Intelligent agricultural equipment management system and method based on Internet of Things

Abstract

The invention belongs to the technical field of agricultural management, particularly relates to an intelligent agricultural equipment management system and method based on the Internet of Things, and aims to solve the problems that an existing system does not adapt to soil and environment requirements of crops in different growth periods, and management closed loops are lacked. The system adopts a four-layer architecture of'perception-transmission-processing-application ', and integrates a monitoring module, a data processing module, a model training module, an equipment control module and the like to form a complete closed loop of'acquisition-analysis-decision-execution-feedback'. A crop growth influence factor model is constructed in different growth periods, and soil and environment parameter requirements are dynamically matched; an accurate adjustment suggestion is generated based on the model, and equipment is driven to be automatically regulated and controlled; and meanwhile, long-term data storage and model iterative optimization are supported, and an automatic and manual dual-management mode is considered. According to the invention, the whole-cycle precise management of crops is realized, the resource utilization efficiency is improved, the labor dependence is reduced, various planting scenes are adapted, and the quality and efficiency improvement and green development of agricultural production are facilitated.

Description

Technical Field

[0001] This invention belongs to the field of agricultural management technology, and specifically relates to a smart agricultural equipment management system and method based on the Internet of Things. Background Technology

[0002] While current smart agricultural equipment management systems have incorporated IoT technology to monitor some environmental parameters and remotely control equipment, significant technical shortcomings remain, making it difficult to meet the demands of precision production in modern agriculture. The core issue is that existing systems lack management strategies designed to address the dynamic needs throughout the entire plant growth cycle. A smart agricultural equipment management system and method based on IoT addresses this by noting that plants have vastly different requirements for soil environment (soil fertility, pH, humidity) and related environmental factors (light intensity, room temperature) at different stages, such as germination, seedling, growth, and flowering / fruiting. For example, seedlings require high soil moisture and low fertility, while fruiting requires sufficient fertility and suitable humidity. Fixed management models easily lead to resource waste (over-fertilization, irrigation) or limited crop growth (insufficient fertility, low humidity), failing to maximize yield and quality.

[0003] Meanwhile, existing systems suffer from fragmented functionality and lack a complete closed loop for an IoT-based smart agricultural equipment management system and method, encompassing data acquisition, analysis, decision-making, and execution. Most systems can only monitor single parameters, failing to integrate multi-dimensional data such as crop health, soil, and environment to construct growth correlation models. This makes it difficult to generate scientific adjustment suggestions based on historical data, and even more difficult to drive equipment to automatically adapt to crop growth stage needs. Consequently, agricultural production still relies on manual experience, resulting in low levels of intelligence and management efficiency. Summary of the Invention

[0004] This invention aims to provide a smart agricultural equipment management system and method based on the Internet of Things (IoT), and seeks to solve the following problems: 1. Monitor, record, and analyze the differentiated needs of plants at different growth stages for soil environment (fertility, pH, humidity) and related environment (light, temperature); 2. The equipment control and environmental regulation are disconnected, making it difficult to achieve automated management of an IoT-based smart agricultural equipment management system and method, which involves "sensing, decision-making, execution". 3. The lack of a complete data loop makes it impossible to build growth models based on historical data and drive dynamic adjustments to the equipment.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution: A smart agricultural equipment management system based on the Internet of Things includes a perception layer, a transmission layer, a processing layer, and an application layer. The perception layer includes a monitoring module and an equipment control module; the transmission layer includes a communication and storage module; the processing layer includes a data processing module, a recording module, a crop growth model training module, and an adjustment suggestion module; and the application layer includes a human-computer interaction module. The modules work together to form a complete management closed loop of "data acquisition-processing-analysis-decision-execution-feedback" to dynamically adapt to the growth needs of plants at different growth stages.

[0006] Preferably, the monitoring module is equipped with a plant health monitoring unit, a soil parameter monitoring unit, and an environmental parameter monitoring unit, and the sampling frequency of the monitoring module can be dynamically adjusted according to the plant growth period. The plant health monitoring unit includes agricultural-specific cameras and spectral sensors, which are used to collect images and spectral data on crop leaf color, morphology, growth height, and signs of pests and diseases, and output crop health index. The soil parameter monitoring unit includes a soil moisture sensor, a soil fertility sensor, and a soil pH sensor, which are used to collect soil moisture, soil nitrogen, phosphorus and potassium content, and soil pH value, respectively. The environmental parameter monitoring unit includes a light sensor and a room temperature sensor, which are used to collect light intensity and ambient temperature, respectively. Preferably, the communication and storage module adopts a hybrid communication mode of "LoRa+4G / 5G". LoRa is used to realize short-range low-power data transmission between sensors and equipment control modules in the farmland, and 4G / 5G is used to realize remote data interaction with the cloud platform. The communication and storage module also includes a local storage unit and a cloud storage unit. The local storage unit deploys an edge computing gateway to store real-time data for the past 7 days. The cloud storage unit uses a distributed database to store historical data, trained crop growth models, and equipment operation logs for long-term storage.

[0007] Preferably, the data processing module is used to process the raw data collected by the monitoring module, specifically including: data cleaning, removing abnormal sensor data and using interpolation to fill in missing data; data conversion, using a CNN convolutional neural network to convert the image data of crop health status into a quantitative health index of 0-100 points, and converting light intensity data into daily effective light duration (i.e., the cumulative time when light intensity is greater than or equal to the crop light compensation point); and data fusion, linking crop health data, soil parameter data, and environmental parameter data of the same farmland zone and the same time point to form a four-dimensional data set of "spatiotemporal-crop-soil-environment".

[0008] Preferably, the recording module is used to classify and archive the standardized data output by the data processing module. The specific recording content includes: basic farmland information, which divides and numbers the farmland according to the location, area and crop variety of the plots, and records the sowing time and crop variety characteristics of each plot; crop-related data, which records the crop health index, pest and disease occurrence and final yield of each plot at different growth stages; soil-related data, which records the historical soil moisture, soil fertilization records and soil pH value changes of each plot in time series; and environmental-related data, which records the historical room temperature data and daily effective sunshine duration data of each plot in time series.

[0009] Preferably, the crop growth model training module is used to construct a crop growth influencing factor model. The specific process is as follows: historical data of the same crop variety at different growth stages are extracted from the recording module. The historical data includes the growth stage time interval, soil parameters (humidity, fertility, pH value), environmental parameters (room temperature, light duration), crop health index, and yield data for the corresponding growth stage. Using the Gradient Boosting Tree (GBRT) or neural network algorithm, with "growth stage" as the time dimension, soil parameters and environmental parameters are used as input features, and crop health index and yield are used as output labels to train a staged crop growth influencing factor model. The model can output the optimal range of soil parameters and the optimal range of environmental parameters that maximize the crop health index ≥ 85 and the yield in different growth stages. After each crop growth cycle is completed, the model automatically incorporates the new data of that cycle for iterative optimization.

[0010] Preferably, the adjustment suggestion module is used to generate soil and environmental adjustment plans. The specific process is as follows: real-time acquisition of the current crop growth stage, current soil parameters, current environmental parameters, and current crop health index output by the data processing module; comparison of the above real-time data with the optimal range of soil parameters and optimal range of environmental parameters for the corresponding growth stage output by the crop growth model training module to determine whether there is parameter deviation; for parameters with deviation, specific adjustment suggestions are generated based on crop variety characteristics and actual farmland conditions. The adjustment suggestions include the target parameter value to be adjusted, the agricultural equipment to be started, the equipment operation parameters, and the suggested execution time window; if the current crop health index is <60 points and there are parameters that are seriously deviated from the optimal range, the adjustment suggestion module will also generate an emergency warning message.

[0011] Preferably, the equipment control module connects to agricultural equipment in the farmland via the MQTT IoT protocol. This agricultural equipment includes irrigation equipment (drip irrigation systems, sprinkler systems), fertilization equipment (integrated water and fertilizer machines), pH adjuster spraying equipment, temperature control equipment (fans, heaters), and supplemental lighting equipment (LED plant growth lights). The equipment control module receives adjustment suggestions from the adjustment suggestion module, parses the equipment operating parameters, and sends control commands to the corresponding agricultural equipment. During equipment execution, the module acquires the equipment's operating status in real time. If a equipment malfunction occurs, the module immediately stops command execution, sends a fault log to the communication and storage module, and simultaneously pushes it to the human-machine interaction module. After completing the adjustment operation, the equipment transmits the execution results back to the data processing module via the communication and storage module.

[0012] Preferably, the human-computer interaction module provides two operating interfaces: a web terminal and a mobile terminal (APP), and has the following functions: data visualization, displaying real-time data, historical records, crop growth model curves, and a list of adjustment suggestions; operation control, allowing users to view and confirm the implementation of adjustment suggestions, or manually modify adjustment parameters and start / stop agricultural equipment in special scenarios; alarms and reports, receiving emergency warning information pushed by the adjustment suggestion module and reminding users in the form of pop-ups and SMS messages, and supporting the generation of agricultural production reports by week, month, or crop growth cycle. The report content includes soil management costs, fertilizer and water consumption, crop yield and quality analysis data.

[0013] A systematic method for managing smart agricultural equipment includes the following steps: S1. Initialization Configuration: Users complete the farmland zoning settings, crop variety information input (including crop growth cycle and characteristics of each growth stage) and sensor and agricultural equipment deployment location binding through the human-machine interaction module. The human-machine interaction module synchronizes the initialization configuration information to the monitoring module and equipment control module through the communication and storage module, and starts sensor sampling and equipment status monitoring. S2. Data Acquisition and Transmission: The monitoring module collects crop health data, soil parameter data, and environmental parameter data at a set frequency and transmits them to the data processing module through the communication and storage module; the equipment control module collects agricultural equipment operating status data in real time and synchronizes it to the data processing module through the communication and storage module. S3. Data Processing and Recording: The data processing module cleans, transforms, and merges the received raw data to generate standardized data, which is then transmitted to the recording module and the adjustment suggestion module respectively. The recording module classifies and archives the standardized data according to farmland zoning and growth period. S4. Model Training and Update: The crop growth model training module periodically extracts historical data from the recording module, iteratively optimizes the crop growth influencing factor model, and stores the optimized model in the cloud storage unit of the communication and storage module. S5. Adjustment suggestion generation: The adjustment suggestion module compares and analyzes real-time standardized data with the crop growth influencing factor model for the corresponding growth stage, generates adjustment suggestions and emergency early warning information, and pushes them to the equipment control module and human-computer interaction module respectively; S6. Equipment Execution and Feedback: The equipment control module receives adjustment suggestions, drives the corresponding agricultural equipment to perform adjustment operations, and transmits the execution results and equipment operating status back to the data processing module through the communication and storage module; S7. Cyclic Optimization: Repeat steps S2-S6 according to the set cycle, and dynamically update and adjust the strategy according to the changes in crop growth period until the crop is harvested.

[0014] The beneficial effects of this invention are as follows: 1. Precisely adapt to the dynamic needs of crop growth: By constructing a crop growth influencing factor model through different growth stages, it can specifically match the differentiated needs of plants at different stages for soil and environment, solve the problem that the existing fixed management mode cannot adapt to crop growth changes, and ensure that crops are always in suitable growth conditions.

[0015] 2. Construct a complete management closed loop: Form a complete closed loop of "monitoring-processing-analysis-decision-execution-feedback", with each module working together to achieve automated operation from data collection to equipment control, breaking the limitations of existing system functions fragmentation and the disconnect between "perception-decision-execution", and reducing reliance on manual labor.

[0016] 3. Improve agricultural resource utilization efficiency: Based on the precise adjustment suggestions generated by the model, irrigation, fertilization and other operations can be carried out to avoid resource waste, reduce the negative impact of agricultural production on the environment, and conform to the concept of green agricultural development.

[0017] 4. Support for continuous optimization of planting plans: Long-term storage of crop growth data throughout the entire growth cycle, automatic model iteration after each growth cycle, and scientific support for subsequent planting strategy optimization by combining historical data, while meeting the needs of agricultural product quality traceability.

[0018] 5. Balancing management flexibility and system reliability: Supports dual-mode management of "automatic + manual", with automatic operation in normal scenarios and manual intervention through the human-computer interaction module in special cases; adopts hybrid communication and dual storage mode to ensure stable data transmission and storage, and is suitable for planting environments such as greenhouses and sheds of different sizes. Attached Figure Description

[0019] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0020] Figure 1 This is a system architecture diagram of the present invention patent; Figure 2 This is a flowchart of the method of this invention patent. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] A smart agricultural equipment management system based on the Internet of Things, the system architecture of which is as follows: Figure 1 As shown, it includes a perception layer, a transmission layer, a processing layer, and an application layer. The perception layer includes a monitoring module and a device control module; the transmission layer includes a communication and storage module; the processing layer includes a data processing module, a recording module, a crop growth model training module, and an adjustment suggestion module; and the application layer includes a human-computer interaction module. These modules work together to form a complete management closed loop of "data acquisition-processing-analysis-decision-execution-feedback" to dynamically adapt to the growth needs of plants at different growth stages.

[0023] Preferably, the monitoring module is equipped with a plant health monitoring unit, a soil parameter monitoring unit, and an environmental parameter monitoring unit, and the sampling frequency of the monitoring module can be dynamically adjusted according to the plant growth period. The plant health monitoring unit includes agricultural-specific cameras and spectral sensors, which are used to collect images and spectral data on crop leaf color, morphology, growth height, and signs of pests and diseases, and output crop health index. The soil parameter monitoring unit includes a soil moisture sensor, a soil fertility sensor, and a soil pH sensor, which are used to collect soil moisture, soil nitrogen, phosphorus and potassium content, and soil pH value, respectively. The environmental parameter monitoring unit includes a light sensor and a room temperature sensor, which are used to collect light intensity and ambient temperature, respectively. The communication and storage module adopts a hybrid communication mode of "LoRa+4G / 5G". LoRa is used to realize short-range low-power data transmission between sensors and equipment control modules in the farmland, while 4G / 5G is used to realize remote data interaction with the cloud platform. The communication and storage module also includes a local storage unit and a cloud storage unit. The local storage unit deploys an edge computing gateway to store real-time data for the past 7 days, while the cloud storage unit uses a distributed database to store historical data, trained crop growth models, and equipment operation logs for long-term storage.

[0024] The data processing module is used to process the raw data collected by the monitoring module, specifically including: data cleaning, removing abnormal sensor data and using interpolation to fill in missing data; data transformation, using a CNN convolutional neural network to convert crop health status image data into a quantitative health index of 0-100 points, and converting light intensity data into daily effective light duration (i.e., the cumulative time when light intensity is greater than or equal to the crop light compensation point); and data fusion, linking crop health data, soil parameter data, and environmental parameter data from the same farmland zone and at the same time point to form a four-dimensional data set of "spatiotemporal-crop-soil-environment".

[0025] Crop Health Index Conversion Formula Let the crop health status image data be I (pixel matrix). After processing by a CNN convolutional neural network, the output normalized feature value CNN(I) (range ([0,1])) is given by: HI=round(CNN(I)*100) Wherein: CNN(I) is the feature extraction and classification output of the CNN network for the input image (normalization is achieved through a fully connected layer and a sigmoid activation function). round( ) is a rounding function that ensures the result is an integer score between 0 and 100.

[0026] 2. Formula for converting daily effective light exposure duration Suppose the light intensity sampling sequence for a certain day is: (Unit: lux), sampling time interval is (Unit: hours), crop light compensation point is (Unit: lux), then the daily effective light exposure duration for: This is an indicator function that takes the value 1 when the condition inside the parentheses is true, and 0 otherwise. The summation range covers all sampling times within a day (e.g., ( ) is 00:00, ( (23:59)

[0027] 3. Data Fusion and Association Formula: Let the multi-dimensional data under the same farmland zone Z and the same time node T be: Crop health data: HI (Health Index); Soil parameter data: ; Environmental parameter data: The merged data set F is then represented as: That is, by associating the above three types of data with partition number Z and timestamp T, a four-dimensional dataset with spatiotemporal annotation is formed.

[0028] The recording module is used to classify and archive the standardized data output by the data processing module. The specific recording content includes: basic farmland information, which divides farmland into zones according to plot location, area and crop variety, and records the sowing time and crop variety characteristics of each zone; crop-related data, which records the crop health index, pest and disease occurrence and final yield of each zone at different growth stages; soil-related data, which records the historical soil moisture, soil fertilization records and soil pH value changes of each zone in time series; and environmental-related data, which records the historical room temperature data and daily effective sunshine duration data of each zone in time series.

[0029] The crop growth model training module is used to construct a model of factors influencing crop growth. The specific process is as follows: Historical data of the same crop variety at different growth stages are extracted from the recording module. This historical data includes the growth stage time interval, corresponding soil parameters (humidity, fertility, pH), environmental parameters (room temperature, light duration), crop health index, and yield data. Using a gradient boosting tree (GBRT) or neural network algorithm, with "growth stage" as the time dimension, soil and environmental parameters are used as input features, and crop health index and yield are used as output labels to train a phased model of factors influencing crop growth. The model can output the optimal ranges for soil and environmental parameters that maximize crop health index ≥ 85 and yield within different growth stages. After each crop growth cycle is completed, the model automatically incorporates new data from that cycle for iterative optimization.

[0030] 1. Formula and Explanation of Crop Growth Influencing Factor Model The phased model mapping relationship is as follows: Let the input feature vector of a crop variety's P-th growth stage (e.g., germination stage (P=1), seedling stage (P=2), etc.) be the combination of soil and environmental parameters X, and the output be the crop health index HI and yield Y. Then the phased growth influencing factor model is expressed as: in: Input feature X: Soil moisture (%) Soil fertility (nitrogen, phosphorus, and potassium content, mg / kg); Soil pH value; Room temperature (°C); : Daily effective light exposure duration (h); Model Mp: A nonlinear mapping function obtained through training with a gradient boosting tree (GBRT) or a neural network, satisfying... Furthermore, the model parameters are dynamically adjusted according to the growth period P; Output : ∈[0,100] (health index), Y∈R + (Yield, kg / mu) 2. Formula for solving the optimal parameter interval The optimal soil and environmental parameter range that maximizes crop health index ≥ 85 and yield during the Pth growth stage is solved by the following constrained optimization problem: X * P =argmax x Y in: The optimal parameter combination corresponds to the optimal range in the output. (Indicates the optimal range of soil moisture). Argmax x Y represents the condition that the constraints are met. Given the premise that the output Y reaches its maximum value, the input parameter X is X.

[0031] 3. Model Iterative Optimization Formula Suppose that after the kth growth cycle, the newly added historical dataset is... ( (where M is the sample size), then the iteratively optimized model M P (k+1) =Optimize(M P (k) , ) Where: M P (k) This is the model after the k-th iteration; Optimize(x) is the model optimization function, which optimizes the new data using gradient boosting iterations of GBRT or backpropagation algorithms of neural networks. The dataset is incorporated into the training, and the model parameters are updated to improve prediction accuracy.

[0032] Explanation of the model iterative optimization formula: (1) The model achieves phased training through the growth period P to ensure that the differences in parameter requirements at different growth stages are accurately captured; (2) The optimal interval solution formula balances crop quality and yield requirements by using constraints (health index ≥ 85) and optimization objectives (maximizing yield); (3) The iterative optimization formula ensures that the model evolves dynamically with the planting cycle and continuously adapts to the actual changes in the farmland environment.

[0033] The adjustment suggestion module is used to generate soil and environmental adjustment plans. The specific process is as follows: The current crop growth stage, current soil parameters, current environmental parameters, and current crop health index are acquired in real time from the data processing module. This real-time data is compared with the optimal ranges for soil parameters and environmental parameters for the corresponding growth stage, as output by the crop growth model training module, to determine if there are any parameter deviations. For parameters with deviations, specific adjustment suggestions are generated based on crop variety characteristics and actual farmland conditions. These suggestions include the target parameter values, the agricultural equipment to be activated, equipment operating parameters, and a suggested execution time window. If the current crop health index is <60 points and there are parameters that significantly deviate from the optimal range, the adjustment suggestion module will also generate an emergency warning message.

[0034] The equipment control module connects to agricultural equipment in the farmland via the MQTT IoT protocol. This equipment includes irrigation equipment (drip irrigation systems, sprinkler irrigation systems), fertilization equipment (integrated water and fertilizer machines), pH adjuster spraying equipment, temperature control equipment (fans, heaters), and supplemental lighting equipment (LED plant growth lights). The equipment control module receives adjustment suggestions from the adjustment suggestion module, parses the equipment operating parameters, and sends control commands to the corresponding agricultural equipment. During equipment execution, the module acquires the equipment's operating status in real time. If a equipment malfunction occurs, the module immediately stops command execution, sends a fault log to the communication and storage module, and simultaneously pushes it to the human-machine interaction module. After the equipment completes the adjustment operation, it sends the execution results back to the data processing module via the communication and storage module.

[0035] The human-computer interaction module provides two operating interfaces: a web terminal and a mobile terminal (APP). It has the following functions: data visualization, displaying real-time data, historical records, crop growth model curves, and a list of adjustment suggestions; operation control, allowing users to view and confirm the execution of adjustment suggestions, or manually modify adjustment parameters and start / stop agricultural equipment in special scenarios; alarms and reports, receiving emergency warning information pushed by the adjustment suggestion module and reminding users in the form of pop-ups and SMS messages, and supporting the generation of agricultural production reports by week, month, or crop growth cycle. The report content includes soil management costs, fertilizer and water consumption, crop yield and quality analysis data.

[0036] A systematic approach to managing smart agricultural equipment, such as Figure 2 As shown, it includes the following steps: S1. Initialization Configuration: Users complete the farmland zoning settings, crop variety information input (including crop growth cycle and characteristics of each growth stage) and sensor and agricultural equipment deployment location binding through the human-machine interaction module. The human-machine interaction module synchronizes the initialization configuration information to the monitoring module and equipment control module through the communication and storage module, and starts sensor sampling and equipment status monitoring. S2. Data Acquisition and Transmission: The monitoring module collects crop health data, soil parameter data, and environmental parameter data at a set frequency and transmits them to the data processing module through the communication and storage module; the equipment control module collects agricultural equipment operating status data in real time and synchronizes it to the data processing module through the communication and storage module. S3. Data Processing and Recording: The data processing module cleans, transforms, and merges the received raw data to generate standardized data, which is then transmitted to the recording module and the adjustment suggestion module respectively. The recording module classifies and archives the standardized data according to farmland zoning and growth period. S4. Model Training and Update: The crop growth model training module periodically extracts historical data from the recording module, iteratively optimizes the crop growth influencing factor model, and stores the optimized model in the cloud storage unit of the communication and storage module. S5. Adjustment suggestion generation: The adjustment suggestion module compares and analyzes real-time standardized data with the crop growth influencing factor model for the corresponding growth stage, generates adjustment suggestions and emergency early warning information, and pushes them to the equipment control module and human-computer interaction module respectively; S6. Equipment Execution and Feedback: The equipment control module receives adjustment suggestions, drives the corresponding agricultural equipment to perform adjustment operations, and transmits the execution results and equipment operating status back to the data processing module through the communication and storage module; S7. Cyclic Optimization: Repeat steps S2-S6 according to the set cycle, and dynamically update and adjust the strategy according to the changes in crop growth period until the crop is harvested.

[0037] The foregoing description of specific exemplary embodiments of the present invention is for illustrative and explanatory purposes. These descriptions are not intended to limit the invention to the precise forms disclosed, and it is obvious that many changes and variations can be made based on the above teachings. Although embodiments of the invention have been shown and described, these specific embodiments are merely explanations of the invention and are not intended to limit it. The specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. The purpose of selecting and describing exemplary embodiments is to explain the specific principles of the invention and its practical application, so that those skilled in the art, after reading this specification, can make modifications, substitutions, variations, and various choices and changes to the embodiments as needed without departing from the principles and spirit of the invention, provided that such modifications, substitutions, variations, and choices and changes are within the scope of the claims of the invention and are protected by patent law.

Claims

1. An Internet of Things-based intelligent agricultural equipment management system, characterized in that: It comprises a perception layer, a transmission layer, a processing layer and an application layer, the perception layer comprises a monitoring module and a device control module, the transmission layer comprises a communication and storage module, the processing layer comprises a data processing module, a record module, a crop growth model training module and an adjustment suggestion module, and the application layer comprises a man-machine interaction module; the modules are cooperated to form a complete management closed loop of "data collection-processing-analysis-decision-execution-feedback", so as to dynamically adapt to the growth needs of plants in different growth periods. 2.The smart agricultural equipment management system based on the Internet of Things according to claim 1, characterized in that: The monitoring module is provided with a plant health monitoring unit, a soil parameter monitoring unit and an environmental parameter monitoring unit, and the sampling frequency of the monitoring module can be dynamically adjusted according to the growth period of the plant; The plant health monitoring unit comprises an agricultural special camera and a spectrum sensor, which are used for collecting image and spectrum data of crop leaf color, shape, growth height and pest signs, and outputting crop health index; The soil parameter monitoring unit comprises a soil humidity sensor, a soil fertility sensor and a soil pH value sensor, which are respectively used for collecting soil humidity, soil nitrogen, phosphorus and potassium element content and soil pH value; The environmental parameter monitoring unit comprises an illumination sensor and an ambient temperature sensor, which are respectively used for collecting illumination intensity and environmental temperature. 3.The smart agricultural equipment management system based on the Internet of Things according to claim 1, characterized in that: The communication and storage module adopts a "LoRa+4G / 5G" hybrid communication mode, LoRa is used for realizing short-distance low-power data transmission of sensors and device control modules in farmland, and 4G / 5G is used for realizing interaction of remote data and cloud platform.

4. The smart agriculture equipment management system based on the Internet of Things according to claim 1, characterized in that: The data processing module is used for processing the original data collected by the monitoring module. 5.The IoT-based smart agricultural equipment management system according to claim 1, wherein: The record module is used for classifying and archiving the standardized data output by the data processing module. 6.The smart agricultural equipment management system based on the Internet of Things according to claim 1, characterized in that: The crop growth model training module is used for constructing a crop growth influencing factor model. 7.The smart agricultural equipment management system based on the Internet of Things according to claim 1, characterized in that: The adjustment suggestion module is used for generating soil and environmental adjustment schemes. 8.The IoT-based smart agricultural equipment management system of claim 1, wherein: The device control module is connected with agricultural devices in farmland through MQTT Internet of Things protocol, and the agricultural devices comprise irrigation equipment, fertilization equipment, pH regulator spraying equipment, temperature control equipment and light supplementing equipment. 9.The smart agricultural equipment management system based on the Internet of Things according to claim 1, characterized in that: The man-machine interaction module provides two operation interfaces of Web end and mobile end.

10. A smart agriculture device management method based on the smart agriculture device management system based on the Internet of Things according to any one of claims 1-9, characterized in that, It comprises the following steps: S1. Initialization configuration: the user completes farmland zoning setting, crop variety information input and binding of deployment positions of sensors and agricultural devices through the man-machine interaction module, the man-machine interaction module synchronizes the initialization configuration information to the monitoring module and the device control module through the communication and storage module, and starts sensor sampling and device state monitoring; S2. Data collection and transmission: the monitoring module collects crop health data, soil parameter data and environmental parameter data at a set frequency, and transmits them to the data processing module through the communication and storage module; the device control module collects agricultural device operation state data in real time, and synchronizes them to the data processing module through the communication and storage module; S3. Data processing and record: the data processing module cleans, converts and fuses the received original data to generate standardized data, which are transmitted to the record module and the adjustment suggestion module respectively; the record module classifies and archives the standardized data according to farmland zoning and growth period. S4. Model training and updating: The crop growth model training module periodically extracts historical data from the record module, iteratively optimizes the crop growth influencing factor model, and stores the optimized model in the cloud storage unit of the communication and storage module; S5. Adjustment suggestion generation: The adjustment suggestion module compares and analyzes the real-time standardized data with the crop growth influencing factor model corresponding to the growth period, generates adjustment suggestions and emergency warning information, and pushes them to the device control module and the human-computer interaction module respectively; S6. Device execution and feedback: The device control module receives the adjustment suggestions, drives the corresponding agricultural equipment to perform adjustment operations, and transmits the execution results and device running status to the data processing module through the communication and storage module; S7. Cycle optimization: Repeat steps S2-S6 according to the set period, dynamically update the adjustment strategy according to the change of crop growth period, and until the crop is harvested.

Images