Search

CN-122022143-A - Intelligent agriculture monitoring management method and system based on big data

CN122022143ACN 122022143 ACN122022143 ACN 122022143ACN-122022143-A

Abstract

The invention discloses a smart agricultural monitoring management method and system based on big data, which belong to the technical field of agricultural monitoring, and the method comprises the following steps of S1, acquiring crop growth environment data and crop body image data; the method comprises the steps of S2, storing crop growth environment data and crop body image data into a storage node, S3, generating a first evolution factor and a second evolution factor when the fact that the data in the current storage node are missing is recognized, S4, calculating according to the first evolution factor and the second evolution factor to generate a compensated complete data set, S5, generating an irrigation or fertilization decision instruction based on the compensated complete data set, and issuing the instruction to preset execution equipment. The system comprises a data acquisition module, a data storage module, a data monitoring module, a data compensation module and a decision generation module. According to the invention, through the steps S1-S5, the reliability of the monitoring data is obviously improved.

Inventors

  • LUO GUIHUA
  • XIAO LEI

Assignees

  • 湘潭瀚荣生态科技有限公司

Dates

Publication Date
20260512
Application Date
20260120

Claims (10)

  1. 1. A smart agriculture monitoring management method based on big data is characterized by comprising the following steps: s1, acquiring crop growth environment data and crop body image data in a large data source according to a preset sampling period; S2, storing the crop growth environment data and the crop body image data into storage nodes of a preset storage unit according to time axis sequences, wherein each storage node corresponds to a complete data set in a sampling period; S3, monitoring the data integrity in the storage node in real time, and triggering a preset data compensation flow when the data in the storage node is identified to be missing currently, wherein the historical crop growth environment data and the historical crop body image data acquired in the same historical sampling period and the adjacent same sampling period are called to generate a first evolution factor; S4, calculating according to the first evolution factor and the second evolution factor to generate an evolution trend factor, adjusting crop growth environment data and crop body image data in the previous storage node by using the evolution trend factor to generate compensation data in the storage node with the current missing, writing the compensation data into the current storage node, and generating a complete data set after compensation; S5, based on the compensated complete data set, generating an irrigation or fertilization decision instruction through a preset crop growth model, and transmitting the instruction to preset execution equipment.
  2. 2. The intelligent agricultural monitoring and management method based on big data as claimed in claim 1, wherein the crop growth environment data in the step S1 comprises air temperature and humidity, soil moisture content and illumination intensity, and the crop body image data comprises leaf surface morphology and color data collected by a high-definition camera deployed in a farmland.
  3. 3. The intelligent agricultural monitoring and management method based on big data as set forth in claim 2, wherein the specific contents of the step S2 are as follows: S21, receiving the crop growth environment data and the crop body image data, performing time stamp verification and format standardization on the crop growth environment data and the crop body image data, and generating standardized data packets, wherein each standardized data packet corresponds to a complete data set of one sampling period; S22, distributing the standardized data packet to storage nodes of the storage unit according to a time axis based on a time stamp sequence of the standardized data packet, generating a unique node identifier by each storage node, and associating a data index table corresponding to the sampling period, wherein the data index table records the data type, the acquisition time and the storage address of the standardized data packet; S23, according to the content of the data index table, executing data integrity check on each storage node, if the check is passed, activating the write-in authority of the storage node, compressing the standardized data packet, and storing the compressed standardized data packet in the corresponding storage address; And after the storage of all the standardized data packets is completed, generating a storage node topological graph based on the data index table, wherein the storage node topological graph dynamically maps the time sequence relation and the data dependency path of each storage node.
  4. 4. The intelligent agricultural monitoring and management method based on big data as set forth in claim 3, wherein the generating step of the first evolution factor in the step S3 is as follows: S31, calling historical crop growth environment data and historical crop body image data acquired in the same historical sampling period and adjacent same sampling period to serve as historical first crop growth environment data and historical first crop body image data, historical second crop growth environment data and historical second crop body image data respectively; S32, taking the historical first crop growth environment data and the historical first crop body image data as an original data set, and taking the historical second crop growth environment data and the historical second crop body image data as a target data set; s33, extracting parameters of air temperature and humidity, soil moisture content and illumination intensity in the original data set and the target data set, and generating a first difference value, a second difference value and a third difference value by calculating normalized Euclidean distances of all the parameters between the original data set and the target data set; S34, extracting leaf surface morphology and color data in the original data set and the target data set to generate a leaf surface expansion area factor, a leaf surface expansion direction factor and a color change trend factor, and calculating to generate a first evolution factor according to the first difference value, the second difference value, the third difference value, the leaf surface expansion area factor, the leaf surface expansion direction factor and the color change trend factor by adopting the following formula: ; Wherein, the Is a first evolution factor; 、 、 、 、 、 Is a preset weight coefficient and meets the following requirements ; Is the first difference; Is the second difference; is the third difference; Is the leaf surface expansion factor; Expanding a direction factor for the leaf surface; is the color change trend factor.
  5. 5. The intelligent agricultural monitoring and management method based on big data as set forth in claim 4, wherein said leaf surface expansion area factor in said step S34 is generated by calculation of impeller profile pixel integral; The generation step of the leaf surface expansion direction factor is as follows: S341, extracting leaf surface morphology data in the original data set and the target data set, respectively serving as a first leaf image and a second leaf image, superposing the first leaf image and the second leaf image to generate a leaf pulse variation superposition graph, and marking the intersection point of a leaf pulse trunk and a secondary vein in the leaf pulse variation superposition graph as a key reference point; S342, extracting the angular offset distance between an offset direction vector of a vein trunk and a secondary vein based on key reference points in the vein change superposition diagram, constructing a vein offset path model according to the offset direction vector and the angular offset distance, inserting preset offset nodes into the vein offset path at preset length intervals, endowing each offset node with a unique spatial identifier, extracting absolute position coordinates of the offset nodes through a three-dimensional space coordinate mapping algorithm, and establishing a leaf coordinate system of the absolute position coordinates by taking a leaf base part as an origin; s343, calculating Euclidean distance matrix and direction covariance matrix among the offset nodes based on the absolute position coordinates of all the offset nodes, and generating a leaf expansion direction factor by extracting the principal axis direction and variation coefficient of leaf vein expansion.
  6. 6. The intelligent agricultural monitoring and management method based on big data as set forth in claim 5, wherein the step of generating the second evolution factor is the same as the step of generating the first evolution factor.
  7. 7. The intelligent agricultural monitoring and management method based on big data as set forth in claim 6, wherein the step of generating the evolution trend factor in the step S4 is as follows: S41, acquiring the first evolution factor and the second evolution factor, calculating the dynamic association degree between the first evolution factor and the second evolution factor, and generating a factor fusion weight ratio based on the dynamic association degree; s42, according to the factor fusion weight ratio, fusing the first evolution factor and the second evolution factor to generate an initial trend factor, and processing the initial trend factor to form a smooth trend sequence; S43, introducing a preset environment disturbance coefficient, dynamically adjusting the response sensitivity of the smooth trend sequence, generating an adaptive trend factor, carrying out boundary constraint and normalization processing on the adaptive trend factor, limiting the output value range of the adaptive trend factor through a preset threshold range, ensuring that the adaptive trend factor is in a preset biological reasonable interval, and generating an evolution trend factor.
  8. 8. The intelligent agricultural monitoring and management method based on big data as set forth in claim 7, wherein the generating step of the compensation data in the step S4 is as follows: s44, based on the evolution trend factor, performing the following operation on the crop growth environment data and the crop body image data in the previous storage node, namely respectively scaling the air temperature and humidity, the soil moisture content and the illumination intensity according to the numerical value and the symbol direction of the evolution trend factor, and performing pixel-level offset correction on the leaf surface morphology and the color data to generate a preliminary compensation data set; s45, performing time sequence consistency check and boundary constraint processing on the preliminary compensation data set, removing abnormal values exceeding a preset reasonable interval by comparing the deviation range of the data of the preliminary compensation data set and the data of the same sampling period of the history, and applying smooth filtering to the residual data to inhibit high-frequency noise, so as to generate compensation data in the storage node with the current occurrence of the deletion; And writing the compensation data into the current storage node, and updating the data dependent path of the storage node topological graph to form a complete data set after compensation.
  9. 9. The intelligent agricultural monitoring and management method based on big data is characterized in that the specific content of the step S5 is that based on the compensated complete data set, crop growth state simulation and demand analysis are conducted on the complete data set through a preset crop growth model, crop water and fertilizer requirement parameters are generated, irrigation priority and fertilization proportion are calculated according to the water and fertilizer requirement parameters and in combination with a preset real-time environment stress factor to form a decision instruction set, the decision instruction set is issued to preset execution equipment through a preset communication interface, the execution equipment is driven to execute operation, and operation feedback data are updated to the storage unit.
  10. 10. The intelligent agricultural monitoring and management system based on big data as set forth in claim 9, wherein the intelligent agricultural monitoring and management system comprises a data acquisition module, a data storage module, a data monitoring module, a data compensation module and a decision generation module; The data acquisition module is used for acquiring crop growth environment data and crop body image data according to a preset sampling period, and transmitting the crop growth environment data and the crop body image data to the data storage module; the data storage module is used for receiving and storing the crop growth environment data and the crop body image data, distributing the crop growth environment data and the crop body image data to storage nodes of a preset storage unit according to a time axis sequence, associating a unique identifier and a data index table with each storage node, and generating a storage node topological graph; The data monitoring module scans the data integrity of the storage node in real time, when the current data loss of the storage node is identified, a data compensation flow is triggered, the historical same sampling period and the historical same crop growth environment data and the historical crop body image data of the adjacent sampling period are called to generate a first evolution factor, the adjacent storage node is called to generate a second evolution factor, and the first evolution factor and the second evolution factor are transmitted to the data compensation module; the data compensation module is used for calculating an evolution trend factor based on the first evolution factor and the second evolution factor, generating compensation data of a current missing storage node by utilizing the evolution trend factor, writing the compensation data into a corresponding storage node, updating a storage node topological graph and forming a compensated complete data set; And the decision generation module is used for generating an irrigation or fertilization decision instruction through a preset crop growth model based on the compensated complete data set and transmitting the instruction to preset execution equipment.

Description

Intelligent agriculture monitoring management method and system based on big data Technical Field The invention relates to the technical field of agricultural monitoring, in particular to an intelligent agricultural monitoring management method and system based on big data. Background With the wide application of the Internet of things, big data and artificial intelligence technology in the agricultural field, an intelligent agricultural system has become an important tool for realizing the fine and efficient management of agricultural production. In the prior art, crop growth environment data and body image data are generally collected in real time through a sensor network (such as a temperature and humidity sensor and a soil moisture sensor) and an image collecting device (such as a camera) which are deployed in a farmland, and the data are transmitted to a cloud or a local server for storage and analysis by depending on a wireless communication network (such as 4G/5G), so that decision behaviors such as irrigation and fertilization are supported. The existing intelligent agricultural system is generally based on an Internet of things architecture to realize a monitoring management function, and the working principle of the intelligent agricultural system can be summarized in the following steps that firstly, environmental parameters such as air temperature and humidity, soil moisture, illumination intensity, pest and disease data and the like are collected in real time through sensors (such as soil moisture content monitors, weather stations and insect pest measuring and reporting lamps) deployed in fields, and crop body image information is obtained by combining video monitoring equipment, secondly, multi-source data are transmitted to a cloud platform by utilizing wireless communication technologies such as 4G/5G, loRa and the like, and finally, the platform stores and analyzes the data and provides services such as environmental early warning, irrigation decision support or remote control equipment (such as intelligent water valves and ventilation systems) for farmers through visual interfaces. However, the prior art has obvious defects that the farmland network is weak in coverage, particularly in remote areas, 4G/5G signals are unstable, data transmission is easily interrupted in severe weather or strong electromagnetic interference, key data are lost, the system relies on simple interpolation to compensate the lost data, and the time-space correlation and multidimensional change rule of crop growth are not combined, so that a compensation result deviates from a real state, and decision accuracy is influenced. Therefore, there is a need to provide a smart agriculture monitoring management method and system based on big data to solve the above problems. Disclosure of Invention The technical problem to be solved by the invention is to overcome the defects that the prior art farmland network is weak in coverage, particularly in remote areas, 4G/5G signals are unstable, data transmission is easy to interrupt in severe weather or strong electromagnetic interference, key data are lost, the system relies on simple interpolation to compensate the lost data, the time-space correlation and multi-dimensional change rule of crop growth are not combined, the compensation result deviates from a real state, and decision accuracy is influenced, and the intelligent agricultural monitoring management method and system based on big data are provided. In order to solve the technical problems, the technical scheme adopted by the invention is that the intelligent agriculture monitoring management method based on big data is provided, and comprises the following steps: s1, acquiring crop growth environment data and crop body image data in a large data source according to a preset sampling period; S2, storing the crop growth environment data and the crop body image data into storage nodes of a preset storage unit according to time axis sequences, wherein each storage node corresponds to a complete data set in a sampling period; S3, monitoring the data integrity in the storage node in real time, and triggering a preset data compensation flow when the data in the storage node is identified to be missing currently, wherein the historical crop growth environment data and the historical crop body image data acquired in the same historical sampling period and the adjacent same sampling period are called to generate a first evolution factor; S4, calculating according to the first evolution factor and the second evolution factor to generate an evolution trend factor, adjusting crop growth environment data and crop body image data in the previous storage node by using the evolution trend factor to generate compensation data in the storage node with the current missing, writing the compensation data into the current storage node, and generating a complete data set after compensation; S5, based on the compensated complete data set, g