Intelligent agricultural management system based on Internet of Things cloud big model

Abstract

The invention discloses a smart agricultural management system based on an Internet of Things cloud big model, and relates to the technical field of smart agricultural management, and the system effectively improves the accuracy and stability of agricultural environment data collection through an intelligent sensing device and an advanced data processing algorithm, and improves the accuracy and stability of agricultural environment data collection. The system can reliably operate even in a severe environment, provides higher-quality data support for precise agricultural production, is smaller in data deviation and higher in reliability compared with a data acquisition device in the prior art, can deeply mine agricultural data values through an embedded fine-tuned AI large model, and can be applied to the field of agricultural production in combination with a rich agricultural knowledge database. According to the method, more accurate and more targeted production management suggestions are provided, farmers are helped to optimize production decisions, production efficiency and agricultural product quality are improved, and the problems of relatively simple intelligent analysis function and accuracy and practicability of decision support in the prior art are improved.

Description

Technical Field

[0001] The present invention relates to the field of smart agricultural management technology, and in particular to a smart agricultural management system based on a large model of the Internet of Things cloud. Background Art

[0002] The existing smart agricultural management system based on the IoT cloud model still has the following drawbacks in actual use:

[0003] Traditional agriculture lacks real-time monitoring and precise data analysis capabilities, making it difficult to detect problems in a timely manner and take precise measures. For example, it is unable to accurately grasp key indicators such as soil moisture, temperature, and nutrients, resulting in inaccurate operations such as irrigation and fertilization, serious waste of resources, and limited crop yields and quality.

[0004] Existing smart agricultural equipment has problems such as large footprint, narrow scope of application, and system incompatibility, which makes it difficult to deploy in different crops and growth environments, unable to meet diverse needs, and difficult for different brands or models of equipment to work together, reducing overall efficiency.

[0005] In existing technologies, pest and disease control mostly relies on manual inspections and spraying of pesticides, which is not only inefficient, but also easily damages the ecological environment due to excessive use of pesticides, affects the quality of agricultural products, and makes it difficult to accurately predict and issue early warnings of pests and diseases, often causing large losses.

[0006] Grain storage management is insufficient, and traditional methods can easily cause grain to become damp, deteriorate, rot, or be attacked by pests. There is a lack of effective real-time monitoring and control measures to ensure the quality of grain storage.

[0007] Agricultural production efficiency is low. Affected by labor shortages and insufficient management, traditional agricultural technologies are unable to fully play their role, resulting in high production costs and low benefits. The existing smart agricultural systems are still not intelligent enough in some aspects and cannot effectively improve overall production efficiency. Summary of the Invention

[0008] The purpose of this invention is to provide a smart agricultural management system based on the Internet of Things cloud model to solve the above-mentioned problems.

[0009] In order to achieve the above-mentioned object, the present invention provides the following technical solutions: a smart agricultural management system based on a large model of the Internet of Things cloud, comprising a device collection unit, a server unit and a Web server unit;

[0010] The equipment collection unit includes crop data collection equipment, grain storage data collection equipment, and AI image monitoring equipment to collect data on the agricultural ecological environment and crop storage environment;

[0011] The server unit stores, processes and analyzes the collected data. It has an embedded, deeply tuned AI agricultural expert model that analyzes the collected data in real time and uploads it to the database.

[0012] The web server unit is used for data visualization and real-time AI monitoring, allowing users to intuitively view environmental data of farmlands and granaries, AI analysis results, and real-time monitoring images.

[0013] Furthermore, the equipment collection unit includes crop data collection equipment, grain storage data collection equipment and AI image monitoring equipment, which collects data on the agricultural ecological environment and crop storage environment, specifically including:

[0014] The STM32 microcontroller development board is used to connect various sensors, such as soil moisture sensors, air temperature and humidity sensors, and light sensors, to achieve real-time collection of farmland and granary environmental data. Communication with sensors is achieved through peripheral interfaces such as I2C, SPI, and UART, and data processing technologies such as filtering, calibration, and compensation are used to improve data reliability. Data is transmitted to the server through the MQTT protocol to ensure efficient and stable data transmission.

[0015] Furthermore, the server unit stores, processes and analyzes the collected data, and embeds a deeply adjusted AI agricultural expert model to analyze the collected data in real time and upload it to the database, specifically including:

[0016] By embedding a fine-tuned AI large language model and customizing the training of a professional agricultural language database, in-depth analysis of data on the planting ecological environment and grain storage environment is carried out; based on the analysis results, the AI ​​model can provide accurate agricultural production management recommendations, such as the optimal time and amount of irrigation and fertilization, and pest and disease control plans.

[0017] Furthermore, the server unit stores, processes and analyzes the collected data, embeds a deeply adjusted AI agricultural expert model, analyzes the collected data in real time, and uploads it to the database, and also includes:

[0018] The database includes an influxdb real-time database and a MySQL database, wherein the influxdb real-time database stores agricultural and granary data, and the MySQL database stores important information.

[0019] Furthermore, the web unit provides data visualization and real-time AI monitoring, allowing users to intuitively view environmental data of farmland and granary, AI analysis results, and real-time monitoring images, including:

[0020] By combining the YOLOv11 algorithm with machine vision and deploying cameras on the NVIDIA Jetson Nano edge computing development board to capture real-time images, real-time monitoring and early warning of pests and diseases, fires, and farm intrusions can be carried out. The YOLOv11 algorithm can accurately identify and quickly respond, detecting and warning of potential threats in the first place. The annotated video stream is forwarded to the SRS streaming server via FFmpeg and the RTMP protocol, and then pushed to the web unit via the HTTP protocol for further processing. At the same time, log information is pushed to the EMQX server via the MQTT protocol for forwarding, ensuring the safety of crops and the integrity of farm facilities.

[0021] Furthermore, the web unit provides data visualization and real-time AI monitoring, allowing users to intuitively view environmental data of farmland and granaries, AI analysis results, and real-time monitoring images. It also includes:

[0022] AI monitoring is mainly responsible for monitoring safety conditions such as pests and diseases, fires, and animal invasions in farmland. It obtains abnormal information about farmland in real time through intelligent means, provides timely and effective data support for farmland safety management, and ensures the healthy growth of crops.

[0023] Compared with the existing technology, the smart agricultural management system based on the IoT cloud model provided by the present invention has the following beneficial effects:

[0024] This smart agricultural management system based on the IoT cloud model effectively improves the accuracy and stability of agricultural environmental data collection through intelligent sensing equipment and advanced data processing algorithms. It can operate reliably even in harsh environments, providing higher-quality data support for precision agricultural production. Compared with existing data collection equipment, its data deviation is smaller and its reliability is higher.

[0025] The embedded fine-tuned AI large model can deeply mine the value of agricultural data, and combined with a rich agricultural knowledge database, provide more accurate and targeted production management suggestions, helping farmers optimize production decisions, improve production efficiency and agricultural product quality, and improve the relatively simple intelligent analysis functions in existing technologies, and the accuracy and practicality of decision support.

[0026] The AI ​​monitoring system based on the YOLOv11 algorithm performs well in terms of detection speed and accuracy. It can quickly and accurately identify abnormal conditions such as pests and diseases, fires, and issue timely warnings, providing stronger protection for crop protection and farm safety. Compared with existing monitoring and early warning systems, it has faster response speed and higher detection accuracy.

[0027] Through hardware equipment and optimization algorithms, the demand for high-end resources is reduced, while the overall performance of the system is improved, allowing users to enjoy more efficient intelligent agricultural management and control services at a lower cost. Compared with the smart agricultural system with existing technology, it has significant cost advantages and higher cost performance, which is conducive to its promotion and application in rural areas and promotes the process of agricultural modernization. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0029] Figure 1 Schematic diagram of the system structure of the present invention;

[0030] Figure 2 Schematic diagram of the system structure of the present invention;

[0031] Figure 3 Schematic diagram of the system structure of the present invention;

[0032] Figure 4 Schematic diagram of the system structure of the present invention;

[0033] Figure 5 Schematic diagram of the system structure of the present invention. DETAILED DESCRIPTION

[0034] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0035] See also Figure 1-5 ,A smart agricultural management system based on the IoT cloud large model, includes a device acquisition unit, a server unit, and a Web server unit;

[0036] The equipment collection unit includes crop data collection equipment, grain storage data collection equipment, and AI image monitoring equipment to collect data on the agricultural ecological environment and crop storage environment;

[0037] The server unit stores, processes and analyzes the collected data. It has an embedded, deeply tuned AI agricultural expert model that analyzes the collected data in real time and uploads it to the database.

[0038] The web server unit is used for data visualization and real-time AI monitoring, allowing users to intuitively view environmental data of farmlands and granaries, AI analysis results, and real-time monitoring images.

[0039] The equipment collection unit includes crop data collection equipment, grain storage data collection equipment and AI image monitoring equipment, which collect data on the agricultural ecological environment and crop storage environment, including:

[0040] The STM32 microcontroller development board is used to connect various sensors, such as soil moisture sensors, air temperature and humidity sensors, and light sensors, to achieve real-time collection of farmland and granary environmental data. Communication with sensors is achieved through peripheral interfaces such as I2C, SPI, and UART, and data processing technologies such as filtering, calibration, and compensation are used to improve data reliability. Data is transmitted to the server through the MQTT protocol to ensure efficient and stable data transmission.

[0041] The equipment collection unit is used to detect multiple data in farmland, including equipment number, light intensity, soil pH, soil temperature, soil moisture, soil nitrogen content, soil phosphorus content, soil potassium content, air temperature, air humidity, air quality, carbon dioxide concentration, methanol concentration, and the longitude and latitude of the equipment's location, providing comprehensive environmental and soil information for agricultural production.

[0042] The server unit stores, processes, and analyzes the collected data. It also embeds a deeply tuned AI agricultural expert model to analyze the collected data in real time and upload it to the database. Specifically, it includes:

[0043] By embedding a fine-tuned AI large language model and customizing the training of a professional agricultural language database, in-depth analysis of data on the planting ecological environment and grain storage environment is carried out; based on the analysis results, the AI ​​model can provide accurate agricultural production management recommendations, such as the optimal time and amount of irrigation and fertilization, and pest and disease control plans.

[0044] The server unit stores, processes, and analyzes the collected data. It has an embedded, deeply tuned AI agricultural expert model that analyzes the collected data in real time and uploads it to the database. It also includes:

[0045] The database includes an influxdb real-time database and a MySQL database, wherein the influxdb real-time database stores agricultural and granary data, and the MySQL database stores important information.

[0046] The web unit provides data visualization and real-time AI monitoring, allowing users to intuitively view environmental data, AI analysis results, and real-time monitoring images of farmland and granaries. Specifically, it includes:

[0047] By combining the YOLOv11 algorithm with machine vision and deploying cameras on the NVIDIA Jetson Nano edge computing development board to capture real-time images, real-time monitoring and early warning of pests and diseases, fires, and farm intrusions can be carried out. The YOLOv11 algorithm can accurately identify and quickly respond, detecting and warning of potential threats in the first place. The annotated video stream is forwarded to the SRS streaming server via FFmpeg and the RTMP protocol, and then pushed to the web unit via the HTTP protocol for further processing. At the same time, log information is pushed to the EMQX server via the MQTT protocol for forwarding, ensuring the safety of crops and the integrity of farm facilities.

[0048] The web unit provides data visualization and real-time AI monitoring, allowing users to intuitively view environmental data, AI analysis results, and real-time monitoring images of farmlands and granaries. It also includes:

[0049] AI monitoring is mainly responsible for monitoring safety conditions such as pests and diseases, fires, and animal invasions in farmland. It obtains abnormal information about farmland in real time through intelligent means, provides timely and effective data support for farmland safety management, and ensures the healthy growth of crops.

[0050] The above description is merely illustrative of certain exemplary embodiments of the present invention. It goes without saying that those skilled in the art will be able to modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the scope of protection of the claims.

Claims

1. A smart agricultural management system based on the IoT cloud model, characterized by: It includes equipment acquisition unit, server unit and Web server unit; The equipment collection unit includes crop data collection equipment, grain storage data collection equipment, and AI image monitoring equipment to collect data on the agricultural ecological environment and crop storage environment; The server unit stores, processes and analyzes the collected data. It has an embedded, deeply tuned AI agricultural expert model that analyzes the collected data in real time and uploads it to the database. The web server unit is used for data visualization and real-time AI monitoring, allowing users to intuitively view environmental data of farmlands and granaries, AI analysis results, and real-time monitoring images.

2. The smart agricultural management system based on the IoT cloud model according to claim 1 is characterized in that: The equipment collection unit includes crop data collection equipment, grain storage data collection equipment and AI image monitoring equipment, which collects data on the agricultural ecological environment and crop storage environment, specifically including: The STM32 microcontroller development board is used to connect various sensors, such as soil moisture sensors, air temperature and humidity sensors, and light sensors, to achieve real-time collection of farmland and granary environmental data. Communication with sensors is achieved through peripheral interfaces such as I2C, SPI, and UART, and data processing technologies such as filtering, calibration, and compensation are used to improve data reliability. Data is transmitted to the server through the MQTT protocol to ensure efficient and stable data transmission.

3. The smart agricultural management system based on the IoT cloud model according to claim 1 is characterized in that: The server unit stores, processes and analyzes the collected data, and embeds a deeply adjusted AI agricultural expert model to analyze the collected data in real time and upload it to the database, specifically including: By embedding a fine-tuned AI large language model and customizing the training of a professional agricultural language database, in-depth analysis of data on the planting ecological environment and grain storage environment is carried out; based on the analysis results, the AI ​​model can provide accurate agricultural production management recommendations, such as the optimal time and amount of irrigation and fertilization, and pest and disease control plans.

4. The smart agricultural management system based on the IoT cloud model according to claim 3 is characterized in that: The server unit stores, processes and analyzes the collected data, embeds a deeply adjusted AI agricultural expert model, analyzes the collected data in real time, and uploads it to the database, and also includes: The database includes an influxdb real-time database and a MySQL database, wherein the influxdb real-time database stores agricultural and granary data, and the MySQL database stores important information.

5. The smart agricultural management system based on the IoT cloud big model according to claim 1 is characterized in that: The web unit provides data visualization and real-time AI monitoring, allowing users to intuitively view environmental data of farmland and granaries, AI analysis results, and real-time monitoring images. Specifically, it includes: By combining the YOLOv11 algorithm with machine vision and deploying cameras on the NVIDIA Jetson Nano edge computing development board to capture real-time images, real-time monitoring and early warning of pests and diseases, fires, and farm intrusions can be carried out. The YOLOv11 algorithm can accurately identify and quickly respond, detecting and warning of potential threats in the first place. The annotated video stream is forwarded to the SRS streaming server via FFmpeg and the RTMP protocol, and then pushed to the web unit via the HTTP protocol for further processing. At the same time, log information is pushed to the EMQX server via the MQTT protocol for forwarding, ensuring the safety of crops and the integrity of farm facilities.

6. The smart agricultural management system based on the IoT cloud model according to claim 5 is characterized in that: The web unit provides data visualization and real-time AI monitoring, allowing users to intuitively view environmental data of farmland and granaries, AI analysis results, and real-time monitoring images. It also includes: AI monitoring is mainly responsible for monitoring safety conditions such as pests and diseases, fires, and animal invasions in farmland. It obtains abnormal information about farmland in real time through intelligent means, provides timely and effective data support for farmland safety management, and ensures the healthy growth of crops.

Images