Crop growth analysis system based on agricultural Internet of Things

Abstract

The invention relates to the technical field of crop environment management, in particular to a crop growth analysis system based on agricultural Internet of Things. The farmland quality monitoring module monitors a plurality of environment variables, then calculates the change rate of the environment variables, and then calculates a comprehensive environment health index; the crop growth evaluation and early warning module is used for a user to input the pesticide application amount every time pesticide application is conducted, then the pesticide application frequency is recorded, and a pesticide residue index is obtained through calculation; the method comprises the following steps: monitoring a regional environment in a farmland, identifying a pixel proportion of a pest and disease damage region based on the regional environment, obtaining a pest and disease damage level based on the pixel proportion of the pest and disease damage region, calculating to obtain a comprehensive health level, and sending out an early warning after judging that the comprehensive health level is lower than a set comprehensive health level threshold value; and the block chain traceability module integrates the pesticide residue index, the pest and disease damage level and the comprehensive health level into a data abstract, generates a traceability two-dimensional code from the data abstract, and binds and displays the traceability two-dimensional code and the data abstract.

Description

Technical Field

[0001] The present invention belongs to the technical field of crop environment management, and in particular relates to a crop growth analysis system based on agricultural Internet of Things. Background Art

[0002] Agricultural production methods need to change and gradually move towards a more refined, intelligent and sustainable management model. In the existing agricultural production management system, it is difficult for consumers to accurately trace the production history of agricultural products, and farmers and producers lack an effective platform to record and share key data in the agricultural production process. This information opacity has greatly affected the market circulation of agricultural products and consumers' trust. Modern agricultural management requires accurate decisions based on a large amount of environmental data, crop growth status, and pest and disease monitoring information. However, in traditional agricultural management, it is often difficult to achieve refined operations. Many farmland management still relies on human judgment and experience rather than scientific monitoring data. In addition, farmland management is usually carried out over a large area, and management measures cannot be adapted to local conditions, making it difficult to formulate different production strategies for the specific conditions of different plots. Traditional agricultural management methods usually rely on manual monitoring and periodic inspections, which is not only time-consuming and labor-intensive, but also often fails to detect crop health problems in a timely manner. Early identification of crop pests and diseases is particularly important because pests and diseases often spread rapidly in a short period of time, causing serious losses to crops. However, in traditional agricultural production, pest and disease monitoring often relies on visual inspection, lacking efficient technical means to achieve early detection and accurate early warning. As the frequency and types of pests and diseases continue to increase, farmers are facing more and more complex challenges, but the lack of effective pest and disease monitoring and early warning mechanisms leads to crop health problems often not being solved in a timely manner. Therefore, a crop growth analysis system based on the agricultural Internet of Things is proposed. Summary of the invention

[0003] The present invention aims to solve the technical problems of data opacity, imprecise management and insufficient crop health monitoring in the agricultural production process, and provides a crop growth analysis system based on the agricultural Internet of Things.

[0004] The technical solution adopted by the present invention to solve the technical problem is: a crop growth analysis system based on agricultural Internet of Things, including a farmland quality monitoring module, a crop growth assessment and early warning module, and a blockchain traceability module.

[0005] The farmland quality monitoring module is set up in the farmland to monitor several environmental variables in the farmland for a period of time, and then calculates the change rate of several current environmental variables based on several environmental variables, and then calculates the comprehensive environmental health index, which is then displayed and sent to the crop growth assessment and early warning module.

[0006] The crop growth assessment and early warning module is set up in the plot, which is used for users to input the amount of pesticide applied each time, and then record the frequency of pesticide application over a period of time, calculate the pesticide residue index, and then transmit it to the blockchain traceability module. It is also used to monitor the regional environment in the farmland, and then identify the pixel ratio of the pest area based on the regional environment, and then obtain the pest level based on the pixel ratio of the pest area, and then calculate the comprehensive health level, and then judge whether it is lower than the set comprehensive health level threshold based on the comprehensive health level. It is also used to issue an early warning after judging that the comprehensive health level is lower than the set comprehensive health level threshold. It is also used to send the comprehensive health level and pest level to the blockchain traceability module after calculating the comprehensive health level.

[0007] The blockchain traceability module is connected to the crop growth assessment and early warning module network. After receiving the pesticide residue index, pest and disease level, and comprehensive health level, it is used to integrate the pesticide residue index, pest and disease level, and comprehensive health level into a data summary, and then generate a traceability QR code, and then bind the traceability QR code to the data summary, and then display the traceability QR code.

[0008] Furthermore, the farmland quality monitoring module includes an environmental monitoring unit and a display module.

[0009] The environmental monitoring unit is connected to the network and is set in the farmland. It is used to monitor a number of environmental variables in the farmland for a period of time, and then calculate the change rate of the current environmental variables based on the environmental variables. Then, the comprehensive environmental health index is calculated based on the change rate of the current environmental variables and the preset weights corresponding to the environmental variables, and then sent to the crop growth assessment and early warning module and the display module.

[0010] The display module is used to display the comprehensive environmental health index after receiving it.

[0011] Furthermore, the environmental monitoring unit calculates the change rate formula of several current environmental variables according to several environmental variables:

[0012] Where R j is the change rate of the current j-th environmental variable, e j (t i ) is at t i The jth environment variable at time t i ∈[tT,t].

[0013] Furthermore, the environmental monitoring unit calculates the comprehensive environmental health index according to the change rate of the environmental variables and the preset weights corresponding to the environmental variables as follows:

[0014] Among them, HI is the comprehensive environmental health index, ωj is the preset weight coefficient of the jth environmental variable, j∈[0,n].

[0015] Furthermore, the crop growth assessment and early warning module includes a pesticide residue monitoring module, a pest and disease identification module, an edge computing module, and an early warning device.

[0016] The pesticide residue monitoring module is set up in the plot, and is used for users to input the amount of pesticide applied each time the pesticide is applied, and then record the frequency of pesticide application over a period of time. The pesticide residue index is calculated based on the frequency of pesticide application, the amount of pesticide application and the preset half-life over a period of time, and then transmitted to the edge computing module and the blockchain traceability module.

[0017] The pest and disease identification module is used to monitor the regional environment within the farmland, and then identify the pixel ratio of the pest and disease area based on the regional environment, and then obtain the pest and disease level based on the pixel ratio of the pest and disease area, and then transmit the pest and disease level to the edge computing module and blockchain traceability module.

[0018] The edge computing module is connected to the pesticide residue monitoring module, the pest identification module, and the blockchain traceability module network, and is used to calculate the comprehensive health level based on the comprehensive environmental health index, the pesticide residue index, and the pest level after receiving the comprehensive environmental health index, the pesticide residue index, and the pest level, and then judge whether it is lower than the set comprehensive health level threshold based on the comprehensive health level. It is also used to trigger an early warning signal after judging that the comprehensive health level is lower than the set comprehensive health level threshold, and then transmit it to the early warning device. It is also used to send the comprehensive health level to the blockchain traceability module after calculating the comprehensive health level.

[0019] The early warning device is connected to the edge computing module network and is used to issue an early warning after receiving the early warning signal.

[0020] Furthermore, the pesticide residue monitoring module calculates the formula of the pesticide residue index based on the pesticide application frequency, pesticide application amount and preset half-life in a period of time before the current moment:

[0021] Among them, U i (t i ) is t i The amount of pesticide applied at the time i, in kg, t i ∈[tT,t], R is the pesticide residue index.

[0022] Furthermore, the pest identification module determines the pest level based on the pixel ratio of the pest area as follows:

[0023] Among them, A totalis the total pixel area of ​​the image region, in m 2 , A disease is the pixel area of ​​the pest and disease area, in m 2 , S disease is the pixel ratio of the pest and disease area,

[0024]

[0025] Among them, D(t k ) is the pest and disease level.

[0026] Furthermore, the edge computing module calculates the comprehensive health level based on the comprehensive environmental health index, pesticide residue index, and pest and disease level: GI = αHI + β(1-R) ​​+ γ(1-D(t k )),

[0027] Among them, GI is the comprehensive health level, α, β, and γ are weight parameters, satisfying α+β+γ=1.

[0028] Furthermore, the blockchain traceability module includes a data integration module, a blockchain unit, and a visualization unit.

[0029] The data integration module is connected to the edge computing module, the pest and disease identification module, and the pesticide residue monitoring module through a network, and is used to integrate the received pesticide residue index, pest and disease level, and comprehensive health level into a data summary, and then transmit the data summary to the blockchain unit.

[0030] The blockchain unit is used to generate a traceability QR code after receiving the data summary, and then bind the traceability QR code to the data summary, and then send the traceability QR code to the visualization unit.

[0031] The visualization unit is used to display the traceability QR code after receiving it.

[0032] Furthermore, the data integration module integrates the pesticide residue index, pest and disease level, and comprehensive health level into a data summary formula: Q(t k )=H hash (R,D(t k ), GI),

[0033] Among them, Q(t k ) is the data summary.

[0034] Beneficial effects of the present invention:

[0035] 1. The farmland quality monitoring module monitors the farmland environment in real time, promptly detects environmental change trends, and can accurately assess the health of the farmland environment. It provides a scientific basis for subsequent crop growth assessments and decisions on pesticide residues, pests and diseases, and supports refined farmland management. By quantifying the rate of change of environmental variables and health indexes, it helps farmers to accurately implement policies for farmland and improve the growth quality and yield of crops.

[0036] 2. Crop Growth Assessment and Early Warning Module By comprehensively considering environmental changes, pesticide application and pest and disease impacts, this module can assess crop health in real time and provide timely early warnings to reduce the risk of crop pests and diseases and pesticide residues. Combining environmental, pesticide application history and pest and disease information, it provides more accurate crop health assessments to help farmers optimize management strategies. The module automatically calculates the comprehensive health level and pest and disease level, and automatically triggers early warnings based on set thresholds, reducing manual intervention and improving farmland management efficiency.

[0037] 3. Blockchain traceability module improves data transparency and credibility: Blockchain technology is used to ensure that data cannot be tampered with and can be traced, effectively improving food safety and production transparency. Consumers can quickly obtain detailed information on crop production, pesticide application, pest and disease management, etc. by scanning the QR code, enhancing their sense of trust. Through blockchain technology, agricultural production data, pesticide residues, pest and disease monitoring and other information are digitally stored and managed, promoting the transformation of agricultural production to intelligent and digital. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is a schematic diagram of the system module of the present invention. DETAILED DESCRIPTION

[0039] The following will clearly and completely describe the concept and technical effects of the present invention in combination with the embodiments, so as to fully understand the purpose, features and effects of the present invention. Figure 1 .

[0040] A crop growth analysis system based on the agricultural Internet of Things, including a farmland quality monitoring module, a crop growth assessment and early warning module, and a blockchain traceability module.

[0041] The farmland quality monitoring module is set up in the farmland to monitor several environmental variables in the farmland for a period of time, and then calculates the change rate of several current environmental variables based on several environmental variables, and then calculates the comprehensive environmental health index, which is then displayed and sent to the crop growth assessment and early warning module.

[0042] The crop growth assessment and early warning module is set up in the plot, which is used for users to input the amount of pesticide applied each time, and then record the frequency of pesticide application over a period of time, calculate the pesticide residue index, and then transmit it to the blockchain traceability module. It is also used to monitor the regional environment in the farmland, and then identify the pixel ratio of the pest area based on the regional environment, and then obtain the pest level based on the pixel ratio of the pest area, and then calculate the comprehensive health level, and then judge whether it is lower than the set comprehensive health level threshold based on the comprehensive health level. It is also used to issue an early warning after judging that the comprehensive health level is lower than the set comprehensive health level threshold. It is also used to send the comprehensive health level and pest level to the blockchain traceability module after calculating the comprehensive health level.

[0043] The blockchain traceability module is connected to the crop growth assessment and early warning module network. After receiving the pesticide residue index, pest and disease level, and comprehensive health level, it is used to integrate the pesticide residue index, pest and disease level, and comprehensive health level into a data summary, and then generate a traceability QR code, and then bind the traceability QR code to the data summary, and then display the traceability QR code.

[0044] In this embodiment, the farmland quality monitoring module monitors the farmland environment in real time, promptly discovers environmental change trends, and can accurately assess the health status of the farmland environment. Provides a scientific basis for subsequent crop growth assessments and decisions on pesticide residues, pests and diseases, and supports refined farmland management. By quantifying the rate of change of environmental variables and the health index, it helps farmers to accurately implement policies for farmland and improve the growth quality and yield of crops. The crop growth assessment and early warning module comprehensively considers environmental changes, pesticide application, and the impact of pests and diseases. This module can assess the health status of crops in real time and provide timely early warnings to reduce the risk of crop pests and diseases and pesticide residues. Combined with the environment, pesticide application history, and pest and disease information, it provides a more accurate crop health assessment to help farmers optimize management strategies. This module automatically calculates the comprehensive health level and pest and disease level, and automatically triggers early warnings according to the set threshold, reducing manual intervention and improving farmland management efficiency. Blockchain traceability module · Improve data transparency and credibility: Use blockchain technology to ensure that data cannot be tampered with and can be traced, effectively improving food safety and production transparency. Consumers can quickly obtain detailed information on crop production, pesticide application, pest and disease management, etc. by scanning the QR code, which enhances their sense of trust. Through blockchain technology, agricultural production data, pesticide residues, pest and disease monitoring and other information can be digitally stored and managed to promote the transformation of agricultural production towards intelligence and digitalization.

[0045] In this embodiment, the farmland quality monitoring module includes an environmental monitoring unit and a display module.

[0046] The environmental monitoring unit is connected to the network and is set in the farmland. It is used to monitor a number of environmental variables in the farmland for a period of time, and then calculate the change rate of the current environmental variables based on the environmental variables. Then, the comprehensive environmental health index is calculated based on the change rate of the current environmental variables and the preset weights corresponding to the environmental variables, and then sent to the crop growth assessment and early warning module and the display module.

[0047] The display module is used to display the comprehensive environmental health index after receiving it.

[0048] In this embodiment, the environmental monitoring unit calculates the change rate of several current environmental variables according to several environmental variables as follows:

[0049] Where R j is the change rate of the current j-th environmental variable, e j (t i ) is at t i The jth environment variable at time t i ∈[tT,t],

[0050] For example, the second environmental variable is temperature, i is 3, and the temperature in the past three hours was 20 degrees Celsius, 22 degrees Celsius, and 24 degrees Celsius. The calculated R2 is 0.1.

[0051] In this embodiment, the environmental monitoring unit calculates the comprehensive environmental health index according to the change rate of the environmental variables and the preset weights corresponding to the environmental variables:

[0052] Among them, HI is the comprehensive environmental health index of the jth environmental variable, ω j is the preset weight coefficient of the jth environment variable, j∈[0,n],

[0053] For example, if R1 is 0.05 and R2 is 0.1, the calculated HI is 0.08.

[0054] In this embodiment, the crop growth assessment and early warning module includes a pesticide residue monitoring module, a pest identification module, an edge computing module, and an early warning device.

[0055] The pesticide residue monitoring module is set up in the plot, and is used for users to input the amount of pesticide applied each time the pesticide is applied, and then record the frequency of pesticide application over a period of time. The pesticide residue index is calculated based on the frequency of pesticide application, the amount of pesticide application and the preset half-life over a period of time, and then transmitted to the edge computing module and the blockchain traceability module.

[0056] The pest and disease identification module is used to monitor the regional environment within the farmland, and then identify the pixel ratio of the pest and disease area based on the regional environment, and then obtain the pest and disease level based on the pixel ratio of the pest and disease area, and then transmit the pest and disease level to the edge computing module and blockchain traceability module.

[0057] The edge computing module is connected to the pesticide residue monitoring module, the pest identification module, and the blockchain traceability module network, and is used to calculate the comprehensive health level based on the comprehensive environmental health index, the pesticide residue index, and the pest level after receiving the comprehensive environmental health index, the pesticide residue index, and the pest level, and then judge whether it is lower than the set comprehensive health level threshold based on the comprehensive health level. It is also used to trigger an early warning signal after judging that the comprehensive health level is lower than the set comprehensive health level threshold, and then transmit it to the early warning device. It is also used to send the comprehensive health level to the blockchain traceability module after calculating the comprehensive health level.

[0058] The early warning device is connected to the edge computing module network and is used to issue an early warning after receiving the early warning signal.

[0059] In this embodiment, by accurately recording the amount and frequency of application, and dynamically calculating the residue index in combination with the half-life of the pesticide, the pesticide residue of the crop can be monitored in real time, helping farmers to adjust the application plan in time. Providing quantitative data support helps farmers accurately evaluate the history and impact of pesticide application on crops, and provides an important basis for subsequent pest control and crop health assessment. Through the pesticide residue index, the excessive or frequent application of pesticides can be identified in time, reducing the potential risks of pesticides to crop growth and consumer health. With the help of image recognition technology, the pest area can be automatically identified, the workload of manual monitoring can be reduced, and the monitoring efficiency can be improved. By calculating the pixel ratio of the pest area, the severity of the pest can be accurately assessed, and a basis can be provided for subsequent decisions such as pesticide use and pest control. Real-time monitoring and evaluation of the distribution of pests and diseases can help farmers take timely measures to prevent the spread of pests and diseases and ensure the healthy growth of crops. Through the fusion analysis of multi-dimensional data, the overall health status of crops is comprehensively calculated, providing a comprehensive reference for farmland management. Automatically calculate and evaluate the health level of crops to support farmers in making scientific decisions and avoid the risk of blindly applying pesticides or ignoring pests and diseases. By calculating the comprehensive health level in real time and comparing it with the set health threshold, crop health problems can be discovered in time, warnings can be automatically triggered, and farmers can take quick action. By linking with the blockchain traceability module, it ensures that the health data and warning information of crops can be recorded and traced in a timely and accurate manner, enhancing the transparency and trust of agricultural management. By receiving the warning signal of the edge computing module in real time, it can issue a warning in time when the health of crops is abnormal, reminding farmers or managers to take necessary measures. Reduce the lag in agricultural management and help farmers discover potential health problems of crops as early as possible to avoid losses. Through a timely early warning mechanism, farmers can quickly respond to farmland environmental problems or pest and disease threats, and improve the growth stability and yield of crops.

[0060] In this embodiment, the pesticide residue monitoring module calculates the formula of the pesticide residue index based on the pesticide application frequency, pesticide application amount and preset half-life in a period of time before the current moment:

[0061] Among them, U i (t i ) is t i The amount of pesticide applied at the time i, in kg, t i ∈[tT,t], R is the pesticide residue index.

[0062] In this embodiment, the pest identification module determines the pest level based on the pixel ratio of the pest area using the formula:

[0063] Among them, A totalis the total pixel area of ​​the image region, in m 2 , A disease is the pixel area of ​​the pest and disease area, in m 2 , S disease is the pixel ratio of the pest and disease area,

[0064]

[0065] Among them, D(t k ) is the pest level, D(t k ) is slight, D(t k )=0.05,D(t k ) is moderate, D(t k )=0.15,D(t k ) is serious, D(t k )=0.30.

[0066] In this embodiment, the edge computing module calculates the comprehensive health level based on the comprehensive environmental health index, pesticide residue index, and pest level as follows: GI = αHI + β(1-R) ​​+ γ(1-D(t k )),

[0067] Among them, GI is the comprehensive health level, α, β, γ are weight parameters, satisfying α+β+γ=1,

[0068] For example, HI is 0.8, R is 2.38, D(t k ) is 0.15, α is 0.4, β is 0.3, γ is 0.3, and GI is 0.2.

[0069] In this embodiment, the blockchain traceability module includes a data integration module, a blockchain unit, and a visualization unit.

[0070] The data integration module is connected to the edge computing module, the pest and disease identification module, and the pesticide residue monitoring module through a network, and is used to integrate the received pesticide residue index, pest and disease level, and comprehensive health level into a data summary, and then transmit the data summary to the blockchain unit.

[0071] The blockchain unit is used to generate a traceability QR code after receiving the data summary, and then bind the traceability QR code to the data summary, and then send the traceability QR code to the visualization unit.

[0072] The visualization unit is used to display the traceability QR code after receiving it.

[0073] After displaying the traceability QR code, the manager will print and post the traceability QR code on the packaged vegetables. Users can scan the traceability QR code to learn detailed information, ensuring the entire process is traceable. Openness and transparency provide a new approach to food safety issues.

[0074] In this embodiment, by integrating and encrypting multiple data sources, it is ensured that the integrated data is not tampered with during the transmission process, and its integrity and consistency are maintained. The process of generating the data summary is irreversible, which ensures the authenticity and non-tamperability of the data, thereby providing verifiable and reliable data support for the farmland production process. By transmitting the summary after data integration to the blockchain, the agricultural management process can be made more transparent, the data manipulation in the intermediate links can be reduced, and the interests of all parties can be protected. Through the encrypted storage and distributed ledger technology of the blockchain, it is ensured that each piece of data is non-tamperable on the chain, and users can query the data with confidence to ensure the authenticity of the information. Each crop or agricultural product can have a unique traceability QR code, which is bound to a specific data summary, so that the traceability information has uniqueness and identity recognition functions. Through the transparent and fair traceability information provided by the blockchain, consumers can clearly trace the source of the product and its production process, and enhance their trust in the quality of agricultural products. Through the traceability QR code displayed by the visualization unit, users can scan the QR code at any time to query the complete health information and production process of the crop, and ensure food safety from the source. The QR code display is simple and intuitive, and consumers can obtain detailed farmland management information without complex operations, realizing efficient and convenient information interaction. Through visual display, it not only provides food safety guarantees for consumers, but also promotes the popularization of traceability concepts in the agricultural industry and enhances the market competitiveness of agricultural products.

[0075] In this embodiment, the data integration module integrates the pesticide residue index, pest and disease level, and comprehensive health level into a data summary formula: Q(t k )=H hash (R,D(t k ), GI),

[0076] Among them, Q(t k ) is the data summary. The process of generating the data summary is irreversible, which ensures the authenticity and non-tamperability of the data, thereby providing verifiable and reliable data support for the farmland production process.

[0077] The above embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, other embodiments obtained by those skilled in the art without creative work shall all fall within the scope of protection of the present invention.

Claims

1. A crop growth analysis system based on agricultural Internet of Things, characterized by: Including farmland quality monitoring module, crop growth assessment and early warning module, blockchain traceability module, The farmland quality monitoring module is arranged in the farmland, and is used to monitor a number of environmental variables in the farmland for a period of time, and then calculate the change rate of the current number of environmental variables according to the number of environmental variables, and then calculate the comprehensive environmental health index, and then display it and send it to the crop growth assessment and early warning module; The crop growth assessment and early warning module is set in the plot, and is used for the user to input the amount of pesticide applied each time the pesticide is applied, and then record the frequency of pesticide application within a period of time, calculate the pesticide residue index, and then transmit it to the blockchain traceability module; and is used to monitor the regional environment in the farmland, and then identify the pixel ratio of the pest area based on the regional environment, and then obtain the pest level based on the pixel ratio of the pest area, and then calculate the comprehensive health level, and then judge whether it is lower than the set comprehensive health level threshold based on the comprehensive health level; and is used to issue an early warning after judging that the comprehensive health level is lower than the set comprehensive health level threshold; and is used to send the comprehensive health level and the pest level to the blockchain traceability module after calculating the comprehensive health level; The blockchain traceability module is connected to the crop growth assessment and early warning module network, and is used to integrate the pesticide residue index, pest and disease level, and comprehensive health level into a data summary after receiving it, and then generate a traceability QR code, and then bind the traceability QR code to the data summary, and then display the traceability QR code.

2. The crop growth analysis system based on the agricultural Internet of Things according to claim 1, characterized in that: The farmland quality monitoring module includes an environmental monitoring unit and a display module. The environmental monitoring unit is connected to a network and is set in the farmland to monitor a number of environmental variables in the farmland for a period of time, and then calculates the change rate of the current number of environmental variables according to the number of environmental variables, and then calculates the comprehensive environmental health index according to the change rate of the current number of environmental variables and the preset weights corresponding to the number of environmental variables, and then sends it to the crop growth assessment and early warning module and the display module; The display module is used to display the comprehensive environmental health index after receiving it.

3. The crop growth analysis system based on agricultural Internet of Things according to claim 1, characterized in that: The environmental monitoring unit calculates the change rate of several current environmental variables according to several environmental variables as follows: Where R j is the change rate of the current j-th environmental variable, e j (t i ) is at t i The jth environment variable at time t i ∈[tT,t].

4. The crop growth analysis system based on agricultural Internet of Things according to claim 1, characterized in that: The environmental monitoring unit calculates the comprehensive environmental health index according to the change rate of several environmental variables and the preset weights corresponding to the several environmental variables: Among them, HI is the comprehensive environmental health index, ω j is the preset weight coefficient of the jth environmental variable, j∈[0,n].

5. The crop growth analysis system based on agricultural Internet of Things according to claim 2, characterized in that: The crop growth assessment and early warning module includes a pesticide residue monitoring module, a pest identification module, an edge computing module, and an early warning device. The pesticide residue monitoring module is set in the plot, and is used for the user to input the amount of pesticide applied each time the pesticide is applied, and then record the frequency of pesticide application within a period of time, and calculate the pesticide residue index based on the frequency of pesticide application within a period of time, the amount of pesticide application and the preset half-life, and then transmit it to the edge computing module and the blockchain traceability module; The pest identification module is used to monitor the regional environment in the farmland, and then identify the pixel ratio of the pest area based on the regional environment, and then obtain the pest level based on the pixel ratio of the pest area, and then transmit the pest level to the edge computing module and the blockchain traceability module; The edge computing module is connected to the pesticide residue monitoring module, the pest identification module, and the blockchain traceability module through a network, and is used to calculate a comprehensive health level based on the comprehensive environmental health index, the pesticide residue index, and the pest level after receiving the comprehensive environmental health index, the pesticide residue index, and the pest level, and then determine whether the comprehensive health level is lower than a set comprehensive health level threshold based on the comprehensive health level; and is used to trigger an early warning signal after determining that the comprehensive health level is lower than the set comprehensive health level threshold, and then transmit the signal to the early warning device; And used to send the comprehensive health level to the blockchain traceability module after calculating the comprehensive health level; The early warning device is connected to the edge computing module network and is used to issue an early warning after receiving an early warning signal.

6. The crop growth analysis system based on agricultural Internet of Things according to claim 5, characterized in that: The pesticide residue monitoring module calculates the pesticide residue index formula based on the pesticide application frequency, pesticide application amount and preset half-life in a period of time before the current moment: Among them, U i (t i ) is t i The amount of pesticide applied at the time i, in kg, t i ∈[tT,t], R is the pesticide residue index.

7. The crop growth analysis system based on agricultural Internet of Things according to claim 5, characterized in that: The formula for the pest identification module to judge the pest level based on the pixel ratio of the pest area is: Among them, A total is the total pixel area of ​​the image region, in m 2 , A disease is the pixel area of ​​the pest and disease area, in m 2 , S disease is the pixel ratio of the pest and disease area, Among them, D(t k ) is the pest and disease level.

8. The crop growth analysis system based on agricultural Internet of Things according to claim 5, characterized in that: The edge computing module calculates the comprehensive health level based on the comprehensive environmental health index, pesticide residue index, and pest level as follows: GI = αHI + β(1-R) ​​+ γ(1-D(t k )), Among them, GI is the comprehensive health level, α, β, and γ are weight parameters, satisfying α+β+γ=1.

9. The crop growth analysis system based on agricultural Internet of Things according to claim 7, characterized in that: The blockchain traceability module includes a data integration module, a blockchain unit, and a visualization unit. The data integration module is connected to the edge computing module, the pest identification module, and the pesticide residue monitoring module through a network, and is used to integrate the received pesticide residue index, pest level, and comprehensive health level into a data summary, and then transmit the data summary to the blockchain unit; The blockchain unit is used to generate a traceability QR code after receiving the data summary, then bind the traceability QR code to the data summary, and then send the traceability QR code to the visualization unit; The visualization unit is used to display the traceability QR code after receiving it.

10. The crop growth analysis system based on agricultural Internet of Things according to claim 9, characterized in that: The data integration module integrates the pesticide residue index, pest and disease level, and comprehensive health level into a data summary formula: Q(t k )=H hash (R,D(t k ), GI), Among them, Q(t k ) is the data summary.

Images