer, pesticide, and equipment management, achieve the optimal agricultural production plan, improve the overall operation efficiency, and consider irrigation, fertilization and pest control, and equipment operation together, which can provide a more stable and suitable growth environment for crops, thereby improving crop health, yield and quality.

[0145] In a preferred embodiment, construct a feedback period according to the management strategy, collect multi-dimensional data sources within the feedback period as updated multi-dimensional data sources, and loop through the steps of performing agricultural management operations, including:

[0146] S701. Obtain the corresponding management matrix according to the management strategy;

[0147] S702. Obtain multiple period management vectors according to the management matrix;

[0148] S703. Obtain a period value according to multiple period management vectors;

[0149] S704. Obtain a duration table, where the duration table includes multiple period intervals and the corresponding feedback durations for each period interval;

[0150] S705. Obtain the corresponding feedback duration from the duration table according to the period interval corresponding to the period value;

[0151] S706. Obtain the time node for performing agricultural management operations according to the management strategy, and mark it as the start time of the feedback duration;

[0152] S707. Obtain the end time based on the start time of the feedback duration and the feedback duration, and construct a feedback period;

[0153] S708. Obtain the multi-dimensional data source within the feedback period, and return it as a new multi-dimensional data source to the step of obtaining the multi-dimensional data source of the agricultural production area.

[0154] In the above steps S701 to S708, extract the management matrix from the current management strategy. This matrix contains key indicators for implementing the strategy. According to the management matrix, further generate multiple time period management vectors. Each vector corresponds to the effect or status of the strategy implementation within a different time period. Calculate the multiple time period management vectors comprehensively to obtain an overall time period value, which is used to reflect the effect distribution of the management strategy in the time dimension. The calculation formula for the time period value is In the formula, D represents the time period value, d represents the number of multiple time period management vectors, d = 1, 2, 3... m, R d represents the d-th time period management vector. Pre-construct a duration table, divide the time period value into several intervals, and set corresponding feedback durations for each interval. According to the calculated time period value, determine the time period interval to which it belongs, and match the corresponding feedback duration from the duration table to clarify the time span of subsequent data collection. Based on the time node during the implementation of the management strategy, mark the start time of the feedback duration to provide a starting reference for the construction of the feedback period. Combine the start time and the feedback duration to calculate the end time of the feedback period and construct a complete feedback period. Within the constructed feedback period, collect multi-dimensional data (such as environmental, crop, equipment, spatial data, etc.), and return these data as a new multi-dimensional data source to the original data acquisition link to achieve a data feedback closed-loop, providing an updated and accurate data basis for the next round of management strategy optimization, being able to continuously update the data source, form a dynamic adaptive closed-loop, and thus continuously correct and optimize the management plan. Data collection within the feedback period can monitor the implementation effect of the strategy in real time, promptly detect deviations or anomalies, and ensure the flexibility and adjustment ability during the agricultural management process.

[0155] Please refer to the appendix Figure 2 As shown, the present invention also provides an Internet of Things-based digital agriculture intelligent management system for the above Internet of Things-based digital agriculture intelligent management method, including:

[0156] A multi-source module for obtaining the multi-dimensional data source of the agricultural production area, where the multi-dimensional data source includes environmental data, crop data, spatial data, and equipment operation data;

[0157] Irrigation module, which is used to analyze environmental data to extract soil information and meteorological information, and generate an irrigation strategy based on the soil information and meteorology;

[0158] Fertilization and pest control module, which is used to analyze crop data to extract crop growth information and pest and disease information, generate a fertilization strategy based on the crop growth information and meteorological information, generate pest and disease diffusion path information according to the pest and disease information, generate a pesticide application strategy by combining the pest and disease diffusion path information and meteorological information, and fuse the fertilization strategy and the pesticide application strategy to generate a fertilization and pest control strategy;

[0159] Spatial module, which is used to analyze spatial data to extract spatial image information and geographical information, and calculate spatial weights based on the spatial image information and geographical information;

[0160] Equipment operation module, which is used to analyze equipment operation data to extract equipment health status information, and generate an equipment operation strategy based on the equipment health status information;

[0161] Management module, which is used to generate a management strategy by combining the irrigation strategy, the fertilization and pest control strategy, the equipment operation strategy and the spatial weights, and perform agricultural management operations according to the management strategy;

[0162] Feedback module, which is used to construct a feedback period according to the management strategy, obtain multi-dimensional data sources within the feedback period, and return them as new multi-dimensional data sources to the multi-source module.

[0163] As described above, the multi-source module deploys various sensors, cameras, and monitoring devices within the agricultural production area to collect environmental data, crop data, spatial data, and equipment operation data in real time. The irrigation module extracts soil information and meteorological information from the environmental data, obtains parameters such as soil humidity, temperature, and precipitation, determines the water demand using the soil and meteorological information, formulates a precise irrigation plan, and realizes the reasonable regulation of water resources. The fertilization and pest control module obtains the crop growth status and pest and disease information through the crop data, judges the crop nutrient demand and prevention and control demand, formulates fertilization strategies and pesticide application strategies respectively in combination with the meteorological information, and then integrates the two to generate a comprehensive fertilization and pest control strategy that not only meets the crop nutrient supply but also prevents and controls pests and diseases. The spatial module uses the spatial data to obtain remote sensing images and geographical information, constructs a crop distribution image through image processing technology and coordinate systems, calculates the spatial weight of the area in combination with the crop distribution and geographical matrix data, and provides a basis for regional differentiation for subsequent management. The equipment operation module monitors indicators such as equipment temperature, vibration, and energy consumption by collecting equipment operation data, evaluates the equipment health status, constructs an equipment health status matrix based on the health status information, calculates the comprehensive health value, and matches the preset equipment operation strategy to ensure that the equipment is always in the best working state. The management module vectorizes the irrigation, fertilization and pest control, equipment operation strategies, and spatial weight data, and obtains a comprehensive management value through weighted calculation. It searches for the corresponding management strategy in the management table according to the comprehensive management value, and automatically or semi-automatically adjusts various agricultural management measures to achieve precise and real-time agricultural production scheduling. The feedback module generates a management matrix based on the execution situation of the current management strategy, extracts the time period management vector and calculates the time period value, and then determines the feedback duration. It re-collects multi-dimensional data within the feedback time period and returns these data as new data sources to the multi-source module to provide the latest information for the next round of decision-making, forming a data-driven continuous optimization closed-loop, realizing precise control of multiple links such as water, fertilizer, pesticides, and equipment operation, ensuring that each management measure can meet the actual crop growth needs, reducing resource waste, being able to quickly respond to environmental changes and equipment status fluctuations, dynamically adjusting management strategies, and improving the emergency response ability.

[0164] And, a digital agricultural intelligent management terminal based on the Internet of Things, comprising:

[0165] One or more processors;

[0166] A storage device on which one or more programs are stored;

[0167] When the one or more programs are executed by the one or more processors, the one or more processors implement the digital agricultural intelligent management method based on the Internet of Things.

[0168] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention. The structures, devices, and operation methods not specifically described and explained in the present invention are implemented according to the conventional means in the art without special explanation and limitation.

Claims

1. A digital agriculture intelligent management method based on the Internet of Things, characterized in that, Including: Obtain multi-dimensional data sources of agricultural production areas, where the multi-dimensional data sources include environmental data, crop data, spatial data, and equipment operation data; Analyze the environmental data to extract soil information and meteorological information, and generate an irrigation strategy based on the soil information and meteorology; Analyze the crop data to extract crop growth information and pest and disease information, generate a fertilization strategy based on the crop growth information and meteorological information, generate pest and disease diffusion path information according to the pest and disease information, generate a pesticide application strategy by combining the pest and disease diffusion path information and meteorological information, and fuse the fertilization strategy and the pesticide application strategy to generate a fertilization and pest control strategy; Analyze the spatial data to extract spatial image information and geographical information, and calculate spatial weights based on the spatial image information and geographical information; Analyze the equipment operation data to extract equipment health status information, and generate an equipment operation strategy based on the equipment health status information; Combine the irrigation strategy, fertilization and pest control strategy, equipment operation strategy, and spatial weights to generate a management strategy, and perform agricultural management operations according to the management strategy; Construct a feedback period according to the management strategy, collect the multi-dimensional data sources within the feedback period as updated multi-dimensional data sources, and loop through the steps of performing agricultural management operations.

2. The digital agriculture intelligent management method based on the Internet of Things according to claim 1, characterized in that The steps of analyzing the environmental data to extract soil information and meteorological information, and generating an irrigation strategy based on the soil information and meteorology include: Obtain soil information and meteorological information from the environmental data; Construct a soil matrix according to the soil information, and extract a soil water content distribution feature matrix with a single row and multiple columns from the soil matrix; Construct a meteorological matrix according to the meteorological information, and extract a meteorological water volume feature matrix with multiple rows and a single column from the meteorological matrix; Obtain the soil moisture trend value according to the soil water content distribution feature matrix and the meteorological water volume feature matrix; Obtain an irrigation trend table, where the irrigation trend table includes multiple soil moisture trend intervals and the corresponding irrigation strategies for each soil moisture trend interval; Obtain the corresponding irrigation strategy from the irrigation trend table according to the soil moisture trend interval where the soil moisture trend value is located.

3. The digital agriculture intelligent management method based on the Internet of Things according to claim 1, characterized in that, The steps of analyzing the crop data to extract crop growth information and pest and disease information, generating a fertilization strategy based on the crop growth information and meteorological information, generating pest and disease diffusion path information according to the pest and disease information, generating a pesticide application strategy by combining the pest and disease diffusion path information and meteorological information, and fusing the fertilization strategy and the pesticide application strategy to generate a fertilization and pest control strategy include: Obtain crop growth information and pest and disease information from the crop data; Construct a crop growth matrix according to the crop growth information and a meteorological matrix according to the meteorological information; Obtain crop fertilization information according to the crop growth matrix and the meteorological matrix, and obtain the corresponding fertilization strategy according to the crop fertilization information; Obtain the corresponding pest and disease matrix according to the pest and disease information, extract the pest and disease diffusion distribution range from the pest and disease matrix, and obtain the pest and disease diffusion path according to the pest and disease diffusion distribution range; Obtain the corresponding pest and disease diffusion vector according to the pest and disease diffusion path and the corresponding meteorological vector according to the meteorological information; Obtain the pest and disease killing value according to the pest and disease diffusion vector and the meteorological vector; Obtain a pesticide application table, where the pesticide application table includes multiple pest and disease killing intervals and the corresponding pesticide application strategies for each pest and disease killing interval; Obtain the corresponding pesticide application strategy from the pesticide application table according to the pest control range corresponding to the pest control value; Obtain the fertilization and pest control strategy according to the fertilization strategy and the pesticide application strategy.

4. The digital agriculture intelligent management method based on the Internet of Things according to claim 3, wherein, The steps of obtaining the fertilization and pest control strategy according to the fertilization strategy and the pesticide application strategy include: Obtain the corresponding fertilization matrix according to the fertilization strategy, and extract the fertilization vector from the fertilization matrix; Obtain the corresponding pesticide application matrix according to the pesticide application strategy, and extract the pesticide application vector from the pesticide application matrix; Obtain the fertilization and pest control value according to the fertilization vector and the pesticide application vector; Obtain the fertilization and pest control table, where the fertilization and pest control table includes multiple fertilization and pest control ranges and the corresponding fertilization and pest control strategies for each fertilization and pest control range; Obtain the corresponding fertilization and pest control strategy from the fertilization and pest control table according to the fertilization and pest control range corresponding to the fertilization and pest control value.

5. The digital agriculture intelligent management method based on the Internet of Things according to claim 1, characterized in that, The steps of parsing spatial data to extract spatial image information and geographic information and calculating the spatial weight based on the spatial image information and geographic information include: Obtain the spatial image information and geographic information according to the spatial data; Obtain the crop distribution image according to the spatial image information; Construct a plane rectangular coordinate system in the crop distribution image; Obtain the coordinates of multiple inflection points of the crop distribution contour according to the plane rectangular coordinate system; Obtain the crop distribution value according to the coordinates of multiple inflection points of the crop distribution contour; Obtain the corresponding geographic matrix according to the geographic information, and obtain the corresponding geographic weight according to the geographic matrix; Obtain the spatial weight according to the crop distribution value and the geographic weight.

6. The digital agriculture intelligent management method based on the Internet of Things according to claim 1, wherein The steps of parsing the device operation data to extract the device health status information and generating the device operation strategy based on the device health status information include: Obtain the device health status information according to the device operation data; Obtain the corresponding device health status matrix according to the device health status information; Obtain the device health status value according to the device health status matrix; Obtain the device operation table, where the device operation table includes multiple device health status ranges and the corresponding device operation strategies for each device health status range; Obtain the corresponding device operation strategy from the device operation table according to the device health status range corresponding to the device health status value.

7. The digital agriculture intelligent management method based on the Internet of Things according to claim 1, characterized in that The steps of generating the management strategy by combining the irrigation strategy, the fertilization and pest control strategy, the device operation strategy, and the spatial weight, and performing agricultural management operations according to the management strategy include: Obtain the corresponding irrigation vector, fertilization and pest control vector, and device operation vector according to the irrigation strategy, the fertilization and pest control strategy, and the device operation strategy respectively; Obtain the comprehensive management value according to the irrigation vector, the fertilization and pest control vector, the device operation vector, and the spatial weight; Obtain the management table, where the management table includes multiple comprehensive management ranges and the corresponding management strategies for each comprehensive management range; Obtain the corresponding management strategy from the management table according to the comprehensive management range corresponding to the comprehensive management value; Perform agricultural management operations according to the management strategy.

8. The digital agriculture intelligent management method based on the Internet of Things according to claim 1, characterized in that The steps of constructing the feedback period according to the management strategy, collecting the multi-dimensional data source within the feedback period as the updated multi-dimensional data source, and looping to perform agricultural management operations include: Obtain the corresponding management matrix according to the management strategy; Obtain multiple period management vectors according to the management matrix; Obtain the period value according to the multiple period management vectors; Obtain the duration table, where the duration table includes multiple period ranges and the corresponding feedback durations for each period range; Obtain the corresponding feedback duration from the duration table according to the time period range corresponding to the time period value; Obtain the time node for performing agricultural management operations according to the management strategy, and mark it as the start time of the feedback duration; Obtain the end time according to the start time of the feedback duration and the feedback duration, and construct a feedback time period; Obtain the multi-dimensional data source within the feedback time period, and return it as a new multi-dimensional data source to the step of obtaining the multi-dimensional data source of the agricultural production area.

9. A digital agriculture intelligent management system based on the Internet of Things, which is applied to the digital agriculture intelligent management method based on the Internet of Things according to any one of claims 1 to 8, and is characterized in that, Include: A multi-source module for obtaining the multi-dimensional data source of the agricultural production area, where the multi-dimensional data source includes environmental data, crop data, spatial data, and equipment operation data; An irrigation module for parsing environmental data to extract soil information and meteorological information, and generating an irrigation strategy based on the soil information and meteorology; A fertilization and pest control module for parsing crop data to extract crop growth information and pest and disease information, generating a fertilization strategy based on the crop growth information and meteorological information, generating pest and disease diffusion path information according to the pest and disease information, generating a pesticide application strategy by combining the pest and disease diffusion path information and meteorological information, and integrating the fertilization strategy and the pesticide application strategy to generate a fertilization and pest control strategy; A spatial module for parsing spatial data to extract spatial image information and geographic information, and calculating spatial weights based on the spatial image information and geographic information; An equipment operation module for parsing equipment operation data to extract equipment health status information, and generating an equipment operation strategy based on the equipment health status information; A management module for generating a management strategy by combining the irrigation strategy, the fertilization and pest control strategy, the equipment operation strategy, and the spatial weight, and performing agricultural management operations according to the management strategy; A feedback module for constructing a feedback time period according to the management strategy, collecting the multi-dimensional data source within the feedback time period as an updated multi-dimensional data source, and looping through the steps of performing agricultural management operations.

10. A digital agriculture intelligent management terminal based on the Internet of Things, characterized in that, Include: One or more processors; A storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the Internet of Things-based digital agriculture intelligent management method according to any one of claims 1 to 8.

Images